CN111965545A - Lithium battery self-discharge detection method, device and system - Google Patents
Lithium battery self-discharge detection method, device and system Download PDFInfo
- Publication number
- CN111965545A CN111965545A CN202010760423.9A CN202010760423A CN111965545A CN 111965545 A CN111965545 A CN 111965545A CN 202010760423 A CN202010760423 A CN 202010760423A CN 111965545 A CN111965545 A CN 111965545A
- Authority
- CN
- China
- Prior art keywords
- self
- lithium battery
- discharge
- data
- discharge current
- 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
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 title claims abstract description 83
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 83
- 238000001514 detection method Methods 0.000 title claims abstract description 53
- 238000012360 testing method Methods 0.000 claims abstract description 56
- 238000010801 machine learning Methods 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 20
- 238000000611 regression analysis Methods 0.000 claims description 19
- 238000012795 verification Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 10
- 230000001419 dependent effect Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 230000002950 deficient Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000032798 delamination Effects 0.000 description 2
- 239000003792 electrolyte Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 229910001416 lithium ion Inorganic materials 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000007086 side reaction Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
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
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
Abstract
The invention relates to the field of battery testing, and provides a lithium battery self-discharge detection method, which comprises the following steps: acquiring first self-discharge current data of a lithium battery to be tested from the test start to a first time point in a self-discharge test environment; inputting the first self-discharge current data into a machine learning prediction model to obtain second self-discharge current data after a first time point of the lithium battery to be tested; and judging the self-discharge performance of the lithium battery to be tested based on the second self-discharge current data. Meanwhile, a corresponding lithium battery self-discharge detection device and system are also provided. The embodiment provided by the invention shortens the detection time of the self-discharge detection of the lithium battery.
Description
Technical Field
The invention relates to the field of battery testing, in particular to a lithium battery self-discharge detection method, a lithium battery self-discharge detection method and a corresponding storage medium.
Background
Electric vehicles powered by lithium ion batteries are widely used. The power battery pack of the electric automobile is formed by a single battery in a module in a serial or parallel mode and then combined into a pack. Each single battery has to have good performance consistency to ensure the performance, cycle life, safety and the like of the battery pack. The main indicators for measuring the consistency of the battery are capacity, self-discharge, internal resistance and the like. Excessive self-discharge may cause thermal runaway, and bring potential safety hazards to electric automobiles. Meanwhile, the measurement of the self-discharge rate is also a key process in the production process of the lithium battery, and longer process time is consumed.
The currently mainstream lithium battery self-discharge measuring method is an open-circuit voltage measuring method, namely standing the formed battery for 3-5H, and then measuring the open-circuit voltage and recording the open-circuit voltage as OCV 1; and standing for a certain time (different battery factories have different process requirements, usually 96-144H), measuring the open-circuit voltage as OCV2, and measuring the self-discharge rate as K1 (OCV1-OCV2) 1000/T, wherein T is the measured interval time. The reason for causing the self-discharge of the lithium battery is complex, mainly the interface side reaction between the anode and the cathode and the electrolyte, the existence of oxygen and impurities in the electrolyte, different SOC states, different environmental temperatures, the water content in the battery and the like. In order to ensure that the lithium battery does not have the phenomenon of overlarge self-discharge at a client, all lithium battery manufacturers stand for a long time before leaving factories as much as possible; however, the excessive standing time can increase the turnover storage space, which leads to the increase of investment cost of factory construction and equipment, and simultaneously prolongs the delivery period.
Disclosure of Invention
In view of the above, the present invention is directed to a method, an apparatus, and a system for detecting self-discharge of a lithium battery, so as to at least solve the above problems.
In a first aspect of the present invention, a lithium battery self-discharge detection method is provided, the method comprising: acquiring first self-discharge current data of a lithium battery to be tested from the test start to a first time point in a self-discharge test environment; inputting the first self-discharge current data into a machine learning prediction model to obtain second self-discharge current data after a first time point of the lithium battery to be tested; and judging the self-discharge performance of the lithium battery to be tested based on the second self-discharge current data.
