A method, device, computer program product, storage medium and electronic device for estimating the core temperature of a lithium-ion battery

Abstract

The present invention discloses a method, device, computer program product, storage medium and electronic device for estimating the core temperature of a lithium-ion battery. The method predicts the core temperature of the battery to be measured through a real-time core temperature prediction model to obtain a predicted value of the battery core temperature, and then inputs it into a real-time surface temperature prediction model to predict the surface temperature of the battery to be measured, obtaining a predicted value of the battery surface temperature; finally, combining the predicted value of the battery surface temperature and the measured surface temperature value, the predicted value of the battery core temperature is feedback-corrected through an extended Kalman filter to obtain an estimated value of the core temperature of the battery to be measured. The estimated value of the core temperature output by this method is basically consistent with the actual value, with small errors, and can well perform real-time online estimation of the core temperature of lithium-ion batteries, providing a basis for the battery thermal management technology. This method is beneficial to maintaining the best performance of the battery, and at the same time can prevent thermal runaway and improve the safety of the battery.

Description

Technical Field

[0001] The present invention belongs to the technical field of battery management, and particularly relates to a method, device, computer program product, storage medium and electronic device for estimating the core temperature of a lithium-ion battery. Background Art

[0002] Due to its high energy density, long cycle life and low self-discharge rate, lithium-ion batteries have become the first choice for energy storage systems such as electric vehicles and energy storage power stations. During the use of lithium-ion batteries, controlling the temperature of the lithium-ion batteries to work at the most suitable operating temperature can bring out their best performance and help avoid potential thermal runaway risks. Existing large-scale energy storage systems usually only install temperature sensors on the surface of lithium-ion batteries to obtain the surface temperature. With the increase in the size of lithium-ion batteries, for larger battery models such as 21700 and 26650, there is a large difference between the surface temperature and the core temperature of the battery. Monitoring only the surface temperature of the battery will cause thermal delay and underestimation of the actual temperature of the lithium-ion battery. In some fast-charging application scenarios of electric vehicles, the core temperature of lithium-ion batteries will rise sharply in a short period of time. If the battery management system only monitors the surface temperature of the lithium-ion battery, it may not be able to take external cooling measures in time, which will then cause thermal runaway or thermal spread of the lithium-ion battery. Therefore, estimating the core temperature of a lithium-ion battery based on the measurement of its surface temperature is an urgent problem to be solved in the application of lithium-ion batteries, which helps the safe application of energy storage systems. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a method for estimating the core temperature of a lithium-ion battery, which takes into account the non-linear and time-varying characteristics of the thermodynamics parameters in the lithium-ion battery temperature model and estimates the core temperature of the lithium-ion battery in real time.

[0004] A method for estimating the core temperature of a lithium-ion battery disclosed by the present invention includes the following steps:

[0005] Conduct a working condition experiment on the battery to be measured to obtain a measured data set, where the measured data set at least includes measured current data, measured surface temperature data and measured ambient temperature data;

[0006] Predict the core temperature of the battery to be measured through a real-time core temperature prediction model to obtain a predicted value of the battery core temperature;

[0007] Predict the surface temperature of the battery to be measured through a real-time surface temperature prediction model to obtain a predicted value of the battery surface temperature;

[0008] Combining the predicted battery surface temperature and the measured value of the battery surface temperature, feedback correction is performed on the predicted value of the battery core temperature through extended Kalman filtering to obtain an estimated value of the core temperature of the battery to be measured;

[0009] The real-time core temperature prediction model is constructed based on the state-dependent model;

[0010] The real-time surface temperature prediction model is constructed based on the state-dependent model and the coupling relationship between the core temperature and the surface temperature of the lithium-ion battery.

[0011] Furthermore, the real-time core temperature prediction model and the real-time surface temperature prediction model are obtained through the following steps:

[0012] S100. Construct a state model of the lithium-ion battery based on the autoregressive form of the state-dependent model:

[0013]

[0014] In the formula, T c is the core temperature of the lithium-ion battery, T a is the ambient temperature, I is the current of the lithium-ion battery, and φ 0,c , is a functional coefficient with respect to T c ;

[0015] S200. Determine φ 0,c ,

[0016] in the state model through a radial basis function neural network;

[0017]

[0018] In the formula, T s is the surface temperature of the lithium-ion battery, T c is the core temperature of the lithium-ion battery, T a is the ambient temperature, and φ 0,s , is a functional coefficient with respect to T s ;

[0019] S400. Determine φ 0,s ,

[0020] S500. Conduct dynamic condition experiments on lithium-ion batteries to obtain a data set; the data set includes at least current data, core temperature data, surface temperature data, and ambient temperature data.

[0021] S600. Use the data in the data set to determine all the parameters in the state model and the observation model through the gradient descent method, and obtain a real-time core temperature prediction model for predicting the core temperature of lithium-ion batteries and a real-time surface temperature prediction model for predicting the surface temperature of lithium-ion batteries.

[0022] Further, φ in step S200 0,c 、 is a functional coefficient; after being determined by a radial basis function neural network, φ 0,c 、 is as follows:

[0023]

[0024] In the formula,

[0025]

[0026] is the weight of the corresponding radial basis function neural network;

[0027] is the scaling factor of the corresponding radial basis function neural network;

[0028] is the center of the corresponding radial basis function neural network.

[0029] Further, φ in step S400 0,s 、 is a functional coefficient; after being determined by a radial basis function neural network, φ 0,s 、 is as follows:

[0030]

[0031] In the formula,

[0032] is the weight of the corresponding radial basis function neural network;

[0033] is the scaling factor of the corresponding radial basis function neural network;

[0034] is the center of the corresponding radial basis function neural network.

[0035] Further, the step S600 includes the following steps:

[0036] S610. Divide the data set into a training set and a test set;

[0037] S620. Use the data in the training set to determine all the parameters in the state model and the observation model through the gradient descent method;

[0038] S630. Use the data in the test set to verify the determined state model and the determined observation model. If the deviation value of the verification result is less than the set value, go to step S640; if the deviation value of the verification result is greater than the set value, return to step S620;

[0039] S640. The determined state model is a real-time core temperature prediction model; the determined observation model is a real-time surface temperature prediction model.

[0040] Another aspect of the present invention also provides a lithium-ion battery core temperature estimation device, and the device includes:

[0041] A first processing module, configured to obtain a measured data set of the dynamic working conditions experiment of the battery to be measured, and the measured data set at least includes measured current data, measured surface temperature data, and measured environmental temperature data;

[0042] A second processing module, configured to input the measured current data and the measured environmental temperature data into the real-time core temperature prediction model to predict the core temperature of the battery to be measured, and obtain a predicted value of the battery core temperature; then input it into the real-time surface temperature prediction model to predict the surface temperature of the battery to be measured, and obtain a predicted value of the battery surface temperature;

[0043] A third processing module, configured to combine the measured value of the battery surface temperature and the predicted value of the battery surface temperature; and perform feedback correction on the predicted value of the battery core temperature through an extended Kalman filter to obtain an estimated value of the core temperature of the battery to be measured.

[0044] Further, the real-time core temperature estimation model and the real-time surface temperature prediction model are obtained through training and optimization by a radial basis function neural network and the gradient descent method based on the current data, core temperature data, surface temperature data, and environmental temperature data of the lithium-ion battery under dynamic working conditions.

[0045] Another aspect of the present invention also provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the above-mentioned lithium-ion battery core temperature estimation method.

[0046] Another aspect of the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned lithium-ion battery core temperature estimation method is implemented.

[0047] Another aspect of the present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the above-mentioned lithium-ion battery core temperature estimation method is implemented.

[0048] The present invention has the following beneficial effects:

[0049] The lithium-ion battery core temperature estimation method provided by the present invention predicts the core temperature of the battery to be measured through a real-time core temperature prediction model obtained by constructing based on a state-dependent model, and obtains a predicted value of the battery core temperature. Then, it inputs the predicted value into a real-time surface temperature prediction model obtained by constructing based on a state-dependent model to predict the surface temperature of the battery to be measured, and obtains a predicted value of the battery surface temperature. Finally, by combining the predicted value of the battery surface temperature and the measured surface temperature value, the predicted value of the battery core temperature is feedback-corrected through an extended Kalman filter to obtain an estimated value of the core temperature. The core temperature value estimated by this method is basically consistent with the actual value, with a small error, and can well estimate the core temperature of the lithium-ion battery in real time, and has good robustness. The lithium-ion battery core temperature estimation method provided by the present invention enables the battery management system to sense the core temperature of the lithium-ion battery in real time, which is helpful for the thermal management of the battery management system, is beneficial for the battery to exert its best performance, and can prevent thermal runaway at the same time, improving the safety of the battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is one of the flowcharts for implementing the lithium-ion battery core temperature estimation method provided by some embodiments of the present invention.

[0051] Figure 2 is a schematic diagram of the data set collected by some embodiments of the present invention. (a) is a graph of the core temperature, surface temperature, and ambient temperature under working condition 1, (b) is a graph of the current under working condition 1; (c) is a graph of the core temperature, surface temperature, and ambient temperature under working condition 2, (d) is a graph of the current under working condition 2.

[0052] Figure 3 is a comparison graph of the predicted value of the core temperature, the predicted value of the surface temperature, and the true value provided by some embodiments of the present invention.

[0053] Figure 4 is a schematic diagram of the errors of the predicted value of the core temperature and the predicted value of the surface temperature provided by some embodiments of the present invention.

[0054] Figure 5It is the second flowchart for implementing the core temperature estimation method of a lithium-ion battery provided by some embodiments of the present invention.

[0055] Figure 6 It is a comparison chart of the estimated result and the true value obtained by the lithium-ion battery core temperature estimation method provided in Embodiment 1 of the present invention.

[0056] Figure 7 It is a comparison chart of the estimated result and the true value obtained by the lithium-ion battery core temperature estimation method provided in Embodiment 2 of the present invention.

[0057] Figure 8 It is a schematic diagram of the error of the estimated result obtained by the lithium-ion battery core temperature estimation method provided in Embodiment 2 of the present invention.

[0058] Figure 9 It is a comparison chart of the estimated result and the true value obtained by the lithium-ion battery core temperature estimation method provided in Embodiment 3 of the present invention.

[0059] Figure 10 It is a schematic diagram of the error of the estimated result obtained by the lithium-ion battery core temperature estimation method provided in Embodiment 3 of the present invention. Detailed implementation manners

[0060] In order to more clearly and completely describe the technical solution of the present invention, the present invention is further described in detail below through specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention, and various changes can be made within the scope defined by the rights of the present invention.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0062] Please refer to Figure 1 , the present invention provides a lithium-ion battery core temperature estimation method, and the method includes the following steps:

[0063] S010. Conduct a working condition experiment on the battery to be measured to obtain a measured data set, and the measured data set includes at least measured current data, measured surface temperature data, and measured ambient temperature data;

[0064] S011. Predict the core temperature of the battery to be measured through a real-time core temperature prediction model to obtain a predicted value of the battery core temperature;

[0065] S012. Predict the surface temperature of the battery to be measured through a real-time surface temperature prediction model, and obtain the predicted value of the battery surface temperature;

[0066] S013. Combine the predicted value of the battery surface temperature and the measured surface temperature value, and perform feedback correction on the predicted value of the battery core temperature through extended Kalman filtering to obtain the estimated value of the core temperature of the battery to be measured.

[0067] The real-time core temperature prediction model and the real-time surface temperature prediction model in the above lithium-ion battery core temperature estimation method are obtained through the following steps:

[0068] S100. Construct the following lithium-ion battery state model based on the autoregressive form of the state-dependent model:

[0069]

[0070] where T c is the core temperature of the lithium-ion battery, T a is the ambient temperature, I is the current of the lithium-ion battery, and φ 0,c 、 are functional coefficients with respect to T c ;

[0071] S200. Determine φ 0,c ,

[0072] φ 0,c , in the state model through a radial basis function neural network. Optionally, after being determined by the radial basis function neural network, φ 0,c , is as follows:

[0073]

[0074] where

[0075]

[0076] are the weights of the corresponding radial basis function neural network;

[0077] are the scaling factors of the corresponding radial basis function neural network;

[0078] are the centers of the corresponding radial basis function neural network.

[0079] S300. Construct the observation model of the lithium-ion battery based on the general form of the state-dependent model and the coupling relationship between the core temperature and the surface temperature of the lithium-ion battery;

[0080]

[0081] Wherein, T s is the surface temperature of the lithium-ion battery, T c is the core temperature of the lithium-ion battery, T a is the ambient temperature, φ 0,s 、 is a functional coefficient with respect to T s ;

[0082] S400. Determine φ in the state model through a radial basis function neural network 0,s ,

[0083] φ 0,s , is a functional coefficient; Optionally, φ in step S400 0,s , after being determined through a radial basis function neural network is:

[0084]

[0085] Wherein,

[0086] is the weight of the corresponding radial basis function neural network;

[0087] is the scaling factor of the corresponding radial basis function neural network;

[0088] is the center of the corresponding radial basis function neural network.

[0089] S500. Conduct dynamic working condition experiments on the lithium-ion battery to obtain a data set; Please refer to Figure 2 , the data set includes current data, core temperature data, surface temperature data, and ambient temperature data.

[0090] S600. Use the data in the data set to respectively determine all the parameters in the state model and the observation model through the gradient descent method, and obtain a real-time core temperature prediction model for predicting the core temperature of the lithium-ion battery and a real-time surface temperature prediction model for predicting the surface temperature of the lithium-ion battery.

[0091] Some embodiments provided by the present invention, step S600 includes the following steps:

[0092] S610. Divide the data set into a training set and a validation set;

[0093] S620. Use the data in the training set to determine all the parameters in the state model and the observation model respectively by the gradient descent method. Specifically, use the gradient descent method to optimize all the weights, scale factors, and centers in the state model and the observation model.

[0094] S630. Use the data in the test set to verify the optimized state model and observation model. If the deviation value of the verification result is less than the set value, go to step S640; if the deviation value of the verification result is greater than the set value, return to step S620.

[0095] S640. Determine the optimized state model as the real-time core temperature prediction model; determine the optimized observation model as the real-time surface temperature prediction model.

[0096] In this embodiment, the real-time core temperature prediction model and the real-time surface temperature prediction model obtained are combined to construct a system equation for online estimation of the lithium-ion core temperature:

[0097]

[0098] Please refer to Figure 2 , Figure 2 where a is the graph of the core temperature, surface temperature, and ambient temperature under working condition 1, Figure 2 b is the current graph under working condition 1; Figure 2 c is the graph of the core temperature, surface temperature, and ambient temperature under working condition 2, Figure 2 d is the current graph under working condition 2. In this embodiment, the data set under working condition 1 is selected as the training set to optimize the state model and the observation model. The data set under working condition 2 is used as the test set to verify the accuracy of the optimized state model and prediction model. Input the current data, surface temperature data, and ambient temperature data under working condition 2 into the above system equation to obtain the corresponding core temperature prediction value and surface temperature prediction value.

[0099] Please refer to Figure 3 for the comparison graph between the above core temperature prediction value and surface temperature prediction value and the true value; as can be seen from Figure 3 , the core temperature and surface temperature predicted by the state model and prediction model optimized by the training set in this embodiment are basically consistent with the true values.

[0100] Please refer to Figure 4 for the error between the above core temperature prediction value and surface temperature prediction value and the true value. As can be seen from Figure 4 , the positive and negative errors between the core temperature prediction value and the true value in this embodiment do not exceed 0.1 °C, and the positive and negative errors between the surface temperature prediction value and the true value do not exceed 0.3 °C, indicating that the state model and prediction model obtained in this embodiment have good accuracy.

[0101] Figure 5 It is the second flowchart for implementing the core temperature estimation method of a lithium-ion battery provided by some embodiments of the present invention. Please refer to Figure 5 , the core temperature estimation method of the lithium-ion battery provided by the present invention inputs the measured ambient temperature data and the measured current data of the battery to be measured into the determined state model to perform real-time core temperature prediction on the battery to be measured, obtaining core temperature prediction data. Then, the obtained core temperature prediction data is input into the determined observation model to obtain the predicted value of the real-time surface temperature of the battery; finally, by combining the predicted value of the battery surface temperature and the measured surface temperature value of the battery to be measured, the obtained core temperature prediction data is updated through the extended Kalman filter to obtain the estimated value of the core temperature of the battery to be measured, and finally this estimated value is output, and at the same time, it is recursively entered into the real-time core temperature estimation of the next moment.

[0102] Next, with reference to the accompanying drawings, the core temperature estimation method of the lithium-ion battery provided by the present invention will be described in detail with specific embodiments.

[0103] Embodiment 1

[0104] In this embodiment, the measured surface temperature, ambient temperature, and current in any selected set of measured data sets are input into the real-time core temperature prediction model and the real-time surface temperature prediction model to predict the core temperature and surface temperature of the battery to be measured, and the prediction results of the core temperature and surface temperature are feedback corrected through the extended Kalman filter to obtain the estimated value of the core temperature of the battery to be measured. Please refer to Figure 6 . The estimated value obtained by estimating the core temperature of the battery to be measured by the core temperature estimation method of the lithium-ion battery provided by the present invention is basically consistent with the true value, indicating that the estimation method provided by the present invention can accurately estimate the core temperature of the lithium-ion battery.

[0105] Embodiment 2

[0106] In this embodiment, when using the real-time core temperature prediction model and the real-time surface temperature prediction model to predict the core temperature and surface temperature of the battery to be measured, the wrong initial core temperature of 17 °C is used; please refer to Figure 7 , when the wrong initial core temperature of 17 °C is used, the wrong initial core temperature will calculate a wrong estimated value of the surface temperature, and thus there is an obvious difference from the actually measured surface temperature value. However, through the real-time core temperature prediction model and the real-time surface temperature prediction model established based on the state-dependent model in this method, and through the feedback correction of the extended Kalman filter, the wrong estimated core temperature value can be quickly corrected to near the actually measured value, indicating that the estimation method provided by the present invention has good robustness. Please refer to Figure 7, when estimating the battery under test using an incorrect initial value that is higher than the correct initial value, the positive and negative errors between the estimated result obtained by the lithium-ion battery core temperature estimation method and the true value do not exceed 0.2 °C, indicating that even when using an incorrect initial value, the estimation method provided by the present invention can still estimate the core temperature of the lithium-ion battery well.

[0107] Example 3

[0108] In this embodiment, when using the real-time core temperature prediction model and the real-time surface temperature prediction model to predict the core temperature and surface temperature of the battery under test, an incorrect initial core temperature of 0 °C was used; please refer to Figure 9 , even when estimating the battery under test using the incorrect initial value of 0 °C, through the real-time core temperature prediction model and the real-time surface temperature prediction model established based on the state-dependent model in this method, and through the extended Kalman filter for feedback correction, the incorrect core temperature estimation value can also be quickly corrected to near the actual measured value. Please refer to Figure 10 , when estimating the battery under test using an incorrect initial value that is lower than the correct initial value, the positive and negative errors between the estimated result obtained by the lithium-ion battery core temperature estimation method and the true value also do not exceed 0.2 °C.

[0109] Example 2 and Example 3 illustrate that regardless of whether a higher or lower incorrect initial value is used, the estimation method provided by the present invention can still accurately estimate the core temperature of the lithium-ion battery, and this estimation method has good robustness.

[0110] Another aspect of the present invention also provides a lithium-ion battery core temperature estimation device, which includes:

[0111] The first processing module is used to obtain the measured data set of the dynamic working conditions experiment of the battery under test, and the measured data set at least includes measured current data, measured surface temperature data, and measured environmental temperature data;

[0112] The second processing module is used to input the measured current data and the measured environmental temperature data into the real-time core temperature prediction model to predict the core temperature of the battery under test, and obtain the predicted value of the battery core temperature; then input it into the real-time surface temperature prediction model to predict the surface temperature of the battery under test, and obtain the predicted value of the battery surface temperature;

[0113] The third processing module is used to combine the measured value of the battery surface temperature and the predicted value of the battery surface temperature; and perform feedback correction on the predicted value of the battery core temperature through the extended Kalman filter to obtain the estimated value of the core temperature of the battery under test.

[0114] In some embodiments provided by the present invention, the real-time core temperature prediction model and the real-time surface temperature prediction model are obtained through training and optimization by a radial basis function neural network and the gradient descent method based on the current data, core temperature data, surface temperature data, and ambient temperature data of the lithium-ion battery under dynamic operating conditions.

[0115] Another aspect of the present invention also provides a computer program product, including a computer program, which when executed by a processor, implements the above-mentioned lithium-ion battery core temperature estimation method.

[0116] Another aspect of the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the above-mentioned lithium-ion battery core temperature estimation method.

[0117] Another aspect of the present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the above-mentioned lithium-ion battery core temperature estimation method when executing the program.

[0118] The above-described embodiments merely represent several implementation manners of the present invention, and their descriptions are relatively specific and detailed, but should not be construed as limiting the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent should be subject to the appended claims.

Claims

1. A method for estimating the core temperature of a lithium-ion battery, characterized in that: The following steps are involved: Performing a working condition experiment on the battery to be tested to obtain a measured data set, wherein the measured data set at least includes current measured data, surface temperature measured data, and ambient temperature measured data; The core temperature of the battery to be tested is predicted by a real-time core temperature prediction model to obtain a predicted value of the battery core temperature; The surface temperature of the battery to be tested is predicted by a real-time surface temperature prediction model to obtain a predicted value of the battery surface temperature; Combining the predicted value of the battery surface temperature with the measured value of the battery surface temperature, performing feedback correction on the predicted value of the battery core temperature through an extended Kalman filter to obtain an estimated value of the core temperature of the battery to be measured; The real-time core temperature prediction model is constructed based on a state-dependent model; The real-time surface temperature prediction model is constructed based on a state-dependent model and a coupling relationship between the core temperature and the surface temperature of the lithium-ion battery; The real-time core temperature prediction model and the real-time surface temperature prediction model are obtained by the following steps: S100, constructing the state model of lithium-ion batteries based on the autoregressive form of the state-dependent model: Where, T c is the core temperature of the lithium-ion battery, T a is the ambient temperature, I is the current of the lithium-ion battery, φ 0,c , It's about T c Functional coefficients of ; S200, determining φ in the state model by using a radial basis function neural network 0,c , S300, constructing an observation model of lithium-ion batteries based on the general form of the state-dependent model and the coupling relationship between the core temperature and the surface temperature of the lithium-ion battery: Where, T s is the surface temperature of the lithium-ion battery, T c is the core temperature of the lithium-ion battery, T a is the ambient temperature, φ 0,s , It's about T s Functional coefficients of ; S400, determining φ in the observation model by using a radial basis function neural network 0,s , S500, conducting a lithium-ion battery dynamic operating condition experiment to obtain a data set; the data set at least includes current data, core temperature data, surface temperature data, and ambient temperature data; S600: Using the data in the data set, all parameters in the state model and the observation model are determined by gradient descent method to obtain a real-time core temperature prediction model for lithium-ion battery core temperature prediction and a real-time surface temperature prediction model for lithium-ion battery surface temperature prediction.

2. A lithium-ion battery core temperature estimation method as claimed in claim 1, characterized in that: In step S200, φ 0,c , is a functional coefficient; 0,c , After being determined by the radial basis function neural network: In the formula, is the weight of the corresponding radial basis function neural network; is the scaling factor of the corresponding radial basis function neural network; is the center of the corresponding radial basis function neural network.

3. A lithium-ion battery core temperature estimation method as claimed in claim 1, characterized in that: In step S400, φ 0,s , is a functional coefficient; 0,s , After being determined by the radial basis function neural network: In the formula, is the weight of the corresponding radial basis function neural network; is the scaling factor of the corresponding radial basis function neural network; is the center of the corresponding radial basis function neural network.

4. A lithium-ion battery core temperature estimation method as claimed in claim 1, characterized in that: The step S600 includes the following steps: S610, dividing the data set into a training set and a test set; S620, using the data in the training set to determine all parameters in the state model and the observation model respectively by a gradient descent method; S630, using the data in the test set to verify the determined state model and the determined observation model, if the deviation value of the verification result is less than the set value, proceed to step S640; If the verification result deviation value is greater than the set value, return to step S620; S640: The determined state model is a real-time core temperature prediction model; and the determined observation model is a real-time surface temperature prediction model.

5. A lithium-ion battery core temperature estimation device, characterized in that: The device comprises: A first processing module is used to obtain a measured data set of a dynamic working condition experiment of a battery to be tested, wherein the measured data set at least includes current measured data, surface temperature measured data and ambient temperature measured data; The second processing module is used to input the current measured data and the ambient temperature measured data into the real-time core temperature prediction model to predict the core temperature of the battery to be tested, and obtain the battery core temperature prediction value; and then input it into the real-time surface temperature prediction model to predict the surface temperature of the battery to be tested, and obtain the battery surface temperature prediction value; The third processing module is used to combine the actual value of the battery surface temperature and the predicted value of the battery surface temperature; perform feedback correction on the predicted value of the battery core temperature through an extended Kalman filter to obtain an estimated value of the core temperature of the battery to be measured.

6. A lithium-ion battery core temperature estimation device as claimed in claim 5, characterized in that: The real-time core temperature prediction model and the real-time surface temperature prediction model are based on the current data, core temperature data, surface temperature data, and ambient temperature data of the dynamic working condition of the lithium-ion battery, and are obtained through radial basis function neural network and gradient descent method training and optimization.

7. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for estimating the core temperature of a lithium-ion battery as claimed in any one of claims 1 to 4 is implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for estimating the core temperature of a lithium-ion battery as claimed in any one of claims 1 to 4 is implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for estimating the core temperature of a lithium-ion battery as described in any one of claims 1 to 4 is implemented.

Images