WO2023185601A1 - 一种电池健康状态信息确定方法、装置及电池*** - Google Patents

一种电池健康状态信息确定方法、装置及电池*** Download PDF

Info

Publication number
WO2023185601A1
WO2023185601A1 PCT/CN2023/083218 CN2023083218W WO2023185601A1 WO 2023185601 A1 WO2023185601 A1 WO 2023185601A1 CN 2023083218 W CN2023083218 W CN 2023083218W WO 2023185601 A1 WO2023185601 A1 WO 2023185601A1
Authority
WO
WIPO (PCT)
Prior art keywords
battery system
charging
health status
battery
status information
Prior art date
Application number
PCT/CN2023/083218
Other languages
English (en)
French (fr)
Inventor
贺宏胜
顾辉
高超
于静美
Original Assignee
北京芯虹科技有限责任公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京芯虹科技有限责任公司 filed Critical 北京芯虹科技有限责任公司
Publication of WO2023185601A1 publication Critical patent/WO2023185601A1/zh

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/392—Determining battery ageing or deterioration, e.g. state of health
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/389—Measuring internal impedance, internal conductance or related variables
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M10/00—Secondary cells; Manufacture thereof
    • H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
    • H01M10/44—Methods for charging or discharging
    • H01M10/443—Methods for charging or discharging in response to temperature
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M10/00—Secondary cells; Manufacture thereof
    • H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
    • H01M10/48—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte
    • H01M10/486—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte for measuring temperature

Definitions

  • the present application relates to the field of charging technology, and in particular to a method, device and battery system for determining battery health status information.
  • the battery system includes at least one battery module including at least one battery cell; at least one storage medium including a set of instructions; and one or more processors in communication with the at least one storage medium, wherein, When executing the instructions, the one or more processors are configured to: obtain charging data related to the battery system, the charging data including charging voltage, charging current, charging time, charging temperature data and historical usage data. At least one; and determining health status information related to the battery system based on the charging data; wherein the health status information includes capacity offset information, SOH value, self-discharge consistency, voltage and pressure related to the battery system. The difference is related to one or more of internal resistance consistency, insulation status, and temperature status.
  • the system further includes a communication module configured to communicate with a reading device so that the reading device reads the health status information through the communication module.
  • determining health status information related to the battery system based on the charging data includes: processing the charging data through a preconfigured machine learning model to determine the health status information, The machine learning model is stored in the storage medium.
  • determining the health status information related to the battery system based on the charging data includes: obtaining a trained machine learning model from a server; and charging the battery system through the trained machine learning model. The data is processed to determine the health status information.
  • the machine learning model includes a trained state information determination model; processing the charging data through the machine learning model to determine the health state information includes: determining through the state information The model processes the charging data to determine current health information of the battery system.
  • the machine learning model further includes a trained state information prediction model; the one or more processors are further configured to: use the state information prediction model to predict the charging data and the current health state. The information is processed to determine the future health status information of the battery system in the next time period.
  • the machine learning model also includes a trained health status judgment model; the one or more processors are also configured to: obtain two or more future health status information of the battery system, the two The two or more future health status information respectively correspond to different future time periods; through the health status judgment model, the two or more future health status information are processed to determine the health status of the battery system.
  • the machine learning model is obtained by: obtaining training samples, the training samples include a plurality of sample groups, each of the sample groups includes historical charging data of the corresponding sample battery, through the status information The historical future health status information obtained by the prediction model and the historical health status obtained by the health status judgment model; training the initial model based on the training samples to obtain a trained machine learning model; wherein, the label of the training sample It includes historical actual health status information corresponding to the historical future health status information, and historical actual health status corresponding to the historical health status.
  • the number of negative samples in the training samples is less than a preset value
  • data simulation or parameter adjustment is used to The number of negative samples is filled.
  • the one or more processors are further configured to update the machine learning model.
  • the one or more processors are further configured to: obtain usage information of the battery system, the usage information including at least one of usage time, charging times, and maintenance times; determine based on the usage information
  • the health category of the battery system includes at least a high health category, a medium health category and a low health category.
  • the one or more processors are further configured to: in response to the battery system belonging to the low health category, perform at least one of the following operations on the battery system: determine whether the battery system is charged before each charge. The health status of the battery system is described, the target data of the battery system is reported to the server, and a backup battery is preset for the battery system.
  • the one or more processors are further configured to: obtain usage feedback information related to the battery system; analyze the usage feedback information to determine characteristic information of the battery system; and pass health status A judgment model processes the characteristic information of the battery system to determine the health status of the battery system.
  • the charging voltage includes at least one of a charging starting voltage, a charging process characteristic voltage, and a charging cutoff voltage
  • the charging temperature data includes at least one of a charging starting temperature and a charging process temperature weight
  • the historical usage data includes at least one of cumulative charge and discharge capacity, cumulative charge and discharge times, and historical battery health status.
  • the system further includes: one or more sensors for detecting at least one of the charging voltage, the charging current, and the charging temperature; a battery management system for managing the battery The charging and discharging behavior of the system; a power supply module for using the electric energy stored in the battery system to provide power for at least one component of the battery system; and/or a positioning module for obtaining location information of the battery system.
  • One embodiment of this specification provides a battery health status information determining device, configured to estimate health status information related to the battery system in a battery system.
  • the device includes: a first acquisition module for acquiring charging data related to the battery system, the charging data including at least one of charging voltage, charging current, charging time, charging temperature data and historical usage data; An evaluation module for determining health status information related to the battery system based on the charging data; wherein the health status information includes capacity offset information, SOH value, and self-discharge consistency related to the battery system. , one or more of voltage difference and internal resistance consistency, insulation status and temperature status.
  • the device includes a storage module and a communication module.
  • the storage module is used to store the health status information.
  • the communication module is used to communicate with a reading device so that the reading device passes The communication module reads the health status information stored in the storage module.
  • One embodiment of this specification provides a device for determining battery health status information, which is configured in a charging device to determine health status information related to a battery system.
  • the device includes: a second acquisition module for acquiring charging data related to the battery system, the charging data including at least one of charging voltage, charging current, charging time, charging temperature data and historical usage data; Two evaluation modules, configured to determine health status information related to the battery system based on the charging data; wherein the health status information includes capacity offset information, SOH value, and self-discharge consistency related to the battery system. , one or more of voltage difference and internal resistance consistency, insulation status and temperature status.
  • One embodiment of this specification provides a method for determining battery health status information, which is executed by a processor in a battery system.
  • the battery system includes at least one battery module, and the battery module includes at least one battery cell.
  • the method includes: obtaining charging data related to the battery system, the charging data including at least one of charging voltage, charging current, charging time, charging temperature data and historical usage data; and determining based on the charging data and Health status information related to the battery system; wherein the health status information includes capacity offset information, SOH value, self-discharge consistency, pressure difference and internal resistance consistency, insulation status and temperature related to the battery system one or more of the states.
  • One embodiment of this specification provides a method for determining battery health status information, which is executed by a processor in a charging device.
  • the method includes: obtaining charging data related to the battery system, the charging data including at least one of charging voltage, charging current, charging time, charging temperature data and historical usage data; and determining the relationship between the battery and the battery based on the charging data.
  • System-related health status information wherein the health status information includes capacity offset information, SOH value, self-discharge consistency, pressure difference and internal resistance consistency, insulation status, and temperature status related to the battery system. one or more.
  • Figure 1 is a schematic diagram of an application scenario of a charging system according to some embodiments of the present application.
  • FIG. 2 is a schematic diagram of a battery system according to some embodiments of the present application.
  • Figure 3 is a software and/or hardware schematic diagram of an exemplary computer device according to some embodiments of this specification.
  • Figure 4 is a schematic module diagram of a device for determining battery health status information according to some embodiments of the present application.
  • Figure 5 is a schematic connection diagram of a battery system according to some embodiments of the present application.
  • Figure 6 is an exemplary flow chart of a method for determining battery health status information according to some embodiments of the present application.
  • Figure 7 is a diagram showing the corresponding relationship between module capacity and cell number according to some embodiments of the present application.
  • Figure 8 is a diagram showing the corresponding relationship between offset and cell number according to some embodiments of the present application.
  • Figure 9 is a diagram showing the corresponding relationship between DC impedance and cell number according to some embodiments of the present application.
  • Figure 10 is an exemplary flow chart of a battery status determination method according to some embodiments of the present application.
  • Figure 11 is an exemplary flow chart of a method for determining battery status information according to some embodiments of the present application.
  • Figure 12 is a schematic module diagram of a device for determining battery health status information according to other embodiments of the present application.
  • Figure 13 is an exemplary flow chart of a method for determining battery health status information according to other embodiments of the present application.
  • system means of distinguishing between different components, elements, parts, portions, or assemblies at different levels.
  • said words may be replaced by other expressions if they serve the same purpose.
  • the battery management system can obtain the voltage, current, temperature, time and other parameters of the battery system during charging or discharging, and then transmit the above parameters to the remote server (for example, remote data platform or monitoring system).
  • the server uses the received data to perform secondary data development, such as battery remaining capacity calculation, fault warning, operation statistics, etc.
  • secondary data development such as battery remaining capacity calculation, fault warning, operation statistics, etc.
  • embodiments of the present application provide a method, device and battery system for determining battery health status information, which can obtain charging data related to the battery system, store and calculate the charging data, and determine the charging data related to the battery system. Relevant health status information is then sent to the server.
  • the operation of evaluating the battery system status can be performed locally by the battery system determination device instead of being uniformly performed by the remote server, thereby reducing the computing load of the server to a certain extent.
  • Figure 1 is a schematic diagram of an application scenario of a charging system according to some embodiments of the present application.
  • the charging system 100 may be used in the field of charging management.
  • charging data can be stored and/or calculated in the battery system, charging equipment, or electrical equipment (for example, electric vehicles, etc.) loaded with the battery system, thereby reducing the calculation of the remote server. Stress and monitoring costs.
  • the charging system 100 may include a charging device 110 , a server 120 , a memory 130 , a network 140 , a battery system 150 and a terminal 160 .
  • the charging device 110 or the battery system 150 may include a computing device (eg, the computing device 300 ) for processing charging data related to the battery system 150 .
  • charging device 110 may refer to a device for charging battery system 150 (eg, a battery system used to power an electric vehicle).
  • the charging device 110 may be a mobile device or a fixed device, for example, it may be fixed on the ground or a wall.
  • the charging device 110 may refer to a charging pile installed in a parking lot, a residential area or a charging station.
  • the charging device 110 may also include a battery replacement station for replacing the battery system 150 .
  • the battery system 150 may include one or more battery modules 151 , where each battery module 151 may be obtained by a plurality of single cells 153 connected in series and/or in parallel.
  • a processing device eg, processor 310 in the battery system 150 may obtain charging data related to the battery system and process it.
  • the processing device in the battery system 150 may be used to obtain charging data of the battery system, battery modules or cells, and determine health status information of the battery system, battery modules or cells based on the charging data.
  • the charging data may include at least one of charging voltage, charging current, charging time, charging temperature data, and historical usage data of the battery system 150
  • the health status information may include capacity offset information, SOH value, One or more of self-discharge consistency, pressure difference and internal resistance consistency, insulation status, and temperature status.
  • the server 120 can perform data transmission with other devices in the charging system 100 (eg, charging device 110, memory 130, battery system 150, terminal 160).
  • the server 120 may receive charging data and/or health status information sent by the charging device 110 or the battery system 150 .
  • the server 120 may send a trained machine learning model or update data for updating the machine learning model to the charging device 110 or the battery system 150 .
  • server 120 may be an independent server or a group of servers. The server group may be centralized or distributed (eg, server 120 may be a distributed system).
  • the server 120 may be local or remote.
  • the server 120 can access information and/or data stored in the charging device 110, the memory 130, and the battery system 150 through the network 140.
  • server 120 may be directly connected to charging device 110, memory 130, and battery system 150 to access information and/or data stored therein.
  • server 120 may be implemented on a cloud platform.
  • the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud cloud, multi-cloud, etc. or any combination thereof.
  • the server 110 may be a server of a battery monitoring platform, such as an owner of a replacement battery pack, a maintenance platform of a battery system, or a manufacturer of a battery system.
  • Memory 130 may provide data storage functionality for charging system 100 .
  • memory 130 may be part of charging device 110 , battery system 150 , and/or server 120 .
  • memory 130 may be used to store trained machine learning models.
  • memory 130 may be used to store charging data and/or status information related to the battery system (eg, current health status information, future health status information, health status, health categories, etc.).
  • the memory 130 may include multiple data pools for storing charging data related to the battery system.
  • memory 130 may store information and/or instructions that are executed or used by processing devices in charging device 110 or battery system 150 to perform the example methods described herein.
  • memory 130 may include bulk memory, removable memory, volatile read-write memory, read-only memory (ROM), etc., or any combination thereof.
  • Exemplary mass storage may include magnetic disks, optical disks, solid state disks, and the like.
  • Exemplary removable storage may include flash drives, floppy disks, optical disks, memory cards, compact disks, tapes, and the like.
  • Exemplary volatile read-write memory may include random access memory (RAM).
  • the memory 130 may be implemented on a cloud platform.
  • Network 140 may facilitate the exchange of data and/or information.
  • one or more components in charging system 100 may send data and/or information to other components in charging system 100 over network 140 .
  • the server 120 may receive status information related to the battery system sent by the charging device 110 or the battery system 150 through the network 140 .
  • the server 120 may send the trained machine learning model or update data for updating the machine learning model to the battery system 150 and/or the memory 130 through the network 140 .
  • network 140 may be any type of wired or wireless network.
  • network 140 may be or include a public network (eg, the Internet), a private network (eg, a local area network (LAN)), a wired network, a wireless network (eg, an 802.11 network, a Wi-Fi network), a frame relay network , virtual private network (VPN), satellite network, telephone network, router, hub, switch, server computer and/or any combination thereof.
  • network 140 may include a fiber optic network, a telecommunications network, an intranet, a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth TM network, a ZigBee TM network, near field communications ( NFC) network, etc. or any combination thereof.
  • network 140 may include one or more network access points.
  • network 140 may include wired or wireless network access points, such as base stations and/or Internet switching points, through which one or more components of charging system 100 may be connected to network 140 to exchange data and /or information.
  • the battery system 150 may be electrically connected to the charging device 110 for charging.
  • battery system 150 It can be a battery pack used to power electric vehicles, electric bicycles, electric motorcycles or other electrical equipment.
  • the battery system 150 can perform data transmission with the charging device 110 .
  • the battery system 150 may obtain charging data from the charging device 110, and the charging data may include at least one of charging voltage, charging current, and charging time.
  • the battery system 150 may include one or more battery modules, each battery module may include one or more single cells, and the one or more battery modules may cooperate to provide power.
  • the battery system 150 may further include one or more sensors, and/or a battery management system (BMS).
  • BMS battery management system
  • the single cell can be used to store electrical energy.
  • Each single cell may include a positive terminal and a negative terminal.
  • the single battery can be any type of battery, such as lead-acid single battery, nickel metal hydride single battery, lithium ion (Li-ion) single battery, etc., which is not limited in this application.
  • the BMS can be used to manage the charging and discharging behaviors of the battery system 150, collect data related to charging and discharging of the battery system 150, and transmit the collected data.
  • the battery system 150 may transmit data through the BMS.
  • the BMS can transmit data to one or more devices of the charging system 100, such as the charging device 110, the server 120, the memory 130, and the terminal 160.
  • One or more sensors within battery system 150 may detect one or more characteristics of battery system 150 .
  • the one or more sensors may include a temperature sensor configured to detect the overall internal temperature of the battery system 150 during charging and discharging, and/or the temperature of one or more internal locations.
  • the one or more sensors may detect charging and discharging current, voltage, etc. of the battery system 150 .
  • the one or more sensors may send detected data to the BMS.
  • the battery system 150 may further include a power supply module, which may be used to utilize the electrical energy stored in the battery system and power external devices and/or at least one component in the battery system 150 under the control of the BMS.
  • the battery system 150 may also include a positioning module for obtaining location information of the battery system.
  • the location information of the battery system can be obtained in real time through the positioning module, so that when the battery fails or is abnormal, corresponding processing can be carried out in a timely manner based on the location information.
  • the server 120 can obtain the location information obtained by the battery system 150 through the positioning module, so as to arrange for maintenance personnel to repair when the battery fails, or to trace the battery assets, monitor the battery status, or terminate the use of the battery when it is damaged, etc.
  • the battery system 150 may also include other customized modules, such as a display module, which is not limited in this specification.
  • the terminal 160 may be various types of devices with information receiving and/or sending functions. Users can interact with server 120 through terminal 160. For example, after the battery system 150 locally evaluates the health status information related to the battery system, the evaluation results can be sent to the server 120 through the network 140 . The user can receive the battery health status information estimation result from the server 120 through the terminal 160 . For another example, the user may send a request to evaluate battery health status information to the server 120 through the terminal 160 . The server 120 may send the request to the battery system 150 so that the battery system 150 locally evaluates the relevant health status information.
  • the terminal 160 may include a mobile phone 160-1, a tablet computer 160-2, a personal computer 160-3, and other electronic devices, such as vehicle-mounted equipment, maintenance equipment, etc.
  • the users may include battery users (eg, electric vehicle users), battery manufacturers, electric vehicle manufacturers, etc.
  • the charging system 100 is for illustrative purposes only and is not intended to limit the scope of this specification.
  • the charging system 100 may also include electrical equipment, such as electric vehicles.
  • electrical equipment such as electric vehicles.
  • Figure 3 is a software and/or hardware schematic diagram of an exemplary computer device according to some embodiments of this specification.
  • the computing device 300 may be part of the charging device 110 or the battery system 150 for determining status information (eg, current health status information, future health status information) of the battery system based on charging data related to the battery system. , health status, health category, etc.).
  • status information eg, current health status information, future health status information
  • the charging device 110 can directly determine the current health status information and future health status information of the battery system based on charging data such as charging voltage, charging current, and charging time of the battery system currently being charged.
  • the battery system 150 can obtain charging data such as charging voltage, charging current, charging time, etc. from the charging device 110, and determine the current health status information and future health status information of the battery system based on the charging data. Health status information, or health status, etc.
  • computing device 300 may include processor 310, memory 320, input/output 330, and communication port 340.
  • Processor 310 may execute computer instructions (eg, program code) and determine health-related information of the battery system according to the methods described herein.
  • Computer instructions may include, for example, routines, programs, objects, components, data structures, procedures, modules, and functions that perform the specific functions described herein.
  • processor 310 may obtain charging data related to battery system 150 and determine current health information, future health information, or health status of the battery system based on the charging data.
  • processor 310 may include at least one processing device (eg, a single-core processing device or a multi-core multi-core processing device).
  • a processing device may include a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction processor (ASIP), a graphics processor (GPU), physical processor (PPU), digital signal processor (DSP), field programmable gate array (FPGA), programmable logic circuit (PLD), controller, microcontroller unit, reduced instruction set computer (RISC) ), microprocessor, etc. or any combination of the above.
  • CPU central processing unit
  • ASIC application specific integrated circuit
  • ASIP application specific instruction processor
  • GPU graphics processor
  • PPU physical processor
  • DSP digital signal processor
  • FPGA field programmable gate array
  • PLD programmable logic circuit
  • controller microcontroller unit, reduced instruction set computer (RISC) ), microprocessor, etc. or any combination of the above.
  • computing device 300 may also include multiple processors, and the operations and/or method steps performed by one processor described in the specification may also be performed jointly or individually by multiple processors.
  • the processor of computing device 300 performs operations A and B simultaneously, it should be understood that operations A and B may be performed jointly or individually by two or more different processors in computing device 300 (e.g., One processor performs operation A and a second processor performs operation B, or the first processor and the second processor jointly perform operations A and B).
  • Memory 320 may store data/information obtained from charging device 110 , battery system 150 , terminal 160 , and/or any other component in charging system 100 .
  • the term data as used herein may be any information including, for example, numbers, text, speech, images, videos, parameters, codes, formulas, files, algorithms, programs, etc., or any combination thereof.
  • memory 320 may be used to store trained machine learning models.
  • memory 320 may be used to store charging data and/or status information related to battery system 150 .
  • the processor 310 may receive the evaluation model update information sent by the server 120 through the network 140 and store it in the memory 320 . The processor 310 may update the evaluation model according to the model update information.
  • memory 320 may store programs and/or instructions, such as computer programs, for execution by processor 310 .
  • memory 320 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), or any combination thereof.
  • Input/output 330 may be used to input and/or output signals, data, information, etc. In some embodiments, input/output 330 may enable a user to interact with components in charging system 100 (eg, charging device 110, server 120). In some embodiments, input/output 330 may include input devices and output devices. Exemplary input devices may include a keyboard, mouse, touch screen, microphone, or any combination thereof. Exemplary output devices may include display devices, speakers, printers, projectors, or any combination thereof. Exemplary display devices may include liquid crystal displays (LCDs), light emitting diode (LED) based displays, flat panel displays, curved displays, television devices, cathode ray tubes, or any combination thereof.
  • LCDs liquid crystal displays
  • LED light emitting diode
  • Communication port 340 may connect with a network (eg, network 140) to facilitate data communications.
  • the communication port 340 may establish a connection between the server 120 and the charging device 110, the memory 130, the battery system 150, and/or the terminal 160. Connections can include wired and wireless connections.
  • communication port 340 may be and/or include a standardized communication port, such as RS232, RS485, etc. In some embodiments, communication port 340 may be a specially designed communication port.
  • Figure 4 is a schematic module diagram of a device for determining battery health status information according to some embodiments of the present application.
  • the battery health status information determining device 400 may be part of the aforementioned battery system 150 .
  • the battery health status information determining device 400 may be part of the processor 310.
  • the battery health status information determination device 400 can be added to a traditional battery system as an independent additional device, thereby providing a localized battery health status information determination function for the traditional battery system. It should be noted that in some embodiments, by adding the battery health status information determination device 400 to the traditional battery system to realize the localized battery health status information determination function, replacement of the battery system can be avoided.
  • the battery health status information determining device 400 may include a first acquisition module 410 and a first evaluation module 420 .
  • the first acquisition module 410 may be used to acquire charging data related to the battery system 150 .
  • the charging data may include at least one of charging voltage, charging current, charging time, charging temperature data, and historical usage data.
  • the first acquisition module 410 may acquire the charging data related to the battery system 150 from the BMS in the battery system 150 and store it in the storage module (eg, the memory 320).
  • the first acquisition module 410 may be used to acquire a trained machine learning model.
  • the first evaluation module 420 may be configured to determine health status information related to the battery system 150 based on the charging data related to the battery system 150 .
  • the first evaluation module 420 can read the health status judgment model from the memory 320 to evaluate the battery health status.
  • the health status information may include one or more of capacity offset information, SOH value, self-discharge consistency, pressure difference and internal resistance consistency, insulation status, and temperature status related to the battery system 150 .
  • the first evaluation module 420 may use any evaluation algorithm or model to evaluate the battery health status information related to the battery system 150 , which is not limited by this application. The method for the first evaluation module 420 to evaluate the battery health status information is detailed in the description of FIG. 6 .
  • the battery health status information determining device 400 may further include a communication module (not shown in the figure).
  • the communication module may be used to communicate with the reading device, so that the reading device reads the charging data and/or related to the battery system 150 stored in the storage module (eg, the memory 320) through the communication module. or health status information. This facilitates inspection, maintenance or escalation Charging data and/or health status information related to the battery system 150 is quickly obtained when battery cells are screened.
  • the reading device may refer to a terminal device (eg, terminal 160) with a data reading function, such as maintenance equipment, etc.
  • charging data and/or health status information related to the battery system 150 can be read by a reading device, so as to determine the current status of the battery system 150 based on the charging data and/or health status information.
  • the communication connection between the communication module and the reading device may include a short-range communication connection, such as NFC, radio frequency identification (RFID), Bluetooth, ZigBee, infrared, etc.
  • the communication connection between the communication module and the reading device may also include a long-distance communication connection.
  • the communication module can implement communication between the battery health status information determining device 400 and the BMS.
  • the first acquisition module 410 can communicate through a Controller Area Network (CAN) to receive charging data of the battery system 150 during the charging process from the BMS 152, such as battery cell or module voltage, battery cell or Module temperature, battery cell or module charging current, charging duration, etc.
  • the communication module may send the charging data to the second evaluation module 420 and/or the storage module.
  • CAN Controller Area Network
  • Figure 5 is a schematic connection diagram of a device for determining battery health status information according to some embodiments of the present application.
  • the battery system 150 can include a battery module 151 and a BMS 152, wherein the battery module 151 and the BMS 152 can include a communication interface (such as a plug interface), and the BMS 152 can use the The communication interface is connected to the battery module 151 and obtains voltage, current, temperature, time and other parameters of the battery module 151 during charging or discharging.
  • a communication interface such as a plug interface
  • the battery health status information determining device 400 may include one or more communication interfaces and be connected to the battery module 151 and/or the BMS 152 through the communication interface to obtain information related to the battery module 151 from the battery module 151 or the BMS 152. charging data.
  • the battery health status information determining device 400 may be connected between the battery module 151 and the BMS 152.
  • the battery health status information determining device 400 may be connected only to the battery module 151 or the BMS 152.
  • the aforementioned one or more sensors may be connected to the battery health status information determining device 400 through the communication interface.
  • Figure 6 is an exemplary flowchart of a method for determining battery health status information according to some embodiments of the present application.
  • the method 600 may be performed by the battery system 150 (eg, the computing device 300 integrated in the battery system 150, the battery health status information determining device 400 shown in FIG. 4).
  • the battery system 150 eg, the computing device 300 integrated in the battery system 150, the battery health status information determining device 400 shown in FIG. 4.
  • a method for determining battery health status information may include the following steps:
  • Step 610 Obtain charging data related to the battery system.
  • the battery health status information determining device 400 may obtain charging data related to the battery system 150 .
  • the battery system 150 may be a power supply device used to power electric vehicles, electric bicycles, electric motorcycles or other electrical equipment.
  • the battery health status information determining device 400 may obtain charging data related to the battery system 150.
  • the charging data may include at least one of charging voltage, charging current, charging time, charging temperature data, and historical usage data of a single battery, a module, or the entire battery system 150 .
  • the battery health status information determining device 400 (eg, communication module) may obtain the charging data from the battery system 150 through wired communication or wireless communication.
  • Exemplary wired communication methods may include CAN communication, and exemplary wireless communication methods may include Bluetooth, NFC, ZigBee, etc.
  • the communication module can obtain charging data from the battery system 150 in real time and send the charging data to the first evaluation module 420 in real time. During the charging process, the first evaluation module 420 may evaluate the battery health status of the battery system 150 in real time according to the charging data. In some embodiments, when the charging device 110 provides charging services for the battery system 150, the communication module can obtain charging data from the battery system 150 in real time and store the charging data in the storage module. The first evaluation module 420 may evaluate the battery health status of the battery system 150 according to the charging data after charging is completed.
  • the first acquisition module 410 can obtain the charging data from the storage module (for example, the memory 320) of the battery system 150. , and sends the charging data to the first evaluation module 420.
  • the first evaluation module 420 can evaluate the battery health status of the battery system 150 in real time based on the charging data before charging. More details can be found in Figure 11 and its associated description.
  • the aforementioned charging voltage may include a charging start voltage, a charging process characteristic voltage, and a charging end voltage.
  • the charging starting voltage may refer to the input voltage when charging starts;
  • the charging process characteristic voltage may refer to the change characteristics of the input voltage during the charging process;
  • the charging end voltage may refer to the input voltage when charging ends.
  • the charging voltage may be constant voltage or variable voltage. pressure.
  • the charging current may be an input current during charging, and the input current may be variable or constant. In some embodiments, the charging current may be a constant current.
  • the charging time may refer to the time used for this charging. In some embodiments, the charging time can be combined with the charging current to reflect the total power of this charge.
  • the charging temperature data may include charging starting temperature and charging process temperature weight.
  • the charging process temperature weight can be understood as the proportion of the charging starting temperature during the charging process in the health status evaluation. It is understandable that there is a certain relationship between battery temperature and battery capacity. The specific performance is as follows: when the temperature drops, the battery capacity also decreases accordingly. In other words, the health of the battery system 150 is related to the charging starting temperature and the charging process temperature weight. Therefore, in some embodiments, the health status assessment result of the battery system 150 can be made more accurate by taking the charging start temperature and the charging process temperature weight into consideration.
  • the charging temperature data may include temperature change data during the charging process, and abnormality during the charging process may be reflected through the temperature change data during the charging process.
  • the charging process temperature weight may change accordingly as the charging starting temperature changes. For example, when the charging starting temperature is 8°C, the corresponding charging process temperature weight can be 0.2; when the charging starting temperature is 10°C, the corresponding charging process temperature weight can be 0.21; when the charging starting temperature is 11°C , the corresponding charging process temperature weight can be 0.215. It should be noted that the above corresponding relationship between the charging start temperature and the charging process temperature weight is only an exemplary description. In the embodiment of the present application, the corresponding relationship between the charging starting temperature and the charging process temperature weight may be, but not Limited to the above examples.
  • historical usage data may include historical battery health status of battery system 150 .
  • the historical usage data may also include the cumulative charge and discharge capacity of the battery system 150, charge and discharge cycles, number of charge and discharge cycles, charge and discharge depth (ratio of a single charge or discharge amount to battery capacity), discharge time The voltage and current, single discharge time, discharge temperature, driving mileage, battery factory time, etc.
  • the historical usage data may include data related to the battery system 150 when the electrical device (eg, an electric vehicle, an electric bicycle, an electric motorcycle, or other electrical device) is in use or not in use.
  • the historical usage data may include the voltage and current, temperature, accumulated charge and discharge capacity, and total voltage of the battery system of the single cells of the battery system 150 during the driving and/or parking of the electric vehicle.
  • the battery system 150 may include multiple cells (also referred to as single cells) or battery modules, and the historical usage data may include historical battery health corresponding to each cell or battery module. Status, accumulated charge and discharge capacity, charge and discharge cycle, number of charge and discharge cycles, charge and discharge depth, driving mileage, battery factory time, etc.
  • the historical usage data of the battery system 150 can be uploaded to the server 120, and the charging device can obtain the data from the server based on the ID corresponding to the battery system 150 (such as the battery number, the chassis number corresponding to the battery system, etc.) or identification information. 120 obtains historical usage data corresponding to the battery system 150 . In some embodiments, the battery health status information determining device 400 may obtain the historical usage data from the BMS of the battery system 150 .
  • the historical usage data of the battery system 150 can reflect the current health status of the battery system 150 to a certain extent. Therefore, in some embodiments, taking the historical usage data of the battery system 150 into consideration can make the battery system 150 more accurate. The health status assessment results are more accurate.
  • Step 620 Determine health status information related to the battery system based on the charging data.
  • the battery health status information determining device 400 may determine the health status information of the battery system 150 based on the charging data of the battery system 150 .
  • the health status information may include one or more of capacity offset information, SOH value, self-discharge consistency, pressure difference and internal resistance consistency, insulation status, and temperature status related to the battery system 150 .
  • the health status information may include capacity offset information, SOH value, insulation status, temperature status, etc. corresponding to each battery cell or battery module. In some embodiments, the health status information may also include system capacity offset information, self-discharge consistency, pressure difference and internal resistance consistency, insulation status, temperature status, and SOH value of the entire battery system 150 .
  • the capacity offset information may refer to the difference between the current capacity of the cell or module and the standard capacity, and is used to characterize the consistency of the electric vehicle battery system.
  • the standard capacity may be determined based on the average capacity of multiple cells or modules.
  • the standard capacity may be determined based on the capacity of the first fully charged cell or module.
  • the capacity offset information can be obtained based on the aforementioned charging data.
  • the capacity offset information may be capacity offset information corresponding to a single cell or battery module, or may be capacity offset information corresponding to a battery system composed of multiple cells or battery modules. .
  • the current capacity of each cell or battery module (ie, the module capacity shown in Figure 7) can be obtained based on the aforementioned charging data, and then each The current capacity of the battery cell or module is compared with the aforementioned standard capacity to obtain the capacity offset information of each battery cell or module as shown in Figure 8.
  • the SOH (state-of-health) value can be used to characterize the health status of cells, modules or battery systems.
  • the SOH value can be the ratio of actual capacity to rated capacity.
  • the actual capacity can refer to the current maximum battery capacity.
  • the actual capacity may change with the use time, the number of uses (ie, the number of charge and discharge cycles), the use environment temperature, usage habits, etc.
  • the SOH value may change with the use time. , usage frequency, usage environment temperature, usage habits and other reasons.
  • the SOH value can be obtained based on the aforementioned charging data.
  • the SOH value may be the SOH value corresponding to a single cell or battery module, or the SOH value corresponding to a battery system composed of multiple cells or battery modules.
  • Self-discharge consistency can characterize the charge retention capability of cells or modules in a battery system. Through self-discharge consistency, we can know whether the amount of electricity that automatically reduces or disappears in the battery cell or module is consistent when not in use. In some embodiments, the self-discharge consistency can be obtained from the aforementioned charging data.
  • the aforementioned health status information may include consistency of pressure difference and internal resistance
  • the consistency of pressure difference and internal resistance may include consistency of pressure difference and internal resistance consistency.
  • the voltage difference consistency and internal resistance consistency between each cell or module in the battery system can be obtained through the aforementioned charging data. For example, the voltage corresponding to each battery cell or module can be determined based on the aforementioned charging voltage, and then the voltage difference between each battery cell or module can be determined based on the voltage.
  • the internal resistance of each battery cell or module can be determined based on the aforementioned charging voltage and charging current, and then the internal resistance consistency between each battery cell or module can be determined based on the internal resistance.
  • the aforementioned insulation state may refer to the insulation relationship between the charging object and the ground, or may also refer to the insulation relationship between the charging object and an adjacent object (such as a car body).
  • the aforementioned charging data may include insulation voltage and/or insulation resistance between the charging object and other objects, and the insulation status of the charging object can be obtained through the insulation voltage and/or insulation resistance.
  • the battery health status information determining device 400 can process the obtained charging data to obtain the aforementioned health status information of the battery system 150, so as to determine whether there is an abnormality in the battery system 150 and predict the potential of the battery system 150. risk of failure.
  • the battery health status information determining device 400 can preprocess the obtained charging data, and obtain the aforementioned health status information based on the preprocessed charging data. For example, preprocessing may include but is not limited to filtering (such as filtering abnormal data), cleaning, increasing data dimensions, etc.
  • the aforementioned health status information may also include impedance information related to the battery system 150 , and the impedance information may be used to characterize the charging and discharging performance of the cell or battery module and the consistency of the battery system.
  • the impedance information may be the impedance information corresponding to a single cell or battery module, or the impedance information corresponding to a battery system composed of multiple cells or battery modules.
  • the impedance information may be obtained based on the charging voltage and charging current associated with the battery system 150 .
  • the minimum DCR (DC impedance) is 0.154m ⁇
  • the maximum DCR is 0.173m ⁇
  • the average DCR of the module is 0.163m ⁇
  • the maximum DCR difference between modules is about 12%, which can be expressed The consistency of current battery systems is relatively good.
  • the battery health status information determining device 400 may use a trained machine learning model to process the obtained charging data to determine health status information related to the battery system 150 .
  • the battery health status information determining device 400 may use a trained machine learning model to process the preprocessed charging data to determine health status information related to the battery system 150 .
  • the trained machine learning model may include at least one of a state information determination model, a state information prediction model, and a health state judgment model.
  • the battery health status information determination device 400 can use a trained status information determination model to process the charging data (such as data mining, feature extraction, etc.) to determine the current health status information of the battery system 150 .
  • the battery health status information determining device 400 can use a trained status information prediction model to process the charging data and the current health status information to determine future health status information of the battery system in the next time period.
  • the battery health status information determination device 400 can use a trained health status judgment model to process two or more future health status information of the battery system 150 to determine the health status of the battery system 150, such as health, abnormality, etc.
  • the machine learning model may be pre-configured locally in the battery health information determining device 400 (eg, stored in the memory 320), or obtained from the server 120 when the charging service is started. For more information on using machine learning models to determine status information of the battery system, see Figure 10 and its related description.
  • the machine learning model may include one of neural networks, transfer learning, gradient boosting decision trees, cluster analysis, outlier analysis, etc., or any combination thereof.
  • the battery health status information determining device 400 may determine a matching machine learning model based on the type of the battery system 150 .
  • the battery system 150 may be divided into battery types (such as lithium-ion batteries, nickel-metal hydride batteries, fuel cells, lead-acid batteries, sodium-sulfur batteries, etc.) or battery capacity levels/voltage levels/current levels. Different types, and then configure the corresponding machine learning models respectively.
  • the battery health status information determining device 400 processes the charging data of the battery system 150, the corresponding machine learning model can be obtained according to the type of the battery system 150 to process the charging data, thereby better adapting to different conditions. The differences between the battery systems 150 ensure the accuracy of the health status information processed by them.
  • the above machine learning model can be trained through several samples.
  • the state information determination model, the state information prediction model, and the health state judgment model can be trained based on corresponding sample data respectively.
  • the machine learning model when the above machine learning model includes at least two of a state information determination model, a state information prediction model, and a health state judgment model, the machine learning model can be obtained through joint training.
  • the processor for example, the server 120, the processor 310) can obtain training samples, and the training samples Including multiple sample groups, each sample group includes the historical charging data of the corresponding sample battery, the current health status information determined by the above-mentioned status information determination model, the historical future health status information obtained by the above-mentioned status information prediction model, and the above-mentioned health status. Judge the historical health status obtained by the model.
  • the processor can train the initial model based on the training samples to obtain the trained machine learning model, wherein the labels of the training samples include the historical actual health status information of the sample battery corresponding to the historical current health status information, and Historical actual health status information corresponding to historical future health status information, and historical actual health status corresponding to the historical health status.
  • the training samples corresponding to the joint training include sample data corresponding to any two of the models
  • the tags contain historical actual data corresponding to any two of the models described.
  • the above-mentioned machine learning model includes a state information determination model and a state information prediction model.
  • Each sample group in the training sample includes historical charging data of the sample battery, current health status information determined by the state information determination model, and the above state information.
  • the labels of the historical and future health status information obtained by the prediction model include the historical actual health status information of the sample battery corresponding to the historical and current health status information, and the historical actual health status information corresponding to the historical and future health status information.
  • various dimensions of historical original data can be preprocessed to realize the characteristics of the sample data.
  • the obtained training samples can be divided into training data and test data according to a preset ratio (such as 8:2, 6:4, or 7:3, etc.).
  • the training data is used for model training, and the test data is used to test the prediction accuracy of the model. For example, 70% of the above training samples can be used as training data, 30% of the samples can be used as test data, and the training data can be used to train the initial model to obtain a trained machine learning model.
  • the prediction results of the test data can be based on the machine learning model.
  • information, historical actual health status information corresponding to future health status information, historical actual health status corresponding to health status to construct a loss function.
  • the loss function can reflect the difference between the prediction result and the label.
  • the battery health status information determining device 400 or the server 120 may adjust the parameters of the machine learning model based on the loss function to reduce the difference between the prediction results and the labels. For example, by continuously adjusting the parameters of the machine learning model, the value of the loss function is reduced or minimized.
  • the trained machine learning model can also be obtained according to other training methods, for example, setting a corresponding initial learning rate (for example, 0.1) and a learning rate decay strategy for the training process. This application is not limited here.
  • the number of negative samples in the training samples is less than a preset value
  • the number of negative samples can be filled through data simulation or parameter adjustment.
  • the number of corresponding negative samples may be smaller than the preset value.
  • the parameter threshold of the battery can be adaptively reduced based on the corresponding parameter value when the faulty battery fails. For example, if the fault temperature corresponding to a battery that has failed in history is 50°C, the initial threshold of the battery safety temperature can be 55°C and adaptively adjusted to 50°C. When the temperature of a battery is greater than the safe temperature, the probability of failure is higher.
  • batteries greater than the temperature threshold will be defined as faulty batteries when obtaining samples, so the number of negative samples will increase.
  • the battery charging and discharging process can be simulated based on the parameter information of the sample battery, and the sample data can be annotated based on the simulated data.
  • the negative samples are filled to make the training samples richer, thereby improving the accuracy of the prediction results of the trained machine learning model.
  • the training of the machine learning model may be performed by the battery health status information determining device 400 (eg, the first evaluation module 420). In some embodiments, training of the machine learning model may also be performed by the server 120 or other devices.
  • the above machine learning model can be updated regularly (such as daily, weekly, or monthly, etc.).
  • the battery health status information determination device 400 may update the status information determination model based on the actual health status information corresponding to the current health status information predicted by the battery system 150 every Monday, and update the status information based on the actual health status information corresponding to the future health status information.
  • the prediction model updates the health status judgment model based on the health status.
  • the trained machine learning model can be updated in real time.
  • the above machine learning model may be updated in response to update instructions (for example, instructions issued by an external monitoring platform). new.
  • the model update may be performed by the battery health status information determining device 400 (for example, the first evaluation module 420), or may be performed by the server 120 or other devices.
  • the updated model may be sent to the battery health status information determining device 400 .
  • the battery health status information determining device 400 may obtain a program for updating the model from a server or other device (eg, a mobile storage device), and update the locally stored machine learning model according to the program for updating the model.
  • Step 630 Send the health status information to the server.
  • the battery health status information determining device 400 determines the corresponding health status information based on the charging data related to the battery system 150
  • the health status information (such as capacity offset information, SOH value, self-discharge properties, pressure difference and internal resistance consistency, insulation status, and temperature status) and/or health status (eg, healthy, abnormal) are sent to the server 120 .
  • the battery health status information determining device 400 can send the charging data and health status information of the battery system 150 to the server 120 to facilitate remote monitoring of the current status of the battery system 150 .
  • the battery health status information determining device 400 may send the health status of the battery system 150 together with related data (such as a plurality of predicted future health status information) to the server 120 .
  • the charging device 110 may send the aforementioned health status information, the health status, and the ID or identification information corresponding to the battery system 150 to the server together.
  • the server 120 can further process the health status information of the battery cells or battery modules.
  • one or more preset thresholds can be set. When a certain battery cell or battery in the battery system 150 is detected, When the status of the module does not meet the preset threshold (for example, less than or greater than the preset threshold), it is determined that the cell or battery module is abnormal, and it is prompted that it needs to be repaired or replaced.
  • the server 120 when the server 120 determines that there is an abnormality based on the health status information sent by the battery health status information determination device 400, it may further determine the ID or identification information corresponding to the abnormal battery cell or battery module, and then based on The ID or identification information determines the location of the abnormal cell or battery module to facilitate subsequent repair or replacement. In some embodiments, the server 120 determines the health status sent by the device 400 based on the battery health status information. For an abnormal battery system, the server 120 may further determine the ID or identification information corresponding to the abnormal battery cell or battery module, and then based on The ID or identification information determines the location of the abnormal cell or battery module to facilitate subsequent repair or replacement.
  • the server 120 may perform further processing based on the received status data to monitor the operating status of the battery system 150 .
  • server 120 may convert received health status information into monitoring charts.
  • the server 120 can perform capacity fading assessment, cell internal resistance assessment, consistency assessment, cell voltage distribution analysis, temperature rise rate assessment, static voltage difference assessment, and undervoltage data assessment on the battery system based on the received status data. , cumulative charging behavior evaluation, cumulative usage status evaluation, cumulative throughput capacity evaluation, etc.
  • the server 120 can predict the failure risk of the battery system 150 based on the received health status information, and make corresponding warnings when it is predicted that the battery system 150 may have a risk of failure, for example, perform abnormal pressure difference warning, temperature difference warning, etc. Abnormal warning, insulation abnormal warning, abnormal self-discharge rate, etc.
  • the terminal 160 may obtain charging data and/or status data of the battery system 150 from the server 120 .
  • the battery health status information determining device 400 can also directly send the charging data and/or status data of the battery system 150 to the terminal 160 .
  • the terminal 160 can display the charging data and/or status data of the battery system 150 through an output module (such as a display screen), and/or issue an early warning prompt based on the status data.
  • terminal 160 may include the reading device described above.
  • the battery health status information determining device 400 may determine the health status information and/or the health status of the battery system based on the discharge data of the battery system, or the discharge data and charging data.
  • the battery health status information determining device 400 can determine the health status information and/or the health status of the battery system when the battery system is in a discharge state or a resting state (that is, not working).
  • such modifications and changes would not depart from the scope of the present application.
  • Figure 10 is an exemplary flow chart of a battery status information determination method according to some embodiments of the present application.
  • the method 1000 may be performed by the battery system 150 (eg, the computing device 300 integrated in the battery system 150, the battery health status information determining device 400 shown in FIG. 4).
  • the battery health status information determining device 400 can use a trained machine learning model to process the charging data of the battery system, etc., to determine the status information of the battery system, for example, the current health status information. , future health status information, health status, etc.
  • the battery status information determining method may include the following steps:
  • Step 1010 Obtain charging data related to the battery system.
  • the battery health status information determining device 400 may obtain charging data related to the battery system 150 .
  • the charging data may include at least one of charging voltage, charging current, charging time, charging temperature data, and historical usage data of a single battery, a module, or the entire battery system 150 . More details can be seen in Figure 6 (eg step 610), which will not be described again here.
  • Step 1020 Process the charging data through a state information determination model to determine current health state information of the battery system.
  • the battery health status information determination device 400 may use a trained status information determination model to process the charging data to determine the current health status information of the battery system 150 .
  • the current health status information may refer to one or more of the capacity offset information, SOH value, self-discharge consistency, voltage difference and internal resistance consistency, insulation status, and temperature status of the battery system at the current moment.
  • the current moment may include the current time point corresponding to when the battery system is charging, the corresponding time point after charging is completed, the corresponding time point when discharging, etc.
  • the state information determination model may include an acquisition layer and a fusion layer.
  • the acquisition layer can be used to obtain the current charging data of the battery system, and the fusion layer can fuse the current charging data to obtain fused charging data.
  • the fusion layer may fuse the current charging data of the battery system 150 based on a preset weight value. For example, the fusion layer can fuse the charging temperature data of the battery system 150 based on the charging process temperature weight and the charging starting temperature of the battery system 150 to obtain the fused charging temperature. For another example, according to the impact of charging voltage, charging current, charging time, charging temperature, etc.
  • different weight values can be set for each type of data, and the fusion layer can be based on the preset weight value corresponding to the battery system 150 , fuse the charging voltage, charging current, charging time, and charging temperature of the battery system 150 to obtain a set of fused charging data.
  • the preset weight value can be statistically obtained by the server 120 based on historical data of the battery system, or manually set by the user. It can be any reasonable value, and this specification does not limit this.
  • different battery systems, or different single cells, or different battery modules may correspond to different preset weight values.
  • the usage time of the battery system is different, and the corresponding preset weight values are different. For example, new batteries and batteries that have been used for a period of time can correspond to different preset weight values.
  • Step 1030 Process the charging data and the current health status information through a status information prediction model to determine future health status information of the battery system in the next time period.
  • the next time period can include any time period after the current moment, such as the next 30 minutes, 1 hour, 3 hours, 5 hours, one day, one week, etc.
  • Future health status information may refer to one or more of the capacity offset information, SOH value, self-discharge consistency, voltage difference and internal resistance consistency, insulation status, and temperature status of the battery system in the next period of time.
  • the battery health status information determination device 400 may utilize a trained status information prediction model to process the charging data of the battery system 150 and the current health status information obtained through the status information determination model to determine the battery system 150 future health status information.
  • the input data of the state information prediction model is the charging data and current health status information of the battery system, and the output is the future health status information of the battery system in the next preset time period (such as one day, one week, etc.).
  • the battery health status information determining device 400 may use a trained status information prediction model to process the charging data of the battery system 150 and the first future health status information in the first time period to determine the battery system 150 Second future health status information in a second time period.
  • the first time period is earlier than the second time period. For example, if the current time is February 1st, the first time period can be the period from February 1st to February 2nd, and the second time period can be the period from February 2nd to February 3rd.
  • the battery health status information determining device 400 may utilize a trained status information prediction model to determine future health status information of the battery system 150 in one or more different next time periods.
  • Step 1040 Process two or more future health status information through the health status judgment model to determine the health status of the battery system.
  • the health status can reflect whether the battery system is healthy or not, for example, healthy or abnormal.
  • the battery health status information determining device 400 can use a trained health status determination model to process two or more future health status information of the battery system 150 to determine the health status of the battery system 150 .
  • the input of the health status judgment model is two or more future health status information of the battery system
  • the output can be the health or abnormality of the current battery system, such as 1 indicating health and 0 indicating abnormality, or it can be the health or abnormality of the current battery system. probability value.
  • the battery health status information determining device 400 may further determine the health or abnormality of the battery system based on a preset probability threshold.
  • the battery health status information determining device 400 can input the first future health status information of the battery system 150 in the first time period and the second future health status information in the second time period into the trained health status judgment model to obtain the health status judgment.
  • the model outputs the health status of the battery system 150 .
  • the battery health status information determining device 400 may obtain usage feedback information related to the battery system 150 interest.
  • usage feedback information may include pictures, text, sounds, videos, etc.
  • the user can upload through the terminal 160 pictures containing the fault location of the battery system 150 , audio or video containing abnormal sounds of the battery system 150 , or input text or voice related to the use of the battery system 150 .
  • the battery health status information determining device 400 can analyze the usage feedback information to determine the characteristic information of the battery system 150 . In some embodiments, the battery health status information determining device 400 can determine the characteristic information of the battery system 150 through image recognition, sound recognition, or keyword extraction. For example, the battery health status information determining device 400 can classify the text feedback information reported by multiple users on the same battery system by extracting keywords from the text to determine the characteristic information of the battery system 150 . For another example, the battery health status information determining device 400 can compare the abnormal sounds of the battery system in the audio or video uploaded by the user with the original prompt sounds or abnormal sounds of the battery system 150 to obtain the characteristic information of the battery system 150 .
  • the battery health status information determining device 400 may process the characteristic information through a health status determination model to determine the health status of the battery system 150 .
  • the health status evaluation can also be achieved for battery systems that do not have charging data (such as new batteries) or have less charging data, improving the applicability of the battery system. sex.
  • the battery health status information determining device 400 when the battery health status information determining device 400 determines that the battery system 150 is abnormal, the battery system's identification, health status, charging data, and health status information may be sent to the server 120 . After receiving the information, the server 120 can issue a warning, such as sending prompt information and/or battery system related data to the terminal 160 . In some embodiments, the battery health status information determining device 400 may issue a warning in response to determining that the battery system 150 is abnormal.
  • Figure 11 is an exemplary flowchart of a battery status information determination method according to some embodiments of the present application.
  • the method 1100 may be performed by the battery system 150 (eg, the computing device 300 integrated in the battery system 150, the battery health status information determining device 400 shown in FIG. 4).
  • the battery health status information determining device 400 can determine the health category of the battery system based on the usage information, and perform corresponding operations on the battery system based on the health category.
  • the battery status information determining method may include the following steps:
  • Step 1110 Obtain usage information of the battery system.
  • the usage information may include at least one of the usage time, charging times, maintenance times, etc. of the single battery, battery module or battery system.
  • the usage time may refer to the time from the start of use of the battery (for example, the time it was installed on the electrical equipment) to the current moment.
  • the number of charging times can refer to the number of historical charging times of the battery from the factory to the present.
  • the battery health status information determining device 400 may obtain the usage information of the battery system 150 from the server 120 . In some embodiments, the battery health status information determining device 400 may obtain the usage information of the battery system 150 from the storage module. In some embodiments, the battery health status information determining device 400 may determine the usage information of the battery system 150 based on its identification information.
  • Step 1120 Determine the health category of the battery system based on the usage information.
  • the health category can reflect the health level of the battery system, such as high health, low health, and medium health. The higher the health level, the lower the probability of failure of the battery system and the corresponding longer service life. For example, if the battery is new or the usage time is less than the first preset value, the probability of failure is low, and it can be defined as high health; the battery has been repaired many times or the usage time is greater than or equal to the second preset value, and the battery has failure If the probability is high, it is defined as low health; if the battery life is greater than or equal to the first preset value and less than the second preset value, it is defined as medium health.
  • the battery health status information determining device 400 may use a trained classification model to determine the health category of the battery system 150 based on the usage information.
  • Classification models can be trained based on a large amount of labeled sample data.
  • the input of the classification model can be the usage information of the battery system, and the output is the health level, such as first level, second level, and third level, where the lower the level, the healthier it is, or low health, medium health, or high health.
  • the battery health status information determining device 400 may perform different operations for battery systems of different health categories. For example, for a battery system with a high health category, the frequency of evaluating the status information of the battery system can be reduced, such as evaluating the health status information and/or health status every 3 times of charging or once a week; for a battery with a medium health category, system, evaluate health status information and/or health status every 2 times of charging or once a day; for battery systems with low health categories, adaptively increase the frequency of evaluation of status information of the battery system, such as real-time or every time it is charged. their health status information and/or health status.
  • the battery health status information determining device 400 can determine the health category of the battery system 150 in real time or regularly (such as every day), and perform corresponding early warning operations for abnormal conditions of the battery system in a timely manner, for example, for low health categories.
  • the battery system provides timely warnings or data reporting.
  • the frequency of identifying the health category of the battery system 150 may be higher than the frequency of determining its status information.
  • the battery health status information determining device 400 can determine the health category of the battery system 150 in real time. When the health category reaches a preset condition (such as greater than the first level), or every week, the current health status information and future health status information are determined. and/or estimates of health status.
  • Step 1130 In response to the battery system belonging to the low health category, perform corresponding operations on the battery system.
  • At least one of the following operations may be performed on the battery system: determining the health status of the battery system before each charge, reporting target data of the battery system to the server, and The battery system is preset with backup batteries.
  • the target data can include charging temperature, charging voltage, charging current, charging time and other data that have a greater impact on the health of the battery.
  • the battery health status information determining device 400 may determine target data based on historical data.
  • the battery health status information determining device 400 can autonomously switch to the connection line with the backup battery to ensure the normal use of the battery system.
  • the battery health status information determining method 1000 can perform corresponding operations, such as alarming, status assessment, etc., based on the health category of the battery system.
  • steps 1130 the battery health status information determining device 400 can perform corresponding operations, such as alarming, status assessment, etc., based on the health category of the battery system.
  • Figure 12 is a schematic module diagram of a device for determining battery health status information according to other embodiments of the present application.
  • the battery health status information determining device 1200 may be part of the aforementioned charging device 110 .
  • the battery health status information determining device 1200 may be a part of the processor 310.
  • the battery health status information determining device 1200 can be added to a traditional charging device as an independent additional device. By installing the battery health status information determining device 1200 on the charging equipment, the battery health status information determining device 1200 obtains the charging data related to the battery system, stores and calculates the charging data, and determines the health status information related to the battery system. , and then sending the health status information to the server 120, which can reduce the computing load of the server.
  • the battery health status information determining device 1200 may include a second acquisition module 1210 and a second evaluation module 1220 .
  • the second acquisition module 1210 may be used to acquire charging data related to the battery system 150 .
  • the second acquisition module 1210 may acquire charging data related to the battery system 150 from the BMS in the battery system 150 and store it in the storage module (eg, the accessor 130 or the memory 320).
  • the second acquisition module 1210 can acquire the charging voltage, charging current, charging time and other data of the currently charging battery system from its own storage module based on the identification information of the battery system.
  • the second evaluation module 1220 may be configured to determine health status information related to the battery system 150 based on the charging data related to the battery system 150 .
  • the second evaluation module 1220 may use any evaluation algorithm or model to evaluate battery health status information related to the battery system 150 , which is not limited by this application.
  • the method for the second evaluation module 1220 to evaluate the battery health status information is detailed in the description of FIG. 13 .
  • the battery health status information determining device 1200 may further include a communication module (not shown in the figure).
  • the communication module may be used to communicate with the reading device, so that the reading device reads the charging data and/or related to the battery system 150 stored in the storage module (eg, the memory 320) through the communication module. or health status information.
  • the communication module may be used to communicate with the battery system 150 to obtain charging data of the battery system.
  • Figure 13 is an exemplary flow chart of a method for determining battery health status information according to other embodiments of the present application.
  • the method 1300 may be performed by the charging device 110 (eg, the computing device 300 integrated in the charging device 110, the battery health status information determining device 1200 shown in FIG. 12).
  • the charging device 110 eg, the computing device 300 integrated in the charging device 110, the battery health status information determining device 1200 shown in FIG. 12.
  • a method for determining battery health status information may include the following steps:
  • Step 1310 Obtain charging data related to the battery system.
  • the battery health status information determining device 1200 may obtain charging data related to the battery system 150 . In some embodiments, when the battery system 150 is being charged using the charging device 110, the battery health status information determining device 1200 may obtain the charging data of the battery system. In some embodiments, the charging data may include at least one of charging voltage, charging current, charging time, charging temperature data, and historical usage data of a single battery, a module, or the entire battery system 150 . In some embodiments, the battery health status information determining device 1200 may obtain its charging data from the battery system 150 through the communication module.
  • Step 1320 Determine health status information related to the battery system based on the charging data.
  • the battery health status information determining device 1200 may determine the health status information of the battery system 150 based on the charging data of the battery system 150 . In some embodiments, when the battery system belongs to the low health category, the battery health status information determining device 1200 can determine the status information of the battery system based on charging data before each charge. In some embodiments, the battery health status information determining device 1200 may use a trained machine learning model to process the obtained charging data to determine status information related to the battery system 150 . In some embodiments, the battery health status information determining device 1200 may obtain the trained machine learning model from a storage module or server. The method for the charging device to determine the battery system status information is similar to the battery system. For more details, see Figure 6-11 and its related descriptions, which will not be described again here.
  • Step 1330 Send the health status information to the server.
  • the battery health status information determining device 1200 may send the health status information and/or the health status to the server 120 after determining the corresponding health status information based on the charging data related to the battery system 150 .
  • the battery health status information determining device 1200 can send the charging data and health status information of the battery system 150 to the server 120 to facilitate remote monitoring of the current status of the battery system 150 .
  • the battery health status information determining device 1200 may send the health status of the battery system 150 together with related data (such as a plurality of predicted future health status information) to the server 120 .
  • the battery health status information determining device 1200 may send the aforementioned health status information, the health status, and the ID or identification information corresponding to the battery system 150 to the server.
  • Possible beneficial effects brought by the embodiments of this specification include but are not limited to: (1) Integrating a battery health status information determination device or adding a battery health status information determination device in the battery system to realize localized assessment of battery health status information; (2) ) The battery health status information determination device transmits the battery health status information results to a remote data platform or monitoring system through wired or wireless means.
  • the remote data platform or monitoring system does not need to evaluate the battery status, which reduces the need for data from the remote data platform or monitoring system.
  • the processing and computing load reduces the construction and operation costs of a remote data platform or monitoring system; (3) battery health status information can be evaluated through the battery system, charging equipment or monitoring device (for example, server 120), improving battery health status information.
  • the possible beneficial effects may be any one or a combination of the above, or any other possible beneficial effects.
  • numbers are used to describe the quantities of components and properties. It should be understood that such numbers used to describe the embodiments are modified by the modifiers "about”, “approximately” or “substantially” in some examples. Grooming. Unless otherwise stated, “about,” “approximately,” or “substantially” means that the stated number is allowed to vary by ⁇ 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending on the desired features of the individual embodiment. In some embodiments, numerical parameters should account for the specified number of significant digits and use general digit preservation methods. Although the numerical ranges and parameters used to identify the breadth of ranges in some embodiments of this specification are approximations, in specific embodiments, such numerical values are set as accurately as is feasible.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Manufacturing & Machinery (AREA)
  • Chemical & Material Sciences (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Electrochemistry (AREA)
  • General Chemical & Material Sciences (AREA)
  • Secondary Cells (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)

Abstract

一种电池健康状态信息确定方法、装置及电池***。电池***（150）包括：至少一个电池模组（151），电池模组（151）包括至少一个电芯；至少一个存储介质，包括一组指令；以及与至少一个存储介质通信的一个或以上处理器（310），其中，当执行指令时，一个或以上处理器（310）用于：获取与电池***（150）相关的充电数据（610），充电数据包括充电电压、充电电流、充电时间、充电温度数据以及历史使用数据中的至少一个；以及基于充电数据确定与电池***（150）相关的健康状态信息（620）；其中，健康状态信息包括与电池***（150）相关的容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态中的一个或多个。

Description

一种电池健康状态信息确定方法、装置及电池***
优先权声明
本申请要求于2022年3月29日提交的申请号为202210316191.7的中国申请的优先权，其全部内容通过引用并入本文。
技术领域
本申请涉及充电技术领域，特别涉及一种电池健康状态信息确定方法、装置及电池***。
背景技术
近年来，随着电芯与组合电池技术的飞速发展，新能源电动汽车的市场保有率持续增加。一般情况下，电动汽车的运行数据可以传输并储存在数据监控***服务器，进行数据二次开发，如电池剩余容量预估、故障预警、运行统计等。随着新能源电动汽车保有量的增加，势必会增加***服务器的计算压力。
发明内容
本说明书实施例之一提供一种电池***。所述电池***包括至少一个电池模组，所述电池模组包括至少一个电芯；至少一个存储介质，包括一组指令；以及与所述至少一个存储介质通信的一个或以上处理器，其中，当执行所述指令时，所述一个或以上处理器用于：获取与所述电池***相关的充电数据，所述充电数据包括充电电压、充电电流、充电时间、充电温度数据以及历史使用数据中的至少一个；以及基于所述充电数据确定与所述电池***相关的健康状态信息；其中，所述健康状态信息包括与所述电池***相关的容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态中的一个或多个。
在一些实施例中，所述***还包括通信模块，所述通信模块用于与读取设备通信连接，以使所述读取设备通过所述通信模块读取所述健康状态信息。
在一些实施例中，所述基于所述充电数据确定与所述电池***相关的健康状态信息，包括：通过预先配置的机器学习模型对所述充电数据进行处理，以确定所述健康状态信息，所述机器学习模型存储在所述存储介质中。
在一些实施例中，所述基于所述充电数据确定与所述电池***相关的健康状态信息，包括：从服务器获取训练好的机器学习模型；通过所述训练好的机器学习模型对所述充电数据进行处理，以确定所述健康状态信息。
在一些实施例中，所述机器学习模型包括训练好的状态信息确定模型；通过所述机器学习模型对所述充电数据进行处理，以确定所述健康状态信息，包括：通过所述状态信息确定模型对所述充电数据进行处理，以确定所述电池***的当前健康状态信息。
在一些实施例中，所述机器学习模型还包括训练好的状态信息预测模型；所述一个或以上处理器还用于：通过所述状态信息预测模型对所述充电数据和所述当前健康状态信息进行处理，以确定所述电池***在下一时间段的未来健康状态信息。
在一些实施例中，所述机器学习模型还包括训练好的健康状态判断模型；所述一个或以上处理器还用于：获取所述电池***的两个或以上未来健康状态信息，所述两个或以上未来健康状态信息分别对应不同的未来时间段；通过所述健康状态判断模型，对所述两个或以上未来健康状态信息进行处理，以确定所述电池***的健康状态。
在一些实施例中，所述机器学习模型通过以下方式获得：获取训练样本，所述训练样本包括多个样本组，每个所述样本组包括相应样本电池的历史充电数据、通过所述状态信息预测模型获得的历史未来健康状态信息、通过所述健康状态判断模型获得的历史健康状态；基于所述训练样本对初始模型进行训练，获得训练好的机器学习模型；其中，所述训练样本的标签包括与所述历史未来健康状态信息对应的历史实际健康状态信息，以及与所述历史健康状态对应的历史实际健康状态。
在一些实施例中，当所述训练样本中负样本的数量小于预设值时，通过数据模拟或参数调节对 所述负样本的数量进行填充。
在一些实施例中，所述一个或以上处理器还用于：对所述机器学习模型进行更新。
在一些实施例中，所述一个或以上处理器还用于：获取所述电池***的使用信息，所述使用信息包括使用时长、充电次数、维修次数中的至少一个；基于所述使用信息确定所述电池***的健康类别，所述健康类别至少包括高健康类别、中健康类别和低健康类别。
在一些实施例中，所述一个或以上处理器还用于：响应于所述电池***属于所述低健康类别，对所述电池***执行以下操作中的至少一个：在每次充电前判断所述电池***的健康状态、向服务器上报所述电池***的目标数据、为所述电池***预设备用电池。
在一些实施例中，所述一个或以上处理器还用于：获取与所述电池***相关的使用反馈信息；对所述使用反馈信息进行分析，确定所述电池***的特征信息；通过健康状态判断模型，对所述电池***的特征信息进行处理，以确定所述电池***的健康状态。
在一些实施例中，所述充电电压包括充电起始电压、充电过程特征电压、充电截止电压中的至少一个；所述充电温度数据包括充电起始温度、充电过程温度权重中的至少一个；所述历史使用数据包括累计充放电量、累计充放电次数、历史电池健康状态中的至少一个。
在一些实施例中，所述***进一步包括：一个或多个传感器，用于检测所述充电电压、所述充电电流、所述充电温度中的至少一个；电池管理***，用于管理所述电池***的充放电行为；供电模块，用于利用所述电池***存储的电能，为所述电池***的至少一个部件供电；和/或定位模块，用于获取所述电池***的位置信息。
本说明书实施例之一提供一种电池健康状态信息确定装置，用于设置在电池***中预估与所述电池***相关的健康状态信息。所述装置包括：第一获取模块，用于获取与所述电池***相关的充电数据，所述充电数据包括充电电压、充电电流、充电时间、充电温度数据以及历史使用数据中的至少一个；第一评估模块，用于基于所述充电数据确定与所述电池***相关的健康状态信息；其中，所述健康状态信息包括与所述电池***相关的容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态中的一个或多个。
在一些实施例中，所述装置包括存储模块以及通信模块，所述存储模块用于存储所述健康状态信息，所述通信模块用于与读取设备通信连接，以使所述读取设备通过所述通信模块读取存储于所述存储模块的所述健康状态信息。
本说明书实施例之一提供一种电池健康状态信息确定装置，用于设置在充电设备中确定与电池***相关的健康状态信息。所述装置包括：第二获取模块，用于获取与所述电池***相关的充电数据，所述充电数据包括充电电压、充电电流、充电时间、充电温度数据以及历史使用数据中的至少一个；第二评估模块，用于基于所述充电数据确定与所述电池***相关的健康状态信息；其中，所述健康状态信息包括与所述电池***相关的容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态中的一个或多个。
本说明书实施例之一提供一种电池健康状态信息确定方法，由电池***中的处理器执行，所述电池***包括至少一个电池模组，所述电池模组包括至少一个电芯。所述方法包括：获取与所述电池***相关的充电数据，所述充电数据包括充电电压、充电电流、充电时间、充电温度数据以及历史使用数据中的至少一个；以及基于所述充电数据确定与所述电池***相关的健康状态信息；其中，所述健康状态信息包括与所述电池***相关的容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态中的一个或多个。
本说明书实施例之一提供一种电池健康状态信息确定方法，由充电设备中的处理器执行。该方法包括：获取与电池***相关的充电数据，所述充电数据包括充电电压、充电电流、充电时间、充电温度数据以及历史使用数据中的至少一个；以及基于所述充电数据确定与所述电池***相关的健康状态信息；其中，所述健康状态信息包括与所述电池***相关的容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态中的一个或多个。
附图说明
本说明书将以示例性实施例的方式进一步说明，这些示例性实施例将通过附图进行详细描述。 这些实施例并非限制性的，在这些实施例中，相同的编号表示相同的结构，其中：
图1是根据本申请一些实施例所示的充电***的应用场景示意图；
图2是根据本申请一些实施例所示的电池***的组成示意图；
图3是根据本说明书一些实施例所示的示例性计算机设备的软件和/或硬件示意图；
图4是根据本申请一些实施例所示的电池健康状态信息确定装置的模块示意图；
图5是根据本申请一些实施例所示的电池***的连接示意图；
图6是根据本申请一些实施例所示的电池健康状态信息确定方法的示例性流程图；
图7是根据本申请一些实施例所示的模块容量与电芯编号的对应关系图；
图8是根据本申请一些实施例所示的偏移量与电芯编号的对应关系图；
图9是根据本申请一些实施例所示的直流阻抗与电芯编号的对应关系图；
图10是根据本申请一些实施例所示的电池状态确定方法的示例性流程图；
图11是根据本申请一些实施例所示的电池状态信息确定方法的示例性流程图；
图12是根据本申请另一些实施例所示的电池健康状态信息确定装置的模块示意图；以及
图13是根据本申请另一些实施例所示的电池健康状态信息确定方法的示例性流程图。
具体实施方式
为了更清楚地说明本说明书实施例的技术方案，下面将对实施例描述中所需要使用的附图作简单的介绍。显而易见地，下面描述中的附图仅仅是本说明书的一些示例或实施例，对于本领域的普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图将本说明书应用于其它类似情景。除非从语言环境中显而易见或另做说明，图中相同标号代表相同结构或操作。
应当理解，本文使用的“***”、“装置”和/或“模块”是用于区分不同级别的不同组件、元件、部件、部分或装配的一种方法。然而，如果其他词语可实现相同的目的，则可通过其他表达来替换所述词语。
如本说明书和权利要求书中所示，除非上下文明确提示例外情形，“一”、“一个”、“一种”和/或“该”等词并非特指单数，也可包括复数。“多个”可以指“两个或以上”。一般说来，术语“包括”与“包含”仅提示包括已明确标识的步骤和元素，而这些步骤和元素不构成一个排它性的罗列，方法或者设备也可能包含其它的步骤或元素。
本说明书中使用了流程图用来说明根据本说明书的实施例的***所执行的操作。应当理解的是，前面或后面操作不一定按照顺序来精确地执行。相反，可以按照倒序或同时处理各个步骤。同时，也可以将其他操作添加到这些过程中，或从这些过程移除某一步或数步操作。
在电池***中，电池管理***(Battery Management System，BMS)可以获取电池***在充电或放电过程中的电压、电流、温度、时间等参数，然后将上述参数传输至远程服务器(例如，远程数据平台或监控***)。服务器利用接收到的数据进行数据二次开发，如电池剩余容量计算、故障预警、运行统计等。目前，随着新能源电动汽车保有量的增加，势必会增加数据监控***服务器的计算压力。
为解决上述问题，本申请实施例中提供一种电池健康状态信息确定方法、装置及电池***，可以获取与电池***相关的充电数据，并对该充电数据进行存储和计算，确定出与电池***相关的健康状态信息，然后将该健康状态信息发送给服务器。在本申请中，评估电池***状态的操作可以由电池***确定装置本地化进行，而不是统一由远程服务器执行，从而可以在一定程度降低服务器的计算负荷。
下面结合附图对本申请实施例所提供的电池健康状态信息确定方法、装置及电池***进行详细描述。
图1是根据本申请一些实施例所示的充电***的应用场景示意图。
充电***100可以用于充电管理领域。在一些实施例中，可以在电池***、充电设备、或装载电池***的用电设备(例如，电动车等)进行充电数据的存储和/或计算，从而减少远程服务器的计算 压力和监控成本。
参照图1，充电***100可以包括充电设备110、服务器120、存储器130、网络140、电池***150和终端160。其中，充电设备110或电池***150可以包括计算设备(例如，计算设备300)，用于对电池***150相关的充电数据进行处理。
在一些实施例中，充电设备110可以指用于给电池***150(例如，用于给电动汽车供电的电池***)进行充电的设备。在一些实施例中，充电设备110可以是移动设备，也可以是固定设备，例如，可以固定在地面或墙壁上。在一些实施例中，充电设备110可以指安装在停车场、住宅小区或充电站内的充电桩。在一些实施例中，充电设备110也可以包括换电站，用于对电池***150进行更换。
在一些实施例中，如图2所示，电池***150可以包括一个或多个电池模组151，其中每个电池模组151可以由多个单体电池153串联和/或并联获得。电池***150中的处理设备(例如，处理器310)可以获取与电池***相关的充电数据，并对其进行处理。例如，电池***150中的处理设备可以用于获取电池***、电池模组或电芯的充电数据，并基于该充电数据确定电池***、电池模组或电芯的健康状态信息。在一些实施例中，该充电数据可以包括充电电压、充电电流、充电时间、充电温度数据以及电池***150的历史使用数据中的至少一个，该健康状态信息可以包括容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态中的一个或多个。
在一些实施例中，服务器120可以与充电***100中的其他设备(例如，充电设备110、存储器130、电池***150、终端160)进行数据传输。例如，服务器120可以接收充电设备110或电池***150发送的充电数据和/或健康状态信息。又例如，服务器120可以向充电设备110或电池***150发送训练好的机器学***台上实现。例如，该云平台可以包括私有云、公共云、混合云、社区云、分布式云、云间云、多云等或其任意组合。在一些实施例中，服务器110可以为电池监测平台的服务端，如替换电池包的拥有者、电池***的维护平台、或电池***的厂商等。
存储器130可以为充电***100提供数据存储功能。在一些实施例中，存储器130可以是充电设备110、电池***150和/或服务器120的一部分。例如，在一些实施例中，存储器130可以用于存储训练好的机器学***台上实现。
网络140可促进数据和/或信息的交换。在一些实施例中，充电***100中的一个或多个组件可通过网络140发送数据和/或信息给充电***100中的其他组件。例如，服务器120可以通过网络140接收充电设备110或电池***150发送的与电池***相关的状态信息。又例如，服务器120可以通过网络140向电池***150和/或存储器130发送训练好的机器学习模型或用于更新机器学习模型的更新数据。在一些实施例中，网络140可是任意类型的有线或无线网络。例如，网络140可以是或包括公共网络(例如，互联网)、专用网络(例如，局部区域网络(LAN))、有线网络、无线网络(例如，802.11网络、Wi-Fi网络)、帧中继网络、虚拟专用网络(VPN)、卫星网络、电话网络、路由器、集线器、交换机、服务器计算机和/或其任意组合。例如，网络140可以包括光纤网络、电信网络、内联网、无线局部区域网络(WLAN)、城域网(MAN)、公共电话交换网络(PSTN)、蓝牙TM网络、ZigBeeTM网络、近场通信(NFC)网络等或其任意组合。在一些实施例中，网络140可以包括一个或多个网络接入点。例如，网络140可以包括有线或无线网络接入点，如基站和/或网际网络交换点，通过这些接入点，充电***100中的一个或多个组件可连接到网络140上以交换数据和/或信息。
电池***150可以与充电设备110进行电连接，以进行充电。在一些实施例中，电池***150 可以是用于给电动汽车、电动自行车、电动摩托车或其他用电设备进行供电的电池包。在一些实施例中，电池***150可以与充电设备110进行数据传输。例如，在电池***150充电的过程中，电池***150可以从充电设备110获取充电数据，该充电数据可以包括充电电压、充电电流、充电时间中的至少一个。在一些实施例中，电池***150可以包括一个或多个电池模组，每个电池模组可以包括一个或多个单体电池，所述一个或多个电池模组可以协同运作进行供电。在一些实施例中，电池***150可以进一步包括一个或多个传感器，和/或电池管理***(Battery management system，BMS)。所述单体电池可以用于存储电能。每个单体电池上可以包括正极端口和负极端口。在本申请中，单体电池可以是任何类型的电池，例如，铅酸单体电池、镍金属氢化物单体电池、锂离子(Li-ion)单体电池等，本申请不作限制。BMS可以用于管理电池***150的充电、放电行为，收集电池***150的与充电、放电相关的数据，传输收集的数据等。在一些实施例中，电池***150可以通过BMS传输数据。在一些实施例中，BMS可以将数据传输至充电***100的一个或多个设备，例如，充电设备110、服务器120、存储器130、终端160。电池***150内的一个或多个传感器可以检测电池***150的一种或多种特性。例如，所述一个或多个传感器可以包括温度传感器，配置为检测电池***150在充、放电时内部整体温度，和/或内部一个或多个位置的温度。又例如，所述一个或多个传感器可以检测电池***150的充、放电电流、电压等。所述一个或多个传感器可以将检测的数据发送至BMS。在一些实施例中，电池***150还可以包括供电模块，该供电模块可以用于利用电池***存储的电能，并在BMS的控制下为外部设备和/或电池***150中的至少一个部件供电。在一些实施例中，电池***150还可以包括定位模块，用于获取电池***的位置信息。通过定位模块可以实时获取电池***的位置信息，从而在电池发生故障或异常时，基于位置信息及时进行相应的处理。例如，服务器120可以获取电池***150通过定位模块获得的位置信息，从而在电池故障时安排维修人员前往维修，或追溯电池资产、监控电池状态，或在电池受到损坏时终止使用等。在一些实施例中，电池***150还可以包括其他定制化的模块，如显示模块，本说明书对此不做限制。
终端160可以是各类具有信息接收和/或发送功能的设备。用户可以通过终端160与服务器120交互。例如，电池***150在本地对电池***相关的健康状态信息进行评估后，可以将评估结果通过网络140发送至服务器120。用户可以通过终端160从服务器120接收电池健康状态信息预估结果。又例如，用户可以通过终端160向服务器120发送评估电池健康状态信息的请求。服务器120可以将所述请求发送至电池***150，使电池***150在本地对相关的健康状态信息进行评估。在一些实施例中，终端160可以包括手机160-1、平板电脑160-2、个人电脑160-3、以及其他电子设备，例如，车载设备，检维修设备等。在一些实施例中，所述用户可以包括电池使用者(例如，电动汽车使用者)、电池制造商、电动汽车制造商等。
应当注意，以上关于充电***100的描述仅出于说明的目的，而无意于限制本说明书的范围。对于本领域普通技术人员而言，可以根据本说明书进行各种变型和修改。例如，充电***100还可以包括用电设备，例如电动汽车等。然而，这些变化和修改不脱离本说明书的范围。
图3是根据本说明书一些实施例所示的示例性计算机设备的软件和/或硬件示意图。
在一些实施例中，计算设备300可以为充电设备110或电池***150的一部分，用于基于与电池***相关的充电数据，确定电池***的状态信息(例如，当前健康状态信息、未来健康状态信息、健康状态、健康类别等)。例如，计算设备300集成在充电设备110中时，充电设备110可以直接基于当前正在充电的电池***的充电电压、充电电流、充电时间等充电数据，从而确定该电池***的当前健康状态信息、未来健康状态信息、或健康状态等。又如，计算设备300集成在电池***150中时，电池***150可以从充电设备110获取充电电压、充电电流、充电时间等充电数据，并基于充电数据确定该电池***的当前健康状态信息、未来健康状态信息、或健康状态等。
如图3所示，在一些实施例中，计算设备300可以包括处理器310、内存320、输入/输出330和通信端口340。
处理器310可以执行计算机指令(例如，程序代码)并根据本文描述的方法确定电池***的健康相关的信息。计算机指令可以包括例如例程、程序、对象、组件、数据结构、过程、模块和功能，它们执行这里描述的特定功能。例如，处理器310可以获取与电池***150相关的充电数据，并基于所述充电数据确定所述电池***的当前健康状态信息、未来健康状态信息或健康状态。在一些实施例中，处理器310可以包括至少一个处理设备(例如，单芯处理设备或多核多芯处理设备)。仅作为示例，处理设备可以包括中央处理器(CPU)、专用集成电路(ASIC)、专用指令处理器(ASIP)、图形处理器 (GPU)、物理处理器(PPU)、数字信号处理器(DSP)、现场可编程门阵列(FPGA)、可编辑逻辑电路(PLD)、控制器、微控制器单元、精简指令集电脑(RISC)、微处理器等或以上任意组合。
仅仅为了说明，在计算设备300中仅描述了一个处理器。然而，应该注意的是，在一些实施例中，计算设备300还可以包括多个处理器，说明书中描述的一个处理器执行的操作和/或方法步骤也可以由多个处理器共同或单独执行。例如，若计算设备300的处理器同时执行操作A和B，则应当理解，操作A和操作B可以由计算设备300中的两个或多个不同的处理器共同或单独地执行(例如，第一处理器执行操作A，第二处理器执行操作B，或者第一处理器和第二处理器联合执行操作A和B)。
内存320可以存储从充电设备110、电池***150、终端160和/或充电***100中的任何其他组件获得的数据/信息。这里使用的术语数据可以是任何信息，包括例如数字、文本、语音、图像、视频、参数、代码、公式、文件、算法、程序等，或其任何组合。例如，内存320可以用于存储训练好的机器学习模型。又如，内存320可以用于存储与电池***150相关的充电数据和/或状态信息。又例如，处理器310可以通过网络140接收服务器120发送的评估模型更新信息，并存储在内存320中。处理器310可以根据模型更新信息对评估模型进行更新。在一些实施例中，内存320可以存储由处理器310执行的程序和/或指令，例如计算机程序。在一些实施例中，内存320可以包括大容量存储器、可移动存储、易失性读写存储器、只读存储器(ROM)或其任意组合。
输入/输出330可用于输入和/或输出信号、数据、信息等。在一些实施例中，输入/输出330可使用户能够与充电***100中的组件(例如，充电设备110、服务器120)交互。在一些实施例中，输入/输出330可以包括输入设备和输出设备。示例性输入设备可以包括键盘、鼠标、触摸屏、麦克风或其任何组合。示例性输出设备可以包括显示设备、扬声器、打印机、投影仪或其任何组合。示例性显示装置可包括液晶显示器(LCD)、基于发光二极管(LED)的显示器、平板显示器、曲面显示器、电视装置、阴极射线管或其任何组合。
通信端口340可以与网络(例如，网络140)连接以促进数据通信。通信端口340可以建立服务器120与充电设备110、存储器130、电池***150和/或终端160之间的连接。连接可以包括有线连接和无线连接。在一些实施例中，通信端口340可以是和/或包括标准化通信端口，例如RS232、RS485等。在一些实施例中，通信端口340可以是专门设计的通信端口。
图4是根据本申请一些实施例所示的电池健康状态信息确定装置的模块示意图。
在一些实施例中，电池健康状态信息确定装置400可以是前述电池***150的一部分。例如，计算设备300集成于电池***150时，电池健康状态信息确定装置400可以为处理器310的一部分。在一些实施例中，电池健康状态信息确定装置400可以作为一个独立的额外装置加装到传统的电池***，从而为传统的电池***提供本地化的电池健康状态信息确定功能。需要说明的是，在一些实施例中，通过在传统电池***的基础上加装电池健康状态信息确定装置400以实现本地化的电池健康状态信息确定功能，可以免于更换电池***。
如图4所示，在一些实施例中，电池健康状态信息确定装置400可以包括第一获取模块410及第一评估模块420。
第一获取模块410可以用于获取与电池***150相关的充电数据。在一些实施例中，该充电数据可以包括充电电压、充电电流、充电时间、充电温度数据以及历史使用数据中的至少一个。例如，第一获取模块410可以从电池***150中的BMS获取与电池***150相关的充电数据，并将其存储在存储模块(例如，内存320)中。在一些实施例中，第一获取模块410可以用于获取训练好的机器学习模型。
第一评估模块420可以用于基于电池***150相关的充电数据确定与电池***150相关的健康状态信息。例如，第一评估模块420可以从内存320中读取健康状态判断模型，进行电池健康状态的评估。在一些实施例中，该健康状态信息可以包括与电池***150相关的容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态中的一个或多个。在一些实施例中，第一评估模块420可以利用任何评估算法或模型对电池***150相关的电池健康状态信息进行评估，本申请不作限制。第一评估模块420进行电池健康状态信息评估的方法详见图6的描述。
在一些实施例中，电池健康状态信息确定装置400还可以包括通信模块(图中未示出)。在一些实施例中，通信模块可以用于与读取设备通信连接，以使读取设备通过该通信模块读取存储于存储模块(例如，内存320)的与电池***150相关的充电数据和/或健康状态信息。从而方便在检维修或梯次 利用电芯筛选时快速获取电池***150相关的充电数据和/或健康状态信息。在一些实施例中，读取设备可以指具有数据读取功能的终端设备(例如，终端160)，例如，检维修设备等。在一些实施例中，可以通过读取设备读取电池***150相关的充电数据和/或健康状态信息，从而基于该充电数据和/或健康状态信息判断电池***150的当前状态。在一些实施例中，通信模块与读取设备的通信连接可以包括近距离通信连接，例如，NFC，射频识别(RFID)、蓝牙、ZigBee、红外等。在一些实施例中，通信模块与读取设备的通信连接也可以包括远距离通信连接。在一些实施例中，通信模块可以实现电池健康状态信息确定装置400与BMS之间的通讯。例如，第一获取模块410可以通过控制器局域网络(Controller Area Network，CAN)通讯，从BMS 152接收电池***150在充电过程的充电数据，例如，电池单体或模组电压、电池单体或模组温度、电池单体或模组充电电流、充电持续时间等。通信模块可以将充电数据发送至第二评估模块420和/或存储模块。
图5是根据本申请一些实施例所示的电池健康状态信息确定装置的连接示意图。
如图5所示，在一些实施例中，电池***150可以包括电池模组151及BMS 152，其中，电池模组151和BMS 152可以包括通信接口(例如插接接口)，BMS 152可以通过该通信接口与电池模组151连接，并获取电池模组151在充电或放电过程中的电压、电流、温度、时间等参数。
电池健康状态信息确定装置400可以包括一个或多个通信接口，并通过该通信接口与电池模组151和/或BMS 152连接，以从电池模组151或BMS 152处获取与电池模组151相关的充电数据。在一些实施例中，电池健康状态信息确定装置400可以连接在电池模组151与BMS 152之间。在一些实施例中，电池健康状态信息确定装置400可以仅与电池模组151或BMS 152连接。在一些实施例中，前述一个或多个传感器可以通过该通信接口与电池健康状态信息确定装置400连接。
应当注意的是，以上描述仅仅是出于说明的目的而提供的，并不旨在限制本申请的范围。对于本领域的普通技术人员来说，可以根据本申请的描述，做出各种各样的变化和修改。然而，这些变化和修改不会背离本申请的范围。
图6是根据本申请一些实施例所示的电池健康状态信息确定方法的示例性流程图。
在一些实施例中，方法600可以由电池***150(例如，集成在电池***150中计算设备300、图4所示的电池健康状态信息确定装置400)执行。
参照图6，在一些实施例中，电池健康状态信息确定方法可以包括如下步骤：
步骤610，获取与电池***相关的充电数据。
在一些实施例中，电池健康状态信息确定装置400可以获取电池***150相关的充电数据。电池***150可以是用于给电动汽车、电动自行车、电动摩托车或其他用电设备进行供电的供电装置。
在一些实施例中，当充电设备110为电池***150提供充电服务时，电池健康状态信息确定装置400可以获取与电池***150相关的充电数据。在一些实施例中，该充电数据可以包括单体电池、模组或整个电池***150的充电电压、充电电流、充电时间、充电温度数据以及历史使用数据等中的至少一个。在一些实施例中，电池健康状态信息确定装置400(例如，通信模块)可以通过有线通信或无线通信的方式从电池***150获取该充电数据。示例性的有线通信方式可以包括CAN通信，示例性的无线通信方式可以包括蓝牙、NFC、ZigBee等。在一些实施例中，当充电设备110为电池***150提供充电服务时，通信模块可以从电池***150实时获取充电数据，并将充电数据实时发送至第一评估模块420。在充电过程中，第一评估模块420可以根据充电数据实时评估电池***150的电池健康状态。在一些实施例中，当充电设备110为电池***150提供充电服务时，通信模块可以从电池***150实时获取充电数据，并将充电数据存储在存储模块中。第一评估模块420可以在充电结束后根据充电数据评估电池***150的电池健康状态。
在一些实施例中，若当前电池***属于低健康类别，在充电设备110为电池***150提供充电服务前，第一获取模块410可以从电池***150的存储模块(例如，内存320)获取充电数据，并将充电数据发送至第一评估模块420。第一评估模块420可以在充电前，根据充电数据实时评估电池***150的电池健康状态。更多详细内容可以参见图11及其相关描述。
在一些实施例中，前述充电电压可以包括充电起始电压、充电过程特征电压、充电截止电压。其中，充电起始电压可以指充电开始时的输入电压；充电过程特征电压可以指充电过程中的输入电压的变化特征；充电截止电压可以指充电截止时的输入电压。在一些实施例中，该充电电压可以为恒压或变 压。
在一些实施例中，充电电流可以为充电时的输入电流，该输入电流可以是变化的或恒定的。在一些实施例中，该充电电流可以为恒流。
在一些实施例中，充电时间可以指本次充电所用的时间。在一些实施例中，该充电时间可以与充电电流相结合，用于反映本次充电的总电量。
在一些实施例中，充电温度数据可以包括充电起始温度、充电过程温度权重。在一些实施例中，充电过程温度权重可以理解为充电过程中的充电起始温度这一因素在其健康状态评估中所占的比重。可以理解的是，电池温度与电池容量存在一定的联系，具体表现为：温度下降，电池容量也相应减小。换言之，即电池***150的健康程度与充电起始温度、充电过程温度权重相关。因此，在一些实施例中，通过将充电起始温度、充电过程温度权重加入考虑可以使得对电池***150的健康状态评估结果更加准确。在一些实施例中，该充电温度数据可以包括充电过程中的温度变化数据，通过充电过程中的温度变化数据可以反映充电过程中的异常。
在一些实施例中，充电过程温度权重可以随充电起始温度的变化而相应变化。例如，充电起始温度为8℃时，对应的充电过程温度权重可以为0.2；当充电起始温度为10℃时，对应的充电过程温度权重可以为0.21；当充电起始温度为11℃时，对应的充电过程温度权重可以为0.215。需要说明的是，以上关于充电起始温度和充电过程温度权重的对应关系仅为示例性说明，在本申请实施例中，充电起始温度与充电过程温度权重之间的对应关系可以是但不限于上述例举情况。
在一些实施例中，历史使用数据可以包括电池***150的历史电池健康状态。在一些实施例中，历史使用数据还可以包括电池***150的累计充放电量、充放电周期、充放电循环次数、充放电深度(单次充电量或放电量与电池容量的比值)、放电时的电压电流、单次放电时间、放电温度、行驶里程、电池出厂时长等。在一些实施例中，历史使用数据可以包括用电设备(例如，电动汽车、电动自行车、电动摩托车或其他用电设备)使用或未使用时，电池***150的相关数据。以电动汽车为例，历史使用数据可以包括电动汽车行使过程中和/或停放过程中，电池***150的单体电池的电压电流、温度、累积充放电量、电池***的总压等。在一些实施例中，电池***150可以包括多个电芯(也可以称为单体电池)或电池模组，该历史使用数据可以包括与每一个电芯或电池模组分别对应的历史电池健康状态、累计充放电量、充放电周期、充放电循环次数、充放电深度、行驶里程、电池出厂时长等。在一些实施例中，电池***150的历史使用数据可以上传至服务器120，充电设备可以基于电池***150所对应的ID(例如电池编号、电池***所对应的车架号等)或标识信息从服务器120获取电池***150所对应的历史使用数据。在一些实施例中，电池健康状态信息确定装置400可以从电池***150的BMS获取该历史使用数据。
需要说明的是，电池***150的历史使用数据可以在一定程度反映电池***150当前的健康状态，因此，在一些实施例中，通过将电池***150的历史使用数据加入考虑可以使得对电池***150的健康状态评估结果更加准确。
步骤620，基于所述充电数据确定与所述电池***相关的健康状态信息。
在一些实施例中，电池健康状态信息确定装置400可以基于电池***150的充电数据确定电池***150的健康状态信息。在一些实施例中，该健康状态信息可以包括与电池***150相关的容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态中的一个或多个。
在一些实施例中，该健康状态信息可以包括与每一个电芯或电池模组分别对应的容量偏移信息、SOH值、绝缘状态以及温度状态等。在一些实施例中，该健康状态信息也可以包括整个电池***150的***容量偏移信息、自放电一致性、压差与内阻一致性、绝缘状态、温度状态以及SOH值。
在一些实施例中，容量偏移信息可以指电芯或模组的当前容量相对于标准容量的差值，用于表征电动汽车电池***的一致性。在一些实施例中，该标准容量可以基于多个电芯或模组的平均容量确定。在一些实施例中，该标准容量可以基于最先充满电的电芯或模组的容量确定。在一些实施例中，该容量偏移信息可以基于前述充电数据得到。在一些实施例中，该容量偏移信息可以是单个电芯或电池模组所对应的容量偏移信息，也可以是多个电芯或电池模组构成的电池***所对应的容量偏移信息。示例性的，参照图7和图8，在一些实施例中，可以先基于前述充电数据得到每一个电芯或电池模组的当前容量(即图7所示的模块容量)，然后将每一个电芯或模组的当前容量与前述标准容量相比较，得到如图8所示的每一个电芯或模组的容量偏移信息。
SOH(state-of-health)值可以用于表征电芯、模组或电池***的健康状态，在一些实施例中，SOH值可以为实际容量与额定容量的比值。其中，实际容量可以指当前最大电池容量，该实际容量可能随使用时间、使用次数(即充放电循环次数)、使用环境温度、使用习惯等原因改变，换句话说，即SOH值可能随使用时间、使用次数、使用环境温度、使用习惯等原因变化。在一些实施例中，该SOH值可以基于前述充电数据得到。在一些实施例中，该SOH值可以是单个电芯或电池模组所对应的SOH值，也可以是多个电芯或电池模组构成的电池***所对应的SOH值。
自放电一致性可以表征电池***中的电芯或模组的荷电保持能力。通过自放电一致性可以知道，在无使用情况下电芯或模组中自动减少或消失的电量是否一致。在一些实施例中，该自放电一致性可以通过前述充电数据得到。
在一些实施例中，前述健康状态信息可以包括压差与内阻一致性，该压差与内阻一致性可以包括压差一致性以及内阻一致性。在一些实施例中，可以通过前述充电数据得到电池***中各个电芯或模组之间的压差一致性及内阻一致性。例如，可以基于前述充电电压确定每一个电芯或模组对应的电压，然后基于该电压确定各个电芯或模组之间的压差。又例如，可以基于前述充电电压和充电电流确定每一个电芯或模组的内阻，然后基于该内阻确定各个电芯或模组之间的内阻一致性。
在一些实施例中，前述绝缘状态可以指充电对象与地之间的绝缘关系，也可以指充电对象与相邻物体(例如汽车车身)之间的绝缘关系。在一些实施例中，前述充电数据可以包括充电对象与其他物体之间的绝缘电压和/或绝缘电阻，通过该绝缘电压和/或绝缘电阻可以得到该充电对象的绝缘状态。
在一些实施例中，电池健康状态信息确定装置400可以将获取到的充电数据进行处理，获得电池***150的前述健康状态信息，以据此判断电池***150是否存在异常，并预测电池***150潜在的故障风险。在一些实施例中，电池健康状态信息确定装置400可以对获取到的充电数据进行预处理，基于预处理后的充电数据获得前述健康状态信息。例如，预处理可以包括但不限于过滤(如过滤异常的数据)、清洗、数据维度增加等。
在一些实施例中，前述健康状态信息还可以包括与电池***150相关的阻抗信息，该阻抗信息可以用于表征电芯或电池模组的充放电性能以及电池***的一致性。在一些实施例中，阻抗信息可以是单个电芯或电池模组所对应的阻抗信息，也可以是多个电芯或电池模组构成的电池***所对应的阻抗信息。在一些实施例中，该阻抗信息可以基于电池***150相关的充电电压及充电电流得到。示例性的，参照图9，在一些实施例中，最小DCR(直流阻抗)为0.154mΩ，最大DCR为0.173mΩ，模块平均DCR为0.163mΩ，模块之间最大DCR差异为12％左右，可以表示当前电池***的一致性相对较好。
在一些实施例中，电池健康状态信息确定装置400可以采用训练好的机器学习模型对获取到的充电数据进行处理，以确定电池***150相关的健康状态信息。在一些实施例中，电池健康状态信息确定装置400可以采用训练好的机器学习模型对预处理后的充电数据进行处理，以确定电池***150相关的健康状态信息。在一些实施例中，训练好的机器学习模型可以包括状态信息确定模型、状态信息预测模型和健康状态判断模型中的至少一个。例如，电池健康状态信息确定装置400可以采用训练好的状态信息确定模型对所述充电数据进行处理(如数据挖掘、特征提取等)，以确定电池***150的当前健康状态信息。又如，电池健康状态信息确定装置400可以采用训练好的状态信息预测模型对所述充电数据和所述当前健康状态信息进行处理，以确定所述电池***在下一时间段的未来健康状态信息。又如，电池健康状态信息确定装置400可以采用训练好的健康状态判断模型对电池***150的两个或以上未来健康状态信息进行处理，确定电池***150的健康状态，例如，健康、异常等。在一些实施例中，该机器学习模型可以预先配置在电池健康状态信息确定装置400本地(例如，存储在内存320中)，或在启动充电服务时从服务器120获取。更多采用机器学习模型确定电池***的状态信息的内容可以参见图10及其相关描述。
在一些实施例中，该机器学习模型可以包括神经网络、迁移学习、梯度提升决策树、聚类分析、离群分析等中的一种或其任意组合。
在一些实施例中，电池健康状态信息确定装置400可以基于电池***150的类型确定与其匹配的机器学习模型。例如，在一些实施例中，可以根据电池类型(如锂离子电池、镍氢电池、燃料电池、铅酸电池和钠硫蓄电池等)或电池容量等级/电压等级/电流等级将电池***150分为不同的类型，然后分别配置对应的机器学习模型。当电池健康状态信息确定装置400对电池***150的充电数据进行处理时，可以根据电池***150的类型获取相应的机器学习模型对充电数据进行处理，从而更好地适应不同 电池***150之间的差异性，确保其处理得到的健康状态信息的准确性。
需要说明的是，上述机器学习模型可以通过若干样本训练得到。在一些实施例中，状态信息确定模型、状态信息预测模型和健康状态判断模型可以分别基于相应的样本数据训练获得。
在一些实施例中，当上述机器学习模型包含状态信息确定模型、状态信息预测模型和健康状态判断模型中至少两个时，该机器学习模型可以通过联合训练获得。以上述机器学习模型包含状态信息确定模型、状态信息预测模型和健康状态判断模型为例，在一些实施例中，处理器(例如，服务器120、处理器310)可以获取训练样本，所述训练样本包括多个样本组，每个样本组包括相应样本电池的历史充电数据、通过上述状态信息确定模型确定的当前健康状态信息、通过上述状态信息预测模型获得的历史未来健康状态信息、通过上述健康状态判断模型获得的历史健康状态。进一步地，所述处理器可以基于训练样本对初始模型进行训练，获得训练好的机器学习模型，其中，训练样本的标签包括样本电池的与历史当前健康状态信息对应的历史实际健康状态信息、与历史未来健康状态信息对应的历史实际健康状态信息，以及与所述历史健康状态对应的历史实际健康状态。
需要说明的是，当上述机器学习模型包含状态信息确定模型、状态信息预测模型和健康状态判断模型中任意两个时，联合训练对应的训练样本包含与所述任意两个模型对应的样本数据，标签包含与所述任意两个模型对应的历史实际数据。例如，上述机器学习模型包含状态信息确定模型、状态信息预测模型，训练样本中每个样本组包括样本电池的历史充电数据、通过所述状态信息确定模型确定的当前健康状态信息、通过上述状态信息预测模型获得的历史未来健康状态信息，标签包括样本电池的与历史当前健康状态信息对应的历史实际健康状态信息、与历史未来健康状态信息对应的历史实际健康状态信息。
在一些实施例中，可以对历史原数据各维度(如充电/放电电压、充电/放电电流、电池容量、充电/放电时间、充电/放电温度等)进行预处理，实现对样本数据的特征的选择，从而获得训练样本。在一些实施例中，可以将获得的训练样本按照预设比例(如8:2、6:4、或7:3等)划分为训练数据和测试数据。其中，训练数据用于进行模型训练，测试数据用于测试模型的预测准确度。例如，可以将上述训练样本中70％的样本作为训练数据，30％的样本作为测试数据，使用训练数据对初始模型进行训练，获得训练好的机器学习模型。在一些实施例中，可以基于机器学习模型对测试数据的预测结果(如当前健康状态信息、未来健康状态信息、健康状态)与测试数据的标签(如与当前健康状态信息对应的历史实际健康状态信息、与未来健康状态信息对应的历史实际健康状态信息、与健康状态对应的历史实际健康状态)构建损失函数。损失函数可以反映预测结果与标签之间的差异大小。电池健康状态信息确定装置400或服务器120可以基于损失函数对机器学习模型的参数进行调整，以减小预测结果与标签之间的差异。例如，通过不断调整机器学习模型的参数，使得损失函数值减小或最小化。在一些实施例中，还可以根据其他训练方法得到训练好的机器学习模型，例如，为训练过程设置相应的初始学习率(例如，0.1)、学习率衰减策略。本申请在此不做限制。
在一些实施例中，当训练样本中负样本的数量小于预设值时，可以通过数据模拟或参数调节对负样本的数量进行填充。例如，异常或故障电池的数量较少时，相应的负样本的数量可能会小于预设值。示例性地，当负样本的数量小于预设值时，可以基于故障电池发生故障时对应的参数值，适应性降低电池的参数阈值。例如，若历史上发生故障的电池对应的故障温度为50℃，则可以将电池安全温度的初始阈值55℃，适应性调整为50℃。当电池的温度大于安全温度时，其发生故障的概率较高，将安全温度的阈值降低后，获取样本时将大于该温度阈值的电池定义为故障电池，从而负样本的数量将增加。又如，可以根据样本电池的参数信息模拟电池充放电过程，基于模拟数据进行样本数据标注。
负样本的数量小于预设值时，通过对负样本进行填充，使得训练样本更丰富，从而提高训练好的机器学习模型的预测结果的准确性。
在一些实施例中，机器学习模型的训练可以由电池健康状态信息确定装置400(例如，第一评估模块420)执行。在一些实施例中，机器学习模型的训练也可以由服务器120或其他设备执行。
在一些实施例中，可以定期(如每天、每周、或每月等)对上述机器学***台发布的指令)对上述机器学习模型进行更 新。模型更新可以由电池健康状态信息确定装置400(例如，第一评估模块420)执行，也可以由服务器120或其他设备执行。更新后的模型可以发送至电池健康状态信息确定装置400。在一些实施例中，电池健康状态信息确定装置400可以从服务器或其它设备(例如，移动存储设备)获取更新模型的程序，根据更新模型的程序对本地存储的机器学习模型进行更新。
步骤630，将所述健康状态信息发送给服务器。
在一些实施例中，电池健康状态信息确定装置400在基于电池***150相关的充电数据确定其对应的健康状态信息后，可以将该健康状态信息(例如容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态)和/或健康状态(例如健康、异常)发送给服务器120。在一些实施例中，电池健康状态信息确定装置400可以将电池***150的充电数据以及健康状态信息一同发送至服务器120，以便于远程监控电池***150的当前状态。在一些实施例中，电池健康状态信息确定装置400可以将电池***150的健康状态以及相关的数据(例如预测的多个未来健康状态信息)一同发送至服务器120。在一些实施例中，充电设备110可以将前述健康状态信息、健康状态以及电池***150对应的ID或标识信息一同发送至服务器。
在一些实施例中，服务器120可以对电芯或电池模组的健康状态信息进行进一步处理，例如，可以设置一个或多个预设阈值，在检测到电池***150中的某一个电芯或电池模组的状态不符合预设阈值时(例如，小于或大于预设阈值)，则判断该电芯或电池模组异常，提示需要对其进行维修或更换。
在一些实施例中，服务器120基于电池健康状态信息确定装置400发送的健康状态信息判断出存在异常时，可以进一步地确定存在异常的电芯或电池模组所对应的ID或标识信息，然后基于ID或标识信息确定异常电芯或电池模组所在的位置，以便于后续的维修或更换。在一些实施例中，服务器120基于电池健康状态信息确定装置400发送的健康状态，对于异常的电池***，可以进一步地确定存在异常的电芯或电池模组所对应的ID或标识信息，然后基于ID或标识信息确定异常电芯或电池模组所在的位置，以便于后续的维修或更换。
在一些实施例中，服务器120可以基于接收到的状态数据进行进一步处理以监控电池***150的运行状态。例如，在一些实施例中，服务器120可以将接收到的健康状态信息转化为监控图表。又如，服务器120可以基于接收到的状态数据对电池***进行容量衰减评估、电芯内阻评估、一致性评估、单体电压分布分析、温升速率评估、静态压差评估、欠压数据评估、累计充电行为评估、累计使用状态评估、累计吞吐容量评估等。在一些实施例中，服务器120可以基于接收到的健康状态信息预测电池***150的故障风险，并在预测到电池***150可能存在故障风险时作出相应的预警，例如，进行压差异常预警、温差异常预警、绝缘异常预警、自放电率异常等。
在一些实施例中，终端160可以从服务器120获取电池***150的充电数据和/或状态数据。在一些实施例中，电池健康状态信息确定装置400也可以直接将电池***150的充电数据和/或状态数据发送至终端160。在一些实施例中，终端160可以通过输出模块(例如显示屏)显示电池***150的充电数据和/或状态数据，和/或根据状态数据发出预警提示。在一些实施例中，终端160可以包括上述读取设备。
应当注意的是，以上关于电池健康状态信息确定方法及其流程的描述，仅出于说明的目的而提供，并非旨在限制本申请的范围。对于本领域的普通技术人员来说，可以根据本申请的描述，做出各种各样的修正和改变。例如，电池健康状态信息确定装置400可以基于电池***的放电数据、或放电数据和充电数据，确定电池***的健康状态信息和/或健康状态。又如，电池健康状态信息确定装置400可以当电池***处于放电状态或静置状态(即不工作)时，确定电池***的健康状态信息和/或健康状态。然而，这些修正和改变不会背离本申请的范围。
图10是根据本申请一些实施例所示的电池状态信息确定方法的示例性流程图。
在一些实施例中，方法1000可以由电池***150(例如，集成在电池***150中计算设备300、图4所示的电池健康状态信息确定装置400)执行。如图10所示，在一些实施例中，电池健康状态信息确定装置400可以采用训练好的机器学习模型对电池***的充电数据等进行处理，确定电池***的状态信息，例如，当前健康状态信息、未来健康状态信息、健康状态等。
参照图10，在一些实施例中，电池状态信息确定方法可以包括如下步骤：
步骤1010，获取与电池***相关的充电数据。
在一些实施例中，电池健康状态信息确定装置400可以获取与电池***150相关的充电数据。在一些实施例中，该充电数据可以包括单体电池、模组或整个电池***150的充电电压、充电电流、充电时间、充电温度数据以及历史使用数据等中的至少一个。更多详细内容可以参见图6(例如步骤610)，此处不再赘述。
步骤1020，通过状态信息确定模型对所述充电数据进行处理，以确定所述电池***的当前健康状态信息。
在一些实施例中，电池健康状态信息确定装置400可以利用训练好的状态信息确定模型对所述充电数据进行处理，以确定电池***150的当前健康状态信息。当前健康状态信息可以指电池***在当前时刻的容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态中的一个或多个。例如，当前时刻可以包括电池***在充电时对应的当前时间点、充电完成后对应的时间点、放电时对应的时间点等。
在一些实施例中，状态信息确定模型可以包括获取层和融合层。其中，获取层可以用于获取电池***的当前充电数据，融合层可以将所述当前充电数据进行融合，得到融合后的充电数据。在一些实施例中，融合层可以基于预设权重值，对电池***150的当前充电数据进行融合。例如，融合层可以基于电池***150的充电过程温度权重和充电起始温度，对电池***150的充电温度数据进行融合，得到融合后的充电温度。又如，根据充电电压、充电电流、充电时间、充电温度等对电池***的健康状态的影响程度，可以为每种数据设置不同的权重值，融合层可以基于电池***150对应的预设权重值，对电池***150的充电电压、充电电流、充电时间、充电温度进行融合，得到一组融合后的充电数据。在一些实施例中，所述预设权重值可以由服务器120基于电池***的历史数据通过统计获得，或由用户手动设置，其可以为任意合理的数值，本说明书对此不做限制。在一些实施例中，不同的电池***、或不同的单体电池、或不同的电池模组可以对应不同的预设权重值。在一些实施例中，电池***的使用时长不同，其对应的预设权重值不同。例如，新电池和使用一段时间的电池，可以分别对应不同的预设权重值。
步骤1030，通过状态信息预测模型对所述充电数据和所述当前健康状态信息进行处理，以确定所述电池***在下一时间段的未来健康状态信息。
下一时间段可以包括当前时刻之后的任意时间段，例如未来30分钟、1个小时、3小时、5小时、一天、一周等。未来健康状态信息可以指电池***在下一时间段的容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态中的一个或多个。
在一些实施例中，电池健康状态信息确定装置400可以利用训练好的状态信息预测模型，对电池***150的充电数据和通过状态信息确定模型获得的当前健康状态信息进行处理，以确定电池***150的未来健康状态信息。其中，状态信息预测模型的输入数据为电池***的充电数据和当前健康状态信息，输出为该电池***在预设的下一时间段(例如一天、一周等)的未来健康状态信息。
在一些实施例中，电池健康状态信息确定装置400可以利用训练好的状态信息预测模型，对电池***150的充电数据和在第一时间段的第一未来健康状态信息进行处理，确定电池***150在第二时间段的第二未来健康状态信息。其中，第一时间段早于第二时间段。例如，若当前时间为2月1日，第一时间段可以为2月1日到2月2日这一时间段，第二时间段可以为2月2日到2月3日这一时间段。在一些实施例中，电池健康状态信息确定装置400可以利用训练好的状态信息预测模型，确定电池***150在一个或多个不同下一时间段的未来健康状态信息。
步骤1040，通过健康状态判断模型，对两个或以上未来健康状态信息进行处理，以确定所述电池***的健康状态。
健康状态可以反映电池***健康与否，例如，健康或异常。在一些实施例中，电池健康状态信息确定装置400可以利用训练好的健康状态判断模型，对电池***150的两个或以上未来健康状态信息进行处理，以确定电池***150的健康状态。其中，健康状态判断模型的输入为电池***的两个或以上未来健康状态信息，输出可以为当前电池***的健康或异常，如1表示健康、0表示异常，或者可以为当前电池***健康或异常的概率值。当输出为概率值时，电池健康状态信息确定装置400可以进一步基于预设的概率阈值，确定电池***健康或异常。例如，电池健康状态信息确定装置400可以将电池***150第一时间段的第一未来健康状态信息、第二时间段的第二未来健康状态信息输入训练好的健康状态判断模型，获得健康状态判断模型输出的电池***150的健康状态。
在一些实施例中，电池健康状态信息确定装置400可以获取与电池***150相关的使用反馈信 息。在一些实施例中，使用反馈信息可以包括图片、文本、声音、视频等。例如，用户可以通过终端160上传包含电池***150故障位置的图片、包含电池***150异常声音的音频或视频，或输入的与电池***150的使用相关的文字或语音。
在一些实施例中，电池健康状态信息确定装置400可以对使用反馈信息进行分析，确定电池***150的特征信息。在一些实施例中，电池健康状态信息确定装置400可以通过图像识别、声音识别、或关键词提取等方式，确定电池***150的特征信息。例如，电池健康状态信息确定装置400可以通过对文本进行关键词提取，将多个用户上报的对同一电池***的文本反馈信息进行分类，以确定电池***150的特征信息。又如，电池健康状态信息确定装置400可以将用户上传的音频或视频中电池***的异常声音，与电池***150原来的提示音或异常音进行比较，得到电池***150的特征信息。
在一些实施例中，电池健康状态信息确定装置400可以通过健康状态判断模型，对所述特征信息进行处理，以确定电池***150的健康状态。
通过基于用户上传的使用反馈信息对电池***的健康状态进行评估，对于尚无充电数据(例如新电池)或充电数据较少的电池***，也可以实现健康状态的评估，提高了电池***的适用性。
在一些实施例中，当电池健康状态信息确定装置400确定电池***150异常时，可以将该电池***的标识、健康状态、充电数据以及健康状态信息发送至服务器120。服务器120接收到该信息后，可以发出警示，例如向终端160发送提示信息和/或电池***的相关数据。在一些实施例中，电池健康状态信息确定装置400可以响应于确定电池***150异常，发出警示。
图11是根据本申请一些实施例所示的电池状态信息确定方法的示例性流程图。
在一些实施例中，方法1100可以由电池***150(例如，集成在电池***150中计算设备300、图4所示的电池健康状态信息确定装置400)执行。如图11所示，在一些实施例中，电池健康状态信息确定装置400可以基于电池***的使用信息确定其健康类别，基于健康类别，对电池***执行相应的操作。
参照图11，在一些实施例中，电池状态信息确定方法可以包括如下步骤：
步骤1110，获取电池***的使用信息。
使用信息可以包括单体电池、电池模组或电池***的使用时长、充电次数、维修次数等中的至少一个。其中，使用时长可以指电池从开始使用(例如，安装在用电设备的时间)到当前时刻的时长。充电次数可以指电池从出厂到当前的历史充电次数。
在一些实施例中，电池健康状态信息确定装置400可以从服务器120获取电池***150的使用信息。在一些实施例中，电池健康状态信息确定装置400可以从存储模块获取电池***150的使用信息。在一些实施例中，电池健康状态信息确定装置400可以基于电池***150的标识信息，确定其使用信息。
步骤1120，基于所述使用信息确定所述电池***的健康类别。
健康类别可以反映电池***的健康等级，例如高健康、低健康、中健康。健康等级越高，该电池***发生故障的概率越低，相应地使用寿命越长。示例性地，新电池或使用时长小于第一预设值，出现故障的概率较低，可以定义为高健康；电池曾多次维修过或使用时长大于或等于第二预设值，出现故障的概率较高，定义为低健康；电池使用时长大于或等于第一预设值且小于第二预设值，定义为中健康。
在一些实施例中，电池健康状态信息确定装置400可以采用训练好的分类模型，基于所述使用信息确定电池***150的健康类别。分类模型可以基于大量带有标注的样本数据训练获得。分类模型的输入可以为电池***的使用信息，输出为健康级别，如第一级、第二级、第三级，其中级别越低，越健康，或低健康、中健康、高健康。
在一些实施例中，对于不同健康类别的电池***，电池健康状态信息确定装置400可以执行不同的操作。示例性地，对于高健康类别的电池***，可以降低对该电池***的状态信息评估频次，如每充3次电或每周评估一次健康状态信息和/或健康状态；对于中健康类别的电池***，每充2次电或每天评估一次健康状态信息和/或健康状态；对于低健康类别的电池***，适应性增加对该电池***的状态信息评估频次，如实时或每次充电时，评估其健康状态信息和/或健康状态。在一些实施例中，电池健康状态信息确定装置400可以实时或定时(如每天)确定电池***150的健康类别，以及时对电池***的异常情况执行相应的预警操作，例如，对于低健康类别的电池***及时进行警示或数据上报。在一 些实施例中，对电池***150健康类别的识别频率可以高于对其状态信息判断的频率。例如，电池健康状态信息确定装置400可以实时判定电池***150的健康类别，当健康类别达到预设的条件(如大于第一级)时，或每周，进行当前健康状态信息、未来健康状态信息和/或健康状态的预估。
步骤1130，响应于所述电池***属于低健康类别，对所述电池***执行相应的操作。
在一些实施例中，响应于电池***属于低健康类别，可以对该电池***执行以下操作中的至少一个：在每次充电前判断电池***的健康状态、向服务器上报电池***的目标数据、为电池***预设备用电池。
目标数据可以包括充电温度、充电电压、充电电流、充电时间等对电池健康状态影响较大的数据。在一些实施例中，电池健康状态信息确定装置400可以基于历史数据确定目标数据。
在一些实施例中，当电池***故障时，电池健康状态信息确定装置400可以自主切换到与备用电池的连接线路上，以保障电池***的正常使用。
应当注意的是，以上关于电池状态信息确定方法1000、方法1100及其流程的描述，仅出于说明的目的而提供，并非旨在限制本申请的范围。对于本领域的普通技术人员来说，可以根据本申请的描述，做出各种各样的修正和改变。例如，在步骤1130中，电池健康状态信息确定装置400可以基于电池***的健康类别，执行相应的操作，如报警、状态评估等。然而，这些修正和改变不会背离本申请的范围。
图12是根据本申请另一些实施例所示的电池健康状态信息确定装置的模块示意图。
在一些实施例中，电池健康状态信息确定装置1200可以是前述充电设备110的一部分。例如，计算设备300集成于电池***110时，电池健康状态信息确定装置1200可以为处理器310的一部分。在一些实施例中，电池健康状态信息确定装置1200可以作为一个独立的额外装置加装到传统的充电设备。通过在充电设备加装电池健康状态信息确定装置1200，电池健康状态信息确定装置1200获取与电池***相关的充电数据，并对该充电数据进行存储和计算，确定出与电池***相关的健康状态信息，然后将该健康状态信息发送给服务器120，可以降低服务器的计算负荷。
如图12所示，在一些实施例中，电池健康状态信息确定装置1200可以包括第二获取模块1210及第二评估模块1220。
第二获取模块1210可以用于获取与电池***150相关的充电数据。例如，第二获取模块1210可以从电池***150中的BMS获取与电池***150相关的充电数据，并将其存储在存储模块(例如，存取器130、或内存320)中。又如，第二获取模块1210可以基于电池***的标识信息，从自身的存储模块中获取当前正在充电的电池***的充电电压、充电电流、充电时间等数据。
第二评估模块1220可以用于基于电池***150相关的充电数据确定与电池***150相关的健康状态信息。在一些实施例中，第二评估模块1220可以利用任何评估算法或模型对电池***150相关的电池健康状态信息进行评估，本申请不作限制。第二评估模块1220进行电池健康状态信息评估的方法详见图13的描述。
在一些实施例中，电池健康状态信息确定装置1200还可以包括通信模块(图中未示出)。在一些实施例中，通信模块可以用于与读取设备通信连接，以使读取设备通过该通信模块读取存储于存储模块(例如，内存320)的与电池***150相关的充电数据和/或健康状态信息。在一些实施例中，通信模块可以用于与电池***150通信连接，以获取电池***的充电数据。
应当注意的是，以上描述仅仅是出于说明的目的而提供的，并不旨在限制本申请的范围。对于本领域的普通技术人员来说，可以根据本申请的描述，做出各种各样的变化和修改。然而，这些变化和修改不会背离本申请的范围。
图13是根据本申请另一些实施例所示的电池健康状态信息确定方法的示例性流程图。
在一些实施例中，方法1300可以由充电设备110(例如，集成在充电设备110中计算设备300、图12所示的电池健康状态信息确定装置1200)执行。
参照图13，在一些实施例中，电池健康状态信息确定方法可以包括如下步骤：
步骤1310，获取与电池***相关的充电数据。
在一些实施例中，电池健康状态信息确定装置1200可以获取电池***150相关的充电数据。在一些实施例中，当电池***150正在使用充电设备110充电时，电池健康状态信息确定装置1200可以获取该电池***的充电数据。在一些实施例中，该充电数据可以包括单体电池、模组或整个电池***150的充电电压、充电电流、充电时间、充电温度数据以及历史使用数据等中的至少一个。在一些实施例中，电池健康状态信息确定装置1200可以通过通信模块从电池***150获取其充电数据。
步骤1320，基于所述充电数据确定与所述电池***相关的健康状态信息。
在一些实施例中，电池健康状态信息确定装置1200可以基于电池***150的充电数据确定电池***150的健康状态信息。在一些实施例中，当电池***属于低健康类别时，电池健康状态信息确定装置1200可以在该电池***每次充电前，基于充电数据确定其状态信息。在一些实施例中，电池健康状态信息确定装置1200可以采用训练好的机器学习模型对获取到的充电数据进行处理，以确定电池***150相关的状态信息。在一些实施例中，电池健康状态信息确定装置1200可以从存储模块或服务器获取训练好的机器学习模型。充电设备确定电池***状态信息的方法与电池***类似，更多详细内容可以参见图6-11及其相关描述，此处不再赘述。
步骤1330，将所述健康状态信息发送给服务器。
在一些实施例中，电池健康状态信息确定装置1200在基于电池***150相关的充电数据确定其对应的健康状态信息后，可以将该健康状态信息和/或健康状态发送给服务器120。在一些实施例中，电池健康状态信息确定装置1200可以将电池***150的充电数据以及健康状态信息一同发送至服务器120，以便于远程监控电池***150的当前状态。在一些实施例中，电池健康状态信息确定装置1200可以将电池***150的健康状态以及相关的数据(例如预测的多个未来健康状态信息)一同发送至服务器120。在一些实施例中，电池健康状态信息确定装置1200可以将前述健康状态信息、健康状态以及电池***150对应的ID或标识信息一同发送至服务器。
应当注意的是，以上关于电池健康状态信息确定方法及其流程的描述，仅出于说明的目的而提供，并非旨在限制本申请的范围。对于本领域的普通技术人员来说，可以根据本申请的描述，做出各种各样的修正和改变。然而，这些修正和改变不会背离本申请的范围。
本说明书实施例可能带来的有益效果包括但不限于：(1)在电池***中集成电池健康状态信息确定装置或加装电池健康状态信息确定装置，实现本地化评估电池健康状态信息；(2)电池健康状态信息确定装置将电池健康状态信息结果通过有线或无线方式传输至远程数据平台或监控***，远程数据平台或监控***无需进行电池状态评估，减小了远程数据平台或监控***对数据处理和计算负荷，降低了远程数据平台或监控***搭建与运营成本；(3)可以通过电池***、充电设备或监测装置(例如，服务器120)，对电池健康状态信息进行评估，提高了对电池状态信息评估的灵活性；(4)基于电池***的充电数据、使用信息、使用反馈等信息等进行电池状态评估，不仅可以快捷评估健康状态，还可以及时发现电池的故障或危害，从而进行提前维修或保养，精准定位故障点，大幅减少售后成本。
需要说明的是，不同实施例可能产生的有益效果不同，在不同的实施例里，可能产生的有益效果可以是以上任意一种或几种的组合，也可以是其他任何可能获得的有益效果。
上文已对基本概念做了描述，显然，对于本领域技术人员来说，上述详细披露仅仅作为示例，而并不构成对本说明书的限定。虽然此处并没有明确说明，本领域技术人员可能会对本说明书进行各种修改、改进和修正。该类修改、改进和修正在本说明书中被建议，所以该类修改、改进、修正仍属于本说明书示范实施例的精神和范围。
同时，本说明书使用了特定词语来描述本说明书的实施例。如“一个实施例”、“一实施例”、和/或“一些实施例”意指与本说明书至少一个实施例相关的某一特征、结构或特点。因此，应强调并注意的是，本说明书中在不同位置两次或多次提及的“一实施例”或“一个实施例”或“一个替代性实施例”并不一定是指同一实施例。此外，本说明书的一个或多个实施例中的某些特征、结构或特点可以进行适当的组合。
此外，除非权利要求中明确说明，本说明书所述处理元素和序列的顺序、数字字母的使用、或其他名称的使用，并非用于限定本说明书流程和方法的顺序。尽管上述披露中通过各种示例讨论了一些目前认为有用的发明实施例，但应当理解的是，该类细节仅起到说明的目的，附加的权利要求并不仅限于披露的实施例，相反，权利要求旨在覆盖所有符合本说明书实施例实质和范围的修正和等价组合。例如，虽然以上所描述的***组件可以通过硬件设备实现，但是也可以只通过软件的解决方案得以实现， 如在现有的服务器或移动设备上安装所描述的***。
同理，应当注意的是，为了简化本说明书披露的表述，从而帮助对一个或多个发明实施例的理解，前文对本说明书实施例的描述中，有时会将多种特征归并至一个实施例、附图或对其的描述中。但是，这种披露方法并不意味着本说明书对象所需要的特征比权利要求中提及的特征多。实际上，实施例的特征要少于上述披露的单个实施例的全部特征。
一些实施例中使用了描述成分、属性数量的数字，应当理解的是，此类用于实施例描述的数字，在一些示例中使用了修饰词“大约”、“近似”或“大体上”来修饰。除非另外说明，“大约”、“近似”或“大体上”表明所述数字允许有±20％的变化。相应地，在一些实施例中，说明书和权利要求中使用的数值参数均为近似值，该近似值根据个别实施例所需特点可以发生改变。在一些实施例中，数值参数应考虑规定的有效数位并采用一般位数保留的方法。尽管本说明书一些实施例中用于确认其范围广度的数值域和参数为近似值，在具体实施例中，此类数值的设定在可行范围内尽可能精确。
针对本说明书引用的每个专利、专利申请、专利申请公开物和其他材料，如文章、书籍、说明书、出版物、文档等，特此将其全部内容并入本说明书作为参考。与本说明书内容不一致或产生冲突的申请历史文件除外，对本说明书权利要求最广范围有限制的文件(当前或之后附加于本说明书中的)也除外。需要说明的是，如果本说明书附属材料中的描述、定义、和/或术语的使用与本说明书所述内容有不一致或冲突的地方，以本说明书的描述、定义和/或术语的使用为准。
最后，应当理解的是，本说明书中所述实施例仅用以说明本说明书实施例的原则。其他的变形也可能属于本说明书的范围。因此，作为示例而非限制，本说明书实施例的替代配置可视为与本说明书的教导一致。相应地，本说明书的实施例不仅限于本说明书明确介绍和描述的实施例。

Claims (20)

  1. 一种电池***，其特征在于，包括：
    至少一个电池模组，所述电池模组包括至少一个电芯；
    至少一个存储介质，包括一组指令；以及
    与所述至少一个存储介质通信的一个或以上处理器，其中，当执行所述指令时，所述一个或以上处理器用于：
    获取与所述电池***相关的充电数据，所述充电数据包括充电电压、充电电流、充电时间、充电温度数据以及历史使用数据中的至少一个；以及
    基于所述充电数据确定与所述电池***相关的健康状态信息；其中，所述健康状态信息包括与所述电池***相关的容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态中的一个或多个。
  2. 如权利要求1所述的电池***，其特征在于，所述***还包括通信模块，所述通信模块用于与读取设备通信连接，以使所述读取设备通过所述通信模块读取所述健康状态信息。
  3. 如权利要求1所述的电池***，其特征在于，所述基于所述充电数据确定与所述电池***相关的健康状态信息，包括：
    通过预先配置的机器学习模型对所述充电数据进行处理，以确定所述健康状态信息，所述机器学习模型存储在所述存储介质中。
  4. 如权利要求1所述的电池***，其特征在于，所述基于所述充电数据确定与所述电池***相关的健康状态信息，包括：
    从服务器获取训练好的机器学习模型；
    通过所述训练好的机器学习模型对所述充电数据进行处理，以确定所述健康状态信息。
  5. 如权利要求3或4所述的电池***，其特征在于，
    所述机器学习模型包括训练好的状态信息确定模型；
    通过所述机器学习模型对所述充电数据进行处理，以确定所述健康状态信息，包括：
    通过所述状态信息确定模型对所述充电数据进行处理，以确定所述电池***的当前健康状态信息。
  6. 如权利要求5所述的电池***，其特征在于，
    所述机器学习模型还包括训练好的状态信息预测模型；
    所述一个或以上处理器还用于：
    通过所述状态信息预测模型对所述充电数据和所述当前健康状态信息进行处理，以确定所述电池***在下一时间段的未来健康状态信息。
  7. 如权利要求6所述的电池***，其特征在于，
    所述机器学习模型还包括训练好的健康状态判断模型；
    所述一个或以上处理器还用于：
    获取所述电池***的两个或以上未来健康状态信息，所述两个或以上未来健康状态信息分别对应不同的未来时间段；
    通过所述健康状态判断模型，对所述两个或以上未来健康状态信息进行处理，以确定所述电池***的健康状态。
  8. 如权利要求7所述的电池***，其特征在于，所述机器学习模型通过以下方式获得：
    获取训练样本，所述训练样本包括多个样本组，每个所述样本组包括相应样本电池的历史充电数据、通过所述状态信息预测模型获得的历史未来健康状态信息、通过所述健康状态判断模型获得的历史健康状态；
    基于所述训练样本对初始模型进行训练，获得训练好的机器学习模型；其中，所述训练样本的标签包括与所述历史未来健康状态信息对应的历史实际健康状态信息，以及与所述历史健康状态对应的历史实际健康状态。
  9. 如权利要求8所述的电池***，其特征在于，当所述训练样本中负样本的数量小于预设值时，通过数据模拟或参数调节对所述负样本的数量进行填充。
  10. 如权利要求3或4所述的电池***，其特征在于，所述一个或以上处理器还用于：
    对所述机器学习模型进行更新。
  11. 如权利要求1所述的电池***，其特征在于，所述一个或以上处理器还用于：
    获取所述电池***的使用信息，所述使用信息包括使用时长、充电次数、维修次数中的至少一个；
    基于所述使用信息确定所述电池***的健康类别，所述健康类别至少包括高健康类别、中健康类别和低健康类别。
  12. 如权利要求11所述的电池***，其特征在于，所述一个或以上处理器还用于：
    响应于所述电池***属于所述低健康类别，对所述电池***执行以下操作中的至少一个：在每次充电前判断所述电池***的健康状态、向服务器上报所述电池***的目标数据、为所述电池***预设备用电池。
  13. 如权利要求1所述的电池***，其特征在于，所述一个或以上处理器还用于：
    获取与所述电池***相关的使用反馈信息；
    对所述使用反馈信息进行分析，确定所述电池***的特征信息；
    通过健康状态判断模型，对所述电池***的特征信息进行处理，以确定所述电池***的健康状态。
  14. 如权利要求1-13中任一项所述的电池***，其特征在于，所述充电电压包括充电起始电压、充电过程特征电压、充电截止电压中的至少一个；所述充电温度数据包括充电起始温度、充电过程温度权重中的至少一个；所述历史使用数据包括累计充放电量、累计充放电次数、历史电池健康状态中的至少一个。
  15. 如权利要求1所述的电池***，其特征在于，进一步包括：
    一个或多个传感器，用于检测所述充电电压、所述充电电流、所述充电温度中的至少一个；
    电池管理***，用于管理所述电池***的充放电行为；
    供电模块，用于利用所述电池***存储的电能，为所述电池***的至少一个部件供电；和/或
    定位模块，用于获取所述电池***的位置信息。
  16. 一种电池健康状态信息确定装置，用于设置在电池***中预估与所述电池***相关的健康状态信息，其特征在于，包括：
    第一获取模块，用于获取与所述电池***相关的充电数据，所述充电数据包括充电电压、充电电流、充电时间、充电温度数据以及历史使用数据中的至少一个；
    第一评估模块，用于基于所述充电数据确定与所述电池***相关的健康状态信息；其中，所述健康状态信息包括与所述电池***相关的容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态中的一个或多个。
  17. 如权利要求16所述的装置，其特征在于，所述装置包括存储模块以及通信模块，所述存储模块用于存储所述健康状态信息，所述通信模块用于与读取设备通信连接，以使所述读取设备通过所述通信模块读取存储于所述存储模块的所述健康状态信息。
  18. 一种电池健康状态信息确定装置，用于设置在充电设备中确定与电池***相关的健康状态信息，其特征在于，包括：
    第二获取模块，用于获取与所述电池***相关的充电数据，所述充电数据包括充电电压、充电电流、充电时间、充电温度数据以及历史使用数据中的至少一个；
    第二评估模块，用于基于所述充电数据确定与所述电池***相关的健康状态信息；其中，所述健康状态信息包括与所述电池***相关的容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态中的一个或多个。
  19. 一种电池健康状态信息确定方法，由电池***中的处理器执行，所述电池***包括至少一个电池模组，所述电池模组包括至少一个电芯，其特征在于，包括：
    获取与所述电池***相关的充电数据，所述充电数据包括充电电压、充电电流、充电时间、充电温度数据以及历史使用数据中的至少一个；以及
    基于所述充电数据确定与所述电池***相关的健康状态信息；其中，所述健康状态信息包括与所述电池***相关的容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态中的一个或多个。
  20. 一种电池健康状态信息确定方法，由充电设备中的处理器执行，其特征在于，包括：
    获取与电池***相关的充电数据，所述充电数据包括充电电压、充电电流、充电时间、充电温度数据以及历史使用数据中的至少一个；以及
    基于所述充电数据确定与所述电池***相关的健康状态信息；其中，所述健康状态信息包括与所述电池***相关的容量偏移信息、SOH值、自放电一致性、压差与内阻一致性、绝缘状态以及温度状态中的一个或多个。
PCT/CN2023/083218 2022-03-29 2023-03-22 一种电池健康状态信息确定方法、装置及电池*** WO2023185601A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210316191.7A CN114675188A (zh) 2022-03-29 2022-03-29 一种电池健康状态信息确定方法、装置及电池***
CN202210316191.7 2022-03-29

Publications (1)

Publication Number Publication Date
WO2023185601A1 true WO2023185601A1 (zh) 2023-10-05

Family

ID=82076211

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/083218 WO2023185601A1 (zh) 2022-03-29 2023-03-22 一种电池健康状态信息确定方法、装置及电池***

Country Status (2)

Country Link
CN (1) CN114675188A (zh)
WO (1) WO2023185601A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117420464A (zh) * 2023-11-24 2024-01-19 广州穗圣信息科技有限公司 一种电动汽车电池组评估方法及***
CN117647743A (zh) * 2024-01-30 2024-03-05 宁德时代新能源科技股份有限公司 电池容量的确定方法、装置、设备及存储介质
CN117851179A (zh) * 2024-01-15 2024-04-09 上海异工同智信息科技有限公司 一种便携式设备***健康状态检测评估方法及***
CN117991108A (zh) * 2024-04-07 2024-05-07 邦邦汽车销售服务(北京)有限公司 一种基于数据的动力电池损伤检测方法与***

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114675188A (zh) * 2022-03-29 2022-06-28 北京芯虹科技有限责任公司 一种电池健康状态信息确定方法、装置及电池***
CN115799690B (zh) * 2022-11-17 2023-12-26 厦门海辰储能科技股份有限公司 一种储能设备的运行方法及***

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107329088A (zh) * 2016-04-29 2017-11-07 株式会社日立制作所 电池的健康状态诊断装置和方法
CN109100655A (zh) * 2018-06-29 2018-12-28 深圳市科列技术股份有限公司 一种动力电池的数据处理方法和装置
CN110015162A (zh) * 2017-06-30 2019-07-16 宝沃汽车（中国）有限公司 电池健康状态检测方法、装置和***以及存储介质
CN112051511A (zh) * 2020-08-26 2020-12-08 华中科技大学 基于多通道技术的动力电池健康状态的估计方法及***
CN113049976A (zh) * 2021-04-27 2021-06-29 武汉理工大学 一种车辆电池健康状态评估方法及***
US20210247447A1 (en) * 2020-01-06 2021-08-12 Tata Consultancy Services Limited Method and system for online estimation of soh and rul of a battery
CN113933732A (zh) * 2021-10-13 2022-01-14 中国汽车工程研究院股份有限公司 新能源汽车动力电池健康状态分析方法、***及存储介质
CN114019400A (zh) * 2021-11-03 2022-02-08 广东产品质量监督检验研究院 锂电池生命周期监控管理方法、***及存储介质
CN114675188A (zh) * 2022-03-29 2022-06-28 北京芯虹科技有限责任公司 一种电池健康状态信息确定方法、装置及电池***

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107329088A (zh) * 2016-04-29 2017-11-07 株式会社日立制作所 电池的健康状态诊断装置和方法
CN110015162A (zh) * 2017-06-30 2019-07-16 宝沃汽车（中国）有限公司 电池健康状态检测方法、装置和***以及存储介质
CN109100655A (zh) * 2018-06-29 2018-12-28 深圳市科列技术股份有限公司 一种动力电池的数据处理方法和装置
US20210247447A1 (en) * 2020-01-06 2021-08-12 Tata Consultancy Services Limited Method and system for online estimation of soh and rul of a battery
CN112051511A (zh) * 2020-08-26 2020-12-08 华中科技大学 基于多通道技术的动力电池健康状态的估计方法及***
CN113049976A (zh) * 2021-04-27 2021-06-29 武汉理工大学 一种车辆电池健康状态评估方法及***
CN113933732A (zh) * 2021-10-13 2022-01-14 中国汽车工程研究院股份有限公司 新能源汽车动力电池健康状态分析方法、***及存储介质
CN114019400A (zh) * 2021-11-03 2022-02-08 广东产品质量监督检验研究院 锂电池生命周期监控管理方法、***及存储介质
CN114675188A (zh) * 2022-03-29 2022-06-28 北京芯虹科技有限责任公司 一种电池健康状态信息确定方法、装置及电池***

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117420464A (zh) * 2023-11-24 2024-01-19 广州穗圣信息科技有限公司 一种电动汽车电池组评估方法及***
CN117851179A (zh) * 2024-01-15 2024-04-09 上海异工同智信息科技有限公司 一种便携式设备***健康状态检测评估方法及***
CN117851179B (zh) * 2024-01-15 2024-06-04 上海异工同智信息科技有限公司 一种便携式设备***健康状态检测评估方法及***
CN117647743A (zh) * 2024-01-30 2024-03-05 宁德时代新能源科技股份有限公司 电池容量的确定方法、装置、设备及存储介质
CN117647743B (zh) * 2024-01-30 2024-06-07 宁德时代新能源科技股份有限公司 电池容量的确定方法、装置、设备及存储介质
CN117991108A (zh) * 2024-04-07 2024-05-07 邦邦汽车销售服务(北京)有限公司 一种基于数据的动力电池损伤检测方法与***

Also Published As

Publication number Publication date
CN114675188A (zh) 2022-06-28

Similar Documents

Publication Publication Date Title
WO2023185601A1 (zh) 一种电池健康状态信息确定方法、装置及电池***
WO2019184848A1 (zh) 电动汽车及其提示***
CN112838631A (zh) 动力电池的充电动态管控装置和动力电池的充电诊断方法
CN110324383B (zh) 云服务器、电动汽车及其中动力电池的管理***、方法
US20230059529A1 (en) Characterization of Rechargeable Batteries Using Machine-Learned Algorithms
CN108400397B (zh) 电池管理***及平台
CN110341541A (zh) 一种新能源汽车用电池管理***及使用方法
CN112349981A (zh) 一种电池管理***
CN117148154A (zh) 电池的异常状态或故障感测方法及执行其的电池管理***
CN110857962A (zh) 电池性能评价方法
CN113098084B (zh) 电池物联网***
CN113595174A (zh) 电池管理方法、装置、设备和服务器
CN115483763B (zh) 一种铅酸电池储能电站监控管理***及方法
CN116298947B (zh) 一种蓄电池核容监测装置
WO2023124733A1 (zh) 电池的管理方法及管理装置及计算机可读存储介质
CN113147487B (zh) 一种电动交通工具充电适配方法
CN112630665B (zh) 一种基于智能网联的锂电池寿命预测***
KR101514660B1 (ko) 배터리 관리시스템 및 이를 이용한 서비스 제공방법
CN115219932A (zh) 用于评价设备电池组的相对老化状态的方法和装置
JP6721170B1 (ja) 非常用充放電器の遠隔監視システム
CN114683964B (zh) 一种电池状态信息确定方法及充电设备
KR102561607B1 (ko) IoT 원격감시 기반의 충전시스템
CN117595462B (zh) 一种二次储能电池组的自适应充放电控制***及其控制方法
EP4209379A1 (en) Method, device and system for vehicle power battery auxiliary equilibrium
CN112152284B (zh) 一种蓄电池智能间隙充电管理***、方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23777971

Country of ref document: EP

Kind code of ref document: A1