Battery cell data processing method, device and equipment of lithium ion battery and medium

Abstract

The invention provides a lithium ion battery cell data processing method and device, equipment and a medium. The method comprises the following steps: acquiring test data under a plurality of test working conditions; constructing a back-propagation neural network of the lithium ion battery, and positively inputting the test data into the back-propagation neural network to obtain predicted voltages of the lithium ion battery under various test conditions; determining voltage change information of the lithium ion battery according to the predicted voltage; inputting the voltage change information and the test data into an equivalent circuit model for preliminary offline identification to obtain an initial cell internal resistance parameter; reversely inputting the initial cell internal resistance parameter into a back-propagation neural network, forwardly inputting the test data into the back-propagation neural network, and correcting the model parameter by the back-propagation neural network to obtain a target back-propagation neural network; and inputting the battery data of the to-be-identified battery into the target back propagation neural network, and predicting to obtain the cell internal resistance parameter of the to-be-identified battery, so as to improve the identification efficiency and precision of the cell internal resistance parameter.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a method, device, equipment and medium for processing cell data of a lithium-ion battery. Background Art

[0002] Lithium-ion batteries are the key to new energy vehicles and their energy storage systems. The accuracy of identifying characteristic parameters such as internal resistance, voltage change and state of charge (SOC) will directly affect the external engineering performance of lithium-ion batteries. The electrochemical reaction rate of the battery will be significantly reduced in a low temperature environment, which will increase the internal polarization of the battery, resulting in the capacity decay and power performance reduction of the lithium-ion battery. The rapid changes in battery performance under a wide temperature range limit the accuracy of existing parameter identification algorithms, and it is difficult to simulate battery performance at low temperatures. In addition, the internal resistance parameters of the battery can also be used to simulate and predict the current-voltage characteristics and life capacity of new battery materials. The accuracy of battery internal resistance identification often determines the accuracy and consistency of the initial parameters of the energy storage battery pack, and ultimately affects the safety and service life of the entire energy storage system after operation.

[0003] At present, the internal resistance parameter identification model can be simplified into an equivalent circuit model or an electrochemical model. The equivalent circuit model cannot accurately identify the dynamic characteristics of the battery at low temperatures. If the electrochemical model considers the low temperature environment and different current rates at the same time, the parameters in the electrochemical model will have strong nonlinear characteristics, and there will be calculation fitting errors, resulting in distorted simulation results. In addition, since it is difficult for the model to quantitatively capture the changes in the physical and electrochemical properties of the internal materials of the battery cell at different temperatures, it is currently necessary to design a large number of tests to more accurately identify the internal resistance of the battery cell, and the identification efficiency is low; however, if the amount of original data is reduced or a shorter transient data duration is designed and the lightweight algorithm model is optimized, the accuracy of battery parameter identification will be low. Therefore, there are certain limitations in the current identification of the internal resistance parameters of batteries. Summary of the invention

[0004] The purpose of the present application is to provide a method, device, equipment and medium for processing cell data of a lithium-ion battery in view of the deficiencies in the above-mentioned prior art, so as to solve the practical problems of low efficiency and low accuracy in identifying the internal resistance parameters of the battery in the prior art.

[0005] To achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for processing cell data of a lithium-ion battery, the method comprising:

[0007] Acquire test data under multiple test conditions, the test data including: ambient temperature, battery temperature, current, voltage, and battery state of charge, wherein the ambient temperature of at least one test condition is less than a preset temperature;

[0008] Constructing a back propagation neural network of the lithium-ion battery, forward inputting the test data under each test condition into the back propagation neural network, and obtaining the predicted voltage of the lithium-ion battery under each test condition;

[0009] Determining voltage change information of the lithium-ion battery according to the predicted voltage of the lithium-ion battery under each test condition;

[0010] Inputting the voltage change information and the test data into a pre-established equivalent circuit model to perform preliminary offline identification of the cell internal resistance parameters to obtain initial cell internal resistance parameters;

[0011] Reversely inputting the initial cell internal resistance parameter into the back propagation neural network, and forwardly inputting the test data into the back propagation neural network, and using the back propagation neural network to correct the model parameters of the back propagation neural network to obtain a target back propagation neural network;

[0012] The battery data of the battery to be identified is input into the target back propagation neural network, and the target back propagation neural network predicts the cell internal resistance parameter of the battery to be identified.

[0013] As an optional implementation, the back propagation neural network of the lithium-ion battery includes an input layer, a hidden layer and an output layer;

[0014] The back propagation neural network for constructing a lithium-ion battery comprises:

[0015] Determine the number of nodes in the input layer and the number of neurons in the hidden layer according to the data type of the test data;

[0016] Determine the number of nodes in the output layer to be one;

[0017] A back propagation neural network of the lithium-ion battery is constructed according to the number of nodes in the input layer, the number of neurons in the hidden layer, and the number of nodes in the output layer.

[0018] As an optional implementation, determining the voltage change information of the lithium-ion battery according to the predicted voltage of the lithium-ion battery under each test condition includes:

[0019] Get the time period to which each test condition belongs;

[0020] A curve of voltage variation of the lithium-ion battery over time is determined according to the predicted voltage of the lithium-ion battery under each test condition and the time period to which each test condition belongs.

[0021] As an optional implementation, the equivalent circuit model is a first-order resistor-capacitor equivalent circuit model, including a parallel circuit of a resistor and a capacitor;

[0022] The step of inputting the voltage change information and the test data into a pre-established equivalent circuit model to perform preliminary offline identification of the cell internal resistance parameters to obtain the initial cell internal resistance parameters includes:

[0023] The voltage change information and the test data are input into the first-order resistance-capacitance equivalent circuit model, and the initial cell internal resistance parameter is extracted from the first-order resistance-capacitance equivalent circuit model.

[0024] As an optional implementation, the initial cell internal resistance parameters include initial ohmic internal resistance, initial polarization internal resistance and initial polarization capacitance, and the voltage change curve over time includes at least a first voltage drop segment, a second voltage drop segment and a voltage rebound segment;

[0025] The initial cell internal resistance parameter is extracted from the first-order resistance-capacitance equivalent circuit model, including:

[0026] Determine the ohmic internal resistance in the initial cell internal resistance parameter by using the first-order resistance-capacitance equivalent circuit model according to the starting voltage and the ending voltage of the first voltage drop segment and the current in the test data;

[0027] Determine the relationship between voltage and time in the second voltage drop section by using the first-order resistance and capacitance equivalent circuit model according to a zero-state response process in a resistance and capacitance loop of the first-order resistance and capacitance equivalent circuit corresponding to the second voltage drop section;

[0028] Determining the relationship between voltage and time in the voltage rebound section according to the voltage rebound section using the first-order resistance-capacitance equivalent circuit model;

[0029] The initial polarization internal resistance and the initial polarization capacitance are extracted from the first-order resistance-capacitance equivalent circuit model according to the relationship between the voltage and time in the second voltage drop segment and the relationship between the voltage and time in the voltage rebound segment.

[0030] As an optional implementation, the method of correcting the model parameters of the back-propagation neural network by the back-propagation neural network to obtain a target back-propagation neural network includes:

[0031] The back propagation neural network obtains a predicted cell internal resistance parameter according to the initial cell internal resistance parameter and the test data;

[0032] According to the error between the predicted battery cell internal resistance parameter and the preset expected output value, the model parameters of the back propagation neural network are iteratively adjusted and iterative prediction is performed until the error between the predicted battery cell internal resistance parameter output by the back propagation neural network and the expected output value meets the preset conditions, thereby obtaining the target back propagation neural network.

[0033] As an optional implementation, the iterative adjustment of the model parameters of the back propagation neural network according to the error between the predicted cell internal resistance parameter and the preset expected output value includes:

[0034] According to the error between the predicted cell internal resistance parameter and the preset expected output value, the error gradient of each layer node is determined by using the chain rule;

[0035] According to the error gradient, the weights and biases of the nodes in each layer of the back propagation neural network are adjusted.

[0036] In a second aspect, an embodiment of the present application provides a cell data processing device for a lithium-ion battery, the device comprising:

[0037] An acquisition module, used to acquire test data under multiple test conditions, the test data including: ambient temperature, battery temperature, current, voltage and battery charge state, wherein the ambient temperature of at least one test condition is less than a preset temperature;

[0038] A prediction module is used to construct a back propagation neural network of the lithium-ion battery, and to input the test data under each test condition into the back propagation neural network to obtain the predicted voltage of the lithium-ion battery under each test condition;

[0039] A determination module, used to determine voltage change information of the lithium-ion battery according to the predicted voltage of the lithium-ion battery under various test conditions;

[0040] The determination module is further used to input the voltage change information and the test data into a pre-established equivalent circuit model to perform preliminary offline identification of the cell internal resistance parameters to obtain initial cell internal resistance parameters;

[0041] A correction module, used for reversely inputting the initial cell internal resistance parameter into the back propagation neural network, and forwardly inputting the test data into the back propagation neural network, and correcting the model parameters of the back propagation neural network by the back propagation neural network to obtain a target back propagation neural network;

[0042] The prediction module is also used to input the battery data of the battery to be identified into the target back propagation neural network, and the target back propagation neural network predicts the cell internal resistance parameters of the battery to be identified.

[0043] As an optional implementation, the prediction module is specifically used for:

[0044] Determine the number of nodes in the input layer and the number of neurons in the hidden layer according to the data type of the test data;

[0045] Determine the number of nodes in the output layer to be one;

[0046] A back propagation neural network of the lithium-ion battery is constructed according to the number of nodes in the input layer, the number of neurons in the hidden layer, and the number of nodes in the output layer.

[0047] As an optional implementation manner, the determining module is specifically used for:

[0048] Get the time period to which each test condition belongs;

[0049] A curve of voltage variation of the lithium-ion battery over time is determined according to the predicted voltage of the lithium-ion battery under each test condition and the time period to which each test condition belongs.

[0050] As an optional implementation manner, the determining module is specifically used for:

[0051] The voltage change information and the test data are input into the first-order resistance-capacitance equivalent circuit model, and the initial cell internal resistance parameter is extracted from the first-order resistance-capacitance equivalent circuit model.

[0052] As an optional implementation manner, the determining module is specifically used for:

[0053] Determine the ohmic internal resistance in the initial cell internal resistance parameter by using the first-order resistance-capacitance equivalent circuit model according to the starting voltage and the ending voltage of the first voltage drop segment and the current in the test data;

[0054] Determine the relationship between voltage and time in the second voltage drop section by using the first-order resistance and capacitance equivalent circuit model according to a zero-state response process in a resistance and capacitance loop of the first-order resistance and capacitance equivalent circuit corresponding to the second voltage drop section;

[0055] Determining the relationship between voltage and time in the voltage rebound section according to the voltage rebound section using the first-order resistance-capacitance equivalent circuit model;

[0056] The initial polarization internal resistance and the initial polarization capacitance are extracted from the first-order resistance-capacitance equivalent circuit model according to the relationship between the voltage and time in the second voltage drop segment and the relationship between the voltage and time in the voltage rebound segment.

[0057] As an optional implementation, the correction module is specifically used for:

[0058] The back propagation neural network obtains a predicted cell internal resistance parameter according to the initial cell internal resistance parameter and the test data;

[0059] According to the error between the predicted battery cell internal resistance parameter and the preset expected output value, the model parameters of the back propagation neural network are iteratively adjusted and iterative prediction is performed until the error between the predicted battery cell internal resistance parameter output by the back propagation neural network and the expected output value meets the preset conditions, thereby obtaining the target back propagation neural network.

[0060] As an optional implementation, the correction module is specifically used for:

[0061] According to the error between the predicted cell internal resistance parameter and the preset expected output value, the error gradient of each layer node is determined by using the chain rule;

[0062] According to the error gradient, the weights and biases of the nodes in each layer of the back propagation neural network are adjusted.

[0063] In a third aspect, an embodiment of the present application provides a computer device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of the lithium-ion battery cell data processing method as described in the first aspect above.

[0064] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the lithium-ion battery cell data processing method as described in the first aspect above are executed.

[0065] The beneficial effects of this application are:

[0066] The present application provides a method, device, equipment and medium for processing data of a lithium-ion battery cell. By designing multiple test conditions for the lithium-ion battery cell, test data under multiple test conditions are obtained, and the test data include test data under low-temperature test conditions where the ambient temperature is less than a preset temperature. The test data under each test condition is forward input into a back propagation neural network, and the back propagation neural network is trained on the test data under each test condition to obtain the predicted voltage of the lithium-ion battery under each test condition, thereby determining the voltage change information of the lithium-ion battery. The voltage change information and the test data under each test condition are input into the equivalent circuit model, and the equivalent circuit model is used to perform preliminary offline identification of the cell internal resistance parameters to obtain the initial cell internal resistance parameters of the lithium-ion battery. The initial cell internal resistance parameters obtained by the preliminary offline identification of the equivalent circuit model are reversely input into the back propagation neural network, and the test data are forwardly input into the back propagation neural network, and the model parameters of the back propagation neural network are iteratively corrected to obtain the corrected target back propagation neural network, so that the target back propagation neural network can train the input battery data of the battery to be identified and predict the cell internal resistance parameters of the battery to be identified. The error caused by online data acquisition is avoided by offline identification of the equivalent circuit model. Before offline identification, the predicted voltage under different test conditions is obtained by training the back propagation neural network, which improves the identification accuracy of the cell internal resistance parameters of the lithium-ion battery in a wide temperature range, especially in a low temperature environment. The target back propagation neural network is obtained by correcting the model parameters of the back propagation neural network, and the cell internal resistance parameters are predicted by the target back propagation neural network, which further improves the identification accuracy and efficiency of the cell internal resistance parameters of the lithium-ion battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0068] Figure 1 A schematic diagram of a flow chart of a method for processing data of a lithium-ion battery cell provided in an embodiment of the present application;

[0069] Figure 2 A schematic diagram of the process of constructing a back propagation neural network for a lithium-ion battery according to a method for processing lithium-ion battery cell data provided in an embodiment of the present application;

[0070] Figure 3 A schematic diagram of the structure of a back propagation neural network provided in an embodiment of the present application;

[0071] Figure 4 A schematic diagram of a flow chart of determining voltage change information of a lithium-ion battery in a method for processing cell data of a lithium-ion battery provided in an embodiment of the present application;

[0072] Figure 5 A schematic diagram of a curve showing a change in voltage over time of a lithium-ion battery provided in an embodiment of the present application;

[0073] Figure 6 A circuit structure diagram of a first-order resistance-capacitance equivalent circuit model provided in an embodiment of the present application;

[0074] Figure 7 A schematic diagram of a process for extracting and obtaining initial cell internal resistance parameters of a lithium-ion battery cell data processing method provided in an embodiment of the present application;

[0075] Figure 8 A schematic diagram of a process of obtaining a target back propagation neural network in a method for processing cell data of a lithium-ion battery provided in an embodiment of the present application;

[0076] Fig. 9 A schematic diagram of a flow chart of iteratively adjusting the model parameters of a back propagation neural network in a method for processing data of a lithium-ion battery cell provided in an embodiment of the present application;

[0077] Fig.10 A module structure diagram of a lithium-ion battery cell data processing device provided in an embodiment of the present application;

[0078] Fig.11 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0079] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0080] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0081] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0082] In the field of lithium-ion battery design, the internal resistance parameter identification model can be simplified into an equivalent circuit model or an electrochemical model. The equivalent circuit model has the disadvantage of being unable to accurately identify the dynamic characteristics of the battery at low temperatures. If the electrochemical model takes into account the low temperature environment and different current rates at the same time, the parameters in the electrochemical model will have strong nonlinear characteristics, and there will be calculation fitting errors, resulting in distorted simulation results. At present, it is necessary to design a large number of tests to more accurately identify the internal resistance of the battery cell, and the identification efficiency is low; if the amount of original data is reduced or a shorter transient data duration is designed and the lightweight algorithm model is optimized, the accuracy of battery parameter identification will be low. At present, the identification of the internal resistance parameters of the battery has certain limitations.

[0083] Based on the above problems, the embodiments of the present application propose a method for processing cell data of a lithium-ion battery to improve the recognition accuracy and efficiency of the internal resistance parameters of the lithium-ion battery cells in a wide temperature range, especially in a low temperature environment.

[0084] Figure 1 The flowchart of the method for processing data of a lithium-ion battery provided in the embodiment of the present application is shown in FIG. 1 , and the execution subject of the method can be any computer device with computing and processing capabilities. Figure 1 As shown, the method includes:

[0085] S101. Acquire test data under multiple test conditions, the test data including: ambient temperature, battery temperature, current, voltage, and battery state of charge, wherein the ambient temperature of at least one test condition is lower than a preset temperature.

[0086] Optionally, multiple test conditions are designed for the lithium-ion battery cells, and the lithium-ion battery cells are charged and discharged at different ambient temperatures, different battery SOCs (5% to 100%), and different current rates. The ambient temperature, current, voltage, and battery SOC are recorded during the test to obtain test data under multiple test conditions. Among them, the current rate is the ratio of the charge and discharge current to the rated capacity of the lithium-ion battery, which is used to characterize the charge and discharge rate of the lithium-ion battery. By designing the ambient temperature of at least one test condition to be lower than the preset temperature, test data under low temperature test conditions can be obtained.

[0087] For example, the preset temperature may be 15°C, and the different ambient temperatures under multiple test conditions may include -30°C, -20°C, 0°C, 10°C, 25°C, and 40°C, that is, the charge and discharge test of the lithium-ion battery cell is performed in a wide temperature range of -30°C to 40°C, at different battery SOCs of 5% to 100%, and at different current rates. The preset temperature may also be 0°C, and the value of the preset temperature is not specifically limited herein.

[0088] S102, constructing a back propagation neural network for the lithium-ion battery, and forward-inputting the test data under each test condition into the back propagation neural network to obtain a predicted voltage of the lithium-ion battery under each test condition.

[0089] Optionally, a back propagation (BP) neural network of the lithium-ion battery is constructed according to the test data under each test condition, the test data obtained under each test condition is normalized, abnormal data is eliminated, and the normalized test data under each test condition is forward input into the BP neural network, the data is divided into a training set and a validation set, and the BP neural network is used to train the normalized test data under each test condition through a forward propagation process to obtain the predicted voltage of the lithium-ion battery under each test condition.

[0090] S103: Determine voltage change information of the lithium-ion battery according to the predicted voltage of the lithium-ion battery under each test condition.

[0091] Optionally, according to the predicted voltage of the lithium-ion battery under each test condition obtained by BP neural network training, voltage variation information of the predicted voltage of the lithium-ion battery when it changes with the ambient temperature, current rate and battery SOC under different test conditions is determined.

[0092] S104, inputting the voltage change information and the test data into a pre-established equivalent circuit model to perform preliminary offline identification of the cell internal resistance parameters, and obtaining initial cell internal resistance parameters.

[0093] Optionally, the voltage change information and the normalized test data under each test condition are input into a pre-established equivalent circuit model, and the equivalent circuit model is used to perform preliminary offline identification of the cell internal resistance parameters, and the initial cell internal resistance parameters of the lithium-ion battery are obtained based on Kirchhoff's law. The offline identification avoids the errors caused by online data collection.

[0094] S105, reversely inputting the initial cell internal resistance parameter into the back propagation neural network, and forwardly inputting the test data into the back propagation neural network, and using the back propagation neural network to correct the model parameters of the back propagation neural network to obtain a target back propagation neural network.

[0095] Optionally, the initial cell internal resistance parameters obtained by preliminary offline identification of the equivalent circuit model are reversely input into the BP neural network, and the normalized test data under each test condition are forwardly input into the BP neural network, and the BP neural network iteratively corrects the model parameters of the BP neural network through the back propagation process to obtain a corrected target BP neural network.

[0096] S106, inputting the battery data of the battery to be identified into the target back propagation neural network, and predicting the internal resistance parameters of the battery cell to be identified by the target back propagation neural network.

[0097] Optionally, the battery data of the battery to be identified is forward input into the target BP neural network, and the target BP neural network trains the battery data of the battery to be identified through a forward propagation process to predict the cell internal resistance parameters of the battery to be identified. The battery data of the battery to be identified may include the current ambient temperature, the battery temperature of the battery to be identified, the current rate of the battery to be identified, the voltage of the battery to be identified, and the SOC of the battery to be identified.

[0098] In this embodiment, by designing multiple test conditions of the battery cell of the lithium-ion battery, test data under multiple test conditions are obtained, and the test data include test data under low temperature test conditions where the ambient temperature is less than the preset temperature. The test data under each test condition is forward input into the back propagation neural network, and the test data under each test condition is trained by the back propagation neural network to obtain the predicted voltage of the lithium-ion battery under each test condition, thereby determining the voltage change information of the lithium-ion battery. The voltage change information and the test data under each test condition are input into the equivalent circuit model, and the equivalent circuit model is used to perform preliminary offline identification of the battery cell internal resistance parameters to obtain the initial battery cell internal resistance parameters of the lithium-ion battery, and the initial battery cell internal resistance parameters obtained by the preliminary offline identification of the equivalent circuit model are reversely input into the back propagation neural network, and the test data is forward input into the back propagation neural network, and the model parameters of the back propagation neural network are iteratively corrected to obtain the corrected target back propagation neural network, so that the target back propagation neural network can train the battery data of the input battery to be identified and predict the battery cell internal resistance parameters of the battery to be identified. The errors caused by online data collection are avoided through offline identification of the equivalent circuit model. Before offline identification, the predicted voltage under different test conditions is obtained by back propagation neural network training, which improves the identification accuracy of the internal resistance parameters of lithium-ion batteries in a wide temperature range, especially in low temperature environments. The target back propagation neural network is obtained by correcting the model parameters of the back propagation neural network, and the internal resistance parameters of the battery cell are predicted by the target back propagation neural network, which further improves the identification accuracy and efficiency of the internal resistance parameters of lithium-ion batteries.

[0099] As an optional implementation, the back propagation neural network of the lithium-ion battery includes an input layer, a hidden layer, and an output layer.

[0100] Optionally, the BP neural network of the lithium-ion battery constructed according to the test data under each test condition includes an input layer, a hidden layer and an output layer. In the forward propagation process, the test data under each test condition is input from the input layer, calculated layer by layer through the hidden layer and transmitted to the output layer; in the reverse propagation process, the error of the output layer is reversely transmitted to iteratively correct the model parameters of the BP neural network.

[0101] Below, the process of constructing a back-propagation neural network for lithium-ion batteries is described in detail.

[0102] Figure 2 A schematic diagram of a flow chart of a back propagation neural network for a lithium-ion battery according to a method for processing lithium-ion battery cell data provided in an embodiment of the present application, such as Figure 2 As shown, the step of constructing the back propagation neural network of the lithium-ion battery in the above step S102 includes:

[0103] S201. Determine the number of nodes in the input layer and the number of neurons in the hidden layer according to the data type of the test data.

[0104] Optionally, the test data under each test condition is used as input features, and the number of nodes of the input layer of the BP neural network is determined according to the number of data types of the test data. Specifically, the ambient temperature, battery temperature, current and battery SOC in the test data are used as input features. The test data includes four data types, and 4 nodes are set in the input layer of the BP neural network. It is worth noting that the voltage in the test data is used to judge the accuracy of the predicted voltage output by the BP neural network, and is not used as an input feature of the BP neural network.

[0105] The number of neurons in the hidden layer of the BP neural network depends on the complexity of the data to be predicted. Based on the cost reduction principle and empirical rules, 5 neurons are set in the hidden layer of the BP neural network.

[0106] S202: Determine the number of nodes in the output layer to be one.

[0107] Optionally, only one node is set in the output layer of the BP neural network for outputting the predicted voltage during the forward propagation process. One node of the output layer of the modified BP neural network is used to output the cell internal resistance parameter of the battery to be identified.

[0108] S203, constructing a back propagation neural network of the lithium-ion battery according to the number of nodes in the input layer, the number of neurons in the hidden layer, and the number of nodes in the output layer.

[0109] Optionally, according to the number of nodes in the input layer, the number of neurons in the hidden layer, the number of nodes in the output layer, the first activation function g 1 (w,b 1 ) and the second activation function g 2 (v,b 2 ), construct the BP neural network of lithium-ion battery. Figure 3 The schematic diagram of the back propagation neural network provided in the embodiment of the present application is shown in FIG. Figure 3 In the forward propagation process of the BP neural network, the ambient temperature, battery temperature, current and battery SOC in the test data under each test condition are input from the four nodes of the input layer respectively, and are calculated layer by layer through the hidden layer and transmitted to the output layer, such as Figure 3 As shown above the output layer, one node in the output layer outputs the predicted voltage.

[0110] In the forward propagation process of the modified target BP neural network, the current ambient temperature, battery temperature, current rate and SOC of the battery to be identified in the battery data of the battery to be identified are input from the four nodes of the input layer respectively, and are calculated layer by layer through the hidden layer and transmitted to the output layer, such as Figure 3 As shown below the output layer, one node of the output layer outputs the cell internal resistance parameter of the battery to be identified. Figure 3 The upper node of the output layer and the lower node of the output layer are the same node. Before correction, the output layer node is used to output the predicted voltage. After correction, the output layer node is used to output the internal resistance parameter of the battery cell.

[0111] In this embodiment, the test data under each test condition is used as input features, and the number of nodes of the input layer of the back propagation neural network is determined according to the number of data types of the test data, and the number of neurons in the hidden layer is determined by using the cost reduction principle and empirical rules. A node is set in the output layer of the back propagation neural network to output the predicted voltage during the forward propagation process; an output layer node of the modified target back propagation neural network is used to output the cell internal resistance parameter of the battery to be identified. According to the number of nodes in the input layer, the number of neurons in the hidden layer, the number of nodes in the output layer, the first activation function and the second activation function, a back propagation neural network for lithium-ion batteries is constructed, which improves the recognition efficiency of the back propagation neural network for lithium-ion batteries.

[0112] The following describes in detail the process of determining the voltage variation information of the lithium-ion battery according to the predicted voltage of the lithium-ion battery under various test conditions.

[0113] Figure 4 A schematic diagram of a flow chart of determining voltage change information of a lithium-ion battery in a method for processing cell data of a lithium-ion battery provided in an embodiment of the present application, such as Figure 4 As shown, the step of determining the voltage change information of the lithium-ion battery according to the predicted voltage of the lithium-ion battery under each test condition in the above step S103 includes:

[0114] S401. Obtain the time period to which each test condition belongs.

[0115] Optionally, in the charge and discharge test of each test condition, the time period to which each test condition belongs is recorded, including the time period to which the discharge step belongs under the test conditions of different ambient temperatures, different current rates and different battery SOCs.

[0116] S402: Determine a curve of a voltage change of the lithium-ion battery over time according to the predicted voltage of the lithium-ion battery under each test condition and the time period to which each test condition belongs.

[0117] Optionally, a curve of the voltage change of the lithium-ion battery over time is generated according to the predicted voltage of the lithium-ion battery under each test condition obtained by BP neural network training and the time period to which each test condition belongs. Figure 5 A schematic diagram of a curve showing a change in voltage over time of a lithium-ion battery provided in an embodiment of the present application, such as Figure 5 As shown, it is a curve of the voltage change of the lithium-ion battery over time under the discharge step of the test conditions of the same ambient temperature, the same current rate and the same battery SOC.

[0118] In this embodiment, in the charge and discharge test of each test condition, the time period to which each test condition belongs is recorded, and a curve of the voltage change over time of the lithium-ion battery is generated according to the predicted voltage of the lithium-ion battery under each test condition and the time period to which each test condition belongs. This facilitates the equivalent circuit model to preliminarily identify the initial cell internal resistance parameters of the lithium-ion battery offline according to the curve of the voltage change over time of the lithium-ion battery.

[0119] As an optional implementation, the equivalent circuit model is a first-order resistor-capacitor equivalent circuit model, including a parallel circuit of a resistor and a capacitor.

[0120] Optionally, the pre-established equivalent circuit model is a first-order resistor-capacitor equivalent circuit model, ie, a Thevenin equivalent circuit model, which includes a parallel circuit of a resistor and a capacitor. Figure 6 The circuit structure diagram of the first-order resistance-capacitance equivalent circuit model provided in the embodiment of the present application is as follows: Figure 6 As shown, OCV is the open circuit voltage, that is, the terminal voltage, R 0 is the initial ohmic internal resistance, R 1 is the initial polarization internal resistance, C 1 is the initial polarization capacitance, U 1 is the initial polarization voltage, where the initial polarization internal resistance R 1 and the initial polarization capacitance C 1 A RC parallel circuit is formed.

[0121] As an optional implementation, the step of inputting the voltage change information and the test data into a pre-established equivalent circuit model to perform preliminary offline identification of the cell internal resistance parameters in the above step S104 to obtain the initial cell internal resistance parameters includes:

[0122] The voltage change information and test data are input into the first-order resistance and capacitance equivalent circuit model, and the initial cell internal resistance parameters are extracted from the first-order resistance and capacitance equivalent circuit model.

[0123] Optionally, the voltage change information of the lithium-ion battery and the normalized test data under each test condition are input into a first-order resistance-capacitance equivalent circuit model, and the first-order resistance-capacitance equivalent circuit model is used to perform preliminary offline identification of the internal resistance parameters of the battery cell, and the initial battery cell internal resistance parameters of the lithium-ion battery are extracted based on Kirchhoff's law.

[0124] In this embodiment, the first-order resistance and capacitance equivalent circuit model obtains the initial cell internal resistance parameters of the lithium-ion battery based on the input voltage change information of the lithium-ion battery and the normalized test data under each test condition, based on Kirchhoff's law. Since there is only one parallel circuit of resistance and capacitance in the first-order resistance and capacitance equivalent circuit model, the complexity of the equivalent circuit is relatively low, which improves the initial identification efficiency of the first-order resistance and capacitance equivalent circuit model.

[0125] As an optional implementation, the initial battery cell internal resistance parameters include initial ohmic internal resistance, initial polarization internal resistance and initial polarization capacitance, and the voltage change curve over time includes at least a first voltage drop segment, a second voltage drop segment and a voltage rebound segment.

[0126] Optionally, refer to Figure 6 The initial cell internal resistance parameters of lithium-ion batteries include the initial ohmic internal resistance R 0 , initial polarization internal resistance R 1 and the initial polarization capacitance C 1 . Reference Figure 5 The voltage change curve over time includes a first voltage drop segment AB, a second voltage drop segment BC and a voltage rebound segment CD, wherein the first voltage drop segment AB indicates that the voltage drops rapidly from point A to point B, the second voltage drop segment BC indicates that the voltage drops slowly from point B to point C, and the voltage rebound segment CD indicates that the voltage rebounds from point C to point D.

[0127] The following is a detailed description of the process of extracting the initial cell internal resistance parameters from the first-order resistance-capacitance equivalent circuit model.

[0128] Figure 7 A schematic diagram of a process for extracting and obtaining initial cell internal resistance parameters of a lithium-ion battery cell data processing method provided in an embodiment of the present application, such as Figure 7 As shown, the step of extracting the initial cell internal resistance parameters from the first-order resistance-capacitance equivalent circuit model in the above steps includes:

[0129] S701, determining the ohmic internal resistance in the initial cell internal resistance parameter according to the starting voltage and ending voltage of the first voltage drop segment and the current in the test data using a first-order resistance-capacitance equivalent circuit model.

[0130] Optionally, continue to refer to Figure 6, obtained from Kirchhoff's law:

[0131]

[0132] U in =U ocv -U 1 -I*R 0

[0133] Where t is time, U 1 is the initial polarization voltage, C 1 is the initial polarization capacitance, R 1 is the initial polarization internal resistance, U in is the input voltage, U ocv is the open circuit voltage, i.e. the terminal voltage, I is the current, R 0 is the initial ohmic internal resistance.

[0134] It is the derivative of the initial polarization voltage with respect to time, which characterizes the rate at which the initial polarization voltage changes with time.

[0135] The first-order resistance-capacitance equivalent circuit model identifies the initial ohmic internal resistance R through the first voltage drop segment when the voltage drops rapidly from the starting voltage at point A to the ending voltage at point B during the discharge pulse excitation process. 0 , based on Ohm's law, determine the initial ohmic internal resistance R 0 :

[0136]

[0137] Among them, R 0 is the initial ohmic internal resistance, U A is the starting voltage at point A, U B is the termination voltage at point B, and I is the current in the test data.

[0138] S702, determining the relationship between voltage and time in the second voltage drop section by using a first-order resistance and capacitance equivalent circuit model according to a zero-state response process in a resistance and capacitance loop of a first-order resistance and capacitance equivalent circuit corresponding to the second voltage drop section.

[0139] Optionally, the first-order resistance-capacitance equivalent circuit model identifies the initial polarization internal resistance R by polarizing the battery during the pulse discharge phase so that the voltage slowly decreases from point B to the second voltage drop at point C. 1 The second voltage drop section corresponds to the zero-state response process in the RC loop of the first-order resistance-capacitance equivalent circuit. The input voltage U in The exponential function relationship with time t is:

[0140]

[0141] Among them, Uin is the input voltage, U ocv is the open circuit voltage, i.e. the terminal voltage, I is the current, R 1 is the initial polarization internal resistance, e is the natural constant, τ is the time constant, τ=R 1 C 1 , t is time, R 0 is the initial ohmic internal resistance.

[0142] S703. Determine the relationship between voltage and time in the voltage rebound segment according to the voltage rebound segment using a first-order resistance-capacitance equivalent circuit model.

[0143] Optionally, the first-order resistance-capacitance equivalent circuit model identifies the initial polarization capacitance C through the voltage rebound segment from point C to point D. 1 , the initial polarization capacitance C corresponding to the voltage rebound segment 1 Input voltage U during discharge in The exponential function relationship with time t is:

[0144]

[0145] Among them, U in is the input voltage, U ocv is the open circuit voltage, i.e. the terminal voltage, I is the current, R 1 is the initial polarization internal resistance, t is the time, C 1 is the initial polarization capacitance.

[0146] S704, extracting the initial polarization internal resistance and the initial polarization capacitance from the first-order resistance and capacitance equivalent circuit model according to the relationship between the voltage and time in the second voltage drop section and the relationship between the voltage and time in the voltage rebound section.

[0147] Optionally, the first-order resistance-capacitance equivalent circuit model converts the exponential function relationship between the voltage and time in the second voltage drop section and the exponential function relationship between the voltage and time in the voltage rebound section into the initial polarization resistance R 1 , initial polarization capacitance C 1 The relationship between time t and current I, and then extract the initial polarization internal resistance R 1 and initial polarization capacitance C 1 .

[0148] In this embodiment, the first-order resistance and capacitance equivalent circuit model determines the initial ohmic internal resistance based on Ohm's law through the first voltage drop section where the voltage drops rapidly from the starting voltage to the end voltage and the current in the test data. The first-order resistance and capacitance equivalent circuit model determines the exponential function relationship between the voltage and time in the second voltage drop section through the zero-state response process in the resistance and capacitance loop of the first-order resistance and capacitance equivalent circuit corresponding to the second voltage drop section; the first-order resistance and capacitance equivalent circuit model determines the exponential function relationship between the voltage and time in the voltage rebound section through the initial polarization capacitor discharge process corresponding to the voltage rebound section. The first-order resistance and capacitance equivalent circuit model converts the exponential function relationship between the voltage and time in the second voltage drop section and the exponential function relationship between the voltage and time in the voltage rebound section into the relationship between the initial polarization resistance, the initial polarization capacitance, time and current, and then extracts the initial polarization internal resistance and the initial polarization capacitance. Through the initial offline identification of the first-order resistance and capacitance equivalent circuit model, the initial ohmic internal resistance, the initial polarization internal resistance and the initial polarization capacitance are extracted to obtain the initial battery cell internal resistance parameters.

[0149] The following describes in detail the process of correcting the model parameters of the back-propagation neural network by the back-propagation neural network to obtain the target back-propagation neural network.

[0150] Figure 8 A schematic diagram of a process of obtaining a target back propagation neural network for a lithium-ion battery cell data processing method provided in an embodiment of the present application, such as Figure 8 As shown, in the above step S105, the step of correcting the model parameters of the back propagation neural network by the back propagation neural network to obtain the target back propagation neural network includes:

[0151] S801, using a back propagation neural network to obtain predicted battery cell internal resistance parameters based on initial battery cell internal resistance parameters and test data.

[0152] Optionally, the BP neural network obtains predicted battery cell internal resistance parameters through training based on the test data under each test condition after normalization processing of the forward input and the initial battery cell internal resistance parameters of the reverse input, based on the model parameters in the BP neural network, and outputs the predicted battery cell internal resistance parameters through the output layer node.

[0153] S802. According to the error between the predicted battery cell internal resistance parameter and the preset expected output value, iteratively adjust the model parameters of the back propagation neural network and perform iterative prediction until the error between the predicted battery cell internal resistance parameter output by the back propagation neural network and the expected output value meets the preset conditions, thereby obtaining the target back propagation neural network.

[0154] Optionally, the BP neural network compares the output predicted cell internal resistance parameter with the preset expected output value, and uses the Mean Squared Error (MES) loss function to determine the error between the predicted cell internal resistance parameter output by the BP neural network and the preset expected output value. The BP neural network performs error analysis and training, iteratively adjusts the model parameters of the BP neural network by the error between the preset expected output value and the predicted cell internal resistance parameter output by the output layer node, and iteratively outputs the predicted cell internal resistance parameter based on the model parameters of the BP neural network during iterative adjustment. When the error between the predicted cell internal resistance parameter output by the BP neural network and the expected output value meets the preset conditions, it is determined that the model parameter adjustment of the BP neural network is completed, and the BP neural network with the model parameter adjustment completed at this time is used as the target BP neural network. Among them, the preset expected output value can be the actual cell internal resistance parameter obtained by simulation or actual test, and the preset condition can be that the error value between the predicted cell internal resistance parameter output by the BP neural network and the expected output value is less than the preset error threshold, or the value of the MES loss function is less than the preset value.

[0155] In this embodiment, the back propagation neural network is trained to obtain the predicted battery cell internal resistance parameters based on the test data under each test condition after normalization of the forward input and the initial battery cell internal resistance parameters of the reverse input, based on the model parameters in the back propagation neural network, and the predicted battery cell internal resistance parameters are output through the output layer node. The back propagation neural network compares the predicted battery cell internal resistance parameters with the preset expected output value, and uses the mean square error loss function to determine the error between the predicted battery cell internal resistance parameters and the preset expected output value. The back propagation neural network performs error analysis and training, and iteratively adjusts the model parameters of the back propagation neural network through the error between the expected output value and the predicted battery cell internal resistance parameter, and performs iterative prediction. When the error between the predicted battery cell internal resistance parameter output by the back propagation neural network and the expected output value meets the preset conditions, the target back propagation neural network is obtained. The model parameters of the back propagation neural network are iteratively adjusted through error analysis training, which improves the prediction accuracy of the target back propagation neural network.

[0156] The following describes in detail the process of iteratively adjusting the model parameters of the back propagation neural network according to the error between the predicted battery cell internal resistance parameter and the preset expected output value.

