CN114200335A - Battery health state prediction method and device based on pulse test - Google Patents
Battery health state prediction method and device based on pulse test Download PDFInfo
- Publication number
- CN114200335A CN114200335A CN202111478320.4A CN202111478320A CN114200335A CN 114200335 A CN114200335 A CN 114200335A CN 202111478320 A CN202111478320 A CN 202111478320A CN 114200335 A CN114200335 A CN 114200335A
- Authority
- CN
- China
- Prior art keywords
- battery
- neural network
- health
- state
- discharge
- 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
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]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
Abstract
The invention relates to a method and a device for predicting the state of health of a battery based on pulse testing, wherein the method comprises the following steps: obtaining internal parameters of a battery, and constructing a training set, a verification set and a test set according to the internal parameters of the battery; constructing a neural network, and training the neural network by using the training set and the verification set to obtain a trained neural network; and predicting the health state of the battery according to the trained neural network and the test set. The battery health state prediction method based on the pulse test improves the accuracy of battery health state prediction.
Description
Technical Field
The invention relates to the technical field of battery health state prediction, in particular to a battery health state prediction method and device based on pulse testing.
Background
The battery health state reflects the safety performance of the battery, the prediction of the battery health state has important significance, most of the existing battery health state prediction technologies predict the battery health state based on the current and the voltage of the battery, the current value and the voltage value of the battery need to be obtained and calculated, the algorithm is more, the calculation process is more complicated, and the prediction accuracy is difficult to guarantee.
Disclosure of Invention
In view of the above, it is desirable to provide a method and an apparatus for predicting a state of health of a battery based on a pulse test, so as to solve the problem of inaccurate prediction result of the state of health of the battery in the prior art.
In order to solve the above problems, the present invention provides a method for predicting a state of health of a battery based on a pulse test, comprising:
obtaining internal parameters of a battery, and constructing a training set, a verification set and a test set according to the internal parameters of the battery;
constructing a neural network, and training the neural network by using the training set and the verification set to obtain a trained neural network;
and predicting the health state of the battery according to the trained neural network and the test set.
Further, before obtaining the internal parameters of the battery, the method comprises the following steps:
and standing the battery for a first preset time, and performing charge-discharge circulation on the battery after standing to obtain the residual capacity of the battery.
Further, obtaining internal parameters of the battery comprises:
and acquiring the residual capacity, the rated capacity and the open-circuit voltage of the battery.
Further, a training set, a validation set and a test set are constructed according to the internal parameters of the battery, and the method comprises the following steps:
obtaining a standard voltage according to the open-circuit voltage of the battery, charging or discharging the battery until the standard voltage is reached, when the standard voltage is greater than a first set threshold value, performing pulse discharge on the battery by using a first preset current to obtain a voltage before and after starting discharge and a voltage before discharge cutoff, and obtaining an ohmic internal resistance and a polarization internal resistance of the battery according to the voltage before and after starting discharge and the voltage before discharge cutoff;
when the standard voltage is smaller than a first set threshold value, pulse charging is carried out on the battery by using first preset current, voltage before and after charging is started and voltage before charging is cut off are obtained, and ohmic internal resistance and polarization resistance of the battery are obtained according to the voltage before and after charging is started and the voltage before charging is cut off;
discharging the battery after pulse charging or pulse discharging by using a second preset current until the voltage variation of the battery reaches a second set threshold value, acquiring a discharging time and a discharging voltage platform, and obtaining the discharging capacity of the battery according to the discharging time and the second preset current;
obtaining the health state of the battery according to the residual capacity and the rated capacity of the battery;
and constructing a training set, a verification set and a test set by using the health state of the battery, the ohmic internal resistance, the polarization internal resistance, the discharge capacity and the discharge voltage platform of the battery.
Further, obtaining the discharge capacity of the battery according to the discharge time and the second preset current, including:
obtaining the discharge capacity of the battery by using a battery discharge capacity calculation formula, the discharge time and the second preset current, wherein the battery discharge capacity calculation formula isWherein, Q is the discharge capacity of the battery, I is a second preset current, and t is the discharge time.
Further, obtaining a battery state of health from the remaining capacity and the rated capacity of the battery includes:
and obtaining the battery health state by utilizing a battery health state calculation formula and the residual capacity and the rated capacity of the battery.
Further, comprising:
the battery state of health calculation formula isWherein Q is1Is the residual capacity, Q, of the battery0The SOH is the state of health of the battery, which is the rated capacity of the battery.
Further, constructing a neural network, comprising:
and constructing a BP neural network, wherein the BP neural network comprises an input layer, a hidden layer and an output layer.
Further, training the neural network using the training set and the validation set, comprising:
and taking the ohmic internal resistance, the polarization internal resistance, the discharge capacity and the discharge voltage platform of the battery as the input of the neural network, and taking the health state of the battery as the output of the neural network.
The invention also provides a battery health state prediction device based on the pulse test, which comprises a data acquisition module, a network training module and a state prediction module;
the data acquisition module is used for acquiring internal parameters of the battery and constructing a training set, a verification set and a test set according to the internal parameters of the battery;
the network training module is used for constructing a neural network, and training the neural network by using the training set and the verification set to obtain a trained neural network;
and the state prediction module is used for predicting the health state of the battery according to the trained neural network and the test set.
The beneficial effects of adopting the above embodiment are: according to the battery health state prediction method based on the pulse test, the internal parameters of the battery are obtained, the training set, the verification set and the test set are constructed according to the internal parameters of the battery, the neural network is constructed, the neural network is trained by using the training set and the verification set, the battery health state prediction is carried out according to the trained neural network and the test set, and the accuracy of the battery health state prediction is improved.
Drawings
FIG. 1 is a schematic flow chart illustrating a method for predicting a state of health of a battery based on a pulse test according to an embodiment of the present invention;
fig. 2 is a block diagram of a battery state of health prediction apparatus based on pulse testing according to an embodiment of the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
The invention provides a method and a device for predicting the state of health of a battery based on pulse test, which are respectively explained in detail below.
The embodiment of the invention provides a battery health state prediction method based on a pulse test, which has a flow schematic diagram, as shown in fig. 1, and comprises the following steps:
s101, obtaining internal parameters of a battery, and constructing a training set, a verification set and a test set according to the internal parameters of the battery;
step S102, constructing a neural network, and training the neural network by using the training set and the verification set to obtain a trained neural network;
and S103, predicting the health state of the battery according to the trained neural network and the test set.
In a specific embodiment, the appearance of the battery is detected, and the battery with bulges, liquid leakage and deformation in the appearance is removed.
As a preferred embodiment, before acquiring the internal parameters of the battery, the method includes:
and standing the battery for a first preset time, and performing charge-discharge circulation on the battery after standing to obtain the residual capacity of the battery.
In a particular embodiment, the first predetermined time is greater than or equal to 24 hours.
As a preferred embodiment, acquiring internal parameters of the battery comprises:
and acquiring the residual capacity, the rated capacity and the open-circuit voltage of the battery.
As a preferred embodiment, constructing a training set, a validation set and a test set according to the internal parameters of the battery includes:
obtaining a standard voltage according to the open-circuit voltage of the battery, charging or discharging the battery until the standard voltage is reached, when the standard voltage is greater than a first set threshold value, performing pulse discharge on the battery by using a first preset current to obtain a voltage before and after starting discharge and a voltage before discharge cutoff, and obtaining an ohmic internal resistance and a polarization internal resistance of the battery according to the voltage before and after starting discharge and the voltage before discharge cutoff;
when the standard voltage is smaller than a first set threshold value, pulse charging is carried out on the battery by using first preset current, voltage before and after charging is started and voltage before charging is cut off are obtained, and ohmic internal resistance and polarization resistance of the battery are obtained according to the voltage before and after charging is started and the voltage before charging is cut off;
discharging the battery after pulse charging or pulse discharging by using a second preset current until the voltage variation of the battery reaches a second set threshold value, acquiring a discharging time and a discharging voltage platform, and obtaining the discharging capacity of the battery according to the discharging time and the second preset current;
obtaining the health state of the battery according to the residual capacity and the rated capacity of the battery;
and constructing a training set, a verification set and a test set by using the health state of the battery, the ohmic internal resistance, the polarization internal resistance, the discharge capacity and the discharge voltage platform of the battery.
In a specific embodiment, the average value of the open-circuit voltage of the battery is calculated to obtain a standard voltage, and the battery is charged or discharged until the standard voltage is reached, when the standard voltage is greater than the standard voltageAt 3.7V, pulse discharging the battery by using the current of 3-5C, standing for 1 minute to obtain the voltage U1 before starting discharging, the voltage U2 after starting discharging and the voltage U3 before stopping discharging, wherein the ohmic internal resistance of the battery isThe internal polarization resistance of the battery is
When the standard voltage is less than 3.7V, pulse charging is carried out on the battery by using the current of 3-5C, the battery is kept stand for 1 minute, the voltage U4 before the charging is started, the voltage U5 after the charging is started and the voltage U6 before the charging is cut off are obtained, and the ohmic internal resistance of the battery isThe internal polarization resistance of the battery is
The second predetermined current is 0.3-1C, and the second predetermined threshold is 0.2-0.5V.
As a preferred embodiment, obtaining the discharge capacity of the battery according to the discharge time and the second preset current includes:
obtaining the discharge capacity of the battery by using a battery discharge capacity calculation formula, the discharge time and the second preset current, wherein the battery discharge capacity calculation formula isWherein, Q is the discharge capacity of the battery, I is a second preset current, and t is the discharge time.
As a preferred embodiment, obtaining the state of health of the battery according to the remaining capacity and the rated capacity of the battery includes:
and obtaining the battery health state by utilizing a battery health state calculation formula and the residual capacity and the rated capacity of the battery.
As a preferred embodiment, comprising:
the battery state of health calculation formula isWherein Q is1Is the residual capacity, Q, of the battery0The SOH is the state of health of the battery, which is the rated capacity of the battery.
As a preferred embodiment, a neural network is constructed, comprising:
and constructing a BP neural network, wherein the BP neural network comprises an input layer, a hidden layer and an output layer.
As a preferred embodiment, training the neural network using the training set and the validation set includes:
and taking the ohmic internal resistance, the polarization internal resistance, the discharge capacity and the discharge voltage platform of the battery as the input of the neural network, and taking the health state of the battery as the output of the neural network.
The embodiment of the invention provides a battery health state prediction device based on a pulse test, which has a structural block diagram, as shown in fig. 2, and comprises a data acquisition module 201, a network training module 202 and a state prediction module 203;
the data acquisition module 201 is configured to acquire internal parameters of a battery, and construct a training set, a verification set, and a test set according to the internal parameters of the battery;
the network training module 202 is configured to construct a neural network, train the neural network by using the training set and the verification set, and obtain a trained neural network;
the state prediction module 203 is configured to predict the state of health of the battery according to the trained neural network and the test set.
In summary, according to the battery health status prediction method and device based on the pulse test, the internal parameters of the battery are obtained, the training set, the verification set and the test set are constructed according to the internal parameters of the battery, the neural network is constructed, the training set and the verification set are used for training the neural network, the battery health status prediction is performed according to the trained neural network and the test set, and the accuracy of the battery health status prediction is improved.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (10)
1. A battery state of health prediction method based on pulse test is characterized by comprising the following steps:
obtaining internal parameters of a battery, and constructing a training set, a verification set and a test set according to the internal parameters of the battery;
constructing a neural network, and training the neural network by using the training set and the verification set to obtain a trained neural network;
and predicting the health state of the battery according to the trained neural network and the test set.
2. The pulse test-based battery state of health prediction method of claim 1, wherein obtaining the internal parameters of the battery is preceded by:
and standing the battery for a first preset time, and performing charge-discharge circulation on the battery after standing to obtain the residual capacity of the battery.
3. The pulse test-based battery state of health prediction method of claim 2, wherein obtaining internal parameters of the battery comprises:
and acquiring the residual capacity, the rated capacity and the open-circuit voltage of the battery.
4. The method of claim 3, wherein constructing a training set, a validation set, and a test set based on the internal parameters of the battery comprises:
obtaining a standard voltage according to the open-circuit voltage of the battery, charging or discharging the battery until the standard voltage is reached, when the standard voltage is greater than a first set threshold value, performing pulse discharge on the battery by using a first preset current to obtain a voltage before and after starting discharge and a voltage before discharge cutoff, and obtaining an ohmic internal resistance and a polarization internal resistance of the battery according to the voltage before and after starting discharge and the voltage before discharge cutoff;
when the standard voltage is smaller than a first set threshold value, pulse charging is carried out on the battery by using first preset current, voltage before and after charging is started and voltage before charging is cut off are obtained, and ohmic internal resistance and polarization resistance of the battery are obtained according to the voltage before and after charging is started and the voltage before charging is cut off;
discharging the battery after pulse charging or pulse discharging by using a second preset current until the voltage variation of the battery reaches a second set threshold value, acquiring a discharging time and a discharging voltage platform, and obtaining the discharging capacity of the battery according to the discharging time and the second preset current;
obtaining the health state of the battery according to the residual capacity and the rated capacity of the battery;
and constructing a training set, a verification set and a test set by using the health state of the battery, the ohmic internal resistance, the polarization internal resistance, the discharge capacity and the discharge voltage platform of the battery.
5. The method for predicting the state of health of the battery based on the pulse test as claimed in claim 4, wherein obtaining the discharge capacity of the battery according to the discharge time and the second preset current comprises:
obtaining the discharge capacity of the battery by using a battery discharge capacity calculation formula, the discharge time and the second preset current, wherein the battery discharge capacity calculation formula isWherein, Q is the discharge capacity of the battery, I is a second preset current, and t is the discharge time.
6. The pulse test-based battery state of health prediction method of claim 4, wherein deriving the battery state of health from the remaining capacity and the rated capacity of the battery comprises:
and obtaining the battery health state by utilizing a battery health state calculation formula and the residual capacity and the rated capacity of the battery.
8. The pulse test-based battery state of health prediction method of claim 1, wherein constructing a neural network comprises:
and constructing a BP neural network, wherein the BP neural network comprises an input layer, a hidden layer and an output layer.
9. The pulse test-based battery state of health prediction method of claim 4, wherein training the neural network with the training set and the validation set comprises:
and taking the ohmic internal resistance, the polarization internal resistance, the discharge capacity and the discharge voltage platform of the battery as the input of the neural network, and taking the health state of the battery as the output of the neural network.
10. A battery health state prediction device based on pulse test is characterized by comprising a data acquisition module, a network training module and a state prediction module;
the data acquisition module is used for acquiring internal parameters of the battery and constructing a training set, a verification set and a test set according to the internal parameters of the battery;
the network training module is used for constructing a neural network, and training the neural network by using the training set and the verification set to obtain a trained neural network;
and the state prediction module is used for predicting the health state of the battery according to the trained neural network and the test set.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111478320.4A CN114200335A (en) | 2021-12-06 | 2021-12-06 | Battery health state prediction method and device based on pulse test |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111478320.4A CN114200335A (en) | 2021-12-06 | 2021-12-06 | Battery health state prediction method and device based on pulse test |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114200335A true CN114200335A (en) | 2022-03-18 |
Family
ID=80650721
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111478320.4A Pending CN114200335A (en) | 2021-12-06 | 2021-12-06 | Battery health state prediction method and device based on pulse test |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114200335A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024036432A1 (en) * | 2022-08-15 | 2024-02-22 | 宁德时代新能源科技股份有限公司 | Direct current resistance measurement method for battery, system, device, and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108009585A (en) * | 2017-12-01 | 2018-05-08 | 国网山东省电力公司信息通信公司 | Lead-acid battery health status Forecasting Methodology based on local message fusion |
US20190049518A1 (en) * | 2016-11-21 | 2019-02-14 | Huazhong University Of Science And Technology | Method and device for monitoring state of charge and state of health of lithium-ion battery |
CN111366848A (en) * | 2019-12-31 | 2020-07-03 | 安徽师范大学 | Battery health state prediction method based on PSO-ELM algorithm |
CN112686380A (en) * | 2020-12-28 | 2021-04-20 | 江苏宝航能源技术有限公司 | Neural network-based echelon power cell consistency evaluation method and system |
CN113567861A (en) * | 2021-07-06 | 2021-10-29 | 上海电机学院 | Estimation method for health state of power battery |
-
2021
- 2021-12-06 CN CN202111478320.4A patent/CN114200335A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190049518A1 (en) * | 2016-11-21 | 2019-02-14 | Huazhong University Of Science And Technology | Method and device for monitoring state of charge and state of health of lithium-ion battery |
CN108009585A (en) * | 2017-12-01 | 2018-05-08 | 国网山东省电力公司信息通信公司 | Lead-acid battery health status Forecasting Methodology based on local message fusion |
CN111366848A (en) * | 2019-12-31 | 2020-07-03 | 安徽师范大学 | Battery health state prediction method based on PSO-ELM algorithm |
CN112686380A (en) * | 2020-12-28 | 2021-04-20 | 江苏宝航能源技术有限公司 | Neural network-based echelon power cell consistency evaluation method and system |
CN113567861A (en) * | 2021-07-06 | 2021-10-29 | 上海电机学院 | Estimation method for health state of power battery |
Non-Patent Citations (1)
Title |
---|
高敬鹏: "《深度学习 卷积神经网络技术与实践》", 机械工业出版社, pages: 45 - 46 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024036432A1 (en) * | 2022-08-15 | 2024-02-22 | 宁德时代新能源科技股份有限公司 | Direct current resistance measurement method for battery, system, device, and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109557477B (en) | Battery system health state estimation method | |
CN102253343B (en) | Method for estimating state of health and state of charge of storage battery | |
US20190128931A1 (en) | Method, a non-transitory storage medium and a battery grading apparatus for automatically grading a lithium-ion battery | |
CN104656021B (en) | The predictor method and device of a kind of remaining battery capacity | |
EP4174505A1 (en) | Battery state determination method, and battery state determination apparatus | |
CN114578237A (en) | Method, system and equipment for rapidly estimating health state of lithium ion battery based on constant-current charging time | |
CN110888074B (en) | Voltage determination method and device for SOC initial value calculation | |
CN116381541B (en) | Health assessment method and system for energy storage lithium battery system | |
CN110888065B (en) | Battery pack state of charge correction method and device | |
CN110988723B (en) | LSTM-based battery internal resistance prediction and fault early warning method | |
CN110857035B (en) | Method and device for determining charging remaining time and electric vehicle | |
CN104335057A (en) | Method and device for determining the actual capacity of a battery | |
CN114200335A (en) | Battery health state prediction method and device based on pulse test | |
EP4446759A1 (en) | Battery capacity determination method and apparatus, and storage medium | |
CN112285583A (en) | Method, device and system for testing maximum capacity of battery cell | |
CN114609523A (en) | Online battery capacity detection method, electronic equipment and storage medium | |
JP2018009963A (en) | Simulation method and simulation device | |
CN113665436B (en) | Battery management method and device | |
KR100844040B1 (en) | Charging battery capacity verification method | |
CN115561636A (en) | Method and system for estimating effective capacity of super-capacitor energy storage system | |
CN114814604A (en) | Battery soc estimation method and device | |
CN115291111B (en) | Training method of battery rest time prediction model and rest time prediction method | |
CN114624596B (en) | Method and device for evaluating battery performance | |
CN114035065B (en) | Battery stress safety threshold value obtaining method, device and storage medium | |
CN114355213B (en) | Data set construction method and device for lithium ion battery state of charge estimation |
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 |