Optionally, the self-discharge test environment includes: connecting the lithium battery to be tested to a self-discharge detection circuit according to a self-discharge test specification; the self-discharge detection circuit includes: and the stabilized voltage power supply and the micro-ammeter are connected with the lithium battery to be tested in series.
Optionally, the machine learning prediction model is a lasso regression analysis model, and parameters in the lasso regression analysis model are obtained after training by using a training set; the training set includes a number of data samples, the data samples including: the self-discharge current data of the lithium battery with the same type as the lithium battery to be tested from the test beginning to the first time point in the self-discharge test environment and/or the historical data of the self-discharge current of the lithium battery to be tested from the test beginning to the first time point in the self-discharge test environment before.
Optionally, the parameters in the lasso regression analysis model include: independent variables, dependent variables, weight parameters and regularization parameters; the values of the weight parameters are determined after training by the training set.
Optionally, after the lasso regression analysis model is trained, the method further includes a step of verifying the trained lasso regression analysis model:
dividing a verification data sample of the self-discharge current into a front section and a rear section according to the first time point; inputting the front-stage verification data sample into the trained lasso regression analysis model to obtain a prediction current sequence corresponding to the rear-stage time; and determining that the deviation between the predicted current sequence in the later period of time and the later verification data sample is less than a deviation threshold value, and then passing the verification.
Optionally, the deviation threshold is related to a deviation between the good product current and the bad product current of the lithium battery to be tested.
Optionally, the first time point is 2 hours after the test starts.
In a second aspect of the present invention, there is also provided a lithium battery self-discharge detection apparatus, comprising: at least one processor; a memory coupled to the at least one processor; the memory stores instructions capable of being executed by the at least one processor, and the at least one processor implements the lithium battery self-discharge detection method by executing the instructions stored in the memory.
In a third aspect of the present invention, there is also provided a lithium battery self-discharge detection system, the system comprising:
the data detection equipment is used for being connected with the lithium battery to be detected and acquiring first self-discharge current data of the lithium battery to be detected from the beginning of the test to a first time point in a self-discharge test environment; the data processing equipment comprises a data prediction module and a performance judgment module; the data prediction module is used for inputting the first self-discharge current data into a machine learning prediction model to obtain second self-discharge current data after a first time point of the lithium battery to be tested; and the performance judging module is used for judging the self-discharge performance of the lithium battery to be tested based on the second self-discharge current data.
In a fourth aspect of the present invention, a computer-readable storage medium is further provided, where instructions are stored in the storage medium, and when executed by a processor, the instructions cause the processor to execute the foregoing lithium battery self-discharge detection method.
Through the technical scheme provided by the invention, the following beneficial effects are achieved: the novel self-discharge detection method based on machine learning introduced by the patent applies the latest artificial intelligence and big data analysis technology to the self-discharge detection of the lithium battery and combines the current detection mode. On the premise of ensuring the same detection effect, the normal-temperature standing process time of the traditional lithium battery is shortened from 144 hours to 74H, so that the standing test time is greatly reduced. The brought benefits are mainly reflected in that the storage space for standing is reduced, the area of a factory building is reduced, the equipment and investment cost is greatly reduced, and meanwhile, the delivery cycle of the product is greatly shortened.
Additional features and advantages of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate an embodiment of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a schematic flow chart of a lithium battery self-discharge detection method according to an embodiment of the present invention;
FIG. 2 is an equivalent circuit model of a self-discharge detection circuit according to an embodiment of the present invention;
FIG. 3 is a logic flow diagram for validating a machine learning predictive model in accordance with an embodiment of the present invention;
FIG. 4 is a data diagram for validating a machine learning prediction model according to one embodiment of the present invention;
fig. 5 is a current test curve diagram in the self-discharge detection of the lithium battery according to an embodiment of the invention.
Detailed Description
In addition, the embodiments of the present invention and the features of the embodiments may be combined with each other without conflict.
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present invention, are given by way of illustration and explanation only, not limitation.
Fig. 1 is a schematic flow chart of a lithium battery self-discharge detection method according to an embodiment of the present invention, as shown in fig. 1. A lithium battery self-discharge detection method, the method comprising: acquiring first self-discharge current data of a lithium battery to be tested from the test start to a first time point in a self-discharge test environment; inputting the first self-discharge current data into a machine learning prediction model to obtain second self-discharge current data after a first time point of the lithium battery to be tested; and judging the self-discharge performance of the lithium battery to be tested based on the second self-discharge current data.
Therefore, the self-discharge performance of the lithium battery can be prevented from being tested by obtaining self-discharge current data through long-time test, the actual test time is compressed to the first time point, and the later data is obtained through prediction, so that the test efficiency is improved, and the delivery cycle of the product is reduced.
In one embodiment of the present invention, the self-discharge test environment includes: connecting the lithium battery to be tested to a self-discharge detection circuit according to a self-discharge test specification; the self-discharge detection circuit includes: and the stabilized voltage power supply and the micro-ammeter are connected with the lithium battery to be tested in series. The self-discharge test environment comprises a test flow and a hardware environment. The test flow comprises the following steps of according to test specifications, a preset standing time, pretreatment and the like, for example: and (3) selecting a certain type of battery, standing for 72H at normal temperature, and measuring in a constant temperature room. The self-discharge detection mode is to directly measure the size of self-discharge current and screen the battery with self-discharge failure by judging the size and trend of the self-discharge current to be stable in a certain time. Fig. 2 is an equivalent circuit model of a self-discharge detection circuit according to an embodiment of the present invention, as shown in fig. 2. In the measured equivalent circuit model, Vsource: external regulated power supply, Vcell: battery voltage, Rs: series resistance, Rsd: parallel resistance through which self-discharge current flows, Isd: a self-discharge current; vcell (Vsource- (isdxrs)), the matching function of the regulated power supply can measure the initial cell voltage and adjust the applied voltage for matching, thereby obtaining accurate self-discharge measurements more quickly. The micro-ammeter can accurately measure the low-level self-discharge current, and the precision reaches +/-plus or minus (0.025% +100nA of the reading). Through the test environment, the self-discharge current of the lithium battery to be tested can be accurately obtained.
In an embodiment provided by the present invention, the machine learning prediction model is a lasso regression analysis model, and parameters in the lasso regression analysis model are obtained after training with a training set; the training set includes a number of data samples, the data samples including: the self-discharge current data of the lithium battery with the same type as the lithium battery to be tested from the test beginning to the first time point in the self-discharge test environment and/or the historical data of the self-discharge current of the lithium battery to be tested from the test beginning to the first time point in the self-discharge test environment before. Lasso regression can enhance the prediction accuracy and interpretability of statistical models. The parameters in the model are trained by adopting the data samples, so that the model can be used for better fitting the data, and the fitted model can better reflect the corresponding relation between the time and the self-discharge current value.
In one embodiment of the present invention, the parameters in the lasso regression analysis model include: independent variables, dependent variables, weight parameters and regularization parameters; the values of the weight parameters are determined after training by the training set. For example, it is defined that the independent variable is x and the dependent variable is y, i.e. the measured actual value. β is a weight parameter, and for each x, there is a β corresponding to it, and the training result of machine learning is to obtain these β. λ is a regularization parameter, which is a fixed value, and is used for constraining the independent variable x and facilitating the solution of the equation, and the calculation formula and details thereof can be referred to in the prior art. The training process is as follows: obtaining a batch of real data, such as 500 sets or 1000 sets of corresponding x and y; substituting the lasso formula, setting a numerical evaluation index, having different choices and subtle differences, solving the equation, and finally obtaining the beta which is the training result. The process of prediction is as follows: for a new X, substituting the formula yields y. There may be many x, for example, one value every 30 seconds in 2 hours, i.e. 3600/30 × 2-240.
In an embodiment provided by the present invention, after the lasso regression analysis model is trained, the method further includes the step of verifying the trained lasso regression analysis model: dividing a verification data sample of the self-discharge current into a front section and a rear section according to time; inputting the front-stage verification data sample into the trained lasso regression analysis model to obtain a prediction current sequence corresponding to the rear-stage time; and determining that the deviation between the predicted current sequence in the later period of time and the later verification data sample is less than a deviation threshold value, and then passing the verification. Fig. 3 is a logic flow diagram for verifying a machine learning prediction model according to an embodiment of the present invention, specifically, as shown in fig. 3, a prediction is performed on data of 2 to 5 hours, and a prediction result is shown in fig. 4, and fig. 4 is a data diagram for verifying a machine learning prediction model according to an embodiment of the present invention: in the figure, the dotted line is a prediction curve, the solid line is an actual test curve, 360 points are predicted in total, the percentage of the average difference absolute value of the predicted value and the actual value to the measured value is 1.6%, and the accuracy of the predicted value reaches 98.4%. The minimum current deviation of the defective product and the good product is measured at the time of 2H, and is 22.52 percent and far larger than the predicted deviation of 1.6 percent. The prediction result can be used as the judgment standard of the self-discharge good product and the defective product.
The deviation threshold value is related to the deviation between the qualified current and the defective current of the lithium battery to be tested. In the above embodiment, the predicted deviation is 1.6%, the deviation of the minimum current between the defective product and the good product is 22.52%, and the difference between the two is large. If the set deviation threshold is too small, the determination of the lasso regression analysis model is not facilitated, but if the set deviation threshold is too large, the error of the self-discharge test is improved. Mathematically, the embodiment is mainly used for eliminating under-fitting and over-fitting phenomena caused by data training through data verification.
In one embodiment of the present invention, the first time point is 2 hours after the test is started. Fig. 5 is a current test curve diagram in the self-discharge detection of the lithium battery according to an embodiment of the present invention, and as can be seen from fig. 5, after the test is performed for 2H, a delamination phenomenon occurs at the beginning of the self-discharge current, and after 5 hours, the delamination is obvious, and a normal battery and a self-discharge poor battery can be distinguished, so that the first time point is set to be 2 hours after the test is started, which can significantly shorten the actual test time and obtain the characteristics of the self-discharge current.
In an embodiment provided by the present invention, there is also provided a lithium battery self-discharge detection apparatus, including: at least one processor; a memory coupled to the at least one processor; the memory stores instructions capable of being executed by the at least one processor, and the at least one processor implements the lithium battery self-discharge detection method by executing the instructions stored in the memory. The control module or processor herein has the functions of numerical calculation and logical operation, and it has at least a central processing unit CPU, a random access memory RAM, a read only memory ROM, various I/O ports and interrupt systems, etc. of data processing capability. Here, the control module or the control device may be, for example, a single chip, a chip, or a processor, which is commonly used hardware, and in a more commonly used case, the control module or the control device is a processor of an intelligent terminal or a PC. Here, when the apparatus is a PC, the foregoing embodiment is a software program running on the PC. When the device is a special electronic device, the functions are realized through a built-in single chip microcomputer or a PLC.
In an embodiment provided by the present invention, there is also provided a lithium battery self-discharge detection system, including: the data detection equipment is used for being connected with the lithium battery to be detected and acquiring first self-discharge current data of the lithium battery to be detected from the beginning of the test to a first time point in a self-discharge test environment; the data processing equipment comprises a data prediction module and a performance judgment module; the data prediction module is used for inputting the first self-discharge current data into a machine learning prediction model to obtain second self-discharge current data after a first time point of the lithium battery to be tested; and the performance judging module is used for judging the self-discharge performance of the lithium battery to be tested based on the second self-discharge current data.
For specific limitations of the lithium battery self-discharge detection system, reference may be made to the above limitations of the lithium battery self-discharge detection method, which are not described herein again. The various modules in the above-described system may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules. The data detection device can be a self-discharge detection device of the lithium battery, and the data processing device can be a self-discharge detection device of the lithium battery.
In an embodiment provided by the present invention, a computer-readable storage medium is further provided, where instructions are stored in the storage medium, and when executed by a processor, the instructions cause the processor to execute the foregoing lithium battery self-discharge detection method.
The embodiment of the invention provides a lithium battery self-discharge detection method aiming at the problem of long test time in the existing self-discharge test, and aiming at the problem that the self-discharge measurement needs to be kept still for more than 4 days to ensure the detection effectiveness, the invention provides a novel self-discharge detection method based on machine learning, on the premise of ensuring the same detection effectiveness, the detection time is greatly shortened, the production line investment and operation cost are reduced, and the product delivery cycle is shortened. The embodiment provided by the invention is applied to the self-discharge test of the battery.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that 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. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A lithium battery self-discharge detection method is characterized by comprising the following steps:
acquiring first self-discharge current data of a lithium battery from the beginning of a test to a first time point in a self-discharge test environment;
inputting the first self-discharge current data into a machine learning prediction model to obtain second self-discharge current data after a first time point of the lithium battery;
and judging the self-discharge performance of the lithium battery based on the second self-discharge current data.
2. The method of claim 1, wherein the self-discharge test environment comprises: connecting the lithium battery to be tested to a self-discharge detection circuit according to a self-discharge test specification; the self-discharge detection circuit includes: and the stabilized voltage power supply and the micro-ammeter are connected with the lithium battery to be tested in series.
3. The method according to claim 1, wherein the machine learning prediction model is a lasso regression analysis model, and parameters in the lasso regression analysis model are obtained after training by using a training set; the training set includes a number of data samples, the data samples including: the self-discharge current data of the lithium battery of the same type as the lithium battery from the test beginning to the first time point in the self-discharge test environment and/or the historical data of the self-discharge current of the lithium battery from the test beginning to the first time point in the self-discharge test environment before.
4. The method of claim 3, wherein the parameters in the lasso regression analysis model include: independent variables, dependent variables, weight parameters and regularization parameters; the values of the weight parameters are determined after training by the training set.
5. The method of claim 4, wherein after training the lasso regression analysis model, the method further comprises the step of validating the trained lasso regression analysis model:
dividing a verification data sample of the self-discharge current into a front section and a rear section according to the first time point;
inputting the front-stage verification data sample into the trained lasso regression analysis model to obtain a prediction current sequence corresponding to the rear-stage time;
and determining that the deviation between the predicted current sequence in the later period of time and the later verification data sample is less than a deviation threshold value, and then passing the verification.
6. The method of claim 5, wherein the deviation threshold is related to a deviation between a pass current and a fail current of the lithium battery.
7. The method of any one of claims 1 to 6, wherein the first time point is 2 hours after the start of the test.
8. A lithium battery self-discharge detection device, comprising:
at least one processor;
a memory coupled to the at least one processor;
the memory stores instructions executable by the at least one processor, and the at least one processor implements the lithium battery self-discharge detection method according to any one of claims 1 to 7 by executing the instructions stored in the memory.
9. A lithium battery self-discharge detection system, the system comprising:
the data detection equipment is used for being connected with the lithium battery to be detected and acquiring first self-discharge current data of the lithium battery from the test start to a first time point in a self-discharge test environment;
the data processing equipment comprises a data prediction module and a performance judgment module;
the data prediction module is used for inputting the first self-discharge current data into a machine learning prediction model to obtain second self-discharge current data after a first time point of the lithium battery;
and the performance judging module is used for judging the self-discharge performance of the lithium battery based on the second self-discharge current data.
10. A computer-readable storage medium having instructions stored therein, wherein the instructions, when executed by a processor, cause the processor to perform the lithium battery self-discharge detection method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010760423.9A CN111965545A (en) | 2020-07-31 | 2020-07-31 | Lithium battery self-discharge detection method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010760423.9A CN111965545A (en) | 2020-07-31 | 2020-07-31 | Lithium battery self-discharge detection method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111965545A true CN111965545A (en) | 2020-11-20 |
Family
ID=73363859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010760423.9A Pending CN111965545A (en) | 2020-07-31 | 2020-07-31 | Lithium battery self-discharge detection method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111965545A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112986850A (en) * | 2021-02-09 | 2021-06-18 | 北京车和家信息技术有限公司 | Calculation method and device for self-discharge parameter value and electric vehicle |
| CN113095000A (en) * | 2021-06-08 | 2021-07-09 | 蜂巢能源科技有限公司 | Method and device for obtaining battery cell discharge capacity, storage medium and electronic equipment |
| CN113311346A (en) * | 2021-05-19 | 2021-08-27 | 北京车和家信息技术有限公司 | Battery cell early warning method and device, cloud platform and storage medium |
| CN113359043A (en) * | 2021-08-09 | 2021-09-07 | 江苏时代新能源科技有限公司 | Method, device and equipment for detecting self-discharge current of battery cell and computer storage medium |
| CN115122933A (en) * | 2022-08-22 | 2022-09-30 | 中国第一汽车股份有限公司 | Electric automobile standing abnormity identification method and device |
| WO2023060394A1 (en) * | 2021-10-11 | 2023-04-20 | 宁德时代新能源科技股份有限公司 | Battery self-discharge detection method, and circuit and device |
| JP7501546B2 (en) | 2022-01-11 | 2024-06-18 | トヨタ自動車株式会社 | Battery inspection method and battery inspection system |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012141166A (en) * | 2010-12-28 | 2012-07-26 | Yokogawa Electric Corp | Self discharge defect detection device and self discharge defect detection method |
| CN105005002A (en) * | 2015-07-01 | 2015-10-28 | 清华大学 | Prediction method and system of cell residual discharge energy based on future voltage calculation |
| US20170153290A1 (en) * | 2015-11-30 | 2017-06-01 | Battelle Energy Alliance, Llc. | Systems and related methods for determining self-discharge currents and internal shorts in energy storage cells |
| CN106842051A (en) * | 2017-01-25 | 2017-06-13 | 天津市捷威动力工业有限公司 | A kind of screening technique of ternary system lithium-ion-power cell self discharge |
| CN107121643A (en) * | 2017-07-11 | 2017-09-01 | 山东大学 | Health state of lithium ion battery combined estimation method |
| CN108519556A (en) * | 2018-04-13 | 2018-09-11 | 重庆邮电大学 | A kind of lithium ion battery SOC prediction techniques based on Recognition with Recurrent Neural Network |
| CN109324294A (en) * | 2018-11-22 | 2019-02-12 | 联想(北京)有限公司 | Data processing method and its device |
| US20190113577A1 (en) * | 2017-10-17 | 2019-04-18 | The Board Of Trustees Of The Leland Stanford Junior University | Data-driven Model for Lithium-ion Battery Capacity Fade and Lifetime Prediction |
| CN109684302A (en) * | 2018-12-04 | 2019-04-26 | 平安科技（深圳）有限公司 | Data predication method, device, equipment and computer readable storage medium |
| CN110163380A (en) * | 2018-04-28 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Data analysing method, model training method, device, equipment and storage medium |
| CN110187291A (en) * | 2019-06-10 | 2019-08-30 | 天津普兰能源科技有限公司 | Lithium ion battery self discharge fast screening devices and screening technique based on DC impedance |
| CN209911514U (en) * | 2019-04-30 | 2020-01-07 | 蜂巢能源科技有限公司 | Self-discharge test system of battery |
| CN110935655A (en) * | 2019-11-15 | 2020-03-31 | 上海理工大学 | Self-discharge rapid screening method based on branch current change of parallel battery pack |
| CN111044928A (en) * | 2019-12-31 | 2020-04-21 | 福州大学 | Lithium battery health state estimation method |
| CN111157908A (en) * | 2020-01-09 | 2020-05-15 | 青岛特来电云科技有限公司 | Battery health degree prediction method based on big data machine learning |
-
2020
- 2020-07-31 CN CN202010760423.9A patent/CN111965545A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012141166A (en) * | 2010-12-28 | 2012-07-26 | Yokogawa Electric Corp | Self discharge defect detection device and self discharge defect detection method |
| CN105005002A (en) * | 2015-07-01 | 2015-10-28 | 清华大学 | Prediction method and system of cell residual discharge energy based on future voltage calculation |
| US20170153290A1 (en) * | 2015-11-30 | 2017-06-01 | Battelle Energy Alliance, Llc. | Systems and related methods for determining self-discharge currents and internal shorts in energy storage cells |
| CN106842051A (en) * | 2017-01-25 | 2017-06-13 | 天津市捷威动力工业有限公司 | A kind of screening technique of ternary system lithium-ion-power cell self discharge |
| CN107121643A (en) * | 2017-07-11 | 2017-09-01 | 山东大学 | Health state of lithium ion battery combined estimation method |
| US20190113577A1 (en) * | 2017-10-17 | 2019-04-18 | The Board Of Trustees Of The Leland Stanford Junior University | Data-driven Model for Lithium-ion Battery Capacity Fade and Lifetime Prediction |
| CN108519556A (en) * | 2018-04-13 | 2018-09-11 | 重庆邮电大学 | A kind of lithium ion battery SOC prediction techniques based on Recognition with Recurrent Neural Network |
| CN110163380A (en) * | 2018-04-28 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Data analysing method, model training method, device, equipment and storage medium |
| CN109324294A (en) * | 2018-11-22 | 2019-02-12 | 联想(北京)有限公司 | Data processing method and its device |
| CN109684302A (en) * | 2018-12-04 | 2019-04-26 | 平安科技（深圳）有限公司 | Data predication method, device, equipment and computer readable storage medium |
| CN209911514U (en) * | 2019-04-30 | 2020-01-07 | 蜂巢能源科技有限公司 | Self-discharge test system of battery |
| CN110187291A (en) * | 2019-06-10 | 2019-08-30 | 天津普兰能源科技有限公司 | Lithium ion battery self discharge fast screening devices and screening technique based on DC impedance |
| CN110935655A (en) * | 2019-11-15 | 2020-03-31 | 上海理工大学 | Self-discharge rapid screening method based on branch current change of parallel battery pack |
| CN111044928A (en) * | 2019-12-31 | 2020-04-21 | 福州大学 | Lithium battery health state estimation method |
| CN111157908A (en) * | 2020-01-09 | 2020-05-15 | 青岛特来电云科技有限公司 | Battery health degree prediction method based on big data machine learning |
Non-Patent Citations (4)
| Title |
|---|
| MAN-FAI NG: "Predicting the state of charge and health of batteries using data-driven machine learning", 《 NATURE MACHINE INTELLIGENCE》, 2 March 2020 (2020-03-02), pages 161 - 170 * |
| 唐子惠: "《医学人工智能导论》", 30 April 2020, pages: 140 - 145 * |
| 李敬兆: "基于模糊神经网络预测技术检测蓄电池剩余电量研究", 《煤矿机械》, no. 8, 31 August 2002 (2002-08-31), pages 21 - 24 * |
| 赵欣: "电动汽车锂电池荷电状态的研究与仿真", 《河北建筑工程学院学报》, vol. 35, no. 1, 31 March 2017 (2017-03-31), pages 117 - 121 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112986850A (en) * | 2021-02-09 | 2021-06-18 | 北京车和家信息技术有限公司 | Calculation method and device for self-discharge parameter value and electric vehicle |
| CN113311346A (en) * | 2021-05-19 | 2021-08-27 | 北京车和家信息技术有限公司 | Battery cell early warning method and device, cloud platform and storage medium |
| CN113311346B (en) * | 2021-05-19 | 2024-02-06 | 北京车和家信息技术有限公司 | Battery cell early warning method and device, cloud platform and storage medium |
| CN113095000A (en) * | 2021-06-08 | 2021-07-09 | 蜂巢能源科技有限公司 | Method and device for obtaining battery cell discharge capacity, storage medium and electronic equipment |
| CN113359043A (en) * | 2021-08-09 | 2021-09-07 | 江苏时代新能源科技有限公司 | Method, device and equipment for detecting self-discharge current of battery cell and computer storage medium |
| CN113359043B (en) * | 2021-08-09 | 2021-10-15 | 江苏时代新能源科技有限公司 | Method, device and equipment for detecting self-discharge current of battery cell and computer storage medium |
| WO2023060394A1 (en) * | 2021-10-11 | 2023-04-20 | 宁德时代新能源科技股份有限公司 | Battery self-discharge detection method, and circuit and device |
| JP7501546B2 (en) | 2022-01-11 | 2024-06-18 | トヨタ自動車株式会社 | Battery inspection method and battery inspection system |
| CN115122933A (en) * | 2022-08-22 | 2022-09-30 | 中国第一汽车股份有限公司 | Electric automobile standing abnormity identification method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111965545A (en) | Lithium battery self-discharge detection method, device and system | |
| CN111157897B (en) | Method and device for evaluating power battery, storage medium and processor | |
| CN116502112B (en) | New energy power supply test data management method and system | |
| CN111490304B (en) | Battery equalization enabling method and device, storage medium and battery pack | |
| CN112433898A (en) | Method and device for testing power consumption value of solid state disk, computer equipment and storage medium | |
| CN112213648B (en) | Method and device for judging balanced opening of battery cells | |
| KR20230129953A (en) | Method, device, apparatus, and storage medium for evaluating consistency of vehicle battery cell | |
| CN114935721B (en) | Lithium ion battery state-of-charge estimation method based on fiber bragg grating sensor | |
| CN103487696A (en) | Evaluation method and device for consistency of busbar temperature rise | |
| CN116203490A (en) | Sensor fault diagnosis method, device, equipment and storage medium | |
| JP5041442B2 (en) | Method for detecting state of power storage device | |
| Ren et al. | Novel strategy based on improved Kalman filter algorithm for state of health evaluation of hybrid electric vehicles Li-ion batteries during short-and longer term operating conditions | |
| Shi et al. | Determination of optimal indicators based on statistical analysis for the state of health estimation of a lithium-ion battery | |
| CN117054892B (en) | Evaluation method, device and management method for battery state of energy storage power station | |
| CN117310535A (en) | Battery abnormality judging method and device based on battery health state | |
| CN112230152B (en) | Method and system for measuring internal resistance increment of single battery cell | |
| CN109596927A (en) | Test method and test macro for battery management system BMS | |
| CN117554812A (en) | Battery thermal runaway early warning method, device, computing equipment and storage medium | |
| CN111190112B (en) | Battery charging and discharging prediction method and system based on big data analysis | |
| CN114924151A (en) | HIL system test system and test method | |
| CN113884785A (en) | Battery management system test method and storage medium | |
| CN113917347A (en) | Method for evaluating self-discharge standard of battery | |
| Olarte et al. | High Temperature VLRA Lead Acid Battery SOH Characterization Based on the Evolution of Open Circuit Voltage at Different States of Charge | |
| CN110221234A (en) | Examine the device and method of battery core monitoring unit sampling functions | |
| CN113030821A (en) | Electric quantity calibration method and device |
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 |