[0157] Fig. 9 A schematic diagram of a flow chart of iteratively adjusting the model parameters of a back propagation neural network in a method for processing data of a lithium-ion battery cell provided in an embodiment of the present application, such as Fig. 9 As shown, the step of iteratively adjusting the model parameters of the back propagation neural network according to the error between the predicted cell internal resistance parameter and the preset expected output value in the above step S802 includes:

[0158] S901. According to the error between the predicted cell internal resistance parameter and the preset expected output value, the error gradient of each layer node is determined by using the chain rule.

[0159] Optionally, the BP neural network uses the chain rule to back-propagate the error between the predicted cell internal resistance parameter and the preset expected output value from the output layer of the BP neural network to the input layer, and during the back-propagation process, the error gradient of each layer node is calculated by the back-propagation algorithm.

[0160] S902. According to the error gradient, adjust the weights and biases of the nodes in each layer of the back propagation neural network.

[0161] Optionally, the model parameters of the BP neural network include the weight W and bias b of each layer of nodes. The BP neural network updates the weight W and bias b of each layer of nodes in the model parameters of the BP neural network according to the error gradient of each layer of nodes in the opposite direction of the error gradient, so that the error is continuously reduced. The BP neural network adjusts the W and bias b of each layer of nodes of the BP neural network based on the following formula:

[0162] [W_{new}=W_{old}-\eta\frac{\partial E}{\partial W}]

[0163] [b_{new}=b_{old}-\eta\frac{\partial E}{\partial b}]

[0164] Among them, W is the weight, b is the bias, E is the error, and \eta is the preset learning rate, which is used to indicate the adjustment speed of the model parameters of the BP neural network.

[0165] In this embodiment, the back propagation neural network uses the chain rule to propagate the error between the predicted battery cell internal resistance parameter and the preset expected output value from the output layer to the input layer, and the error gradient of each layer of nodes is determined by the back propagation algorithm during the back propagation process. The back propagation neural network adjusts the weights and biases of each layer of nodes in the model parameters of the back propagation neural network according to the error gradient of each layer of nodes. The weights and biases of each layer of nodes are updated in the reverse direction of the error gradient through the back propagation neural network, so that the error is continuously reduced until the error meets the preset conditions to obtain the target back propagation neural network.

[0166] Based on the same inventive concept, an embodiment of the present application also provides a lithium-ion battery cell data processing device corresponding to the lithium-ion battery cell data processing method. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned lithium-ion battery cell data processing method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0167] Fig.10 The module structure diagram of the lithium-ion battery cell data processing device provided in the embodiment of the present application is as follows: Fig.10 As shown, the device comprises:

[0168] The acquisition module 1001 is used to acquire test data under multiple test conditions, the test data including: ambient temperature, battery temperature, current, voltage and battery charge state, wherein the ambient temperature of at least one test condition is less than a preset temperature.

[0169] The prediction module 1002 is used to construct a back propagation neural network for the lithium-ion battery, and forward input the test data under each test condition into the back propagation neural network to obtain the predicted voltage of the lithium-ion battery under each test condition.

[0170] The determination module 1003 is used to determine the voltage change information of the lithium-ion battery according to the predicted voltage of the lithium-ion battery under various test conditions.

[0171] The determination module 1003 is further used to input the voltage change information and the test data into a pre-established equivalent circuit model to perform preliminary offline identification of the cell internal resistance parameters, so as to obtain the initial cell internal resistance parameters.

[0172] The correction module 1004 is used to reversely input the initial battery cell internal resistance parameters into the back propagation neural network, and forwardly input the test data into the back propagation neural network, and the back propagation neural network corrects the model parameters of the back propagation neural network to obtain the target back propagation neural network.

[0173] The prediction module 1002 is further used to input the battery data of the battery to be identified into the target back propagation neural network, and the target back propagation neural network predicts the internal resistance parameters of the battery cell to be identified.

[0174] As an optional implementation, the prediction module 1002 is specifically used for:

[0175] According to the data type of the experimental data, the number of nodes in the input layer and the number of neurons in the hidden layer are determined.

[0176] The number of nodes in the output layer is determined to be one.

[0177] According to the number of nodes in the input layer, the number of neurons in the hidden layer, and the number of nodes in the output layer, a back propagation neural network for lithium-ion batteries is constructed.

[0178] As an optional implementation manner, the determination module 1003 is specifically configured to:

[0179] Get the time period to which each test condition belongs.

[0180] According to the predicted voltage of the lithium-ion battery under each test condition and the time period to which each test condition belongs, a curve of the voltage change of the lithium-ion battery over time is determined.

[0181] As an optional implementation manner, the determination module 1003 is specifically configured to:

[0182] The voltage change information and test data are input into the first-order resistance and capacitance equivalent circuit model, and the initial cell internal resistance parameters are extracted from the first-order resistance and capacitance equivalent circuit model.

[0183] As an optional implementation manner, the determination module 1003 is specifically configured to:

[0184] The ohmic internal resistance in the initial cell internal resistance parameter is determined by the first-order resistance-capacitance equivalent circuit model according to the starting voltage and ending voltage of the first voltage drop segment and the current in the test data.

[0185] The relationship between voltage and time in the second voltage drop section is determined by the first-order resistance and capacitance equivalent circuit model according to the zero-state response process in the resistance and capacitance loop of the first-order resistance and capacitance equivalent circuit corresponding to the second voltage drop section.

[0186] The relationship between voltage and time in the voltage rebound section is determined based on the voltage rebound section using a first-order resistance-capacitance equivalent circuit model.

[0187] The initial polarization internal resistance and initial polarization capacitance are extracted from the first-order resistance and capacitance equivalent circuit model according to the relationship between voltage and time in the second voltage drop section and the relationship between voltage and time in the voltage rebound section.

[0188] As an optional implementation, the correction module 1004 is specifically used for:

[0189] The back propagation neural network obtains the predicted battery cell internal resistance parameters based on the initial battery cell internal resistance parameters and test data.

[0190] According to the error between the predicted battery cell internal resistance parameter and the preset expected output value, the model parameters of the back propagation neural network are iteratively adjusted and iterative prediction is performed until the error between the predicted battery cell internal resistance parameter output by the back propagation neural network and the expected output value meets the preset conditions, thereby obtaining the target back propagation neural network.

[0191] As an optional implementation, the correction module 1004 is specifically used for:

[0192] According to the error between the predicted cell internal resistance parameter and the preset expected output value, the chain rule is used to determine the error gradient of each layer node.

[0193] According to the error gradient, adjust the weights and biases of each layer of the back-propagation neural network.

[0194] The present application also provides a computer device, such as Fig.11 1 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application, including: a processor 111, a memory 112 and a bus 113. The memory 112 stores machine-readable instructions executable by the processor 111 (for example, Fig.10 In the device, the execution instructions corresponding to the acquisition module 1001, the prediction module 1002, the determination module 1003 and the correction module 1004 are obtained, etc.), when the computer device is running, the processor 111 and the memory 112 communicate through the bus 113, and when the machine-readable instructions are executed by the processor 111, the steps of the lithium-ion battery cell data processing method in the above embodiment are executed.

[0195] The embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the lithium-ion battery cell data processing method in the above embodiment are executed.

[0196] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0197] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), disk or optical disk and other media that can store program code.

[0198] The above are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. A method for processing cell data of a lithium-ion battery, characterized in that: include: Acquire test data under multiple test conditions, the test data including: ambient temperature, battery temperature, current, voltage, and battery state of charge, wherein the ambient temperature of at least one test condition is less than a preset temperature; Constructing a back propagation neural network of the lithium-ion battery, forward inputting the test data under each test condition into the back propagation neural network, and obtaining the predicted voltage of the lithium-ion battery under each test condition; Determining voltage change information of the lithium-ion battery according to the predicted voltage of the lithium-ion battery under each test condition; Inputting the voltage change information and the test data into a pre-established equivalent circuit model to perform preliminary offline identification of the cell internal resistance parameters to obtain initial cell internal resistance parameters; Reversely inputting the initial cell internal resistance parameter into the back propagation neural network, and forwardly inputting the test data into the back propagation neural network, and using the back propagation neural network to correct the model parameters of the back propagation neural network to obtain a target back propagation neural network; The battery data of the battery to be identified is input into the target back propagation neural network, and the target back propagation neural network predicts the cell internal resistance parameter of the battery to be identified.

2. The method according to claim 1, characterized in that The back propagation neural network of the lithium-ion battery includes an input layer, a hidden layer and an output layer; The back propagation neural network for constructing a lithium-ion battery comprises: Determine the number of nodes in the input layer and the number of neurons in the hidden layer according to the data type of the test data; Determine the number of nodes in the output layer to be one; A back propagation neural network of the lithium-ion battery is constructed according to the number of nodes in the input layer, the number of neurons in the hidden layer, and the number of nodes in the output layer.

3. The method according to claim 1, characterized in that The step of determining voltage change information of the lithium-ion battery according to the predicted voltage of the lithium-ion battery under each test condition includes: Get the time period to which each test condition belongs; A curve of voltage variation of the lithium-ion battery over time is determined according to the predicted voltage of the lithium-ion battery under each test condition and the time period to which each test condition belongs.

4. The method according to claim 1, characterized in that: The equivalent circuit model is a first-order resistance-capacitance equivalent circuit model, including a parallel circuit of a resistor and a capacitor; The step of inputting the voltage change information and the test data into a pre-established equivalent circuit model to perform preliminary offline identification of the cell internal resistance parameters to obtain the initial cell internal resistance parameters includes: The voltage change information and the test data are input into the first-order resistance-capacitance equivalent circuit model, and the initial cell internal resistance parameter is extracted from the first-order resistance-capacitance equivalent circuit model.

5. The method according to claim 4, characterized in that The initial cell internal resistance parameters include initial ohmic internal resistance, initial polarization internal resistance and initial polarization capacitance, and the voltage variation curve over time includes at least a first voltage drop segment, a second voltage drop segment and a voltage rebound segment; The initial cell internal resistance parameter is extracted from the first-order resistance-capacitance equivalent circuit model, including: Determine the ohmic internal resistance in the initial cell internal resistance parameter by using the first-order resistance-capacitance equivalent circuit model according to the starting voltage and the ending voltage of the first voltage drop segment and the current in the test data; Determine the relationship between voltage and time in the second voltage drop section by using the first-order resistance and capacitance equivalent circuit model according to a zero-state response process in a resistance and capacitance loop of the first-order resistance and capacitance equivalent circuit corresponding to the second voltage drop section; Determining the relationship between voltage and time in the voltage rebound section according to the voltage rebound section using the first-order resistance-capacitance equivalent circuit model; The initial polarization internal resistance and the initial polarization capacitance are extracted from the first-order resistance-capacitance equivalent circuit model according to the relationship between the voltage and time in the second voltage drop segment and the relationship between the voltage and time in the voltage rebound segment.

6. The method according to claim 1, characterized in that The method of correcting the model parameters of the back-propagation neural network by the back-propagation neural network to obtain a target back-propagation neural network includes: The back propagation neural network obtains a predicted cell internal resistance parameter according to the initial cell internal resistance parameter and the test data; According to the error between the predicted battery cell internal resistance parameter and the preset expected output value, the model parameters of the back propagation neural network are iteratively adjusted and iterative prediction is performed until the error between the predicted battery cell internal resistance parameter output by the back propagation neural network and the expected output value meets the preset conditions, thereby obtaining the target back propagation neural network.

7. The method according to claim 6, characterized in that The iterative adjustment of the model parameters of the back propagation neural network according to the error between the predicted cell internal resistance parameter and the preset expected output value includes: According to the error between the predicted cell internal resistance parameter and the preset expected output value, the error gradient of each layer node is determined by using the chain rule; According to the error gradient, the weights and biases of the nodes in each layer of the back propagation neural network are adjusted.

8. A lithium-ion battery cell data processing device, characterized in that: The device comprises: An acquisition module, used to acquire test data under multiple test conditions, the test data including: ambient temperature, battery temperature, current, voltage and battery state of charge, wherein the ambient temperature of at least one test condition is less than a preset temperature; A prediction module is used to construct a back propagation neural network of the lithium-ion battery, and to input the test data under each test condition into the back propagation neural network to obtain the predicted voltage of the lithium-ion battery under each test condition; A determination module, used to determine voltage change information of the lithium-ion battery according to the predicted voltage of the lithium-ion battery under various test conditions; The determination module is further used to input the voltage change information and the test data into a pre-established equivalent circuit model to perform preliminary offline identification of the cell internal resistance parameters to obtain initial cell internal resistance parameters; A correction module, used for reversely inputting the initial cell internal resistance parameter into the back propagation neural network, and forwardly inputting the test data into the back propagation neural network, and correcting the model parameters of the back propagation neural network by the back propagation neural network to obtain a target back propagation neural network; The prediction module is also used to input the battery data of the battery to be identified into the target back propagation neural network, and the target back propagation neural network predicts the cell internal resistance parameters of the battery to be identified.

9. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of the lithium-ion battery cell data processing method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for processing cell data of a lithium-ion battery according to any one of claims 1 to 7 are executed.

Images