CN111241154B - Storage battery fault early warning method and system based on big data - Google Patents
Storage battery fault early warning method and system based on big data Download PDFInfo
- Publication number
- CN111241154B CN111241154B CN202010001150.XA CN202010001150A CN111241154B CN 111241154 B CN111241154 B CN 111241154B CN 202010001150 A CN202010001150 A CN 202010001150A CN 111241154 B CN111241154 B CN 111241154B
- Authority
- CN
- China
- Prior art keywords
- data
- storage battery
- battery fault
- fault
- early warning
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
- 238000003860 storage Methods 0.000 title claims abstract description 275
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000004458 analytical method Methods 0.000 claims abstract description 79
- 238000007405 data analysis Methods 0.000 claims abstract description 39
- 238000012545 processing Methods 0.000 claims abstract description 19
- 230000002159 abnormal effect Effects 0.000 claims description 86
- 238000010219 correlation analysis Methods 0.000 claims description 34
- 230000003068 static effect Effects 0.000 claims description 24
- 238000007418 data mining Methods 0.000 claims description 11
- 238000012544 monitoring process Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 6
- 230000002452 interceptive effect Effects 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 208000032953 Device battery issue Diseases 0.000 claims 8
- 238000013500 data storage Methods 0.000 claims 2
- 230000015654 memory Effects 0.000 description 20
- 238000010586 diagram Methods 0.000 description 10
- 238000007726 management method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000006399 behavior Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 238000007619 statistical method Methods 0.000 description 5
- 230000005856 abnormality Effects 0.000 description 4
- 238000003066 decision tree Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000035484 reaction time Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 2
- 238000013499 data model Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000002269 spontaneous effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 238000000540 analysis of variance Methods 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008033 biological extinction Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000004073 vulcanization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Secondary Cells (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention relates to a storage battery fault early warning method based on big data, which comprises the following steps: capturing mass data of a target platform; processing and storing mass data based on a distributed system architecture; according to the mass data, carrying out retrieval analysis to obtain a data analysis result aiming at least one storage battery fault class; establishing at least one storage battery fault early warning target model according to the data analysis result; acquiring target data of the bicycle, and carrying out predictive analysis on the target data through at least one storage battery fault early warning target model to obtain a storage battery fault prediction result of the bicycle; and obtaining storage battery early warning information based on the storage battery fault prediction result, and sending the storage battery early warning information to the terminal. The invention can make early warning before the fault of the storage battery possibly occurs based on big data, and improves the safety.
Description
Technical Field
The invention relates to the field of battery safety, in particular to a storage battery fault early warning method and system based on big data.
Background
Along with the great popularization of the new energy electric vehicles by the country, more and more new energy electric vehicles drive on the street and the roadway of the city. Meanwhile, the mileage anxiety of people on electric automobiles is always on the topic of no-round. For this reason, manufacturers who provide energy storage devices for electric vehicles have to greatly increase the energy density of power storage batteries to meet national policy requirements and expectations. But at the same time the safety problem of the power accumulator is made more pronounced. With the increase of the energy density of the power storage battery, the ternary materials are widely used, and the power storage battery has more and more cases of faults and even spontaneous combustion. The method provides a real subject for a host factory for producing various large automobiles, namely, how to perform early warning and early prevention before the power storage battery breaks down.
The power storage battery is very difficult to pre-warn and prevent in advance before the fault occurs. The prior art detection means, such as the actual detection of an electric automobile to a special detection mechanism, is a very time-consuming and labor-consuming process for evaluating the condition of the battery, and is more difficult in the aspect of actual fault early warning. The traditional power storage battery fault early warning method is that the hardware detects the obvious changes of the voltage, current, pressure difference and internal resistance of the battery cell, and an alarm is sent out after the early warning threshold value is reached. Specifically, the fault alarm information CAN be sent to the controller area network (Controller Area Network, CAN, an internationally standardized serial communication protocol) bus through the changes of voltage, temperature and pressure difference monitored by the battery management system, and the instrument gives an alarm. The alarm is sent out at this time, and the reaction time is short, and sometimes the reaction time is short, so that the problem that the vehicle has failed or the battery has spontaneous combustion is solved. The fault early warning method is only suitable for emergency treatment of faults or emergency escape of personnel, has poor applicability for early prevention of faults of the vehicle power storage battery, and cannot well solve the early fault early warning problem of battery faults.
At present, new energy automobile monitoring platforms are established in the country, the place and the enterprises, wherein the important thing is to collect the data of the power battery. That is to say, we have now provided the basis of carrying out big data analysis to the service condition of power battery, and enterprise's own establishment power battery trouble early warning platform based on big data analysis has also provided implementation condition. The method can be used for carrying out early warning on possible impending faults of the vehicle power battery directly through collecting historical battery data and combining real-time data and then applying a big data analysis method.
Disclosure of Invention
The invention discloses a storage battery fault early warning method and system based on big data, which aim to solve the problem of early warning of storage battery faults. The technical scheme is as follows:
in a first aspect, the invention discloses a storage battery fault early warning method based on big data, which comprises the following steps:
capturing mass data of at least one target platform;
processing and storing the mass data based on a distributed system architecture;
according to the mass data, carrying out retrieval analysis to obtain a data analysis result aiming at least one storage battery fault class;
According to the data analysis result, at least one storage battery fault early warning target model is established;
acquiring target data of a bicycle, and performing predictive analysis on the target data of the bicycle through the at least one storage battery fault early warning target model to obtain a storage battery fault prediction result of the bicycle;
and obtaining storage battery early warning information based on the storage battery fault prediction result, and sending the storage battery early warning information to the bicycle terminal or the user terminal equipment.
Further, the capturing mass data of the at least one target platform includes:
grabbing storage battery dynamic data recorded by a new energy vehicle monitoring platform, wherein the storage battery dynamic data comprises storage battery real-time state data, storage battery historical state data and storage battery historical fault data;
grabbing storage battery static data recorded by a new energy vehicle storage battery traceability platform;
grabbing vehicle running environment data recorded by a third party environment data providing platform;
and/or capturing vehicle use state data and user use behavior data recorded by the Internet of vehicles data platform.
Further, based on the distributed system architecture, processing and storing the mass data includes:
Carrying out data cleaning, arrangement and/or analysis on the mass data to obtain structured data;
based on the distributed system architecture, the structured data is stored in a data warehouse to enable the structured data to be retrieved or queried.
Further, performing search analysis according to the mass data, and obtaining a data analysis result aiming at least one storage battery fault category comprises:
counting the fault types, the fault frequency and/or the fault sources of the storage battery according to the historical fault data of the storage battery to obtain a fault counting analysis result;
aiming at each storage battery fault category in the fault statistics analysis result, obtaining the fault occurrence time of each storage battery fault category according to the storage battery historical fault data;
retrieving and collecting historical state data of the storage battery and static data of the storage battery in a certain time range before and after the fault occurrence time from the data warehouse as abnormal data of the storage battery;
and carrying out data mining and analysis according to the battery abnormal data to obtain characteristic analysis results of the battery abnormal data aiming at each storage battery fault type and correlation analysis results of each storage battery fault type and the battery abnormal data.
Further, performing search analysis according to the mass data, and obtaining a data analysis result aiming at least one storage battery fault class further comprises:
retrieving and collecting relevant user usage behavior data, vehicle usage state data and/or vehicle operation environment data from the data warehouse as external abnormal data for each battery fault category in the fault statistics analysis result;
and carrying out data mining and analysis according to the external abnormal data to obtain characteristic analysis results of the external abnormal data aiming at each storage battery fault type and correlation analysis results of each storage battery fault type and the external abnormal data.
Further, performing search analysis according to the mass data, and obtaining a data analysis result aiming at least one storage battery fault class further comprises:
for each storage battery fault category in the fault statistics analysis result, searching and collecting historical fault data and/or historical state data of the bicycle from the data warehouse as bicycle abnormal data;
and carrying out data mining and analysis according to the bicycle abnormal data to obtain characteristic analysis results of the bicycle abnormal data aiming at each storage battery fault type and correlation analysis results of each storage battery fault type and the bicycle abnormal data.
Further, according to the data analysis result, establishing at least one storage battery fault early warning target model includes:
establishing at least one storage battery fault early warning general model corresponding to each storage battery fault class according to the characteristic analysis result of the battery abnormal data, the characteristic analysis result of external abnormal data, the correlation analysis result of each storage battery fault class and the battery abnormal data and/or the correlation analysis result of each storage battery fault class and the external abnormal data aiming at each storage battery fault class in the fault statistics analysis result;
according to the characteristic analysis result of the bicycle abnormal data and the correlation analysis result of each storage battery fault type and the bicycle abnormal data, the at least one storage battery fault early warning general model is adjusted and corrected to obtain at least one storage battery fault early warning model aiming at the bicycle;
and acquiring random sample data of the bicycle, and training the at least one storage battery fault early-warning model through the random sample data to obtain at least one storage battery fault early-warning target model.
Further, the obtaining the target data of the bicycle, and performing prediction analysis on the target data of the bicycle through the at least one storage battery fault early-warning target model, so as to obtain a storage battery fault prediction result of the bicycle comprises:
acquiring real-time target data of the bicycle through a vehicle-mounted terminal acquisition device of the bicycle;
acquiring static data of the storage battery of the bicycle recorded by a storage battery tracing platform as static target data;
and importing the real-time target data and the static target data of the single vehicle into the at least one storage battery fault early warning target model to obtain a storage battery fault prediction result related to the single vehicle, wherein the storage battery fault prediction result comprises a predicted fault type, fault occurrence time, fault occurrence probability and/or fault source.
Further, the obtaining the battery fault early-warning information based on the battery fault prediction result and sending the battery fault early-warning information to the bicycle terminal or the user terminal device includes:
screening the battery fault prediction result according to a preset threshold value, and describing the screened battery fault prediction result in natural language based on a preset rule to obtain battery fault early warning information;
The storage battery fault early warning information is sent to the bicycle terminal or user terminal equipment;
and/or transmitting the data analysis result for at least one storage battery fault class to the bicycle terminal or the user terminal device in a visual representation form.
In a second aspect, the invention also discloses a storage battery fault early warning system based on big data, the system comprises:
the interactive interface is used for setting a fault early warning mode by a user; the storage battery fault early warning device is used for displaying storage battery fault early warning information; and/or for displaying the visualized data analysis results for at least one battery fault class;
the data grabbing unit is used for grabbing mass data of at least one target platform; and/or acquiring target data of the bicycle;
the data processing unit is used for processing and storing the mass data based on a distributed system architecture;
the data analysis unit is used for carrying out retrieval analysis according to the mass data to obtain a data analysis result aiming at least one storage battery fault type;
the early warning model unit is used for establishing at least one storage battery fault early warning target model according to the data analysis result; and/or the method is used for carrying out predictive analysis on the target data of the bicycle through the at least one storage battery fault early warning target model to obtain a storage battery fault prediction result of the bicycle;
And the early warning prompting unit is used for obtaining storage battery fault early warning information based on the storage battery fault prediction result and sending the storage battery fault early warning information to the bicycle terminal or the user terminal equipment.
By adopting the technical scheme, the storage battery fault early warning method and system based on big data have the following beneficial effects: the invention mainly establishes a data model through extracting, analyzing and arranging the dynamic storage battery data recorded by the existing new energy monitoring platform and the dynamic storage battery static data recorded by the battery tracing platform, the environment data of vehicle operation and the user use behavior data, and a large data statistics method to mine potential rules of various faults of the storage battery, and early warning is carried out before the faults possibly occur, so that the safety of the battery and the safety of people and vehicles are practically ensured. Compared with the method which uses special detection equipment and requires the user to send inspection at regular time, the early warning method provided by the invention realizes the real-time detection and prediction of the state of the storage battery, and has higher applicability. In addition, a unified evaluation system can be established through a big data model analysis mode, the data of the power storage battery are evaluated under a unified standard, and the result is more contrastive. Meanwhile, the prediction system platform supports the expansion of a follow-up prediction model, and early warning of the storage battery fault can be more accurate and finer.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a storage battery fault early warning method based on big data provided by an embodiment of the invention;
fig. 2 is a schematic diagram of data transmission processing in a storage battery fault early warning method based on big data according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a distributed system architecture in a storage battery fault early warning method based on big data according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a conventional Hadoop ecosystem architecture provided by an embodiment of the present invention;
fig. 5 (1) to (3) are schematic flow diagrams of a result of data analysis for at least one battery fault class according to the search analysis performed on the massive data provided by the embodiment of the present invention;
FIG. 6 is a schematic flow chart of establishing at least one storage battery fault early warning target model according to the data analysis result provided by the embodiment of the invention;
Fig. 7 is a schematic structural diagram of a battery fault early warning system based on big data according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
Reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic may be included in at least one implementation of the invention. In the description of the present invention, it should be understood that the terms "first," "second," "third," and "fourth," etc. in the description and claims of the invention and in the above-described figures are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Fig. 1 is a schematic flow chart of a method for early warning of a battery fault based on big data according to an embodiment of the present invention, and the present specification provides the steps of the method according to the embodiment or the schematic flow chart, but may include more or fewer steps based on conventional or non-creative labor. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution. When implemented in a real system or server product, the methods illustrated in the embodiments or figures may be performed sequentially or in parallel (e.g., in a parallel processor or multithreaded environment). Specifically, as shown in fig. 1, the storage battery fault early warning method based on big data may include:
s110: and capturing mass data of at least one target platform.
Preferably, step S110 in the embodiment of the present invention may include:
grabbing storage battery dynamic data recorded by a new energy vehicle monitoring platform, wherein the storage battery dynamic data comprises storage battery real-time state data, storage battery historical state data and storage battery historical fault data;
grabbing storage battery static data recorded by a new energy vehicle storage battery traceability platform;
Grabbing vehicle running environment data recorded by a third party environment data providing platform;
and/or capturing vehicle use state data and user use behavior data recorded by the Internet of vehicles data platform.
Preferably, the new energy vehicle monitoring platform can be a vehicle detection platform of a national or enterprise new energy vehicle, vehicle information is uploaded to a platform server by a vehicle manufacturer, the vehicle information comprises various types of static data and dynamic data of the vehicle, and the data accords with the national standard 32960; the new energy vehicle storage battery traceability platform can be a national or enterprise storage battery traceability platform, and static data of the storage battery is uploaded to a platform server by an automobile manufacturer, a vendor and the like; the Internet of vehicles data platform can be a vehicle application type platform and records all application data generated when a user drives a vehicle.
Preferably, the battery real-time status data and the historical status data may include, but are not limited to, battery terminal voltage, total battery pack current, battery terminal temperature, state of charge, charge-discharge status, battery health status; the battery historical fault data may include, but is not limited to, fault category, fault time, fault source, and fault cause; the battery static data may include, but is not limited to, battery base information, battery production information, battery pack model information, battery module model information, battery cell model information, battery pack rated power; the vehicle operating environment data may include, but is not limited to, vehicle location, weather data, and weather duty cycle data; the vehicle usage status data may include, but is not limited to, vehicle usage, vehicle travel area, vehicle average range and vehicle average travel duration; the user usage behavior data may include, but is not limited to, user gender, user age, user brake average reaction time, user driving average speed, and user driving pattern.
It will be appreciated that the mass data has a large number, high speed, variety, low value density and true large data features. By means of a distributed architecture, distributed statistical analysis and distributed data mining can be performed on the mass data.
Fig. 2 is a schematic diagram of data transmission processing in a storage battery fault early warning method based on big data provided in an embodiment of the invention. In some possible embodiments, the mass data may be classified into structured data, semi-structured data, and unstructured data, may be classified into historical data and real-time data, and may be classified into platform log data, network data, and database data. Different data grabbing modes can be adopted according to different types of data.
As shown in fig. 2, taking the weather data in the vehicle running environment data as an example, the data may be obtained from the website platform through a public application programming interface (Application Programming Interface, API) and/or web crawler tool provided by the third party environment data providing platform. Taking real-time data and historical data in the dynamic data of the storage battery as examples, and periodically uploading vehicle data containing storage battery information to a national grade new energy vehicle monitoring platform according to national requirements of vehicle enterprises, and acquiring real-time data recorded by the new energy vehicle monitoring platform through a platform log acquisition system; and the historical data stored by the new energy vehicle monitoring platform can be obtained through copying and backing up the historical data. Taking real-time data in the static data of the storage battery as an example, the real-time data can be directly connected with a background server of a new energy vehicle storage battery traceability platform through a database acquisition system so as to acquire the data stored in the database by the new energy vehicle storage battery traceability platform.
S120: and processing and storing the mass data based on a distributed system architecture.
Preferably, step S120 in the embodiment of the present invention may include:
carrying out data cleaning, arrangement and/or analysis on the mass data to obtain structured data;
based on the distributed system architecture, the structured data is stored in a data warehouse to enable the structured data to be retrieved or queried.
It will be appreciated that the mass data includes structured data, semi-structured data and unstructured data, and that the data needs to be converted into a unified format for storage.
Fig. 3 is a schematic diagram of a distributed system architecture in a storage battery fault early warning method based on big data according to an embodiment of the present invention.
Hadoop is a system architecture capable of performing distributed processing on big data, and the core design is a distributed file system HDFS (Hadoop Distributed File System, HDFS), a distributed computing engine model (e.g. MapReduce), a data warehouse tool Hive and a distributed database Hbase. Fig. 4 is a schematic diagram of a conventional Hadoop ecosystem architecture according to an embodiment of the present invention. Specifically, as shown in fig. 4, the HDFS provides storage for massive data, and the MapReduce provides calculation for massive data. Hive is an open source data warehouse that can support PB-level scalability. Hbase is mainly used for storing massive structured data.
SpringCloud is a micro-service framework, is a tool set for quickly constructing a universal mode of a distributed system, and is suitable for small and medium enterprises to establish own data analysis platforms. The data quality management refers to a series of management activities such as identification, measurement, monitoring and early warning on various data quality problems possibly caused in each stage of the life cycle of data planning, acquisition, storage, sharing, maintenance, application and extinction, and the data quality is further improved by improving and enhancing the management level of an organization. Data asset management refers to a set of business functions that plan, control and provide data and information assets, including planning, policies, schemes, projects, procedures, methods and procedures to develop, execute and oversee related data, thereby controlling, protecting, delivering and enhancing the value of data assets.
In the distributed storage process, massive data acquired from a platform needs to be cleaned, sorted or parsed, and concurrent processing is mainly performed based on clusters.
In a specific embodiment, as shown in fig. 2, based on the historical data batch processed by the Hbase cluster mode, the big data offline computing program such as MapReduce, spark realizes the access and preprocessing of the data; real-time data is processed based on a Kafka cluster mode stream, and large data real-time computing programs such as Storm, flink, spark Streaming and other computing frameworks realize access and preprocessing of the data. The preprocessing of the data can be extracting available characteristics of the data, and establishing a large-width table for modeling analysis of the data.
S130: and carrying out retrieval analysis according to the mass data to obtain a data analysis result aiming at least one storage battery fault class.
Preferably, as shown in fig. 5 (1), step S130 in the embodiment of the present invention may include the following steps:
s131: and counting the fault types, the fault frequency and/or the fault sources of the storage battery according to the historical fault data of the storage battery to obtain a fault counting analysis result.
Preferably, the data is summarized according to the search, wherein the total number of vehicles of the failed vehicles is not less than 20%, and the summarized data is provided with a failure type label field or a failure category analysis rule
Preferably, certain data processing operations such as missing value analysis, normalization or discretization of abnormal value continuous variable, time sequence analysis, continuous analysis and the like can be performed on the summarized data to obtain relevant statistical data of driving strokes and/or charging strokes, and the number and type distribution of battery faults in the strokes can be counted according to the relevant statistical data, so that the fault statistical analysis result is obtained. Further, the results of the fault statistics analysis may be visualized as part of the analysis report content.
In particular, the battery fault categories may include, but are not limited to: short circuit, circuit breaking, deformation, liquid leakage, drying, vulcanization and polarity reversal.
S132: and aiming at each storage battery fault type in the fault statistical analysis result, obtaining the fault occurrence time of each storage battery fault type according to the storage battery historical fault data.
In some possible embodiments, by identifying the time point of the battery fault in the journey, the content of each type of data before and after the time point is regarded as abnormal data, and the abnormal data is used for analyzing the association of the abnormal data and the battery fault.
S133: and retrieving and collecting the historical state data of the storage battery and the static state data of the storage battery in a certain time range before and after the occurrence time of the fault from the data warehouse as abnormal data of the storage battery.
In a particularly practical embodiment, the certain time range may be determined as one hour.
S134: and carrying out data mining and analysis according to the battery abnormal data to obtain characteristic analysis results of the battery abnormal data aiming at each storage battery fault type and correlation analysis results of each storage battery fault type and the battery abnormal data.
In some possible embodiments, the characteristic analysis results of the battery anomaly data may include, but are not limited to: state of Charge (SOC), total voltage, total current, dynamic resistance, data relating to the highest and lowest voltages, data relating to the highest and lowest temperatures, data relating to the State of non-uniformity of the module-battery pack-cell system voltages, cell self-discharge rate and temperature differential expansion trend characteristics.
In some possible embodiments, according to the battery abnormal data and/or the characteristic analysis result of the battery abnormal data, calculating the influence index of each type of data of the storage battery before and after the occurrence of the fault. Further, the correlation degree of the fault type and various data of the storage battery can be qualitatively and quantitatively measured by drawing corresponding time sequence charts, perspective tables and other graphic qualitative analysis, and also by methods of statistical correlation analysis, chi-square test, analysis of variance and the like, and the correlation degree can be used as a correlation analysis result.
Preferably, as shown in fig. 5 (2), step S130 in the embodiment of the present invention may further include the following steps:
s135: and searching and collecting relevant user use behavior data, vehicle use state data and/or vehicle running environment data from the data warehouse as external abnormal data for each storage battery fault type in the fault statistical analysis result.
S136: and carrying out data mining and analysis according to the external abnormal data to obtain characteristic analysis results of the external abnormal data aiming at each storage battery fault type and correlation analysis results of each storage battery fault type and the external abnormal data.
In some possible embodiments, the feature analysis results of the external anomaly data include, but are not limited to: instantaneous vehicle speed, accelerator pedal state and value, brake pedal state and value.
In some possible embodiments, the data types of the vehicle type, the vehicle use, the vehicle type, the driving area, the total vehicle operation time, the total vehicle operation mileage, the average vehicle operation time, the operation unit and the like may be screened or used as comparison items for analogy, so that the association analysis of the external abnormal data and each storage battery fault type may be further performed, and the correlation analysis result may be obtained.
Preferably, as shown in fig. 5 (3), step S130 in the embodiment of the present invention may further include:
s137: and for each storage battery fault category in the fault statistical analysis result, searching and collecting historical fault data and/or historical state data of the bicycle from the data warehouse as bicycle abnormal data.
S138: and carrying out data mining and analysis according to the bicycle abnormal data to obtain characteristic analysis results of the bicycle abnormal data aiming at each storage battery fault type and correlation analysis results of each storage battery fault type and the bicycle abnormal data.
In some possible embodiments, the feature analysis results of the bicycle anomaly data include, but are not limited to: the type of bicycle fault, the frequency of bicycle fault, the bicycle charge state and the bicycle health state. The correlation analysis result can be obtained by counting the fault condition of the bicycle and the data characteristics of the related data.
S140: and establishing at least one storage battery fault early warning target model according to the data analysis result.
Preferably, as shown in fig. 6, step S140 in the embodiment of the present invention may include:
s141: and establishing at least one storage battery fault early warning universal model corresponding to each storage battery fault class according to the characteristic analysis result of the battery abnormal data, the characteristic analysis result of the external abnormal data, the correlation analysis result of each storage battery fault class and the battery abnormal data and/or the correlation analysis result of each storage battery fault class and the external abnormal data aiming at each storage battery fault class in the fault statistics analysis result.
In some possible embodiments, the at least one general model of battery fault early warning corresponding to each battery fault category may include, but is not limited to, a regression analysis type prediction model, a probability estimation type prediction model, a time series type prediction model, and a machine learning type prediction model. The machine learning type prediction model automatically mines data characteristics, is more commonly used in situations with support vector machines, decision trees and neural networks, and is particularly suitable for situations with a large amount of data.
It is understood that the at least one battery fault early warning general model corresponding to each battery fault class is based on the feature analysis result of the battery abnormality data, the feature analysis result of the external abnormality data, the correlation analysis result of each battery fault class and the battery abnormality data, and/or the correlation analysis result of each battery fault class and the external abnormality data in the overall data, and thus can be widely duplicated as a general model.
S142: and according to the characteristic analysis result of the bicycle abnormal data and the correlation analysis result of each storage battery fault type and the bicycle abnormal data, adjusting and correcting the at least one storage battery fault early-warning general model to obtain at least one storage battery fault early-warning model aiming at the bicycle.
Preferably, the correlation analysis result of each storage battery fault category and the bicycle abnormal data is aimed at the data mining analysis result of the bicycle, and the data type with a larger degree of the bicycle image is incorporated into any of the prediction models, so that at least one storage battery fault early warning model which is more accurate for the bicycle can be independently established.
S143: and acquiring random sample data of the bicycle, and training the at least one storage battery fault early-warning model through the random sample data to obtain at least one storage battery fault early-warning target model.
In some possible embodiments, various data of part of continuous time points of the bicycle in a normal running state are randomly collected to serve as positive samples, various data of historical fault time points serve as negative samples, and a classifier model is built. In addition, the method is not limited to the bicycle, and various data recorded and stored in the platform in the embodiment of the invention can be randomly collected as training data when the vehicle is in a normal running state and the fault occurs.
Further, algorithms such as logistic regression, decision trees, random forests, gradient lifting iteration decision trees (Gradient Boosting Decision Tree, GBDT) and the like are adopted to fit the association of dependent variable fault information and independent variable type data, and the probability of a certain fault of a vehicle at a certain moment can be obtained. In the model training process, residual errors, posterior errors and the like can be used as probability statistics test, and also mean square error can be used for sample test.
It can be appreciated that after the prediction model is built, the prediction model is trained through a large amount of sample data, so that the accuracy and the fineness of early warning of the faults of the storage battery are improved.
In some possible embodiments, the model may also output relevant statistical indicators based on historical data; an analysis report is provided according to the model output, illustrating the law of occurrence of faults based on the discovery of sample data.
S150: obtaining target data of a bicycle, and carrying out predictive analysis on the target data of the bicycle through the at least one storage battery fault early warning target model to obtain a storage battery fault prediction result of the bicycle.
Preferably, step S150 in the embodiment of the present invention may include:
s151: and acquiring real-time target data of the bicycle through the vehicle-mounted terminal acquisition equipment of the bicycle.
In some possible embodiments, the in-vehicle terminal acquisition device may be an in-vehicle T-BOX (Telematics BOX). The vehicle-mounted T-BOX is connected to the CAN bus through an interface, data acquisition is carried out through a CAN network, and data such as vehicle information, vehicle controller information, motor controller information, a battery management system BMS (Battery Management System, BMS), a vehicle-mounted charger and the like are mainly acquired, recorded and analyzed. After information is collected, the vehicle-mounted T-BOX stores the collected real-time data in an internal storage medium according to a time interval of not more than 30s at maximum, and if a 3-level alarm occurs, the vehicle-mounted T-BOX stores the collected real-time data according to the time interval of not more than 1s at maximum. Meanwhile, the vehicle-mounted T-BOX is provided with a mobile communication module, a Bluetooth module, a wireless communication module and the like and is used for uploading the acquired real-time target data of the bicycle to an analysis end.
In some possible embodiments, the real-time target data of the bicycle can be detected and acquired by an on-board photoelectric wave sensing device of the bicycle.
S152: and acquiring the static data of the storage battery of the bicycle recorded by the storage battery tracing platform as static target data.
In other possible embodiments, the battery static data of the bicycle can also be acquired through a data platform.
S153: and importing the real-time target data and the static target data of the single vehicle into the at least one storage battery fault early warning target model to obtain a storage battery fault prediction result related to the single vehicle, wherein the storage battery fault prediction result comprises a predicted fault type, fault occurrence time, fault occurrence probability and/or fault source.
In some possible embodiments, the storage battery fault early-warning target model at least includes 15 national standard faults, and the storage battery fault early-warning target model may be further added in an expanding manner according to new fault categories occurring in the massive data.
In some possible embodiments, real-time environmental data can also be pulled from the third party environmental data providing platform, and imported into the model to configure relevant parameters.
S160: and obtaining storage battery early warning information based on the storage battery fault prediction result, and sending the storage battery early warning information to the bicycle terminal or the user terminal equipment.
Preferably, step S160 in the embodiment of the present invention may include the steps of:
s161: and screening the storage battery fault prediction result according to a preset threshold value, and describing the screened storage battery fault prediction result in natural language based on a preset rule to obtain storage battery fault early warning information.
In some possible embodiments, the predicted result of the storage battery includes a predicted fault type, a predicted fault occurrence time, a predicted fault occurrence probability and/or a predicted fault source, and the predicted result may be screened according to a preset threshold value for the probability of occurrence of the fault and the predicted fault occurrence time. The predicted result after screening can be structured data, and based on a natural language processing technology, the structured data can be converted into natural language, so that humanized early warning service is provided.
S162: the storage battery fault early warning information is sent to the bicycle terminal or user terminal equipment;
and/or transmitting the data analysis result for at least one storage battery fault class to the bicycle terminal or the user terminal device in a visual representation form.
In some possible embodiments, a battery fault early-warning system may be established according to the battery fault early-warning target model, where the battery fault early-warning system includes an early-warning prompt unit, and the early-warning prompt unit includes a communication module, and is configured to send the early-warning information and/or the data analysis result to a display screen, a central console or mobile application software of the vehicle-mounted terminal through a mobile network or a wireless network.
It is understood that the data analysis results may be presented in visual form, including but not limited to pie charts, bar charts, graphs, timing charts, and pivot charts.
The embodiment of the invention also provides a storage battery fault early warning system based on big data, as shown in fig. 7, the storage battery fault early warning system based on big data can comprise:
an interactive interface 701, configured to set a fault early warning mode by a user; the storage battery fault early warning device is used for displaying storage battery fault early warning information; and/or for displaying the visualized data analysis results for at least one battery fault class.
A data grabbing unit 702, configured to grab mass data of at least one target platform; and/or obtain target data for the bicycle.
The data processing unit 703 is configured to process and store the massive data based on a distributed system architecture.
And the data analysis unit 704 is configured to perform search analysis according to the massive data, so as to obtain a data analysis result for at least one storage battery fault class.
The early warning model unit 705 is configured to establish at least one storage battery fault early warning target model according to the data analysis result; and/or the method is used for carrying out predictive analysis on the target data of the bicycle through the at least one storage battery fault early warning target model to obtain a storage battery fault prediction result of the bicycle.
And the early warning prompting unit 706 is configured to obtain early warning information of the battery fault based on the battery fault prediction result, and send the early warning information of the battery fault to the bicycle terminal or the user terminal device.
The embodiment of the invention also provides a computer device, which comprises: the storage battery fault early warning method based on big data comprises a processor and a memory, wherein at least one instruction, at least one section of program, a code set or an instruction set is stored in the memory, and the at least one instruction, the at least one section of program, the code set or the instruction set is loaded and executed by the processor so as to realize the storage battery fault early warning method based on big data.
The memory may be used to store software programs and modules that the processor executes by running the software programs and modules stored in the memory to thereby execute various functional applications. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, application programs required for functions, and the like; the storage data area may store data created according to the use of the device, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide access to the memory by the processor.
The method embodiments provided by the embodiments of the present invention may be performed in a computer terminal, a server, or a similar computing device, i.e., the computer apparatus may include a computer terminal, a server, or a similar computing device. Fig. 8 is a block diagram of a hardware structure of a computer device for running a battery fault early warning method based on big data according to an embodiment of the present invention, and as shown in fig. 8, the internal structure of the computer device may include, but is not limited to: processor, network interface and memory. The processors, network interfaces, and memories in the computer device may be connected by a bus or other means, and in fig. 8 shown in the embodiment of the present disclosure, the connection by a bus is an example.
Among them, a processor (or CPU (Central Processing Unit, central processing unit)) is a computing core and a control core of a computer device. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI, mobile communication interface, etc.). Memory (Memory) is a Memory device in a computer device for storing programs and data. It will be appreciated that the memory herein may be a high speed RAM memory device or a non-volatile memory device, such as at least one magnetic disk memory device; optionally, at least one memory device located remotely from the processor. The memory provides a storage space that stores an operating system of the electronic device, which may include, but is not limited to: windows (an operating system), linux (an operating system), android (an Android, a mobile operating system) system, IOS (a mobile operating system) system, etc., the invention is not limited in this regard; also stored in the memory space are one or more instructions, which may be one or more computer programs (including program code), adapted to be loaded and executed by the processor. In the embodiment of the specification, the processor loads and executes one or more instructions stored in the memory to realize the storage battery fault early warning method for the big genetic data provided by the embodiment of the method.
The embodiment of the invention also provides a computer storage medium, wherein at least one instruction, at least one section of program, a code set or an instruction set is stored in the storage medium, and the at least one instruction, the at least one section of program, the code set or the instruction set is loaded by a processor and executes the storage battery fault early warning method based on big data.
Alternatively, in the present embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, system and server embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the description of method embodiments in part.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (8)
1. The storage battery fault early warning method based on big data is characterized by comprising the following steps:
capturing mass data of at least one target platform;
Processing and storing the mass data based on a distributed system architecture;
according to the mass data, carrying out retrieval analysis to obtain a characteristic analysis result of abnormal data aiming at least one storage battery fault type and a correlation analysis result of the at least one storage battery fault type and the abnormal data, wherein the abnormal data is one or more of battery abnormal data, external abnormal data or bicycle abnormal data;
aiming at each storage battery fault type, establishing a storage battery fault early warning general model corresponding to each storage battery fault type in the at least one storage battery fault type according to a characteristic analysis result of the abnormal data of the storage battery, a characteristic analysis result of the external abnormal data, a correlation analysis result of each storage battery fault type and the abnormal data of the storage battery and/or a correlation analysis result of each storage battery fault type and the external abnormal data;
according to the feature analysis result of the bicycle abnormal data and the correlation analysis result of each storage battery fault type and the bicycle abnormal data, the storage battery fault early warning general model corresponding to each storage battery fault type is adjusted and corrected to obtain at least one storage battery fault early warning model aiming at the bicycle, and each storage battery fault early warning model corresponds to one storage battery fault type;
Acquiring random sample data of the bicycle, and training the at least one storage battery fault early-warning model through the random sample data to obtain at least one storage battery fault early-warning target model, wherein each storage battery fault early-warning target model corresponds to one storage battery fault class;
acquiring target data of the bicycle, wherein the target data comprises real-time target data of the bicycle acquired through a vehicle-mounted terminal acquisition device of the bicycle and static target data determined according to storage battery static data of the bicycle recorded by a storage battery tracing platform;
the real-time target data and the static target data are subjected to predictive analysis through a storage battery fault early warning target model corresponding to each storage battery fault type, and a storage battery fault prediction result of the bicycle is obtained;
obtaining storage battery fault early warning information based on the storage battery fault prediction result, and sending the storage battery fault early warning information to the bicycle terminal or the user terminal equipment;
and adjusting the data storage interval period of the vehicle-mounted terminal acquisition equipment according to the early warning level corresponding to the storage battery fault early warning information.
2. The method for early warning of battery failure based on big data according to claim 1, wherein capturing mass data of at least one target platform comprises:
grabbing storage battery dynamic data recorded by a new energy vehicle monitoring platform, wherein the storage battery dynamic data comprises storage battery real-time state data, storage battery historical state data and storage battery historical fault data;
grabbing storage battery static data recorded by a new energy vehicle storage battery traceability platform;
grabbing vehicle running environment data recorded by a third party environment data providing platform;
and/or capturing vehicle use state data and user use behavior data recorded by the Internet of vehicles data platform.
3. The method for early warning of battery failure based on big data according to claim 1, wherein the processing and storing the mass data based on the distributed system architecture comprises:
carrying out data cleaning, arrangement and/or analysis on the mass data to obtain structured data;
based on the distributed system architecture, the structured data is stored in a data warehouse to enable the structured data to be retrieved or queried.
4. The method for early warning of a battery fault based on big data according to claim 2, wherein the performing the search analysis according to the massive data to obtain a feature analysis result of the abnormal data for at least one battery fault class and a correlation analysis result of the at least one battery fault class and the abnormal data includes:
counting the fault types, the fault frequency and/or the fault sources of the storage battery according to the historical fault data of the storage battery to obtain a fault counting analysis result;
aiming at each storage battery fault category in the fault statistics analysis result, obtaining the fault occurrence time of each storage battery fault category according to the storage battery historical fault data;
taking historical state data of the storage battery and static data of the storage battery in a certain time range before and after the fault occurrence time as abnormal data of the storage battery;
and carrying out data mining and analysis according to the battery abnormal data to obtain characteristic analysis results of the battery abnormal data aiming at each storage battery fault type and correlation analysis results of each storage battery fault type and the battery abnormal data.
5. The method for early warning of battery failure based on big data according to claim 4, wherein the performing the search analysis according to the massive data obtains a feature analysis result of the abnormal data for at least one battery failure category and a correlation analysis result of the at least one battery failure category and the abnormal data, further comprising:
aiming at each storage battery fault category in the fault statistics analysis result, acquiring related user use behavior data, vehicle use state data and/or vehicle running environment data as the external abnormal data;
and carrying out data mining and analysis according to the external abnormal data to obtain characteristic analysis results of the external abnormal data aiming at each storage battery fault type and correlation analysis results of each storage battery fault type and the external abnormal data.
6. The method for early warning of battery failure based on big data according to claim 4, wherein the performing the search analysis according to the massive data obtains a feature analysis result of the abnormal data for at least one battery failure category and a correlation analysis result of the at least one battery failure category and the abnormal data, further comprising:
For each storage battery fault category in the fault statistics analysis result, acquiring historical fault data and/or historical state data of the bicycle as bicycle abnormal data;
and carrying out data mining and analysis according to the bicycle abnormal data to obtain characteristic analysis results of the bicycle abnormal data aiming at each storage battery fault type and correlation analysis results of each storage battery fault type and the bicycle abnormal data.
7. The battery fault early-warning method based on big data according to any one of claims 4 to 6, characterized in that the obtaining battery fault early-warning information based on the battery fault prediction result and transmitting the battery fault early-warning information to the bicycle terminal or the user terminal device includes:
screening the battery fault prediction result according to a preset threshold value, and describing the screened battery fault prediction result in natural language based on a preset rule to obtain battery fault early warning information;
the storage battery fault early warning information is sent to the bicycle terminal or user terminal equipment;
and/or transmitting the data analysis result for at least one storage battery fault class to the bicycle terminal or the user terminal device in a visual representation form.
8. A battery fault early warning system based on big data, the system comprising:
the interactive interface is used for setting a fault early warning mode; the storage battery fault early warning device is used for displaying storage battery fault early warning information; and/or for displaying the visualized feature analysis results of the anomaly data for at least one battery fault class and the correlation analysis results of the at least one battery fault class and the anomaly data;
the data grabbing unit is used for grabbing mass data of at least one target platform;
the data processing unit is used for processing and storing the mass data based on a distributed system architecture;
the data analysis unit is used for carrying out search analysis according to the mass data to obtain a characteristic analysis result of abnormal data aiming at least one storage battery fault type and a correlation analysis result of the at least one storage battery fault type and the abnormal data, wherein the abnormal data is one or more of battery abnormal data, external abnormal data or bicycle abnormal data;
the early warning model unit is used for establishing a storage battery fault early warning general model corresponding to each storage battery fault type in the at least one storage battery fault type according to the characteristic analysis result of the battery abnormal data, the characteristic analysis result of the external abnormal data, the correlation analysis result of each storage battery fault type and the battery abnormal data and/or the correlation analysis result of each storage battery fault type and the external abnormal data; according to the feature analysis result of the bicycle abnormal data and the correlation analysis result of each storage battery fault type and the bicycle abnormal data, the storage battery fault early warning general model corresponding to each storage battery fault type is adjusted and corrected to obtain at least one storage battery fault early warning model aiming at the bicycle, and each storage battery fault early warning model corresponds to one storage battery fault type; acquiring random sample data of the bicycle, and training the at least one storage battery fault early-warning model through the random sample data to obtain at least one storage battery fault early-warning target model, wherein each storage battery fault early-warning target model corresponds to one storage battery fault class; acquiring target data of the bicycle, wherein the target data comprises real-time target data of the bicycle acquired through a vehicle-mounted terminal acquisition device of the bicycle and static target data determined according to storage battery static data of the bicycle recorded by a storage battery tracing platform; the real-time target data and the static target data are subjected to predictive analysis through a storage battery fault early warning target model corresponding to each storage battery fault type, and a storage battery fault prediction result of the bicycle is obtained;
The early warning prompting unit is used for obtaining storage battery fault early warning information based on the storage battery fault prediction result and sending the storage battery fault early warning information to an interactive interface of the bicycle terminal or an interactive interface of user terminal equipment; and adjusting the data storage interval period of the vehicle-mounted terminal acquisition equipment according to the early warning level corresponding to the storage battery fault early warning information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010001150.XA CN111241154B (en) | 2020-01-02 | 2020-01-02 | Storage battery fault early warning method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010001150.XA CN111241154B (en) | 2020-01-02 | 2020-01-02 | Storage battery fault early warning method and system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111241154A CN111241154A (en) | 2020-06-05 |
| CN111241154B true CN111241154B (en) | 2024-04-12 |
Family
ID=70864780
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010001150.XA Active CN111241154B (en) | 2020-01-02 | 2020-01-02 | Storage battery fault early warning method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111241154B (en) |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113888775A (en) * | 2020-06-19 | 2022-01-04 | 比亚迪股份有限公司 | Vehicle early warning method, server, storage medium, vehicle early warning system and vehicle |
| CN111901158B (en) * | 2020-07-14 | 2023-07-25 | 广东好太太智能家居有限公司 | Intelligent household distribution network fault data analysis method, equipment and storage medium |
| CN111983468B (en) * | 2020-08-24 | 2022-11-18 | 哈尔滨理工大学 | Safety degree estimation method of lithium power battery based on neural network |
| CN112622676A (en) * | 2020-11-09 | 2021-04-09 | 特瓦特能源科技有限公司 | Monitoring method and system for power battery safe charging |
| CN112622690A (en) * | 2020-11-09 | 2021-04-09 | 特瓦特能源科技有限公司 | Monitoring method and system for power battery safe charging |
| CN112684349A (en) * | 2021-01-25 | 2021-04-20 | 中国第一汽车股份有限公司 | Analysis method, verification method, device, equipment and medium for battery monomer failure |
| CN113093013B (en) * | 2021-03-31 | 2022-02-08 | 安庆师范大学 | Integrated estimation method for health state of lithium battery pack |
| CN113494939A (en) * | 2021-04-15 | 2021-10-12 | 浙江工商大学 | Distributed monitoring method for rural domestic sewage |
| CN113344352A (en) * | 2021-05-28 | 2021-09-03 | 重庆长安汽车股份有限公司 | Storage battery feed risk identification method based on machine learning algorithm |
| CN113310647B (en) * | 2021-06-30 | 2022-11-15 | 中国第一汽车股份有限公司 | Method and device for detecting leakage of battery pack, electronic equipment and storage medium |
| CN113807547A (en) * | 2021-08-12 | 2021-12-17 | 江铃汽车股份有限公司 | Vehicle fault early warning method and system, readable storage medium and computer equipment |
| CN113844266A (en) * | 2021-08-20 | 2021-12-28 | 云度新能源汽车有限公司 | Method and storage device for predicting and identifying faults of power battery |
| CN113761728B (en) * | 2021-08-24 | 2022-06-03 | 威海广泰空港设备股份有限公司 | Airport electric special vehicle fault early warning method based on Internet of vehicles platform |
| CN113837608A (en) * | 2021-09-24 | 2021-12-24 | 浙江中烟工业有限责任公司 | Tobacco throwing management and control and early warning platform based on big data analysis |
| CN115122933A (en) * | 2022-08-22 | 2022-09-30 | 中国第一汽车股份有限公司 | Electric automobile standing abnormity identification method and device |
| CN116087782B (en) * | 2022-11-09 | 2024-02-02 | 苏州首帆电子科技有限公司 | Automobile battery fault early warning method, system, device and storage medium |
| CN116028782B (en) * | 2023-03-27 | 2023-08-01 | 佛山隆深机器人有限公司 | Fuel cell data visualization system and method |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105372600A (en) * | 2015-11-24 | 2016-03-02 | 珠海朗尔电气有限公司 | Storage battery fault diagnosis system and method based on big data |
| CN106058987A (en) * | 2016-06-29 | 2016-10-26 | 浙江万马新能源有限公司 | Electric vehicle charging method and electric vehicle charging device based on storage battery monitoring and fault diagnosis |
| CN107528095A (en) * | 2017-07-31 | 2017-12-29 | 清华大学 | Low tension battery failure prediction method based on new energy vehicle storing card data |
| CN108008332A (en) * | 2017-11-29 | 2018-05-08 | 国网山东省电力公司电力科学研究院 | A kind of new energy Remote testing device method for diagnosing faults based on data mining |
| CN108460144A (en) * | 2018-03-14 | 2018-08-28 | 西安华光信息技术有限责任公司 | A kind of coal equipment fault early-warning system and method based on machine learning |
| CN108556647A (en) * | 2018-01-16 | 2018-09-21 | 上海应用技术大学 | The safety on line method for early warning of Prospect of EVS Powered with Batteries based on cloud platform and battery management system |
| CN109459702A (en) * | 2018-11-09 | 2019-03-12 | 爱驰汽车有限公司 | Battery status analysis method and device based on car networking |
| CN109656975A (en) * | 2018-12-13 | 2019-04-19 | 上海航天电源技术有限责任公司 | Fault early warning system and method based on big data |
| CN109684422A (en) * | 2018-12-28 | 2019-04-26 | 河南城建学院 | A kind of single index prediction of the big data platform based on artificial intelligence and method for early warning |
| CN110018425A (en) * | 2019-04-10 | 2019-07-16 | 北京理工大学 | A kind of power battery fault diagnosis method and system |
| WO2019138286A1 (en) * | 2018-01-11 | 2019-07-18 | 株式会社半導体エネルギー研究所 | Abormality detection device for secondary battery, abnormality detection method, and program |
| CN110110905A (en) * | 2019-04-17 | 2019-08-09 | 华电国际电力股份有限公司十里泉发电厂 | A kind of electrical equipment fault based on CNN judges method for early warning, terminal and readable storage medium storing program for executing |
| CN110569997A (en) * | 2019-09-16 | 2019-12-13 | 国网江苏省电力有限公司苏州供电分公司 | charging station operation maintenance method based on multi-dimensional data system |
-
2020
- 2020-01-02 CN CN202010001150.XA patent/CN111241154B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105372600A (en) * | 2015-11-24 | 2016-03-02 | 珠海朗尔电气有限公司 | Storage battery fault diagnosis system and method based on big data |
| CN106058987A (en) * | 2016-06-29 | 2016-10-26 | 浙江万马新能源有限公司 | Electric vehicle charging method and electric vehicle charging device based on storage battery monitoring and fault diagnosis |
| CN107528095A (en) * | 2017-07-31 | 2017-12-29 | 清华大学 | Low tension battery failure prediction method based on new energy vehicle storing card data |
| CN108008332A (en) * | 2017-11-29 | 2018-05-08 | 国网山东省电力公司电力科学研究院 | A kind of new energy Remote testing device method for diagnosing faults based on data mining |
| WO2019138286A1 (en) * | 2018-01-11 | 2019-07-18 | 株式会社半導体エネルギー研究所 | Abormality detection device for secondary battery, abnormality detection method, and program |
| CN108556647A (en) * | 2018-01-16 | 2018-09-21 | 上海应用技术大学 | The safety on line method for early warning of Prospect of EVS Powered with Batteries based on cloud platform and battery management system |
| CN108460144A (en) * | 2018-03-14 | 2018-08-28 | 西安华光信息技术有限责任公司 | A kind of coal equipment fault early-warning system and method based on machine learning |
| CN109459702A (en) * | 2018-11-09 | 2019-03-12 | 爱驰汽车有限公司 | Battery status analysis method and device based on car networking |
| CN109656975A (en) * | 2018-12-13 | 2019-04-19 | 上海航天电源技术有限责任公司 | Fault early warning system and method based on big data |
| CN109684422A (en) * | 2018-12-28 | 2019-04-26 | 河南城建学院 | A kind of single index prediction of the big data platform based on artificial intelligence and method for early warning |
| CN110018425A (en) * | 2019-04-10 | 2019-07-16 | 北京理工大学 | A kind of power battery fault diagnosis method and system |
| CN110110905A (en) * | 2019-04-17 | 2019-08-09 | 华电国际电力股份有限公司十里泉发电厂 | A kind of electrical equipment fault based on CNN judges method for early warning, terminal and readable storage medium storing program for executing |
| CN110569997A (en) * | 2019-09-16 | 2019-12-13 | 国网江苏省电力有限公司苏州供电分公司 | charging station operation maintenance method based on multi-dimensional data system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111241154A (en) | 2020-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111241154B (en) | Storage battery fault early warning method and system based on big data | |
| Wang et al. | A data-driven method for battery charging capacity abnormality diagnosis in electric vehicle applications | |
| CN109100655B (en) | Data processing method and device for power battery | |
| CN103617110A (en) | Server device condition maintenance system | |
| CN106650963A (en) | Electric car charging equipment detection and maintenance managing method and device | |
| CN113189495B (en) | Battery health state prediction method and device and electronic equipment | |
| CN115330275B (en) | Echelon utilization method and device for retired battery | |
| CN110927606B (en) | Battery state monitoring method and device | |
| WO2022174679A1 (en) | Method and apparatus for predicting voltage inconsistency fault of battery cells, and server | |
| CN112101597A (en) | Electric vehicle leasing operation platform vehicle fault pre-judging system, method and device | |
| US20220283242A1 (en) | Method and device for managing battery data | |
| Li et al. | A Novel Method for Lithium‐Ion Battery Fault Diagnosis of Electric Vehicle Based on Real‐Time Voltage | |
| DE102022120962A1 (en) | BATTERY ERROR DETECTION | |
| CN116720324A (en) | Traction substation key equipment fault early warning method and system based on prediction model | |
| CN114579659A (en) | System and method for estimating and sorting utilization potential of power battery by gradient utilization | |
| CN117347869B (en) | Data analysis method and device for energy storage battery management system, electronic equipment and medium | |
| CN117310500A (en) | Battery state classification model construction method and battery state classification method | |
| CN113986893A (en) | Active early warning system and method based on generator car risk identification | |
| CN117214719A (en) | New energy vehicle battery health evaluation system based on big data | |
| CN111381165A (en) | Vehicle power battery monitoring method, device and platform | |
| CN117332337A (en) | Battery thermal runaway early warning method, device, server and storage medium | |
| CN114239388A (en) | Method and system for predicting remaining life of battery by fusing test and Internet of vehicles | |
| Fransson et al. | Finding patterns in vehicle diagnostic trouble codes: A data mining study applying associative classification | |
| CN116502156B (en) | Intelligent identification method and system for light CT abnormal state of converter station | |
| Sun et al. | A Data-Driven Algorithm for Short Circuit Fault Diagnosis of Power Batteries |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 612, building 1, 1760 Jiangling Road, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Zhejiang Geely Remote New Energy Commercial Vehicle Group Co.,Ltd. Applicant after: GEELY SICHUAN COMMERCIAL VEHICLE Co.,Ltd. Applicant after: Zhejiang Geely new energy Commercial Vehicle Development Co.,Ltd. Applicant after: ZHEJIANG GEELY HOLDING GROUP Co.,Ltd. Address before: Room 612, building 1, 1760 Jiangling Road, Binjiang District, Hangzhou City, Zhejiang Province Applicant before: ZHEJIANG GEELY NEW ENERGY COMMERCIAL VEHICLE GROUP Co.,Ltd. Applicant before: GEELY SICHUAN COMMERCIAL VEHICLE Co.,Ltd. Applicant before: Zhejiang Geely new energy Commercial Vehicle Development Co.,Ltd. Applicant before: ZHEJIANG GEELY HOLDING GROUP Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230726 Address after: Room 612, building 1, 1760 Jiangling Road, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Zhejiang Geely Remote New Energy Commercial Vehicle Group Co.,Ltd. Applicant after: GEELY SICHUAN COMMERCIAL VEHICLE Co.,Ltd. Applicant after: ZHEJIANG GEELY HOLDING GROUP Co.,Ltd. Address before: Room 612, building 1, 1760 Jiangling Road, Binjiang District, Hangzhou City, Zhejiang Province Applicant before: Zhejiang Geely Remote New Energy Commercial Vehicle Group Co.,Ltd. Applicant before: GEELY SICHUAN COMMERCIAL VEHICLE Co.,Ltd. Applicant before: Zhejiang Geely new energy Commercial Vehicle Development Co.,Ltd. Applicant before: ZHEJIANG GEELY HOLDING GROUP Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |