CN114690040A - Method for predicting optimal charging initial SOC of power battery of electric vehicle - Google Patents

Method for predicting optimal charging initial SOC of power battery of electric vehicle Download PDF

Info

Publication number
CN114690040A
CN114690040A CN202210337441.5A CN202210337441A CN114690040A CN 114690040 A CN114690040 A CN 114690040A CN 202210337441 A CN202210337441 A CN 202210337441A CN 114690040 A CN114690040 A CN 114690040A
Authority
CN
China
Prior art keywords
data
battery
charging
power battery
optimal
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.)
Pending
Application number
CN202210337441.5A
Other languages
Chinese (zh)
Inventor
张爽
高蓓
许崇霞
刘辉
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.)
Rizhao Polytechnic
Original Assignee
Rizhao Polytechnic
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 Rizhao Polytechnic filed Critical Rizhao Polytechnic
Priority to CN202210337441.5A priority Critical patent/CN114690040A/en
Publication of CN114690040A publication Critical patent/CN114690040A/en
Pending legal-status Critical Current

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]
    • 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]
    • G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/389—Measuring internal impedance, internal conductance or related variables
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/392—Determining battery ageing or deterioration, e.g. state of health

Landscapes

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

Abstract

The invention discloses a method for predicting the optimal charging initial SOC of an electric vehicle power battery, which comprises two parts, namely system construction and system implementation, wherein the system construction comprises three stages of data processing, model solving and model training; the system comprises three stages of data processing, data import and result output. The invention belongs to the technical field of battery life prediction, and particularly relates to a method for optimizing bad charging behaviors such as too high charging frequency and the like, and prolonging the service life of a battery, so that the pollution of the battery to the environment is reduced; the method for predicting the optimal charging starting SOC of the power battery of the electric vehicle has the advantages that reasonable suggestions are given to vehicle owners to reduce mileage anxiety and improve user confidence of the pure electric vehicle.

Description

Method for predicting optimal charging initial SOC of power battery of electric vehicle
Technical Field
The invention belongs to the technical field of battery life prediction, and particularly relates to a method for predicting the optimal charging initial SOC of an electric vehicle power battery.
Background
With the continuous increase of the quantity of electric automobiles, the electric automobile technology taking the three electric technologies of battery, motor and electric control as the core is continuously improved, and particularly on the basis of the innate internet of vehicles technology of the electric automobiles, the data uploading and downloading technology is mature, which all provides a basis for analyzing and optimizing the performance of the electric automobiles based on the operation data.
In the aspect of monitoring battery safety and battery health degree, represented by Sun-Wenchun spring academy of Beijing university, the early warning of vehicle safety is realized by monitoring the voltage, temperature, internal resistance and other relevant data of the battery, analyzing and monitoring the battery health degree through a series of algorithms, discovering the abnormal problem of the battery in time, and realizing the functions of platform early warning and the like.
The invention patents similar to the battery life prediction part in the scheme are as follows:
CN 202110474679.8A method and system for predicting the service life of a power battery of a new energy vehicle, which obtains relevant data for predicting the service life of the power battery of a vehicle connected with a big data platform and filters the data to obtain relevant data of the number of remaining charge and discharge cycles of the power battery, trains a neural network on the filtered data to establish a service life prediction model of the power battery of the vehicle, obtains relevant data for predicting the service life of the current power battery of the vehicle connected with the big data platform after establishing the model, substitutes the relevant data for predicting the service life of the power battery of the vehicle into the service life prediction model of the power battery of the vehicle, and outputs a service life prediction result of the power battery.
CN201910204690.5 a method and system for predicting the life of a power battery, based on the migration learning mode, using the life test data of the power battery to obtain a third life curve, then using the first life curve obtained by the actual battery sample data and the third life curve to obtain a life offset curve; and finally, the life deviation curve is used for carrying out superposition correction on the third life curve to obtain a predicted life curve of the power battery, so that the aim of obtaining the corresponding relation between the service life of the power battery and the actual service life in the complete life cycle of the power battery on the basis of limited actual battery sample data is fulfilled, and the predicted life curve is obtained by superposing and correcting the first life curve and the third life curve, so that the predicted life curve is closer to the actual condition, and the accuracy of predicting the service life of the power battery is improved.
CN202010306169.5 method, device, computer equipment and medium for obtaining power battery life data, providing a method, device, computer equipment and medium for obtaining power battery life data, obtaining planned charge and discharge times of a target power battery, inputting the planned charge and discharge times into a power battery life data regression model constructed in advance, wherein the power battery life data regression model is obtained by model construction based on an accelerated aging data set of a sample power battery, the target power battery capacity data set can be used for describing the life data of the target power battery, a target confidence interval is used as the reference probability of the target power battery capacity data set and describes the uncertainty of the target power battery capacity data set, therefore, the power battery life data regression model can output the corresponding target power battery capacity data set and the target confidence interval according to the planned charge and discharge times, and then the problem that the service life data of the power battery cannot be acquired is solved.
CN201910777292.2 a battery management system of area estimation electric automobile power battery life function discloses a battery management system of area estimation electric automobile power battery life function, includes: the method comprises the five steps of obtaining parameters, charging, calculating, comparing service life and informing. The method can accurately obtain the service life of the battery pack and provide the service life for the vehicle owner, so that the vehicle owner can conveniently and visually know the service life and the residual life of the vehicle-mounted battery pack.
The prior art associated with the present application includes:
(1) battery health degree analysis technique based on car networking big data: the health degree of the battery is evaluated by acquiring data such as temperature, voltage, internal resistance and the like of the battery on the electric automobile and inputting the data into a model.
(2) Vehicle safety early warning technology for battery safety: based on the battery data of the electric automobile, a model is adopted for analysis, and vehicle safety early warning is realized by means of a preset threshold value.
The defects existing in the prior art are as follows: the service life of the power battery is affected by the use frequency, the charging initial SOC, the charging time and the like of the power battery, but a technology specially for predicting the optimal charging time of the electric automobile does not exist at present, and the current technology cannot realize the prediction of the optimal charging initial SOC of the electric automobile.
Disclosure of Invention
In view of the above situation, in order to overcome the defects of the prior art, the invention provides a method for predicting the optimal initial charging SOC of an electric vehicle power battery, which is a method for predicting the optimal initial charging SOC of the electric vehicle power battery based on a genetic algorithm and a coefficient of variation algorithm and solves the problem that the optimal initial charging SOC of the electric vehicle cannot be predicted in the background art.
The technical scheme adopted by the invention is as follows: a method for predicting the optimal charging initial SOC of an electric vehicle power battery comprises a system building step and a system implementing step, wherein the system building step comprises three stages of data processing, model solving and model training; the system comprises three stages of data processing, data import and result output;
the system building comprises the following steps:
the method comprises the following steps: data processing: collecting data related to an automobile battery through an electric automobile vehicle-mounted terminal;
transmitting the acquired data to an enterprise platform through a mobile network;
the enterprise platform forwards the data to the centralized platform for unified storage;
cleaning the collected battery data on the platform, removing null values and dirty data (error data), and then performing standardized arrangement on the data;
step two: solving the model: solving the data corresponding to the longest service life of the power battery by adopting a genetic algorithm for analysis to obtain the charging behavior characteristics under the optimal service life, thereby determining the initial charging SOC of the power battery under the optimal service life;
(1) data initialization
Initializing the data fields subjected to standardized arrangement in the first step in a binary mode to obtain binary sample data;
(2) adaptive function solving
Considering that the number of model factors is large, the weight is rapidly solved by adopting a coefficient of variation method, and the specific calculation process is as follows:
1) solving the standard deviation of each factor in the data after the standardized arrangement
Figure BDA0003574895620000031
Wherein xiIs a sample value, mu is a sample mean value;
substituting the values of the factors such as voltage consistency, temperature consistency, battery charging initial SOC, battery internal resistance, pressure difference, temperature difference and charging times into a formula in sequence, and solving the standard deviation sigma of each factor1-σ7；
2) Solving the coefficient of variation of each factor of the data after standardized arrangement
Figure BDA0003574895620000032
Sigma solved in the step 1)1-σ7Substituting the mean value mu 1-mu 7 corresponding to each factor into the above formula to obtain the variation coefficient c of each factorv1-cv7；
3) Solving each factor weight
Because the sum of the weights of all the factors is 1 and has an equal proportional relation with the variation coefficient, the following can be obtained by solving:
Figure BDA0003574895620000033
substituting the data obtained in the step 2) and solving a weight function to finally obtain a self-adaptive function as follows:
f(x)＝ω1U+ω2T+ω3S+ω4R+ω5ΔU+ω6ΔT+ω7n
wherein, f (x) is the life length of the battery, U is the voltage consistency, T is the temperature consistency, S is the initial SOC of the battery charging, R is the internal resistance value of the battery, delta U is the pressure difference, delta T is the temperature difference, and n is the charging frequency;
(3) cross breeding
Performing pairwise cross breeding on the initialized data, wherein the cross rate is selected to be 100%, and the probability of variation is set to be 0, while the variation possibly existing in the cross breeding process is not considered;
then substituting the descendants obtained by cross breeding into an adaptive function to solve and find an optimal sample, and outputting the initial SOC data of the battery charging of the optimal sample as a result;
step three: model training
Processing other incremental data by the data processing method in the first step, importing a model for result verification, completing model training if the result meets the actual condition, otherwise supplementing the data of the time to the sample data of the last time, and repeating the first step and the second step until the output result achieves the expected effect;
further, the system implementation comprises the following steps:
the method comprises the following steps: data processing: the data processing mode is the same as that of a system building part;
step two: data import: inputting the data processed in the first step into a model, and calculating through the model;
step three: and (4) outputting a result: after the model is calculated, the initial SOC permutation and combination of the optimal charging of the power storage battery is output, the output result is displayed in the form of a large screen of a vehicle-mounted computer or a mobile phone APP, and meanwhile, the result supports regular refreshing and correction.
Furthermore, in the step of solving the weight of each factor, the battery with the longest service life is selected as a theoretical value, and a sample which is larger than or equal to the theoretical value is obtained as an optimal solution in a cross breeding mode.
Further, data collection in system construction is carried out once from the beginning of each charging to the end of the charging.
After adopting the structure, the invention has the following beneficial effects: according to the method for predicting the optimal charging initial SOC of the power battery of the electric automobile, poor charging behaviors such as too high charging frequency can be optimized, the service life of the battery can be prolonged, and therefore the pollution of the battery to the environment is reduced; reasonable suggestions are given to the vehicle owner, mileage anxiety is reduced, and user confidence of the pure electric vehicle is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
Fig. 1 is a system setup flow chart of a method for predicting an optimal charging start SOC of an electric vehicle power battery according to the present invention;
fig. 2 is a system implementation flowchart of a method for predicting an optimal initial charging SOC of a power battery of an electric vehicle according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to 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 embodiments; all other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiment provides a method for predicting the initial SOC of the optimal charging of an electric vehicle power battery, which comprises a system building step and a system implementing step, wherein the system building step comprises three stages of data processing, model solving and model training; the system comprises three stages of data processing, data import and result output;
the system building comprises the following steps:
the method comprises the following steps: data processing
The method comprises the steps that automobile battery related data (data are shown in table 1 in detail) are collected through an electric automobile vehicle-mounted terminal, then are transmitted to an enterprise platform through a mobile network, and are forwarded to a centralized platform by the enterprise platform to be uniformly stored, the whole process is required to strictly follow national relevant laws and regulations, and client personal information is not involved on the premise of ensuring safety; cleaning the collected battery data on the platform, and removing null values and dirty data (error data); then, carrying out standardized arrangement on the data, wherein the data after the arrangement is shown in a table 2; the data acquisition is carried out from the beginning of each charging to the end of the charging;
Figure BDA0003574895620000051
TABLE 1 electric vehicle data related to battery acquisition
Figure BDA0003574895620000052
TABLE 2 normalized collated data
Step two: solving the model: solving the data corresponding to the longest service life of the power battery by adopting a genetic algorithm for analysis to obtain the charging behavior characteristics under the optimal service life, thereby determining the initial charging SOC of the power battery under the optimal service life;
(1) data initialization
Initializing the data fields in table 2 in a binary manner to obtain binary sample data, which is exemplified as follows:
unique identification bit: 0000001
Cell voltage uniformity: 0
Battery temperature uniformity: 1
Battery charge start SOC: 101
Internal resistance of the battery: 1111000
Pressure difference: 1010
Temperature difference: 101
Battery life length: 111001000010
Charging times are as follows: 10011100010000.

Claims (4)

1. A method for predicting the optimal charging initial SOC of an electric vehicle power battery is characterized by comprising the following steps: the method comprises two parts of system construction and system implementation;
the system construction comprises the following steps:
the method comprises the following steps: data processing: collecting data related to an automobile battery through an electric automobile vehicle-mounted terminal;
transmitting the acquired data to an enterprise platform through a mobile network;
the enterprise platform forwards the data to the centralized platform for unified storage;
cleaning the collected battery data on the platform, removing null values and error data, and then performing standardized arrangement on the data;
step two: solving a model: solving the data corresponding to the longest service life of the power battery by adopting a genetic algorithm for analysis to obtain the charging behavior characteristics under the optimal service life, thereby determining the initial charging SOC of the power battery under the optimal service life;
(1) data initialization
Initializing the data fields subjected to standardized arrangement in the step one in a binary mode to obtain binary sample data;
(2) adaptive function solution
The weight is quickly solved by adopting a coefficient of variation method, and the specific calculation process is as follows:
1) solving the standard deviation of each factor in the data after standardized arrangement
Figure FDA0003574895610000011
Wherein xiIs a sample value, mu is a sample mean value;
substituting the values of the factors such as voltage consistency, temperature consistency, battery charging initial SOC, battery internal resistance, pressure difference, temperature difference and charging times into a formula in sequence, and solving the standard deviation sigma of each factor1-σ7；
2) Solving the coefficient of variation of each factor of the data after standardized arrangement
Figure FDA0003574895610000012
Sigma solved in the step 1)1-σ7Substituting the mean value mu 1-mu 7 corresponding to each factor into the above formula to obtain the variation coefficient c of each factorv1-cv7；
3) Solving each factor weight
Solving to obtain:
Figure FDA0003574895610000013
substituting the data obtained in the step 2) into the data, solving a weight function, and finally obtaining the self-adaptive function as follows:
f(x)＝ω1U+ω2T+ω3S+ω4R+ω5ΔU+ω6ΔT+ω7n
wherein, f (x) is the life length of the battery, U is the voltage consistency, T is the temperature consistency, S is the initial SOC of the battery charging, R is the internal resistance value of the battery, delta U is the pressure difference, delta T is the temperature difference, and n is the charging frequency;
(3) cross breeding
Performing pairwise cross breeding on the initialized data, wherein the cross rate is selected to be 100%, and the probability of variation is set to be 0, while the variation possibly existing in the cross breeding process is not considered;
substituting the descendants obtained by cross breeding into an adaptive function to solve and find an optimal sample, and outputting the initial SOC data of the battery charging of the optimal sample as a result;
step three: model training
And (3) processing other incremental data by the data processing method in the first step, importing the model for result verification, finishing model training if the result accords with the actual condition, otherwise supplementing the data of the time with the sample data of the last time, and repeating the first step and the second step until the output result achieves the expected effect.
2. The method for predicting the optimal charging starting SOC of the power battery of the electric automobile according to claim 1, wherein: the system implementation comprises the following steps:
the method comprises the following steps: data processing: the data processing mode is the same as that of a system building part;
step two: data import: inputting the data processed in the first step into a model, and calculating through the model;
step three: and (4) outputting a result: after the model is calculated, the initial SOC permutation and combination of the optimal charging of the power storage battery is output, the output result is displayed in the form of a large screen of a vehicle-mounted computer or a mobile phone APP, and meanwhile, the result supports regular refreshing and correction.
3. The method for predicting the optimal charging starting SOC of the power battery of the electric automobile according to claim 1, wherein: in the step of solving the weight of each factor, the battery with the longest service life is selected as a theoretical value, and a sample which is not less than the theoretical value is obtained as an optimal solution in a cross breeding mode.
4. The method for predicting the optimal charging starting SOC of the power battery of the electric automobile according to claim 1, wherein: data acquisition in system construction takes the beginning of charging to the end of charging as one time.
CN202210337441.5A 2022-03-31 2022-03-31 Method for predicting optimal charging initial SOC of power battery of electric vehicle Pending CN114690040A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210337441.5A CN114690040A (en) 2022-03-31 2022-03-31 Method for predicting optimal charging initial SOC of power battery of electric vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210337441.5A CN114690040A (en) 2022-03-31 2022-03-31 Method for predicting optimal charging initial SOC of power battery of electric vehicle

Publications (1)

Publication Number Publication Date
CN114690040A true CN114690040A (en) 2022-07-01

Family

ID=82141567

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210337441.5A Pending CN114690040A (en) 2022-03-31 2022-03-31 Method for predicting optimal charging initial SOC of power battery of electric vehicle

Country Status (1)

Country Link
CN (1) CN114690040A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116365066A (en) * 2023-05-19 2023-06-30 东莞市易利特新能源有限公司 BMS module-based power management system

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116365066A (en) * 2023-05-19 2023-06-30 东莞市易利特新能源有限公司 BMS module-based power management system
CN116365066B (en) * 2023-05-19 2023-09-22 东莞市易利特新能源有限公司 BMS module-based power management system

Similar Documents

Publication Publication Date Title
JP5944291B2 (en) Battery parameter estimation apparatus and method
CN110010987B (en) Big data-based electric vehicle remaining charging time prediction method
CN110568361A (en) Method for predicting health state of power battery
CN111323719A (en) Method and system for online determination of health state of power battery pack of electric automobile
CN113960476B (en) Power battery fault monitoring method and system based on information physical fusion technology
CN108556682B (en) Driving range prediction method, device and equipment
CN115622203B (en) Analysis reminding method and system based on charging data of vehicle-mounted wireless charger
CN112540317A (en) Battery health state estimation and residual life prediction method based on real vehicle data
CN110609233A (en) Method for predicting SOH of energy storage battery based on big data
CN110687450B (en) Lithium battery residual life prediction method based on phase space reconstruction and particle filtering
CN116609676B (en) Method and system for monitoring state of hybrid energy storage battery based on big data processing
CN112098874B (en) Lithium ion battery electric quantity prediction method considering aging condition
CN113064089A (en) Internal resistance detection method, device, medium and system of power battery
CN113191547B (en) New energy vehicle power battery charging optimization method and system
CN111983459A (en) Health state testing and evaluating method based on vehicle lithium ion battery
CN113093020A (en) Method for predicting remaining service life of lithium ion battery based on LSTM neural network
CN113777510A (en) Lithium battery state of charge estimation method and device
CN114690040A (en) Method for predicting optimal charging initial SOC of power battery of electric vehicle
CN114646888A (en) Assessment method and system for capacity attenuation of power battery
CN115684936A (en) Power battery health failure probability calculation and health failure map establishment method based on machine learning
CN114329337A (en) Method and system for predicting insulation resistance of electric vehicle and storage medium
CN113608126B (en) Lithium battery SOC online prediction method under different temperatures
CN114924203A (en) Battery SOH prediction analysis method and electric automobile
CN113119796B (en) Electric vehicle residual charging time prediction method and system based on cloud sparse charging data
CN115544900B (en) Method for analyzing electric vehicle endurance mileage influence factors based on shape algorithm

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