CN116540117A - Power battery Y capacitance prediction system and prediction method - Google Patents
Power battery Y capacitance prediction system and prediction method Download PDFInfo
- Publication number
- CN116540117A CN116540117A CN202310295967.6A CN202310295967A CN116540117A CN 116540117 A CN116540117 A CN 116540117A CN 202310295967 A CN202310295967 A CN 202310295967A CN 116540117 A CN116540117 A CN 116540117A
- Authority
- CN
- China
- Prior art keywords
- capacitance
- voltage
- value
- power battery
- prediction
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000012360 testing method Methods 0.000 claims abstract description 66
- 238000009413 insulation Methods 0.000 claims abstract description 31
- 238000013528 artificial neural network Methods 0.000 claims abstract description 21
- 238000000611 regression analysis Methods 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 9
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 238000005259 measurement Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 abstract description 3
- 230000002708 enhancing effect Effects 0.000 abstract description 3
- 239000003990 capacitor Substances 0.000 description 4
- 238000001816 cooling Methods 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 239000007788 liquid Substances 0.000 description 2
- 239000000110 cooling liquid Substances 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
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]
- G01R31/385—Arrangements for measuring battery or accumulator 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
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
-
- 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
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
- G01R31/1263—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/389—Measuring internal impedance, internal conductance or related variables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/52—Testing for short-circuits, leakage current or ground faults
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of Resistance Or Impedance (AREA)
Abstract
The invention discloses a power battery Y capacitance prediction system and a prediction method, which utilize a power battery to calculate a capacitance value in a front-stage station withstand voltage test, analyze data with the capacitance value tested by an insulation resistance value, a battery total voltage, a rear-stage station LCR meter and the like, find out a corresponding mathematical relationship, and aim at calculating a relatively more accurate capacitance value by utilizing the withstand voltage test value in combination with the mathematical relationship of historical test data in an actual production test, and meanwhile, can omit the testing steps of the LCR meter and the like in the traditional mode so as to achieve the effects of reducing cost and enhancing efficiency. According to the invention, a combined prediction model is established through multiple regression analysis and the cross application of the BP neural network, the model comprehensively considers the influence factors of the association of the actual test and the influence of the voltage-withstanding leakage current calculation capacitance value and the direct measurement capacitance value, and the BP-multiple regression prediction model has a better fitting effect in the prediction process, so that the prediction accuracy is greatly improved, and a better prediction effect is achieved.
Description
Technical Field
The invention relates to a power battery testing technology, in particular to a power battery Y capacitance prediction system and a prediction method.
Background
The power battery Y capacitor is a structural capacitor between the anode and the cathode of the battery and the metal shell of the battery pack or the internal liquid cooling pipeline, and is formed by unreasonable design of the internal structure of the battery. It is mainly classified into 2 classes: the battery pack is characterized in that the battery pack is fixed by a metal tray, the battery module and the tray are respectively fixed by bolts, the tray is fixed with a vehicle, and a Y capacitor is formed between a battery pack electrode and the battery pack tray; the other type is a circulating liquid cooling battery pack, a metal pipeline containing cooling liquid is arranged between battery cells to realize constant temperature control, and a Y capacitor is formed between an electrode of the battery pack and the cooling pipeline. The Y capacitance is too large, and the stored energy may damage other parts or persons, so that the capacitance of the Y capacitance needs to be controlled.
In the process of power battery production test, according to the requirements of capacitive coupling test required by national standard requirements (G B/T18384-2020), the capacitance value test of the positive electrode of the battery pack to the shell and the negative electrode of the battery pack to the shell can be carried out by adopting LCR (LCR) meter and other modes on a common test station on a production line.
In addition to the Y capacitance test, a plurality of tests such as insulation, voltage withstanding, total voltage and the like are also performed in the production process of the power battery, wherein the value of leakage current obtained in the alternating current voltage withstanding test can be calculated according to a formula.
The prior art mainly adopts an LCR meter or a universal meter to directly measure the corresponding capacitance value of the power battery, belongs to an independent testing step, and needs corresponding testing instruments and testing time.
Disclosure of Invention
The invention aims at: the power battery Y capacitance prediction system and the prediction method are provided, a capacitance value is calculated by using the power battery in a front-stage station withstand voltage test, data analysis is carried out on the capacitance value and the insulation resistance value, the total battery voltage, a rear-stage station LCR meter and other tested capacitance values, and a corresponding mathematical relationship is found, so that in an actual production test, the relatively more accurate capacitance value is calculated by using the withstand voltage test value and the mathematical relationship of historical test data, and meanwhile, the testing steps of the LCR meter and other traditional modes can be omitted, and the effects of reducing cost and enhancing efficiency are achieved.
The technical scheme of the invention is as follows:
a power battery Y capacitance prediction system comprises an insulation withstand voltage tester, a voltage acquisition module, an LCR meter, a computer and a database; wherein:
an insulation voltage-withstand tester for testing voltage-withstand leakage current value and insulation resistance value of a power battery positive electrode to a shell and a power battery negative electrode to the shell; the voltage-resistant leakage current value of the voltage-resistant tester is read through a computer, and a corresponding capacitance value is calculated; storing the measured insulation resistance value, the leakage current value and the calculated capacitance value in a database;
the voltage acquisition module is used for acquiring the total voltage of the power battery, the voltage value of the positive electrode of the power battery to the shell and the voltage value of the negative electrode of the power battery to the shell, reading and measuring corresponding values through a computer, and storing the voltage values in the database;
and the LCR meter is used for directly measuring capacitance values of the positive electrode to the shell and the negative electrode to the shell of the power battery, measuring corresponding capacitance values through a computer reading instrument and storing the capacitance values in a database.
Preferably, the insulation voltage-resistant testing module, the voltage acquisition module and the LCR meter respectively complete corresponding tests through the switching module.
Preferably, the computer reads the leakage current of the withstand voltage tester, and the formula for calculating the corresponding capacitance value is as follows:
wherein C is capacitance value, U (AC) The ac voltage amplitude, f is ac voltage frequency, and I, R is withstand voltage leakage current value and insulation resistance value, respectively.
Preferably, in the database, a corresponding test data set is formed for the input data, and a prediction model is established, and a BP neural network and multiple regression analysis cross analysis is adopted to predict the measured value of the Y capacitance, so that a relatively more accurate capacitance value of the new battery is predicted.
A power battery Y capacitance prediction method comprises the following steps:
step one, inputting the following data (1) - (3) to form corresponding test data sets respectively:
(1) The positive electrode of the power battery tested by the insulation voltage-resistant tester is opposite to the shell, and the negative electrode is opposite to the voltage-resistant leakage current value, insulation resistance value and calculated capacitance value of the shell; (2) The voltage acquisition module acquires the total voltage of the power battery, the voltage of the power battery opposite to the shell, and the negative voltage of the power battery opposite to the shell; (3) The capacitance value of the positive electrode to the shell and the negative electrode to the shell of the power battery tested by the LCR meter;
step two, predicting the measured value of the Y capacitance by establishing a prediction model and adopting the cross analysis application of BP neural network and multiple regression analysis;
firstly, analyzing influence factors influencing the Y capacitance value and change rules and trends of the capacitance value, voltage, insulation resistance and leakage current, then, analyzing main influence factors influencing the Y capacitance value through a Stepwise regression analysis, constructing a BP-multiple regression prediction model by utilizing multiple regression analysis and a BP neural network, predicting the Y capacitance value, and analyzing a prediction result.
Preferably, the second step specifically includes the steps of:
s1: acquiring a test data set;
s2: test dataset was measured according to 8: dividing the training set and the testing set in proportion;
s3: establishing a Stepwise regression model for screening influence factors, wherein the Stepwise regression model is expressed as follows:
Y＝a0+a 1X1+a2X2+a3X3+a4X4+a5X5；
wherein Y, X, X2, X3, X4, X5 represent the respective variables of the test store; a0, a1, a2 … a5 represent Stepwise regression coefficients;
s4: and (3) selecting variables of the test data set as significant influence factors to establish a multiple regression prediction model, and calculating a predicted value yr of the Y capacitance:
yr＝a 1Yi+a2X1i+a3X2i+a4X3i+a5X4i+a6X5i；
wherein Yi, X1i, X2i, X3i, X4i, X5i represent related variables, respectively; a1, a2, a3, a4, a5, a6 represent variable coefficients;
s5: in a BP neural network prediction model, selecting a withstand voltage leakage current value, a calculated capacitance value and a capacitance value measured by an LCR table as predicted input and output of a Y capacitance value;
s6: and combining multiple regression with a BP neural network model to obtain a final Y capacitance predicted value according to the following formula:
y＝ω1yb+ω2yr；
wherein Y represents the final Y capacitance value; yb represents the predicted Y capacitance value of the BP neural network prediction model; yr represents the Y capacitance value predicted by the multiple regression prediction model; ω1 and ω2 represent weights of the BP neural network prediction model and the multiple regression prediction model, respectively.
Preferably, after obtaining the final Y capacitance predicted value, testing and verifying the algorithm accuracy according to the data of the test set, and performing model optimization to finally obtain a trained Y capacitance test predicted model; and inputting the measured data into a trained Y capacitance prediction model, and predicting the Y capacitance of the main positive pair shell and the main negative pair shell of the power battery.
The invention has the advantages that:
1. the invention calculates the capacitance value by using the voltage withstand test of the front stage station of the power battery, analyzes the data with the insulation resistance value, the total voltage of the battery, the capacitance value tested by the LCR meter of the rear stage station and the like, and finds out the corresponding mathematical relationship, so as to calculate the relatively more accurate capacitance value by using the voltage withstand test value and the mathematical relationship of the historical test data in the actual production test, and meanwhile, can omit the testing steps of the LCR meter and other traditional modes, thereby achieving the effects of reducing cost and enhancing efficiency.
2. According to the invention, a combined prediction model is established through multiple regression analysis and the cross application of the BP neural network, the model comprehensively considers the influence factors of the association of the actual test and the influence of the voltage-withstanding leakage current calculation capacitance value and the direct measurement capacitance value, and the BP-multiple regression prediction model has a better fitting effect in the prediction process, so that the prediction accuracy is greatly improved, and a better prediction effect is achieved.
Drawings
The invention is further described below with reference to the accompanying drawings and examples:
fig. 1 is a device diagram of a power battery Y capacitance prediction system according to the present invention.
Detailed Description
As shown in FIG. 1, the power battery Y capacitance prediction system comprises an insulation and voltage withstanding tester, a voltage acquisition module, an LCR meter, a computer and a database; wherein:
an insulation voltage-withstand tester for testing voltage-withstand leakage current value and insulation resistance value of a power battery positive electrode to a shell and a power battery negative electrode to the shell; the voltage-resistant leakage current value of the voltage-resistant tester is read through a computer, and a corresponding capacitance value is calculated; storing the measured insulation resistance value, the leakage current value and the calculated capacitance value in a database;
the computer reads the leakage current of the withstand voltage tester, and the formula for calculating the corresponding capacitance value is as follows:
wherein C is capacitance value, U (AC) The ac voltage amplitude, f is ac voltage frequency, and I, R is withstand voltage leakage current value and insulation resistance value, respectively.
The voltage acquisition module is used for acquiring the total voltage of the power battery, the voltage value of the positive electrode of the power battery to the shell and the voltage value of the negative electrode of the power battery to the shell, reading and measuring corresponding values through a computer, and storing the voltage values in the database;
and the LCR meter is used for directly measuring capacitance values of the positive electrode to the shell and the negative electrode to the shell of the power battery, measuring corresponding capacitance values through a computer reading instrument and storing the capacitance values in a database.
The insulation voltage-resistant testing module, the voltage acquisition module and the LCR meter respectively complete corresponding tests through the switching module.
In the database, a corresponding test data set is formed for the input data, and a prediction model is established, and a measurement value of the Y capacitance is predicted by adopting cross analysis application of BP neural network and multiple regression analysis, so that a relatively more accurate capacitance value of the new battery is predicted.
Specifically, the method for predicting the Y capacitance of the power battery comprises the following steps:
step one, inputting the following data (1) - (3) to form corresponding test data sets respectively:
(1) The positive electrode of the power battery tested by the insulation voltage-resistant tester is opposite to the shell, and the negative electrode is opposite to the voltage-resistant leakage current value, insulation resistance value and calculated capacitance value of the shell; (2) The voltage acquisition module acquires the total voltage of the power battery, the voltage of the power battery opposite to the shell, and the negative voltage of the power battery opposite to the shell; (3) The capacitance value of the positive electrode to the shell and the negative electrode to the shell of the power battery tested by the LCR meter;
step two, predicting the measured value of the Y capacitance by establishing a prediction model and adopting the cross analysis application of BP neural network and multiple regression analysis;
firstly, analyzing influence factors influencing the Y capacitance value and change rules and trends of the capacitance value, voltage, insulation resistance and leakage current, then, analyzing main influence factors influencing the Y capacitance value through a Stepwise regression analysis, constructing a BP-multiple regression prediction model by utilizing multiple regression analysis and a BP neural network, predicting the Y capacitance value, and analyzing a prediction result.
The second step specifically comprises the following steps:
s1: acquiring a test data set;
s2: test dataset was measured according to 8: dividing the training set and the testing set in proportion;
s3: establishing a Stepwise regression model for screening influence factors, wherein the Stepwise regression model is expressed as follows:
Y＝a0+a 1X1+a2X2+a3X3+a4X4+a5X5；
wherein Y, X, X2, X3, X4, X5 represent the respective variables of the test store; a0, a1, a2 … a5 represent Stepwise regression coefficients;
s4: and (3) selecting variables of the test data set as significant influence factors to establish a multiple regression prediction model, and calculating a predicted value yr of the Y capacitance:
yr＝a 1Yi+a2X1i+a3X2i+a4X3i+a5X4i+a6X5i；
wherein Yi, X1i, X2i, X3i, X4i, X5i represent related variables, respectively; a1, a2, a3, a4, a5, a6 represent variable coefficients;
s5: in a BP neural network prediction model, selecting a withstand voltage leakage current value, a calculated capacitance value and a capacitance value measured by an LCR table as predicted input and output of a Y capacitance value;
s6: and combining multiple regression with a BP neural network model to obtain a final Y capacitance predicted value according to the following formula:
y＝ω1yb+ω2yr；
wherein Y represents the final Y capacitance value; yb represents the predicted Y capacitance value of the BP neural network prediction model; yr represents the Y capacitance value predicted by the multiple regression prediction model; ω1 and ω2 respectively represent weights of the BP neural network prediction model and the multiple regression prediction model;
s7: after the final Y capacitance predicted value is obtained, the accuracy of the algorithm is tested and verified according to the data of the test set, model optimization is carried out, and finally a trained Y capacitance test predicted model is obtained;
s8: and inputting the measured data into a trained Y capacitance prediction model, and predicting the Y capacitance of the main positive pair shell and the main negative pair shell of the power battery.
According to the invention, a combined prediction model is established through multiple regression analysis and the cross application of the BP neural network, the model comprehensively considers the influence factors of the association of the actual test and the influence of the voltage-withstanding leakage current calculation capacitance value and the direct measurement capacitance value, and the BP-multiple regression prediction model has a better fitting effect in the prediction process, so that the prediction accuracy is greatly improved, and a better prediction effect is achieved.
The above embodiments are only for illustrating the technical concept and features of the present invention, and are intended to enable those skilled in the art to understand the content of the present invention and implement the same according to the content of the present invention, and are not intended to limit the scope of the present invention. All modifications made according to the spirit of the main technical proposal of the invention should be covered in the protection scope of the invention.
Claims (7)
1. The power battery Y capacitance prediction system is characterized by comprising an insulation withstand voltage tester, a voltage acquisition module, an LCR meter, a computer and a database; wherein:
an insulation voltage-withstand tester for testing voltage-withstand leakage current value and insulation resistance value of a power battery positive electrode to a shell and a power battery negative electrode to the shell; the voltage-resistant leakage current value of the voltage-resistant tester is read through a computer, and a corresponding capacitance value is calculated; storing the measured insulation resistance value, the leakage current value and the calculated capacitance value in a database;
the voltage acquisition module is used for acquiring the total voltage of the power battery, the voltage value of the positive electrode of the power battery to the shell and the voltage value of the negative electrode of the power battery to the shell, reading and measuring corresponding values through a computer, and storing the voltage values in the database;
and the LCR meter is used for directly measuring capacitance values of the positive electrode to the shell and the negative electrode to the shell of the power battery, measuring corresponding capacitance values through a computer reading instrument and storing the capacitance values in a database.
2. The power battery Y capacitance prediction system according to claim 1, wherein the insulation withstand voltage test module, the voltage acquisition module, and the LCR meter respectively complete the corresponding tests through the switching module.
3. The power battery Y capacitance prediction system according to claim 1, wherein the computer reads the leakage current of the withstand voltage tester, and calculates the formula of the corresponding capacitance value as follows:
U (AC) ＝I×R,
wherein C is capacitance value, U (AC) The ac voltage amplitude, f is ac voltage frequency, and I, R is withstand voltage leakage current value and insulation resistance value, respectively.
4. A power cell Y capacitance prediction system according to claim 3 wherein in the database, corresponding test data sets are formed for the input data, and a prediction model is built to predict the measured value of the Y capacitance by applying a cross analysis of the BP neural network and a multiple regression analysis to predict a relatively more accurate capacitance value of the new cell.
5. The power battery Y capacitance prediction method is characterized by comprising the following steps of:
step one, inputting the following data (1) - (3) to form corresponding test data sets respectively:
(1) The positive electrode of the power battery tested by the insulation voltage-resistant tester is opposite to the shell, and the negative electrode is opposite to the voltage-resistant leakage current value, insulation resistance value and calculated capacitance value of the shell; (2) The voltage acquisition module acquires the total voltage of the power battery, the voltage of the power battery opposite to the shell, and the negative voltage of the power battery opposite to the shell; (3) The capacitance value of the positive electrode to the shell and the negative electrode to the shell of the power battery tested by the LCR meter;
step two, predicting the measured value of the Y capacitance by establishing a prediction model and adopting the cross analysis application of BP neural network and multiple regression analysis;
firstly, analyzing influence factors influencing the Y capacitance value and change rules and trends of the capacitance value, voltage, insulation resistance and leakage current, then, analyzing main influence factors influencing the Y capacitance value through a Stepwise regression analysis, constructing a BP-multiple regression prediction model by utilizing multiple regression analysis and a BP neural network, predicting the Y capacitance value, and analyzing a prediction result.
6. The method for predicting the Y capacitance of a power battery according to claim 5, wherein in the second step, the method specifically comprises the steps of:
s1: acquiring a test data set;
s2: test dataset was measured according to 8: dividing the training set and the testing set in proportion;
s3: establishing a Stepwise regression model for screening influence factors, wherein the Stepwise regression model is expressed as follows:
Y＝a0+a1X1+a2X2+a3X3+a4X4+a5X5；
wherein Y, X, X2, X3, X4, X5 represent the respective variables of the test store; a0, a1, a2 … a5 represent Stepwise regression coefficients;
s4: and (3) selecting variables of the test data set as significant influence factors to establish a multiple regression prediction model, and calculating a predicted value yr of the Y capacitance:
yr＝a1Yi+a2X1i+a3X2i+a4X3i+a5X4i+a6X5i；
wherein Yi, X1i, X2i, X3i, X4i, X5i represent related variables, respectively; a1, a2, a3, a4, a5, a6 represent variable coefficients;
s5: in a BP neural network prediction model, selecting a withstand voltage leakage current value, a calculated capacitance value and a capacitance value measured by an LCR table as predicted input and output of a Y capacitance value;
s6: and combining multiple regression with a BP neural network model to obtain a final Y capacitance predicted value according to the following formula:
y＝ω1yb+ω2yr；
wherein Y represents the final Y capacitance value; yb represents the predicted Y capacitance value of the BP neural network prediction model; yr represents the Y capacitance value predicted by the multiple regression prediction model; ω1 and ω2 represent weights of the BP neural network prediction model and the multiple regression prediction model, respectively.
7. The power battery Y capacitance prediction method according to claim 6, wherein after the final Y capacitance prediction value is obtained, the algorithm accuracy is tested and verified according to the data of the test set, and model optimization is performed, so that a trained Y capacitance test prediction model is finally obtained; and inputting the measured data into a trained Y capacitance prediction model, and predicting the Y capacitance of the main positive pair shell and the main negative pair shell of the power battery.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310295967.6A CN116540117A (en) | 2023-03-24 | 2023-03-24 | Power battery Y capacitance prediction system and prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310295967.6A CN116540117A (en) | 2023-03-24 | 2023-03-24 | Power battery Y capacitance prediction system and prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116540117A true CN116540117A (en) | 2023-08-04 |
Family
ID=87451304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310295967.6A Pending CN116540117A (en) | 2023-03-24 | 2023-03-24 | Power battery Y capacitance prediction system and prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116540117A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116953544A (en) * | 2023-09-20 | 2023-10-27 | 苏州清研精准汽车科技有限公司 | Battery pack insulation resistance detection method and system |
-
2023
- 2023-03-24 CN CN202310295967.6A patent/CN116540117A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116953544A (en) * | 2023-09-20 | 2023-10-27 | 苏州清研精准汽车科技有限公司 | Battery pack insulation resistance detection method and system |
| CN116953544B (en) * | 2023-09-20 | 2024-01-16 | 苏州清研精准汽车科技有限公司 | Battery pack insulation resistance detection method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xiong et al. | Towards a smarter battery management system: A critical review on battery state of health monitoring methods | |
| Zhu et al. | A state of charge estimation method for lithium-ion batteries based on fractional order adaptive extended kalman filter | |
| Lai et al. | Co-estimation of state of charge and state of power for lithium-ion batteries based on fractional variable-order model | |
| Guo et al. | A state-of-health estimation method of lithium-ion batteries based on multi-feature extracted from constant current charging curve | |
| Qiao et al. | Toward safe carbon–neutral transportation: Battery internal short circuit diagnosis based on cloud data for electric vehicles | |
| CN110488194B (en) | Lithium battery SOC estimation method and system based on electrochemical impedance model | |
| Bruch et al. | Novel method for the parameterization of a reliable equivalent circuit model for the precise simulation of a battery cell's electric behavior | |
| CN112069739B (en) | Battery fractional order model parameter identification method | |
| Zhang et al. | Aging performance characterization and state-of-health assessment of retired lithium-ion battery modules | |
| Chang et al. | A novel fast capacity estimation method based on current curves of parallel-connected cells for retired lithium-ion batteries in second-use applications | |
| GB2610366A (en) | "Standardized temperature" -based online estimation method for state of health of battery within wide temperature range | |
| CN103983920B (en) | A kind of method of the model of the electrokinetic cell setting up electric vehicle | |
| CN112580284B (en) | Hybrid capacitor equivalent circuit model and online parameter identification method | |
| CN110496799B (en) | Method for distinguishing abnormal cell by formation | |
| CN116540117A (en) | Power battery Y capacitance prediction system and prediction method | |
| CN112350400A (en) | Lithium battery pack non-hierarchical active and passive equalization circuit and method | |
| CN103424712A (en) | Method for measuring residual capacity of battery in online manner on basis of particle swarm optimization | |
| CN109613446A (en) | A kind of aging of lithium battery detection method based on time series analysis | |
| CN115508721B (en) | Lithium ion battery lithium separation detection method | |
| Li et al. | A framework for states co-estimation of hybrid energy storage systems based on fractional-order theory | |
| CN103135057B (en) | A kind of method for fast measuring of self-discharge of battery performance | |
| Liu et al. | State of charge estimation algorithm based on fractional-order adaptive extended Kalman filter and unscented Kalman filter | |
| Wu et al. | State of health estimation of the LiFePO4 power battery based on the forgetting factor recursive Total Least Squares and the temperature correction | |
| CN115128465A (en) | Battery thermal simulation system and method and electronic equipment | |
| Zhu et al. | Lithium-ion battery degradation diagnosis and state-of-health estimation with half cell electrode potential |
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 |