CN113919222B - Online calculation method for internal temperature of battery pack - Google Patents
Online calculation method for internal temperature of battery pack Download PDFInfo
- Publication number
- CN113919222B CN113919222B CN202111175223.8A CN202111175223A CN113919222B CN 113919222 B CN113919222 B CN 113919222B CN 202111175223 A CN202111175223 A CN 202111175223A CN 113919222 B CN113919222 B CN 113919222B
- Authority
- CN
- China
- Prior art keywords
- battery pack
- battery
- temperature
- model
- heat generation
- 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.)
- Active
Links
- 238000004364 calculation method Methods 0.000 title claims abstract description 14
- 230000020169 heat generation Effects 0.000 claims abstract description 32
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000001816 cooling Methods 0.000 claims abstract description 14
- 239000000178 monomer Substances 0.000 claims abstract description 11
- 238000013528 artificial neural network Methods 0.000 claims abstract description 5
- 238000005259 measurement Methods 0.000 claims abstract description 5
- 238000012360 testing method Methods 0.000 claims description 27
- 210000004027 cell Anatomy 0.000 claims description 26
- 238000003062 neural network model Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 9
- 230000007613 environmental effect Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000010420 art technique Methods 0.000 description 1
- 239000000110 cooling liquid Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Secondary Cells (AREA)
Abstract
The invention provides an on-line calculation method for the internal temperature of a battery pack, which is mainly based on a power battery heat generation model and a neural network to calculate the internal multipoint temperature of the battery pack, wherein the input of the model is the external measurement point temperature of a battery and the terminal voltage and current of each monomer of the battery pack; outputting the temperature values including internal multiple points at other positions of the battery pack; the model is applicable to a battery pack with or without a cooling system. The method for calculating the internal temperature of the battery pack on line can better calculate the internal temperature of the battery pack and the temperature of each single battery in practical implementation.
Description
Technical Field
The invention belongs to the technical field of power battery management, and particularly relates to a method for realizing online calculation of internal temperature of a battery pack.
Background
The internal temperature of the battery pack is one of important monitoring parameters in the operation of the battery management system, and by monitoring the numerical value and the change rule of the battery pack, the temperature uniformity of the battery pack and the safety state of the battery pack can be directly obtained, and multi-dimensional data information can be provided for battery pack state estimation and life prediction. However, in the current real vehicles, temperature detection of the battery pack mostly only uses a temperature sensor to measure the temperature of the outer surface of the battery pack, but no omnibearing temperature detection can be performed on the interior of the battery pack and each battery cell, so that the obtained temperature information is not representative enough. And for the temperature calculation of the battery pack, the temperature calculation is stopped in off-line finite element simulation calculation, the calculated amount is extremely large, and the on-line application of a real vehicle is difficult to realize, so that the temperature monitoring inside the battery pack is not easy to be monitored. In some prior art techniques for estimating the core temperature of a battery, the core, the surface, and the air of the battery are considered as a mass point respectively to build a thermal model of the battery for estimating the core temperature of the battery, and although the internal single-point temperature can be estimated, the simultaneous calculation of the multi-point temperatures cannot be achieved.
Disclosure of Invention
Aiming at the technical problems in the art, the invention provides an on-line calculation method for the internal temperature of a battery pack, which specifically comprises the following steps:
Step S1, carrying out an open circuit voltage test on battery monomers to obtain an OCV-SOC curve and an entropy heat coefficient of the battery monomers, and establishing a heat generation model of the power battery by using test results to calculate the heat generation amount of each battery monomer;
s2, performing thermal characteristic test tests on the battery pack at different environmental temperatures and working conditions by using a plurality of temperature sensors arranged in the battery pack to obtain steady-state temperatures of the battery pack corresponding to different working conditions;
S3, taking the heat generation quantity, steady-state temperature, SOC of the battery pack and temperature values of certain external measurement points of a certain battery pack as model inputs, taking the temperatures of the rest positions of the battery pack including a plurality of points inside as model outputs, and establishing a battery pack internal temperature estimation neural network model;
S4, inputting the test data obtained in the steps S1 and S2 as a training set into the neural network model for training;
And S5, running the trained neural network model in the power battery management system, and carrying out real-time online calculation on the internal temperature of the battery pack by using the collected battery pack running data.
Further, the step S1 specifically includes:
S101, carrying out a small-current open-circuit voltage test on each battery cell to obtain an OCV-SOC curve of each battery cell;
step S102, keeping the battery cells under different SOC (state of charge) and changing the environmental temperature of the battery cells, measuring the open-circuit voltage change rule of the battery cells, and calculating to obtain the entropy coefficient of the battery cells;
and step S103, establishing a heat generation model of the power battery based on Bernardi battery heat generation theory by using the results obtained in the previous two steps.
Further, the step S2 specifically includes:
step S201, arranging temperature sensors among a plurality of battery cells in the battery pack during the grouping process;
And step 203, performing a plurality of thermal characteristic test tests on the battery pack under different temperatures and working conditions, recording data information such as voltage, current, internal multipoint temperature and the like, and if the cooling system is started, measuring and recording a steady-state temperature result of the battery pack under no current load after the cooling system is started.
Further, the step S3 specifically includes:
Step S301, establishing a BP neural network model aiming at the internal temperature estimation of the battery pack, and using tansig as an activation function and purelin and logsig as hidden layer functions;
Step S302, the model input is the battery pack heat generation amount, steady-state temperature, SOC and the acquisition value of a certain battery pack external temperature sensor in a period window, the temperatures of a plurality of points in the battery pack are model output, and the proper neuron number is given according to the length and the accuracy requirement of the window.
Further, the step S4 specifically includes:
Step S401, the test results obtained in the steps S1 and S2 are arranged, and the heat generation quantity of each battery cell is calculated by utilizing voltage and current data based on the established heat generation model;
step S402, giving parameters such as a proper gradient descent function, a learning rate, iteration times, target errors and the like of the neural network, taking input and output into a neural network model for training, and storing the trained model.
Further, the step S5 specifically includes:
Step S501, writing the trained model into a power battery management system;
Step S502, acquiring a battery cooling system state, acquiring voltage, current and external temperature information of a battery pack by using an acquisition module of a battery management system, calculating heat generation amount and inputting the heat generation amount into a trained neural network model;
And S503, acquiring a multi-point temperature estimation result in the battery pack on line in real time.
The method provided by the invention is mainly based on a power battery heat generation model and a neural network to calculate the multi-point temperature inside the battery pack, wherein the input of the model is the temperature of an external measurement point of the battery, and the terminal voltage and current of each single cell of the battery pack; outputting the temperature values including internal multiple points at other positions of the battery pack; the model is applicable to a battery pack with or without a cooling system. The method for calculating the internal temperature of the battery pack on line can better calculate the internal temperature of the battery pack and the temperature of each single battery in practical implementation.
Drawings
FIG. 1 is a schematic general flow chart of the method provided by the invention;
FIG. 2 is a graph showing the estimated internal point temperature for a cooling system on condition according to an embodiment of the present invention;
FIG. 3 is a corresponding internal point temperature estimation for a cooling system shutdown in accordance with an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention provides an on-line calculation method for the internal temperature of a battery pack, as shown in fig. 1, specifically comprising the following steps:
Step S1, carrying out an open circuit voltage test on battery monomers to obtain an OCV-SOC curve and an entropy heat coefficient of the battery monomers, and establishing a heat generation model of the power battery by using test results to calculate the heat generation amount of each battery monomer;
s2, performing thermal characteristic test tests on the battery pack at different environmental temperatures and working conditions by using a plurality of temperature sensors arranged in the battery pack to obtain steady-state temperatures of the battery pack corresponding to different working conditions;
S3, taking the heat generation quantity, steady-state temperature, SOC (state of charge) of the battery pack and temperature values of certain external measurement points of a certain battery pack as model inputs, taking a plurality of point temperatures in the battery pack as model outputs, and establishing a battery pack internal temperature estimation neural network model;
The steady-state temperature refers to the temperature of the battery pack after the steady-state temperature gradually reaches a certain difference value with the environment due to the temperature difference between the environment temperature and the cooling liquid under the condition that no heat source exists in the multi-point temperature.
