CN115275410A - Battery temperature rise abnormity early warning method - Google Patents
Battery temperature rise abnormity early warning method Download PDFInfo
- Publication number
- CN115275410A CN115275410A CN202210981495.5A CN202210981495A CN115275410A CN 115275410 A CN115275410 A CN 115275410A CN 202210981495 A CN202210981495 A CN 202210981495A CN 115275410 A CN115275410 A CN 115275410A
- Authority
- CN
- China
- Prior art keywords
- battery
- temperature rise
- warned
- data
- temperature
- 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
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/48—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte
- H01M10/486—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte for measuring temperature
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/4207—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells for several batteries or cells simultaneously or sequentially
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/425—Structural combination with electronic components, e.g. electronic circuits integrated to the outside of the casing
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/48—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte
- H01M10/482—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte for several batteries or cells simultaneously or sequentially
Landscapes
- Engineering & Computer Science (AREA)
- General Chemical & Material Sciences (AREA)
- Electrochemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Chemical & Material Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention relates to a battery temperature rise abnormity early warning method, which comprises a preparation stage and an actual measurement stage; the preparation phase comprises the following steps: step 1-1: acquiring various historical data of the battery and performing primary processing; step 1-2: performing characteristic engineering on the preliminarily processed historical data to obtain input data of a plurality of neural network algorithms; step 1-3: based on input data of a neural network algorithm, modeling by adopting the neural network algorithm to obtain a temperature rise prediction model for predicting the temperature of the battery; the actual measurement stage comprises the following steps: step 2-1: acquiring use data of the battery to be pre-warned, and predicting by using a temperature rise prediction model to obtain temperature data of the battery to be pre-warned for a period of time in the future; step 2-2: and obtaining an early warning index based on the temperature data of a period of time in the future, judging whether the temperature rise of the battery to be early warned is abnormal or not by using the early warning index, and early warning when the temperature rise is abnormal. The early warning method and the early warning device realize early warning of abnormal temperature rise of the battery in a period of time in the future, have foresight property and wide applicability.
Description
Technical Field
The invention belongs to the field of battery safety, and particularly relates to a battery temperature rise abnormity early warning method.
Background
In the prior art, the abnormal temperature rise of the battery is mainly detected by the sensor through detecting signals such as temperature, voltage and smoke in the battery, the current state of the battery can be judged only, and the battery has certain delay and cannot accurately predict the future state of the battery.
Disclosure of Invention
The invention aims to provide a battery temperature rise abnormity early warning method capable of predicting the future state of a battery so as to prospectively detect battery temperature rise abnormity
In order to achieve the purpose, the invention adopts the technical scheme that:
a battery temperature rise abnormity early warning method comprises a preparation stage and an actual measurement stage;
the preparation phase comprises the following steps:
step 1-1: acquiring various types of historical data of a battery similar to the battery to be pre-warned, and performing primary processing on the historical data;
step 1-2: performing characteristic engineering on the preliminarily processed historical data to obtain input data of a plurality of neural network algorithms;
step 1-3: based on the input data of the neural network algorithm, modeling the battery by adopting the neural network algorithm to obtain a temperature rise prediction model for predicting the temperature of the battery;
the actual measurement stage comprises the following steps:
step 2-1: acquiring various use data of the battery to be pre-warned, and predicting to obtain temperature data of the battery to be pre-warned for a period of time in the future by using the temperature rise prediction model;
step 2-2: and obtaining an early warning index based on the temperature data of the battery to be early warned in a period of time in the future, so as to judge whether the temperature rise of the battery to be early warned is abnormal or not by utilizing the early warning index, and early warning when the temperature rise of the battery to be early warned is abnormal.
In the steps 1-3, the neural network algorithm is an LSTM, GRU or transformer algorithm.
In the step 1-3, the neural network algorithm is integrated with battery parameter calculation, charge and discharge behavior accumulated data calculation and electrochemical parameter calculation related to the battery.
In the step 1-2, the input data of the neural network algorithm includes the highest voltage and the lowest voltage of the battery, the SOC of the battery, the current of the battery, the total voltage of the battery, the highest temperature and the lowest temperature of the battery.
In step 1-1, the preliminary processing of the historical data includes cleaning, analyzing, and sampling.
In the step 1-1, a sampling method adopted for sampling the historical data uses a logic of sampling a sample mixing rule.
In the step 2-1, the usage data of the battery to be pre-warned includes real-time charging and discharging data, a timestamp and charging and discharging behavior accumulated data.
In the step 2-2, the early warning index comprises a temperature variance of the battery to be early warned for a period of time in the future and/or a temperature rise rate of the battery to be early warned for a period of time in a sliding window; and if the temperature variance of the battery to be pre-warned in a period of time in the future is larger than a preset first threshold value and/or the rising rate of the temperature in the sliding window in a period of time is larger than a preset second threshold value, judging that the temperature rise of the battery to be pre-warned is abnormal.
The length of the sliding window is 25 to 35s.
The actual measurement phase further comprises the following steps:
step 2-3: and feeding back the early warning index and the abnormal temperature rise of the battery to be early warned to a battery big data platform as a prediction result to form a closed loop.
Due to the application of the technical scheme, compared with the prior art, the invention has the following advantages: the battery temperature rise early warning method based on the battery big data has the advantages that the battery temperature rise state in the future is predicted by utilizing a deep learning algorithm, and a series of temperature rise abnormal indexes are combined, so that the early warning of the battery temperature rise abnormality in a period of time in the future is realized, the method is prospective, wide in applicability, not limited to power batteries, and also applicable to energy storage batteries.
Drawings
Fig. 1 is a flowchart of a battery temperature rise abnormality warning method of the present invention.
Detailed Description
The invention will be further described with reference to examples of embodiments shown in the drawings.
The first embodiment is as follows: as shown in fig. 1, a battery temperature rise abnormality warning method provided for an electric vehicle battery includes a preparation stage and an actual measurement stage.
The preparation phase comprises the following steps:
step 1-1: and acquiring various types of historical data of the battery similar to the battery to be pre-warned from the battery big data platform, and performing primary processing on the historical data. The preliminary processing of the historical data includes cleaning, analysis and sampling, and the sampling method adopted for sampling the historical data uses the logic of sampling by a sample mixing rule.
Step 1-2: and performing characteristic engineering on the preliminarily processed historical data to obtain input data of a plurality of types of neural network algorithms. The resulting input data to the neural network algorithm includes the highest and lowest voltages of the battery, the SOC of the battery, the current of the battery, the total voltage of the battery, the highest and lowest temperatures of the battery.
Step 1-3: and modeling the battery by adopting a neural network algorithm based on the input data of the neural network algorithm to obtain a temperature rise prediction model for predicting the temperature of the battery. The neural network algorithm has various types, including LSTM, GRU and the like, and is suitable for predicting the battery temperature, and by combining the scheme, a transformer algorithm is adopted for modeling aiming at the length of a predicted time sequence: the transformer algorithm is a time series prediction neural network algorithm, and can accurately predict data change conditions in a long period of time in the future according to historical data, such as the temperature of a battery to be predicted in the patent. In order to adapt to the scene of the battery, the calculation of battery parameters (such as resistance), the calculation of charging and discharging behavior accumulated data (including accumulated driving mileage, accumulated charging time, accumulated charging electric quantity, accumulated discharging electric quantity, accumulated time distribution of the highest temperature interval of the battery, accumulated charging power interval distribution and the like) and the calculation of electrochemical parameters (such as charging and discharging depth, charging and discharging multiplying power and the like) related to the battery are integrated into the neural network algorithm, so that the transformer algorithm is modified slightly, and the performance is improved in the production environment of the patent.
The actual measurement stage comprises the following steps:
step 2-1: the method comprises the steps of obtaining various use data of a battery to be pre-warned, wherein the use data comprises real-time charging and discharging data, a timestamp, charging and discharging behavior accumulated data (including accumulated driving mileage, accumulated charging time, accumulated charging electric quantity, accumulated discharging electric quantity, accumulated battery highest temperature interval time distribution, accumulated charging power interval distribution and the like), and the like, and predicting and obtaining temperature data of the battery to be pre-warned for a period of time in the future by using a temperature rise prediction model.
Step 2-2: and obtaining an early warning index based on the temperature data of the battery to be early warned in a period of time in the future, so as to judge whether the temperature rise of the battery to be early warned is abnormal or not by utilizing the early warning index, and early warning when the temperature rise of the battery to be early warned is abnormal. The early warning index comprises the temperature variance of the battery to be early warned for a period of time in the future and/or the rising rate of the temperature of the battery to be early warned for a period of time in the sliding window. If the temperature variance of the battery to be warned in a future period of time is larger than a preset first threshold A and/or the rising rate of the temperature in a sliding window (the length of the sliding window is 25 to 35s, in the embodiment, the length of the sliding window is 30 s) in a period of time is larger than a preset second threshold B, it is determined that the temperature rise of the battery to be warned is abnormal. The first threshold value A and the second threshold value B are obtained through multiple experimental experiences.
Step 2-3: and feeding back the early warning index and whether the temperature rise of the battery to be early warned is abnormal as a prediction result to a battery big data platform to form a closed loop.
And (4) repeating the steps 2-1 to 2-3 to continuously warn the abnormal temperature rise of the battery to be warned.
Different from the traditional hardware early warning, the scheme fully utilizes battery big data, studies and judges future temperature rise abnormity, effectively extracts the characteristics of time dimension by adopting a transformer neural network algorithm, and accurately predicts a long sequence. The scheme has strong foresight, and the method can be applied to any battery.
The above embodiments are merely illustrative of the technical ideas and features of the present invention, and the purpose thereof is to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the protection scope of the present invention. All equivalent changes and modifications made according to the spirit of the present invention should be covered within the protection scope of the present invention.
Claims (10)
1. A battery temperature rise abnormity early warning method is characterized in that: the early warning method for the abnormal temperature rise of the battery comprises a preparation stage and an actual measurement stage;
the preparation phase comprises the following steps:
step 1-1: acquiring various types of historical data of a battery similar to the battery to be pre-warned, and performing primary processing on the historical data;
step 1-2: performing characteristic engineering on the preliminarily processed historical data to obtain input data of a plurality of neural network algorithms;
step 1-3: based on the input data of the neural network algorithm, modeling the battery by adopting the neural network algorithm to obtain a temperature rise prediction model for predicting the temperature of the battery;
the actual measurement stage comprises the following steps:
step 2-1: acquiring various use data of the battery to be pre-warned, and predicting to obtain temperature data of the battery to be pre-warned for a period of time in the future by using the temperature rise prediction model;
step 2-2: and obtaining an early warning index based on the temperature data of the battery to be early warned in a period of time in the future, so as to judge whether the temperature rise of the battery to be early warned is abnormal or not by utilizing the early warning index, and early warning when the temperature rise of the battery to be early warned is abnormal.
2. The battery temperature rise abnormality warning method according to claim 1, characterized in that: in the steps 1-3, the neural network algorithm is an LSTM, GRU or transformer algorithm.
3. The battery temperature-rise abnormality warning method according to claim 2, characterized in that: in the step 1-3, the neural network algorithm is integrated with battery parameter calculation, charge and discharge behavior accumulated data calculation and electrochemical parameter calculation related to the battery.
4. The battery temperature rise abnormality warning method according to claim 1, characterized in that: in the step 1-2, the input data of the neural network algorithm includes the highest voltage and the lowest voltage of the battery, the SOC of the battery, the current of the battery, the total voltage of the battery, the highest temperature and the lowest temperature of the battery.
5. The battery temperature rise abnormality warning method according to claim 1, characterized in that: in step 1-1, the preliminary processing of the historical data includes cleaning, analyzing, and sampling.
6. The battery temperature rise abnormality warning method according to claim 5, characterized in that: in the step 1-1, a sampling method adopted for sampling the historical data uses a logic of sampling a sample mixing rule.
7. The battery temperature rise abnormality warning method according to claim 1, characterized in that: in the step 2-1, the usage data of the battery to be pre-warned includes real-time charging and discharging data, a timestamp and charging and discharging behavior accumulated data.
8. The battery temperature rise abnormality warning method according to claim 1, characterized in that: in the step 2-2, the early warning index comprises a temperature variance of the battery to be early warned for a period of time in the future and/or a temperature rise rate of the battery to be early warned for a period of time in a sliding window; and if the temperature variance of the battery to be pre-warned in a period of time in the future is larger than a preset first threshold value and/or the rising rate of the temperature in the sliding window in a period of time is larger than a preset second threshold value, judging that the temperature rise of the battery to be pre-warned is abnormal.
9. The battery temperature rise abnormality warning method according to claim 8, characterized in that: the length of the sliding window is 25 to 35s.
10. The battery temperature rise abnormality warning method according to claim 1, characterized in that: the actual measurement phase further comprises the following steps:
step 2-3: and feeding back the early warning index and the abnormal temperature rise of the battery to be early warned to a battery big data platform as a prediction result to form a closed loop.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210981495.5A CN115275410A (en) | 2022-08-16 | 2022-08-16 | Battery temperature rise abnormity early warning method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210981495.5A CN115275410A (en) | 2022-08-16 | 2022-08-16 | Battery temperature rise abnormity early warning method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115275410A true CN115275410A (en) | 2022-11-01 |
Family
ID=83751244
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210981495.5A Pending CN115275410A (en) | 2022-08-16 | 2022-08-16 | Battery temperature rise abnormity early warning method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115275410A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116995276A (en) * | 2023-09-27 | 2023-11-03 | 爱德曼氢能源装备有限公司 | Cooling method and system for fuel cell power generation system |
CN117748019A (en) * | 2023-12-20 | 2024-03-22 | 深圳市助尔达电子科技有限公司 | Storage battery temperature monitoring management system |
-
2022
- 2022-08-16 CN CN202210981495.5A patent/CN115275410A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116995276A (en) * | 2023-09-27 | 2023-11-03 | 爱德曼氢能源装备有限公司 | Cooling method and system for fuel cell power generation system |
CN116995276B (en) * | 2023-09-27 | 2023-12-29 | 爱德曼氢能源装备有限公司 | Cooling method and system for fuel cell power generation system |
CN117748019A (en) * | 2023-12-20 | 2024-03-22 | 深圳市助尔达电子科技有限公司 | Storage battery temperature monitoring management system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Lipu et al. | A review of state of health and remaining useful life estimation methods for lithium-ion battery in electric vehicles: Challenges and recommendations | |
CN112092675B (en) | Battery thermal runaway early warning method, system and server | |
CN110794305B (en) | Power battery fault diagnosis method and system | |
CN110161414B (en) | Power battery thermal runaway online prediction method and system | |
CN115275410A (en) | Battery temperature rise abnormity early warning method | |
Hussein | Capacity fade estimation in electric vehicle li-ion batteries using artificial neural networks | |
Farmann et al. | A comprehensive review of on-board State-of-Available-Power prediction techniques for lithium-ion batteries in electric vehicles | |
CN103336248B (en) | Based on the cycle life of lithium ion battery Forecasting Methodology of cell degradation state model | |
Berecibar et al. | State of health estimation algorithm of LiFePO4 battery packs based on differential voltage curves for battery management system application | |
US8519674B2 (en) | Method for estimating battery degradation in a vehicle battery pack | |
Duan et al. | Deep neural network battery impedance spectra prediction by only using constant-current curve | |
Xu et al. | State-of-health estimation for lithium-ion batteries based on Wiener process with modeling the relaxation effect | |
CN111551860B (en) | Battery internal short circuit diagnosis method based on relaxation voltage characteristics | |
CN109604186A (en) | Power battery performance flexibility assesses method for separating | |
Sun et al. | Modified relative entropy-based lithium-ion battery pack online short-circuit detection for electric vehicle | |
EP3992648A1 (en) | Battery diagnosis device and method | |
CN113281671A (en) | Lithium ion battery remaining service life prediction method and system based on IGS-SVM | |
Liu et al. | Online health prognosis for lithium-ion batteries under dynamic discharge conditions over wide temperature range | |
CN116609676B (en) | Method and system for monitoring state of hybrid energy storage battery based on big data processing | |
KR102632198B1 (en) | Apparatus and method for predicting and managing force evolution over cycle in battery packs | |
Rui-hao et al. | Battery state of charge estimation for electric vehicle based on neural network | |
CN113447828A (en) | Lithium battery temperature estimation method and system based on Bayesian neural network | |
CN112363061A (en) | Thermal runaway risk assessment method based on big data | |
CN114646888A (en) | Assessment method and system for capacity attenuation of power battery | |
Diao et al. | Research on Electric Vehicle Charging Safety Warning Based on A-LSTM Algorithm |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication |