CN115015769A - Power battery residual value estimation method, device, equipment and medium - Google Patents

Power battery residual value estimation method, device, equipment and medium Download PDF

Info

Publication number
CN115015769A
CN115015769A CN202210954269.8A CN202210954269A CN115015769A CN 115015769 A CN115015769 A CN 115015769A CN 202210954269 A CN202210954269 A CN 202210954269A CN 115015769 A CN115015769 A CN 115015769A
Authority
CN
China
Prior art keywords
target
curve
battery
capacity
initial
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.)
Granted
Application number
CN202210954269.8A
Other languages
Chinese (zh)
Other versions
CN115015769B (en
Inventor
郑伟鹏
丁柏栋
胡银平
李艳芹
高若峰
徐玉洁
李文剑
龙腾飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Jiecheng Nickel Cobalt New Energy Technology Co ltd
Original Assignee
Shenzhen Jiecheng Nickel Cobalt New Energy Technology Co ltd
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 Shenzhen Jiecheng Nickel Cobalt New Energy Technology Co ltd filed Critical Shenzhen Jiecheng Nickel Cobalt New Energy Technology Co ltd
Priority to CN202210954269.8A priority Critical patent/CN115015769B/en
Publication of CN115015769A publication Critical patent/CN115015769A/en
Application granted granted Critical
Publication of CN115015769B publication Critical patent/CN115015769B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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]
    • G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/60—Other road transportation technologies with climate change mitigation effect
    • Y02T10/70—Energy storage systems for electromobility, e.g. batteries

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Secondary Cells (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)

Abstract

The embodiment of the invention discloses a method, a device, equipment and a medium for estimating a residual value of a power battery, wherein the method comprises the following steps: acquiring a target temperature, a target charging and discharging frequency, an initial internal resistance corresponding to a target battery pack and an initial battery life curve; detecting a target battery cell in a target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle time predicted value, the residual battery capacity and a capacity attenuation curve section; determining a target battery life curve corresponding to the target temperature according to the initial battery life curve, the total cycle number predicted value, the residual battery capacity and the capacity attenuation curve section; and estimating each electric core in the target battery pack according to the single electric core residual value estimation configuration corresponding to the target temperature and the target battery life curve to obtain a single electric core residual value estimation result of the target battery pack corresponding to the target temperature. Thereby improving the accuracy of the estimated single core residual value.

Description

Power battery residual value estimation method, device, equipment and medium
Technical Field
The invention relates to the technical field of batteries, in particular to a method, a device, equipment and a medium for estimating a residual value of a power battery.
Background
With the development of new energy technology, electric vehicles are widely used. As the utilization time of the battery pack of the electric vehicle increases, the performance of the battery pack may be degraded. Because the performance requirement of the electric automobile on the battery pack is high, when the performance is lower than the requirement of the electric automobile, the battery pack needs to be retired. The abandonment of the battery pack can cause great threat to the ecological environment, and the electric core in the decommissioned battery pack is put into some suitable occasions for recycling, thus having great significance to the protection of the ecological environment. At present, the residual battery capacity of a battery core is directly detected, then the residual value of the battery core is determined according to the residual battery capacity, and the environmental factors of the occasion of recycling are not considered, so that the accuracy of the residual value of the battery core is not high.
Disclosure of Invention
Therefore, it is necessary to provide a method, an apparatus, a device and a medium for estimating a residual value of a power battery, aiming at the technical problem that the accuracy of the residual value of a single battery cell is not high due to the fact that only residual battery capacity is considered and environmental factors of a recycling occasion are not considered when the residual value of the single battery cell is estimated at present.
A power battery residual value estimation method, the method comprising:
acquiring a target temperature, a target charging and discharging frequency, an initial internal resistance corresponding to a target battery pack and an initial battery life curve;
detecting a target battery cell in the target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle time predicted value, a residual battery capacity and a capacity attenuation curve section;
determining a target battery life curve corresponding to the target temperature according to the initial battery life curve, the total cycle number predicted value, the residual battery capacity and the capacity attenuation curve section;
and estimating each electric core in the target battery pack according to the single electric core residual value estimation configuration corresponding to the target temperature and the target battery life curve to obtain a single electric core residual value estimation result of the target battery pack corresponding to the target temperature.
Further, the step of detecting the target electric core in the target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle time prediction value, a residual battery capacity and a capacity attenuation curve segment includes:
acquiring a counter, and initializing the value of the counter to 1;
at the target temperature, sequentially charging, standing for a preset time and discharging the target battery cell to obtain the capacity of a discharged battery and the discharge end time;
judging whether the value of the counter is 1 or not, or whether the value of the counter is the target charging and discharging times or not;
if so, performing internal resistance detection after finishing discharging on the target battery cell to obtain discharging finishing internal resistance and internal resistance detection time, and generating a single detection finishing signal, otherwise, generating the single detection finishing signal;
responding to the single detection end signal, adding 1 to the value of the counter, and repeatedly executing the steps of sequentially charging, standing for a preset time length and discharging the target electric core at the target temperature to obtain the capacity of a discharged battery and the discharge end time until the value of the counter is greater than the target charging and discharging times;
determining a temperature relation index corresponding to the target temperature according to a preset first relation function, each discharge finishing internal resistance and each internal resistance detection time;
determining the predicted value of the total cycle times according to a preset second relation function, the temperature relation index, the initial internal resistance and the finishing discharge internal resistance with the earliest internal resistance detection time;
generating the capacity decay curve segment according to the capacity of each discharge battery and each discharge end time;
the discharged battery capacity at which the end time of discharge is earliest is taken as the remaining battery capacity.
Further, the first relation function is: m = (Rb/Ra) n(t) Rb is the discharge ending internal resistance at the latest internal resistance detection time, Ra is the discharge ending internal resistance at the earliest internal resistance detection time, n (t) is the temperature relation index corresponding to the target temperature, t is the target temperature, and M is the target charge-discharge frequency;
the second relationship function is: t (x) = (Ra/R0) n(t) R0 is the initial internal resistance, and t (x) is the total cycle number prediction value.
Further, the step of determining a target battery life curve corresponding to the target temperature according to the initial battery life curve, the total cycle number predicted value, the remaining battery capacity and the capacity fading curve segment includes:
matching a most similar curve segment from the initial battery life curve according to the capacity fading curve segment, wherein the value corresponding to the most similar curve segment is that the minimum cycle number is greater than or equal to the total cycle number predicted value;
and determining the target battery life curve corresponding to the target temperature according to the capacity attenuation curve segment, the most similar curve segment, the total cycle number predicted value, the residual battery capacity and the initial battery life curve.
Further, the step of matching a most similar curve segment from the initial battery life curve according to the capacity fading curve segment, wherein the cycle number with the minimum value corresponding to the most similar curve segment is greater than or equal to the predicted total cycle number value includes:
inputting the capacity attenuation curve segment into a curve segment classification prediction model corresponding to the initial battery life curve for prediction to obtain a classification prediction vector;
extracting candidate vector elements from the classified predictive vectors, wherein the cycle number of the corresponding classified curve segment of the candidate vector elements in the initial battery life curve is greater than or equal to the total cycle number predictive value;
obtaining the vector element with the largest value from each candidate vector element as a hit vector element;
and taking the classification curve segment corresponding to the hit vector element in the initial battery life curve as the most similar curve segment.
Further, before the step of inputting the capacity fading curve segment into the curve segment classification prediction model corresponding to the initial battery life curve for prediction to obtain a classification prediction vector, the method further includes:
obtaining a training sample set corresponding to an initial model and the initial battery life curve, wherein each training sample in the training sample set comprises: the curve segment label is a classification curve segment in the initial battery life curve;
training the initial model by adopting the training sample set;
taking the initial model after training as the curve segment classification prediction model;
wherein the initial model comprises: an encoder comprising k +1 encoding layers, a decoder comprising k decoding layers, k being an integer greater than 2, and a classification layer being a fully-connected layer employing a softmax activation function;
k +1 coding layers are linearly connected, and k decoding layers are linearly connected;
the output of the encoder is taken as the input of the decoder, and the output of the decoder is taken as the input of the classification layer;
the output of the (k + 1) -g th encoding layer is used as the input of the g th decoding layer, g is an integer larger than 0, and g is smaller than or equal to k.
Further, the step of determining the target battery life curve corresponding to the target temperature according to the capacity fade curve segment, the most similar curve segment, the predicted total cycle number, the remaining battery capacity, and the initial battery life curve includes:
extracting a curve segment behind the most similar curve segment from the initial battery life curve to serve as a curve segment to be spliced;
sequentially splicing the most similar curve segment and the curve segment to be spliced to obtain a curve to be corrected;
and correcting the curve to be corrected according to the capacity attenuation curve segment, the total cycle number predicted value and the residual battery capacity to obtain the target battery life curve corresponding to the target temperature.
A power battery residual value estimation method and device comprises the following steps:
the data acquisition module is used for acquiring a target temperature, a target charging and discharging frequency, an initial internal resistance corresponding to a target battery pack and an initial battery life curve;
the detection module is used for detecting a target battery cell in the target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle time prediction value, a residual battery capacity and a capacity attenuation curve section;
a target battery life curve determining module, configured to determine a target battery life curve corresponding to the target temperature according to the initial battery life curve, the total cycle number prediction value, the remaining battery capacity, and the capacity fading curve segment;
and the single-cell residual value estimation result determining module is used for estimating each cell in the target battery pack according to the single-cell residual value estimation configuration corresponding to the target temperature and the target battery life curve to obtain a single-cell residual value estimation result of the target battery pack corresponding to the target temperature.
A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of:
acquiring a target temperature, a target charging and discharging frequency, an initial internal resistance corresponding to a target battery pack and an initial battery life curve;
detecting a target battery cell in the target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle time predicted value, a residual battery capacity and a capacity attenuation curve section;
determining a target battery life curve corresponding to the target temperature according to the initial battery life curve, the total cycle number predicted value, the residual battery capacity and the capacity attenuation curve section;
and estimating each electric core in the target battery pack according to the single electric core residual value estimation configuration corresponding to the target temperature and the target battery life curve to obtain a single electric core residual value estimation result of the target battery pack corresponding to the target temperature.
A computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of:
acquiring a target temperature, a target charging and discharging frequency, an initial internal resistance corresponding to a target battery pack and an initial battery life curve;
detecting a target battery cell in the target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle time predicted value, a residual battery capacity and a capacity attenuation curve section;
determining a target battery life curve corresponding to the target temperature according to the initial battery life curve, the total cycle number predicted value, the residual battery capacity and the capacity attenuation curve section;
and estimating each electric core in the target battery pack according to the single electric core residual value estimation configuration corresponding to the target temperature and the target battery life curve to obtain a single electric core residual value estimation result of the target battery pack corresponding to the target temperature.
According to the power battery residual value estimation method, in the whole single battery residual value estimation process, not only are the total cycle number predicted value, the residual battery capacity, the initial internal resistance and the initial battery life curve of the battery core comprehensively considered, but also the target temperature under the occasion of recycling is considered, so that the accuracy of the estimated single battery residual value is improved; and detecting the target battery cell in the target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle number predicted value, a residual battery capacity and a capacity attenuation curve segment, and generating the capacity attenuation curve segment according to the attenuation relation between the battery capacity and the cycle number during detection to provide a basis for accurately determining a future target battery life curve of the battery cell in the target battery pack, so that the accuracy of a single battery cell residual value estimation result at the target temperature is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Wherein:
FIG. 1 is a flow chart of a power battery residual estimation method in one embodiment;
FIG. 2 is a block diagram of a device for estimating residual value of power battery according to an embodiment;
FIG. 3 is a block diagram of a computer device in one embodiment.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
In one embodiment, as shown in FIG. 1, a power battery residual estimation method is provided. The method can be applied to both the terminal and the server, and this embodiment is exemplified by being applied to the terminal. The power battery residual value estimation method specifically comprises the following steps:
s1: acquiring a target temperature, a target charging and discharging frequency, an initial internal resistance corresponding to a target battery pack and an initial battery life curve;
specifically, the target temperature, the target charge and discharge frequency, and the initial internal resistance and the initial battery life curve corresponding to the target battery pack input by the user may be obtained, the target temperature, the target charge and discharge frequency, and the initial internal resistance and the initial battery life curve corresponding to the target battery pack may also be obtained from the database, and the target temperature, the target charge and discharge frequency, and the initial internal resistance and the initial battery life curve corresponding to the target battery pack may also be obtained from a third-party application.
The target temperature is an ambient temperature in the case of recycling. For example, the target temperature is any of 25 ℃, 30 ℃ and 45 ℃.
The target number of charge/discharge times is the number of charge/discharge times required for detection of the target battery pack. The number of times of one charge and discharge includes: once charged and once discharged. For example, the target number of charge and discharge is 30 or 50.
Optionally, the number of times of one charge and discharge includes: once charged, once left to stand and once discharged.
The target battery pack is a battery pack for which residual value estimation is required.
The battery pack may be a battery pack of an electric vehicle. In an electric vehicle, each battery pack includes several hundred cells.
It is to be understood that the present application is also applicable to the estimation of the residual value of the battery pack of other devices, and is not limited herein.
And the nameplate information is information carried by the target battery pack when the target battery pack leaves the factory. And information such as initial internal resistance, an initial battery life curve, rated battery capacity and the like can be obtained according to the nameplate information of the target battery pack. The initial internal resistance is the internal resistance of the battery cell in the battery pack when the battery cell leaves the factory. The initial battery life curve is a battery life curve of the battery cell in the battery pack when the battery cell leaves a factory, and the battery life curve can be a battery life curve tested by a manufacturer and/or a battery life curve obtained in advance according to tests at different temperatures. The battery life curve is a relation curve of the cycle number and the battery capacity, wherein the cycle number is used as an x-axis coordinate, and the battery capacity is used as a y-axis coordinate. The rated battery capacity is the battery capacity of the battery cells in the battery pack when the battery cells leave the factory.
S2: detecting a target battery cell in the target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle time predicted value, a residual battery capacity and a capacity attenuation curve section;
specifically, any one of the cells in the target battery pack is taken as a target cell; and at the target temperature, performing charge and discharge cycle detection on the target battery cell, and generating a total cycle number predicted value, a residual battery capacity and a capacity attenuation curve section according to the detected data and the initial internal resistance.
And the total cycle time predicted value is the predicted value of the total cycle time of the target battery cell when the current round of detection starts.
The remaining battery capacity is the battery capacity of the target battery cell at the beginning of the current round of detection.
And the capacity attenuation curve segment is a curve segment of the attenuation of the charge and discharge times and the battery capacity of the target battery cell in the current round of detection.
S3: determining a target battery life curve corresponding to the target temperature according to the initial battery life curve, the total cycle number predicted value, the residual battery capacity and the capacity attenuation curve section;
specifically, firstly, according to the capacity attenuation curve segment, a similar curve segment is found out from an initial battery life curve, and then according to the total cycle number predicted value and the residual battery capacity, the similar curve segment and a curve segment behind the similar curve segment in the initial battery life curve are corrected, so that a target battery life curve corresponding to the target temperature is obtained.
And (3) a target battery life curve corresponding to the target temperature, namely a battery life curve of the target battery cell when the target battery cell works at the target temperature.
S4: and estimating each electric core in the target battery pack according to the single electric core residual value estimation configuration corresponding to the target temperature and the target battery life curve to obtain a single electric core residual value estimation result of the target battery pack corresponding to the target temperature.
Optionally, the single-core residual value estimation configuration corresponding to the target temperature includes: scrap condition and single-core residual value estimation indexes. The rejection conditions include: and (3) a total cycle time threshold and/or an internal resistance threshold, for example, if the actual total cycle time reaches the total cycle time threshold at the target temperature, the battery cell is discarded, and if the actual internal resistance reaches the internal resistance threshold, the battery cell is discarded.
Specifically, a parameter value corresponding to each parameter in a single-core residual value estimation configuration corresponding to a target temperature is obtained from the target battery life curve, the obtained parameter values are substituted into the single-core residual value estimation configuration corresponding to the target temperature for estimation, and the estimated data are used as a single-core residual value estimation result of the target battery pack corresponding to the target temperature.
It can be understood that, since the usage states of the electric cores in the same battery pack are substantially the same, by estimating the single electric core residual value estimation result corresponding to the target electric core of the target battery pack at the target temperature, the single electric core residual value estimation result can be used as the single electric core residual value estimation result of other electric cores of the target battery pack.
It is understood that by modifying the specific value of the target temperature and repeatedly performing steps S1 to S4, the single-cell residual value estimation result of the cell of the target battery pack at each target temperature can be determined. And obtaining the single-cell residual value estimation result with the largest value from the single-cell residual value estimation results corresponding to the target battery pack, and taking the situation that the target estimation result corresponds to the target temperature and is recycled as a target situation. Thereby improving the value of recycling and reusing to the maximum extent.
The service environment of the electric core of the battery pack of the electric automobile after retirement is not as complicated as that of the electric automobile, so that the estimation result of the single-core residual value of the applicable temperature environment (namely the target temperature) after retirement can be predicted according to the capacity attenuation curve section of the target temperature by simulating the temperature test (the capacity attenuation curve sections of different temperatures) of the actual service environment after retirement.
In the whole single-cell residual value estimation process, the total cycle number predicted value, the residual battery capacity, the initial internal resistance and the initial battery life curve of the cell are comprehensively considered, and the target temperature in the occasion of recycling is also considered, so that the accuracy of the estimated single-cell residual value is improved; and detecting the target battery cell in the target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle number predicted value, a residual battery capacity and a capacity attenuation curve segment, and generating the capacity attenuation curve segment according to the attenuation relation between the battery capacity and the cycle number during detection to provide a basis for accurately determining a future target battery life curve of the battery cell in the target battery pack, so that the accuracy of a single battery cell residual value estimation result at the target temperature is improved.
In an embodiment, the step of detecting the target electric core in the target battery pack according to the initial internal resistance, the target temperature, and the target charge-discharge number to obtain a total cycle number prediction value, a remaining battery capacity, and a capacity fading curve segment includes:
s21: acquiring a counter, and initializing the value of the counter to 1;
specifically, the counter may be acquired from a database, or may be written in a program that implements the present application.
S22: at the target temperature, sequentially charging, standing for a preset time and discharging the target battery cell to obtain the capacity of a discharged battery and the discharge end time;
specifically, at the target temperature, firstly, a preset first battery nominal capacity is adopted to perform current constant-current charging on the target battery core until the target battery core reaches a charging cut-off voltage, then, the target battery core is kept still for a preset time, and finally, a preset second battery nominal capacity is adopted to perform current constant-current discharging on the target battery core until the target battery core reaches a discharging cut-off voltage, so that one-time charging and discharging is completed; the electric quantity discharged by the target battery cell at this time is taken as a discharge battery capacity, and the end time of the discharge of the target battery cell at this time is taken as a discharge end time, so that a data pair (that is, the discharge battery capacity and the discharge end time) is obtained.
The charge cutoff voltage is an upper limit of the operating voltage of the target cell.
The discharge cutoff voltage is the lower limit of the operating voltage of the target cell.
It is understood that the preset nominal capacity of the first battery and the preset nominal capacity of the second battery may be the same or different.
S23: judging whether the value of the counter is 1 or not, or whether the value of the counter is the target charging and discharging times or not;
s24: if so, performing internal resistance detection after finishing discharging on the target battery cell to obtain discharging finishing internal resistance and internal resistance detection time, and generating a single detection finishing signal, otherwise, generating the single detection finishing signal;
specifically, if so, the value of the counter is 1, or the value of the counter is the target charge and discharge frequency. If the value of the counter is 1, this means that the charge and discharge is performed for the first time, and the internal resistance needs to be tested, so that the internal resistance after the discharge of the target cell is detected, the detected internal resistance is used as the internal resistance for finishing the discharge, the starting time of detecting the internal resistance is used as the internal resistance detection time, and a single detection finishing signal is generated when the detection is finished. If the value of the counter is not 1 and the value of the counter is not the target charging and discharging times, the internal resistance detection is not needed, and therefore the single detection end signal is directly generated.
It can be understood that, a method for detecting the internal resistance after the target electric core finishes discharging may be selected by a person skilled in the art from the prior art, and details are not described herein.
S25: responding to the single detection end signal, adding 1 to the value of the counter, and repeatedly executing the steps of sequentially charging, standing for a preset time length and discharging the target electric core at the target temperature to obtain the capacity of a discharged battery and the discharge end time until the value of the counter is greater than the target charging and discharging times;
specifically, the value of the counter is increased by 1 in response to the single detection end signal, so that a foundation is provided for the next charge and discharge; repeatedly executing the steps of sequentially charging, standing for a preset time and discharging the target battery cell at the target temperature to obtain the capacity of the discharged battery and the discharge ending time, namely repeatedly executing the steps S22 to S25 until the value of the counter is greater than the target charging and discharging times; when the value of the counter is greater than the target charge and discharge number, it means that the number of charges and discharges to the target cell at this time reaches the target charge and discharge number, and therefore, it is necessary to stop repeatedly performing steps S22 to S25 and start performing step S26.
S26: determining a temperature relation index corresponding to the target temperature according to a preset first relation function, each discharge finishing internal resistance and each internal resistance detection time;
because the temperature, the cycle number and the internal resistance have an incidence relation, parameter values of parameters in a preset first relation function are determined according to the discharge finishing internal resistance and the internal resistance detection time, and the temperature relation index corresponding to the target temperature can be calculated by substituting the determined parameter values into the preset first relation function.
The preset first relation function is a function generated according to the incidence relation among the temperature, the cycle number and the internal resistance.
S27: determining the predicted value of the total cycle times according to a preset second relation function, the temperature relation index, the initial internal resistance and the finishing discharge internal resistance with the earliest internal resistance detection time;
the preset second relation function is a function generated according to the incidence relation among the temperature, the cycle number and the internal resistance.
Specifically, according to the temperature relation index, the initial internal resistance and the ending internal resistance with the earliest internal resistance detection time, parameter values of parameters in a preset second relation function are determined, and the determined parameter values are substituted into the preset second relation function, so that a total cycle number predicted value can be calculated.
S28: generating the capacity fading curve segment according to each discharge battery capacity and each discharge ending time;
specifically, a curve segment is generated from each of the discharge battery capacities and each of the discharge end times, and the generated curve segment is defined as the capacity fading curve segment, wherein the number of charge and discharge times corresponding to the discharge end time is defined as an x-axis coordinate of the capacity fading curve segment, and the discharge battery capacity is defined as a y-axis coordinate of the capacity fading curve segment.
S29: the discharged battery capacity at which the end time of discharge is earliest is taken as the remaining battery capacity.
Specifically, the discharge battery capacity with the earliest discharge end time is used as the remaining battery capacity, so that the battery capacity of the target cell at the start of the current round of detection is used as the remaining battery capacity.
In the embodiment, the target battery cell is sequentially charged, kept stand for a preset time and discharged at the target temperature, so that the target battery cell is tested at the temperature under the condition of simulated cyclic recycling, and a basis is provided for determining the single battery cell residual value estimation result at the target temperature; determining a total cycle time predicted value based on the association relationship among the temperature, the cycle time and the internal resistance by determining a temperature relation index corresponding to the target temperature according to a preset first relation function, each internal resistance for finishing discharge and each internal resistance detection time and determining the total cycle time predicted value according to a preset second relation function, the temperature relation index, the initial internal resistance and the internal resistance for finishing discharge with the earliest internal resistance detection time, so that the accuracy of the determined total cycle time predicted value is improved; the capacity decay curve segment is generated according to the capacity of each discharge battery and each discharge end time, and a basis is provided for determining a target battery life curve corresponding to a target temperature based on the capacity decay curve segment.
In one embodiment, the first relation function is: m = (Rb/Ra) n(t) Rb is the discharge ending internal resistance at the latest internal resistance detection time, Ra is the discharge ending internal resistance at the earliest internal resistance detection time, n (t) is the temperature relation index corresponding to the target temperature, t is the target temperature, and M is the target charge-discharge frequency;
the second relationship function is: t (x) = (Ra/R0) n(t) R0 is the initial internal resistance, and t (x) is the total cycle number prediction value.
The embodiment determines the first relation function and the second relation function according to the incidence relation among the temperature, the cycle number and the internal resistance, and provides a basis for determining the total cycle number predicted value based on the incidence relation among the temperature, the cycle number and the internal resistance.
In one embodiment, the step of determining a target battery life curve corresponding to the target temperature according to the initial battery life curve, the predicted total cycle number, the remaining battery capacity and the capacity fade curve segment includes:
s31: matching a most similar curve segment from the initial battery life curve according to the capacity attenuation curve segment, wherein the value corresponding to the most similar curve segment is that the minimum cycle number is greater than or equal to the predicted value of the total cycle number;
specifically, a curve segment most similar to the capacity fade curve segment is found from the initial battery life curve, and the found curve segment is regarded as the most similar curve segment. And the cycle number which is the minimum value corresponding to the most similar curve segment is limited to be more than or equal to the total cycle number predicted value, so that the accuracy of the found most similar curve segment is improved.
Optionally, a curve segment with the most similar initial slope, average slope, ending slope and slope variance to the capacity fade curve segment is found from the initial battery life curve, and the found curve segment is used as the most similar curve segment. The initial slope is the slope of the point at which the curve segment begins. The average slope is the average of the slopes of the various points of the curve segment. The ending slope is the slope of the point at which the curve segment ends. The slope variance is the variance of the slope of each point of the curve segment.
S32: and determining the target battery life curve corresponding to the target temperature according to the capacity attenuation curve segment, the most similar curve segment, the total cycle number predicted value, the residual battery capacity and the initial battery life curve.
Specifically, the most similar curve segment and a curve segment behind the most similar curve segment in the initial battery life curve are used as curve segments to be spliced, and the curve segments to be spliced are corrected according to the capacity attenuation curve segment, the predicted value of the total cycle number and the residual battery capacity, so that the target battery life curve corresponding to the target temperature is obtained.
In this embodiment, the position of the capacity attenuation curve segment of the target electric core in the initial battery life curve is located through the similarity of the curves, the most similar curve segment is extracted through the located position, and then the target battery life curve corresponding to the target temperature is determined according to the capacity attenuation curve segment, the most similar curve segment, the predicted value of the total cycle number, the residual battery capacity and the initial battery life curve, so that the battery life curve of the temperature (namely the target temperature) of the target electric core on the occasion of recycling is accurately determined, and a basis is provided for accurately estimating the single-electric-core residual value estimation result.
In one embodiment, the step of matching a most similar curve segment from the initial battery life curve according to the capacity fading curve segment, where a minimum cycle number corresponding to the most similar curve segment is greater than or equal to the predicted total cycle number value includes:
s311: inputting the capacity attenuation curve segment into a curve segment classification prediction model corresponding to the initial battery life curve for prediction to obtain a classification prediction vector;
specifically, the capacity fading curve segment is input to a curve segment classification prediction model corresponding to the initial battery life curve for prediction, and a vector obtained by prediction is used as a classification prediction vector.
Each vector element in the classification prediction vector corresponds to a classification curve segment (i.e., a curve segment divided at preset intervals) in the initial battery life curve in the nameplate information corresponding to the target battery pack. The value of each vector element in the classification prediction vector is a probability value from 0 to 1, which may be 0, or 1, or a decimal from 0 to 1. The value of each vector element in the classified prediction vector represents the probability of similarity.
Optionally, the curve segment classification prediction model is used for performing classification prediction, and the curve segment classification prediction model is a model obtained based on vector machine training.
S312: extracting candidate vector elements from the classified predictive vectors, wherein the cycle number of the corresponding classified curve segment of the candidate vector elements in the initial battery life curve is greater than or equal to the total cycle number predictive value;
specifically, a classification curve segment with a cycle number greater than or equal to the total cycle number prediction value is extracted from corresponding classification curve segments in the initial battery life curve, and a vector element corresponding to each extracted classification curve segment in the classification prediction vector is used as a candidate vector element.
S313: obtaining the vector element with the largest value from each candidate vector element as a hit vector element;
specifically, the vector element with the largest value is obtained from each candidate vector element, and the obtained vector element is used as a hit vector element.
S314: and taking the classification curve segment corresponding to the hit vector element in the initial battery life curve as the most similar curve segment.
Specifically, the classification curve segment corresponding to the hit vector element in the initial battery life curve is used as the most similar curve segment, so that the most similar curve segment is found.
According to the embodiment, the prediction is carried out through the curve segment classification prediction model, and the prediction accuracy is improved through the network model capability of the curve segment classification prediction model.
In an embodiment, before the step of inputting the capacity attenuation curve segment into the curve segment classification prediction model corresponding to the initial battery life curve for prediction to obtain a classification prediction vector, the method further includes:
s3111: obtaining a training sample set corresponding to an initial model and the initial battery life curve, wherein each training sample in the training sample set comprises: the curve segment label is a classification curve segment in the initial battery life curve;
specifically, an initial model and a training sample set corresponding to the initial battery life curve input by a user may be obtained, the initial model and the training sample set corresponding to the initial battery life curve may also be obtained from a database, and the initial model and the training sample set corresponding to the initial battery life curve may also be obtained from a third-party application.
In the same training sample, the curve segment label is the identification of the curve segment that is most similar to the curve segment sample.
S3112: training the initial model by adopting the training sample set;
specifically, the method for training the initial model by using the training sample set may be selected by a person skilled in the art from the prior art, and is not described herein again.
S3113: taking the initial model after training as the curve segment classification prediction model;
wherein the initial model comprises: an encoder comprising k +1 encoding layers, a decoder comprising k decoding layers, k being an integer greater than 2, and a classification layer being a fully-connected layer employing a softmax activation function;
k +1 coding layers are linearly connected, and k decoding layers are linearly connected;
the output of the encoder is taken as the input of the decoder, and the output of the decoder is taken as the input of the classification layer;
the output of the (k + 1) -g th encoding layer is used as the input of the g th decoding layer, g is an integer larger than 0, and g is smaller than or equal to k.
Specifically, the encoder is used for extracting features, the decoder is used for decoding the features extracted by the encoder, and the classification layer is used for performing classification prediction on data decoded by the decoder.
softmax activation function, normalizing the activation function.
Optionally, the decoding layer first fuses the two input features, and then decodes the fused features. Methods of fusion include, but are not limited to: any one of splicing, resampling and splicing first and then resampling. For two features, for example, inputting two features of the 1 st decoding layer includes: the output characteristic of the last encoding layer and the output characteristic of the 2 nd last decoding layer, and the input of the two characteristics of the 2 nd decoding layer comprises: the output characteristic of the 1 st decoding layer and the output characteristic of the 3 rd last decoding layer.
In the embodiment, the output of the (k + 1) -g th coding layer is used as the input of the g th decoding layer, so that the skip connection between the coder and the decoder is realized, the information sharing between the coder and the decoder is realized through the skip connection, and the accuracy of model prediction is improved; by setting the number of encoding layers to 1 more than the decoding layers, it is advantageous to make the input of each decoding layer an integrated result of two features.
In one embodiment, the step of determining the target battery life curve corresponding to the target temperature according to the capacity fade curve segment, the most similar curve segment, the predicted total cycle number, the remaining battery capacity and the initial battery life curve includes:
s321: extracting a curve segment behind the most similar curve segment from the initial battery life curve to serve as a curve segment to be spliced;
specifically, a curve segment behind the most similar curve segment is extracted from the initial battery life curve, and the extracted curve segment is used as a curve segment to be spliced.
S322: sequentially splicing the most similar curve segment and the curve segment to be spliced to obtain a curve to be corrected;
specifically, the tail end of the most similar curve segment is spliced with the head end of the curve segment to be spliced, and the spliced curve is used as a curve to be corrected.
S323: and correcting the curve to be corrected according to the capacity attenuation curve segment, the total cycle number predicted value and the residual battery capacity to obtain the target battery life curve corresponding to the target temperature.
Specifically, according to the capacity attenuation curve segment, the total cycle number predicted value and the residual battery capacity, correcting an x-axis coordinate and a y-axis coordinate of the curve to be corrected, and taking the corrected curve as the target battery life curve corresponding to the target temperature. Correcting the starting point of the curve to be corrected according to the total cycle number predicted value and the residual battery capacity, namely correcting the starting point of the curve to be corrected to be the same as the corresponding point of the total cycle number predicted value and the residual battery capacity; and according to the relation between the cycle times of the capacity attenuation curve segment and the attenuation of the battery capacity, correcting the corresponding relation between the cycle times and the battery capacity of the curve to be corrected with the corrected starting point, and taking the curve with the corrected segment length as the target battery life curve corresponding to the target temperature. It is understood that the target battery life curve corresponding to the target temperature has the same shape as the curve to be corrected.
Optionally, based on a least square algorithm, the curve to be corrected is corrected according to the capacity attenuation curve segment, the total cycle number predicted value and the remaining battery capacity, and the corrected curve is used as the target battery life curve corresponding to the target temperature.
That is to say, the target battery life curve corresponding to the target temperature is the target battery life curve of the target battery cell in the target battery pack at the target temperature, the x-axis coordinate of the target battery life curve is the cycle number of the target battery cell operating at the target temperature, and the y-axis coordinate of the target battery life curve is the battery capacity of the target battery cell operating at the target temperature, so that the cycle number of the target battery cell operating at the target temperature and the battery capacity fading condition can be known only by querying the target battery life curve corresponding to the target temperature.
And correcting the curve to be corrected, namely converting the x-axis coordinate of the curve to be corrected from the factory expected working temperature to the target temperature, and converting the y-axis coordinate of the curve to be corrected from the factory expected working temperature to the target temperature.
Because the curve to be corrected is one section of the initial battery life curve, the initial battery life curve is a curve at the predicted working temperature of the factory, and the relationship between the cycle number and the battery capacity may be different at different temperatures, for example, if the curve to be corrected is directly taken as the target battery life curve, the battery capacity is attenuated by a first value, and the cycle number is 1 at 30 ℃, the battery capacity is attenuated by a second value, and the second value is greater than the first value, if the curve to be corrected is taken as the target battery life curve, the accuracy of the estimation result of the residual value of the single battery cell will be affected, in order to solve the problem, the embodiment corrects the curve to be corrected according to the capacity attenuation curve section, the predicted value of the total cycle number and the residual battery capacity, and obtains the target battery life curve corresponding to the target temperature, thereby obtaining the battery life curve of the target battery pack according with the target temperature, the accuracy of the determined single-core residual value estimation result is improved.
As shown in fig. 2, in one embodiment, there is provided a power battery residual value estimation method apparatus, the apparatus including:
the data acquisition module 800 is configured to acquire a target temperature, a target charge and discharge frequency, and an initial internal resistance and an initial battery life curve corresponding to a target battery pack;
the detection module 802 is configured to detect a target battery cell in the target battery pack according to the initial internal resistance, the target temperature, and the target charge-discharge number, so as to obtain a total cycle number prediction value, a remaining battery capacity, and a capacity fading curve segment;
a target battery life curve determining module 803, configured to determine a target battery life curve corresponding to the target temperature according to the initial battery life curve, the total cycle number predicted value, the remaining battery capacity, and the capacity fading curve segment;
a single-cell residual estimation result determining module 804, configured to estimate each cell in the target battery pack according to the single-cell residual estimation configuration corresponding to the target temperature and the target battery life curve, to obtain a single-cell residual estimation result of the target battery pack corresponding to the target temperature.
In the whole single-cell residual value estimation process, the total cycle number predicted value, the residual battery capacity, the initial internal resistance and the initial battery life curve of the cell are comprehensively considered, and the target temperature in the occasion of recycling is also considered, so that the accuracy of the estimated single-cell residual value is improved; and detecting the target battery cell in the target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle number predicted value, a residual battery capacity and a capacity attenuation curve segment, and generating the capacity attenuation curve segment according to the attenuation relation between the battery capacity and the cycle number during detection to provide a basis for accurately determining a future target battery life curve of the battery cell in the target battery pack, so that the accuracy of a single battery cell residual value estimation result at the target temperature is improved.
FIG. 3 is a diagram illustrating an internal structure of a computer device in one embodiment. The computer device may be specifically a terminal, and may also be a server. As shown in fig. 3, the computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program that, when executed by the processor, causes the processor to implement the power battery residue estimation method. The internal memory may also have a computer program stored therein that, when executed by the processor, causes the processor to perform a power battery residue estimation method. Those skilled in the art will appreciate that the architecture shown in fig. 3 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is proposed, comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of:
acquiring a target temperature, a target charging and discharging frequency, an initial internal resistance corresponding to a target battery pack and an initial battery life curve;
detecting a target battery cell in the target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle time predicted value, a residual battery capacity and a capacity attenuation curve section;
determining a target battery life curve corresponding to the target temperature according to the initial battery life curve, the total cycle number predicted value, the residual battery capacity and the capacity attenuation curve section;
and estimating each electric core in the target battery pack according to the single electric core residual value estimation configuration corresponding to the target temperature and the target battery life curve to obtain a single electric core residual value estimation result of the target battery pack corresponding to the target temperature.
In the whole single-cell residual value estimation process, the total cycle number predicted value, the residual battery capacity, the initial internal resistance and the initial battery life curve of the cell are comprehensively considered, and the target temperature in the occasion of recycling is also considered, so that the accuracy of the estimated single-cell residual value is improved; and detecting the target battery cell in the target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle number predicted value, a residual battery capacity and a capacity attenuation curve segment, and generating the capacity attenuation curve segment according to the attenuation relation between the battery capacity and the cycle number during detection to provide a basis for accurately determining a future target battery life curve of the battery cell in the target battery pack, so that the accuracy of a single battery cell residual value estimation result at the target temperature is improved.
In one embodiment, a computer-readable storage medium is proposed, in which a computer program is stored which, when executed by a processor, causes the processor to carry out the steps of:
acquiring a target temperature, a target charging and discharging frequency, an initial internal resistance corresponding to a target battery pack and an initial battery life curve;
detecting a target battery cell in the target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle time predicted value, a residual battery capacity and a capacity attenuation curve section;
determining a target battery life curve corresponding to the target temperature according to the initial battery life curve, the total cycle number predicted value, the residual battery capacity and the capacity attenuation curve section;
and estimating each electric core in the target battery pack according to the single electric core residual value estimation configuration corresponding to the target temperature and the target battery life curve to obtain a single electric core residual value estimation result of the target battery pack corresponding to the target temperature.
In the whole single-cell residual value estimation process, the total cycle number predicted value, the residual battery capacity, the initial internal resistance and the initial battery life curve of the cell are comprehensively considered, and the target temperature in the occasion of recycling is also considered, so that the accuracy of the estimated single-cell residual value is improved; and detecting the target battery cell in the target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle number predicted value, a residual battery capacity and a capacity attenuation curve segment, and generating the capacity attenuation curve segment according to the attenuation relation between the battery capacity and the cycle number during detection to provide a basis for accurately determining a future target battery life curve of the battery cell in the target battery pack, so that the accuracy of a single battery cell residual value estimation result at the target temperature is improved.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), synchronous Link (Synchlink) DRAM (SLDRAM), Rambus (Rambus) direct RAM (RDRAM), direct bused dynamic RAM (DRDRAM), and bused dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent application shall be subject to the appended claims.

Claims (10)

1. A power battery residual value estimation method, the method comprising:
acquiring a target temperature, a target charging and discharging frequency, an initial internal resistance corresponding to a target battery pack and an initial battery life curve;
detecting a target battery cell in the target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle time predicted value, a residual battery capacity and a capacity attenuation curve section;
determining a target battery life curve corresponding to the target temperature according to the initial battery life curve, the total cycle number predicted value, the residual battery capacity and the capacity attenuation curve section;
and estimating each electric core in the target battery pack according to the single electric core residual value estimation configuration corresponding to the target temperature and the target battery life curve to obtain a single electric core residual value estimation result of the target battery pack corresponding to the target temperature.
2. The method for estimating the residual value of the power battery according to claim 1, wherein the step of detecting the target battery cell in the target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle prediction value, a residual battery capacity and a capacity fading curve segment includes:
acquiring a counter, and initializing the value of the counter to 1;
at the target temperature, sequentially charging, standing for a preset time and discharging the target battery cell to obtain the capacity of a discharged battery and the discharge ending time;
judging whether the value of the counter is 1 or not, or whether the value of the counter is the target charging and discharging times or not;
if so, performing internal resistance detection after finishing discharging on the target battery cell to obtain discharging finishing internal resistance and internal resistance detection time, and generating a single detection finishing signal, otherwise, generating the single detection finishing signal;
responding to the single detection end signal, adding 1 to the value of the counter, and repeatedly executing the steps of sequentially charging, standing for a preset time length and discharging the target electric core at the target temperature to obtain the capacity of a discharged battery and the discharge end time until the value of the counter is greater than the target charging and discharging times;
determining a temperature relation index corresponding to the target temperature according to a preset first relation function, each discharge finishing internal resistance and each internal resistance detection time;
determining the predicted value of the total cycle times according to a preset second relation function, the temperature relation index, the initial internal resistance and the finishing discharge internal resistance with the earliest internal resistance detection time;
generating the capacity decay curve segment according to the capacity of each discharge battery and each discharge end time;
the discharged battery capacity at which the end time of discharge is earliest is taken as the remaining battery capacity.
3. The power battery residual estimation method according to claim 2, characterized in that the first relation function is: m = (Rb/Ra) n(t) Rb is the discharge ending internal resistance at the latest internal resistance detection time, Ra is the discharge ending internal resistance at the earliest internal resistance detection time, n (t) is the temperature relation index corresponding to the target temperature, t is the target temperature, and M is the target charge-discharge frequency;
the second relationship function is: t (x) = (Ra/R0) n(t) R0 is the initial internal resistance, T (x) is the total number of cyclesAnd (6) counting and predicting values.
4. The method for estimating residual value of power battery according to claim 1, wherein the step of determining a target battery life curve corresponding to the target temperature according to the initial battery life curve, the predicted value of total cycle number, the remaining battery capacity and the capacity fading curve segment comprises:
matching a most similar curve segment from the initial battery life curve according to the capacity attenuation curve segment, wherein the value corresponding to the most similar curve segment is that the minimum cycle number is greater than or equal to the predicted value of the total cycle number;
and determining the target battery life curve corresponding to the target temperature according to the capacity attenuation curve segment, the most similar curve segment, the total cycle number predicted value, the residual battery capacity and the initial battery life curve.
5. The method for estimating residual value of power battery according to claim 4, wherein the step of matching a most similar curve segment from the initial battery life curve according to the capacity fading curve segment, wherein the most similar curve segment corresponds to a value that the minimum cycle number is greater than or equal to the predicted total cycle number value, comprises:
inputting the capacity attenuation curve segment into a curve segment classification prediction model corresponding to the initial battery life curve for prediction to obtain a classification prediction vector;
extracting candidate vector elements from the classified predictive vectors, wherein the cycle number of the corresponding classified curve segment of the candidate vector elements in the initial battery life curve is greater than or equal to the total cycle number predictive value;
obtaining the vector element with the largest value from each candidate vector element as a hit vector element;
and taking the classification curve segment corresponding to the hit vector element in the initial battery life curve as the most similar curve segment.
6. The method for estimating residual value of power battery according to claim 5, wherein before the step of inputting the capacity attenuation curve segment into a curve segment classification prediction model corresponding to the initial battery life curve for prediction, a classification prediction vector is obtained, the method further comprises:
obtaining a training sample set corresponding to an initial model and the initial battery life curve, wherein each training sample in the training sample set comprises: the curve segment label is a classification curve segment in the initial battery life curve;
training the initial model by adopting the training sample set;
taking the initial model after training as the curve segment classification prediction model;
wherein the initial model comprises: an encoder comprising k +1 encoding layers, a decoder comprising k decoding layers, k being an integer greater than 2, and a classification layer being a fully-connected layer employing a softmax activation function;
k +1 coding layers are linearly connected, and k decoding layers are linearly connected;
the output of the encoder is taken as the input of the decoder, and the output of the decoder is taken as the input of the classification layer;
the output of the (k + 1) -g th encoding layer is used as the input of the g th decoding layer, g is an integer larger than 0, and g is smaller than or equal to k.
7. The method according to claim 4, wherein the step of determining the target battery life curve corresponding to the target temperature according to the capacity fade curve segment, the most similar curve segment, the predicted total cycle number, the remaining battery capacity and the initial battery life curve comprises:
extracting a curve segment behind the most similar curve segment from the initial battery life curve to serve as a curve segment to be spliced;
sequentially splicing the most similar curve segment and the curve segment to be spliced to obtain a curve to be corrected;
and correcting the curve to be corrected according to the capacity attenuation curve segment, the total cycle number predicted value and the residual battery capacity to obtain the target battery life curve corresponding to the target temperature.
8. A power battery residual value estimation method and device are characterized by comprising the following steps:
the data acquisition module is used for acquiring a target temperature, a target charging and discharging frequency, an initial internal resistance corresponding to a target battery pack and an initial battery life curve;
the detection module is used for detecting a target battery cell in the target battery pack according to the initial internal resistance, the target temperature and the target charging and discharging times to obtain a total cycle time prediction value, a residual battery capacity and a capacity attenuation curve section;
a target battery life curve determining module, configured to determine a target battery life curve corresponding to the target temperature according to the initial battery life curve, the predicted total cycle number, the remaining battery capacity, and the capacity fading curve segment;
and the single-cell residual value estimation result determining module is used for estimating each cell in the target battery pack according to the single-cell residual value estimation configuration corresponding to the target temperature and the target battery life curve to obtain a single-cell residual value estimation result of the target battery pack corresponding to the target temperature.
9. A computer-readable storage medium, storing a computer program which, when executed by a processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 7.
10. A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method according to any one of claims 1 to 7.
CN202210954269.8A 2022-08-10 2022-08-10 Power battery residual value estimation method, device, equipment and medium Active CN115015769B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210954269.8A CN115015769B (en) 2022-08-10 2022-08-10 Power battery residual value estimation method, device, equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210954269.8A CN115015769B (en) 2022-08-10 2022-08-10 Power battery residual value estimation method, device, equipment and medium

Publications (2)

Publication Number Publication Date
CN115015769A true CN115015769A (en) 2022-09-06
CN115015769B CN115015769B (en) 2022-11-11

Family

ID=83065981

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210954269.8A Active CN115015769B (en) 2022-08-10 2022-08-10 Power battery residual value estimation method, device, equipment and medium

Country Status (1)

Country Link
CN (1) CN115015769B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116047311A (en) * 2023-03-06 2023-05-02 中国华能集团清洁能源技术研究院有限公司 Online prediction method and device for residual life of energy storage battery
CN116593902A (en) * 2023-07-13 2023-08-15 中国铁塔股份有限公司江西省分公司 Fault diagnosis method based on fusion of performance parameters of iron lithium battery into AI model
CN116774058A (en) * 2023-08-18 2023-09-19 深圳凌奈智控有限公司 Battery life prediction method, device, equipment and storage medium

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108318825A (en) * 2018-01-31 2018-07-24 胡继业 Reuse the residual value appraisal procedure of accumulator
CN109633474A (en) * 2018-11-14 2019-04-16 江苏大学 A kind of lithium ion battery residual life prediction technique
CN111812536A (en) * 2020-07-06 2020-10-23 安徽恒明工程技术有限公司 Rapid evaluation method for retired power battery residual value
CN112255558A (en) * 2019-12-31 2021-01-22 蜂巢能源科技有限公司 Method and device for calculating battery calendar life attenuation
CN113075557A (en) * 2021-05-20 2021-07-06 张家港清研检测技术有限公司 Vehicle owner self-adaptive power battery residual life prediction method
JP2021110576A (en) * 2019-12-20 2021-08-02 國家中山科學研究院 Quick evaluation method of battery residual capacity
CN113497280A (en) * 2020-03-19 2021-10-12 比亚迪股份有限公司 Charging control method and device for lithium battery, readable storage medium and electronic equipment
CN113884910A (en) * 2021-10-19 2022-01-04 岚图汽车科技有限公司 Power battery residual value evaluation method, device, equipment and readable storage medium
CN114325400A (en) * 2021-11-24 2022-04-12 北京百度网讯科技有限公司 Method and device for determining remaining life of battery, electronic equipment and storage medium
CN114545272A (en) * 2022-01-19 2022-05-27 北京海博思创科技股份有限公司 Battery life prediction method, device and equipment
CN114636932A (en) * 2022-03-14 2022-06-17 华中科技大学 Method and system for predicting remaining service life of battery
US20220242274A1 (en) * 2018-04-27 2022-08-04 Panasonic Intellectual Property Corporation Of America Control method, server, in-vehicle device, and recording medium

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108318825A (en) * 2018-01-31 2018-07-24 胡继业 Reuse the residual value appraisal procedure of accumulator
US20220242274A1 (en) * 2018-04-27 2022-08-04 Panasonic Intellectual Property Corporation Of America Control method, server, in-vehicle device, and recording medium
CN109633474A (en) * 2018-11-14 2019-04-16 江苏大学 A kind of lithium ion battery residual life prediction technique
JP2021110576A (en) * 2019-12-20 2021-08-02 國家中山科學研究院 Quick evaluation method of battery residual capacity
CN112255558A (en) * 2019-12-31 2021-01-22 蜂巢能源科技有限公司 Method and device for calculating battery calendar life attenuation
CN113497280A (en) * 2020-03-19 2021-10-12 比亚迪股份有限公司 Charging control method and device for lithium battery, readable storage medium and electronic equipment
CN111812536A (en) * 2020-07-06 2020-10-23 安徽恒明工程技术有限公司 Rapid evaluation method for retired power battery residual value
CN113075557A (en) * 2021-05-20 2021-07-06 张家港清研检测技术有限公司 Vehicle owner self-adaptive power battery residual life prediction method
CN113884910A (en) * 2021-10-19 2022-01-04 岚图汽车科技有限公司 Power battery residual value evaluation method, device, equipment and readable storage medium
CN114325400A (en) * 2021-11-24 2022-04-12 北京百度网讯科技有限公司 Method and device for determining remaining life of battery, electronic equipment and storage medium
CN114545272A (en) * 2022-01-19 2022-05-27 北京海博思创科技股份有限公司 Battery life prediction method, device and equipment
CN114636932A (en) * 2022-03-14 2022-06-17 华中科技大学 Method and system for predicting remaining service life of battery

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李亮: "电动车退役锂电池在通信基站梯次利用的研究", 《中国优秀硕士学位论文全文数据库 工程科技I辑》 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116047311A (en) * 2023-03-06 2023-05-02 中国华能集团清洁能源技术研究院有限公司 Online prediction method and device for residual life of energy storage battery
CN116047311B (en) * 2023-03-06 2023-06-13 中国华能集团清洁能源技术研究院有限公司 Online prediction method and device for residual life of energy storage battery
CN116593902A (en) * 2023-07-13 2023-08-15 中国铁塔股份有限公司江西省分公司 Fault diagnosis method based on fusion of performance parameters of iron lithium battery into AI model
CN116593902B (en) * 2023-07-13 2023-10-31 中国铁塔股份有限公司江西省分公司 Fault diagnosis method based on fusion of performance parameters of iron lithium battery into AI model
CN116774058A (en) * 2023-08-18 2023-09-19 深圳凌奈智控有限公司 Battery life prediction method, device, equipment and storage medium
CN116774058B (en) * 2023-08-18 2023-10-20 深圳凌奈智控有限公司 Battery life prediction method, device, equipment and storage medium

Also Published As

Publication number Publication date
CN115015769B (en) 2022-11-11

Similar Documents

Publication Publication Date Title
CN115015769B (en) Power battery residual value estimation method, device, equipment and medium
CN114114049B (en) Lithium ion battery life prediction method based on sample migration
US20230112978A1 (en) Method and apparatus for calculating cell state, and storage medium
CN110806540B (en) Battery cell test data processing method, device and system and storage medium
CN113553534A (en) Method and device for calculating quick charging remaining time, vehicle and storage medium
CN116466236A (en) Battery remaining life prediction method, device, equipment and readable storage medium
CN110579716A (en) Battery detection method and device
CN113083739B (en) Battery cell sorting method and device and computer equipment
CN115598556A (en) Method for determining state of health of power battery of electric vehicle and server
CN116559667A (en) Model training method and device, battery detection method and device, equipment and medium
CN114935721A (en) Lithium ion battery charge state estimation method based on fiber grating sensor
CN115421050A (en) Method, system, equipment and storage medium for estimating state of health of battery
CN113125965B (en) Method, device and equipment for detecting lithium separation of battery and storage medium
CN112417767A (en) Attenuation trend determination model construction method and attenuation trend determination method
CN116154914B (en) Battery charging management method and device
CN110068409B (en) Lithium battery stress prediction method and device
CN116256651A (en) Battery thermal incapacitation early warning method, system and readable storage medium
CN116298944A (en) Charging remaining time display control method, device, equipment, vehicle and medium
CN111239628B (en) Method and system for detecting attenuation degree of secondary storage battery and series module
CN117148170B (en) Battery energy storage system and energy storage test method thereof
CN115825790B (en) Early warning method, device and system for battery insulation fault and computer equipment
CN116736174B (en) Method, apparatus, computer device and storage medium for predicting remaining life of battery
CN116125321A (en) SOH estimation method and device for power battery, electronic equipment and storage medium
CN114819394A (en) Charge state prediction method and device, electronic equipment and storage medium
CN117269766B (en) Battery SOH prediction method for unbalanced use scene

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
GR01 Patent grant
GR01 Patent grant