S4, inputting the test data obtained in the steps S1 and S2 as a training set into the neural network model for training;
and S5, running the trained neural network model in the power battery management system, and carrying out real-time online calculation on the multipoint temperature inside the battery by using the collected battery pack running data.
In a preferred embodiment of the present invention, the step S1 specifically includes:
S101, carrying out a small-current open-circuit voltage test on each battery cell to obtain an OCV-SOC curve of each battery cell;
step S102, keeping the battery cells under different SOC (state of charge) and changing the environmental temperature of the battery cells, measuring the open-circuit voltage change rule of the battery cells, and calculating to obtain the entropy coefficient of the battery cells;
and step S103, establishing a heat generation model of the power battery based on Bernardi battery heat generation theory by using the results obtained in the previous two steps.
In a preferred embodiment of the present invention, the step S2 specifically includes:
step S201, arranging temperature sensors among a plurality of battery cells in the battery pack during the grouping process;
And step 203, performing a plurality of thermal characteristic test tests on the battery pack under different temperatures and working conditions, recording data information such as voltage, current, internal multipoint temperature and the like, and if the cooling system is started, measuring and recording a steady-state temperature result of the battery pack under no current load after the cooling system is started.
In a preferred embodiment of the present invention, the step S3 specifically includes:
Step S301, establishing a BP neural network model aiming at the internal temperature estimation of the battery pack, and using tansig as an activation function and purelin and logsig as hidden layer functions;
Step S302, the model input is the battery pack heat generation amount, steady-state temperature, SOC and the acquisition value of a certain battery pack external temperature sensor in a period window, the temperatures of a plurality of points in the battery pack are model output, and the proper neuron number is given according to the length and the accuracy requirement of the window.
In a preferred embodiment of the present invention, the step S4 specifically includes:
Step S401, the test results obtained in the steps S1 and S2 are arranged, and the heat generation quantity of each battery cell is calculated by utilizing voltage and current data based on the established heat generation model;
step S402, giving parameters such as a proper gradient descent function, a learning rate, iteration times, target errors and the like of the neural network, taking input and output into a neural network model for training, and storing the trained model.
In a preferred embodiment of the present invention, the step S5 specifically includes:
Step S501, writing the trained model into a power battery management system;
Step S502, acquiring a battery cooling system state, acquiring voltage, current and external temperature information of a battery pack by using an acquisition module of a battery management system, calculating heat generation amount and inputting the heat generation amount into a trained neural network model;
And S503, acquiring a multi-point temperature estimation result in the battery pack on line in real time.
In a specific example based on the invention, the battery pack is a 4-3 string ternary battery pack with the monomer capacity of 50Ah, a temperature sensor is arranged among a plurality of batteries in the battery pack, and the whole experimental process is completed in high-low temperature environment simulation equipment in order to keep the environmental factors stable. Fig. 2 and 3 show the corresponding internal point temperature estimates for the cooling system on and off, respectively, it being seen that the deviation between the estimates and the actual measured values remains at a more desirable level at all times.
It should be understood that, the sequence number of each step in the embodiment of the present invention does not mean that the execution sequence of each process should be determined by the function and the internal logic of each process, and should not limit the implementation process of the embodiment of the present invention.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (3)
1. An on-line calculation method for the internal temperature of a battery pack is characterized in that: the method specifically comprises the following steps:
Step S1, carrying out an open circuit voltage test on battery monomers to obtain an OCV-SOC curve and an entropy heat coefficient of the battery monomers, and establishing a heat generation model of the power battery by using test results to calculate the heat generation amount of each battery monomer; the method specifically comprises the following steps:
S101, carrying out a small-current open-circuit voltage test on each battery cell to obtain an OCV-SOC curve of each battery cell;
step S102, keeping the battery cells under different SOC (state of charge) and changing the environmental temperature of the battery cells, measuring the open-circuit voltage change rule of the battery cells, and calculating to obtain the entropy coefficient of the battery cells;
step S103, establishing a heat generation model of the power battery based on Bernardi battery heat generation theory by utilizing the results obtained in the previous two steps;
s2, performing thermal characteristic test tests on the battery pack at different environmental temperatures and working conditions by using a plurality of temperature sensors arranged in the battery pack to obtain steady-state temperatures of the battery pack corresponding to different working conditions; the method specifically comprises the following steps:
step S201, arranging temperature sensors among a plurality of battery cells in the battery pack during the grouping process;
Step S203, performing a plurality of thermal characteristic test tests on the battery pack under different temperatures and working conditions, recording voltage, current and internal multipoint temperature data information of the battery pack, and if a cooling system is started, measuring and recording a steady-state temperature result of the battery pack under no current load after the cooling system is started;
S3, taking the heat generation quantity, steady-state temperature, SOC of the battery pack and temperature values of certain external measurement points of a certain battery pack as model inputs, taking the temperatures of the rest positions of the battery pack including a plurality of points inside as model outputs, and establishing a battery pack internal temperature estimation neural network model; the method specifically comprises the following steps:
Step S301, establishing a BP neural network model aiming at the internal temperature estimation of the battery pack, and using tansig as an activation function and purelin and logsig as hidden layer functions;
Step S302, inputting a model into a collection value of battery pack heat generation amount, steady-state temperature, SOC and a certain battery pack external temperature sensor in a period of time window, wherein the temperatures of a plurality of points in the battery pack are output as the model, and the number of the proper neurons is given according to the length and the accuracy requirement of the window;
S4, inputting the test data obtained in the steps S1 and S2 as a training set into the neural network model for training;
and S5, running the trained neural network model in the power battery management system, and carrying out real-time online calculation on the multipoint temperature inside the battery by using the collected battery pack running data.
2. The method of claim 1, wherein: the step S4 specifically includes:
Step S401, the test results obtained in the steps S1 and S2 are arranged, and the heat generation quantity of each battery cell is calculated by utilizing voltage and current data based on the established heat generation model;
Step S402, giving a proper gradient descent function, a learning rate, iteration times and target error parameters of the neural network, taking the input and output into a neural network model for training, and storing the trained model.
3. The method of claim 2, wherein: the step S5 specifically includes:
Step S501, writing the trained model into a power battery management system;
Step S502, acquiring a battery cooling system state, acquiring voltage, current and external temperature information of a battery pack by using an acquisition module of a battery management system, calculating heat generation amount and inputting the heat generation amount into a trained neural network model;
And S503, acquiring a multi-point temperature estimation result in the battery pack on line in real time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111175223.8A CN113919222B (en) | 2021-10-09 | 2021-10-09 | Online calculation method for internal temperature of battery pack |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111175223.8A CN113919222B (en) | 2021-10-09 | 2021-10-09 | Online calculation method for internal temperature of battery pack |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113919222A CN113919222A (en) | 2022-01-11 |
CN113919222B true CN113919222B (en) | 2024-07-23 |
Family
ID=79238542
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111175223.8A Active CN113919222B (en) | 2021-10-09 | 2021-10-09 | Online calculation method for internal temperature of battery pack |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113919222B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115438588B (en) * | 2022-09-29 | 2023-05-09 | 中南大学 | Temperature prediction method, system, equipment and storage medium for lithium battery |
CN116306032B (en) * | 2023-05-17 | 2023-08-25 | 宁德时代新能源科技股份有限公司 | Temperature prediction method, device, equipment and storage medium |
CN117477105A (en) * | 2023-12-28 | 2024-01-30 | 浙江一舟电子科技股份有限公司 | Battery temperature monitoring method, device and medium for energy storage battery module |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109659637A (en) * | 2018-11-08 | 2019-04-19 | 北京交通大学 | The lithium ion battery low-temperature charging method of alternating current-direct current superposition |
CN110532600A (en) * | 2019-07-19 | 2019-12-03 | 北京航空航天大学 | A kind of power battery thermal management system and method |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7583059B2 (en) * | 2003-12-18 | 2009-09-01 | Lg Chem, Ltd. | Apparatus and method for estimating state of charge of battery using neural network |
CN110687462B (en) * | 2019-11-04 | 2020-09-04 | 北京理工大学 | Power battery SOC and capacity full life cycle joint estimation method |
CN112068000B (en) * | 2020-09-27 | 2022-03-11 | 哈尔滨工业大学(威海) | Peak power prediction method considering power battery durability influence |
-
2021
- 2021-10-09 CN CN202111175223.8A patent/CN113919222B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109659637A (en) * | 2018-11-08 | 2019-04-19 | 北京交通大学 | The lithium ion battery low-temperature charging method of alternating current-direct current superposition |
CN110532600A (en) * | 2019-07-19 | 2019-12-03 | 北京航空航天大学 | A kind of power battery thermal management system and method |
Also Published As
Publication number | Publication date |
---|---|
CN113919222A (en) | 2022-01-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113919222B (en) | Online calculation method for internal temperature of battery pack | |
Farmann et al. | A comprehensive review of on-board State-of-Available-Power prediction techniques for lithium-ion batteries in electric vehicles | |
CN107390127A (en) | A kind of SOC estimation method | |
Xu et al. | Hierarchical estimation model of state-of-charge and state-of-health for power batteries considering current rate | |
CN113447828B (en) | Lithium battery temperature estimation method and system based on Bayesian neural network | |
Sun et al. | Adaptive evolution enhanced physics-informed neural networks for time-variant health prognosis of lithium-ion batteries | |
CN112989690B (en) | Multi-time-scale state-of-charge estimation method for lithium battery of hybrid electric vehicle | |
Jafari et al. | Prediction of the battery state using the digital twin framework based on the battery management system | |
CN115267555A (en) | Battery SOH (State of health) evaluation system of energy storage system based on battery multipoint temperature measurement | |
CN112926186B (en) | Online estimation method for internal temperature of single super capacitor | |
CN114186437B (en) | Multi-physical field coupling degradation model order reduction method for reliability simulation analysis of power supply system | |
CN113702855A (en) | Lithium battery pack health state online prediction method based on multi-physical-field simulation and neural network | |
Xu et al. | State-of-charge estimation and health prognosis for lithium-ion batteries based on temperature-compensated Bi-LSTM network and integrated attention mechanism | |
Feng et al. | An adaptive state of charge estimation method of lithium-ion battery based on residual constraint fading factor unscented Kalman filter | |
CN113687251B (en) | Double-model-based lithium ion battery pack voltage abnormality fault diagnosis method | |
CN113109722B (en) | Multi-factor battery charging internal resistance modeling method integrating charging multiplying power | |
CN117330987B (en) | Method, system, medium and apparatus for time-based battery state of health assessment | |
CN113109726A (en) | Method for estimating internal resistance of lithium ion battery based on error compensation multi-factor dynamic internal resistance model | |
TWI810098B (en) | battery management device, battery management program | |
Sugashini et al. | Hybrid Deep Learning Algorithm for the State of Charge Prediction of the Lithium-Ion Battery for Electric Vehicles | |
CN116125284A (en) | Internal short circuit diagnosis method and system for lithium ion battery | |
CN116047339A (en) | Lithium ion battery pack SOC estimation method and device based on thermoelectric coupling model | |
Wang et al. | Thermal fault diagnosis method of Lithium battery based on LSTM and battery physical model | |
CN115986229A (en) | Method for judging health degree of battery based on charging segment data | |
CN114720901A (en) | Method for estimating health state of lithium ion battery |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |