Battery charging and discharging state monitoring system

Abstract

The invention relates to a battery charging and discharging state monitoring system, and belongs to the technical field of battery management. A battery charge and discharge state monitoring system comprises a data acquisition module, a data calculation module, an algorithm prediction module and a thermal runaway early warning module. The data acquisition module is used for acquiring the voltage, current and temperature of the current battery; the data calculation module is used for extracting electrochemical data and heat effect data of the battery in the charging and discharging process; and the algorithm prediction module is used for training the NARX dynamic neural network by using the electrochemical data and the thermal effect data. On the basis of real-time data acquisition and dynamic calculation of an electrochemical and thermal effect model, key features such as battery internal resistance, state of charge (SOC), total heat production and temperature change rate are accurately extracted, and prediction of the thermal effect state at the next moment is realized in combination with an NARX dynamic neural network; and the system can still accurately warn the thermal runaway risk in an early warning mode under the rapidly-changing working condition.

Description

Technical Field

[0001] The present invention belongs to the technical field of battery management, and in particular, relates to a battery charging and discharging state monitoring system. Background Art

[0002] With the widespread use of lithium batteries in electric vehicles, energy storage systems, power grid base stations and other facilities, the battery may experience problems such as rapid temperature rise and abnormal voltage fluctuations during the charging and discharging process. Especially in the case of overcharging, overdischarging or harsh external environment, thermal runaway may occur, causing serious consequences such as fire; its safety monitoring issues are increasingly receiving attention. However, existing technologies still have significant deficiencies in battery operating status monitoring and thermal runaway risk warning.

[0003] On the one hand, because it is difficult to directly measure the key parameters of the battery's operating status, traditional battery management systems (BMS) rely on surface parameters for monitoring and judge battery abnormalities through a single voltage or temperature threshold; they fail to accurately analyze and extract the key characteristics of the battery under complex working conditions, especially under high load or overcharge conditions, which may lead to missed or false reports of thermal runaway risks. On the other hand, existing thermal runaway monitoring methods usually lag behind the actual occurrence time of the risk, making it difficult to achieve early warning and active intervention of thermal runaway, increasing the instability and potential risks of battery operation. Summary of the invention

[0004] In order to solve the technical problems that traditional battery management systems fail to accurately analyze and extract the key characteristics of batteries under complex working conditions; and that thermal runaway monitoring methods usually lag behind the actual occurrence time of risks, the present invention provides a battery charge and discharge state monitoring system. Based on real-time data acquisition and dynamic calculation of electrochemical and thermal effect models, key features such as battery internal resistance, state of charge (SOC), total heat generation and temperature change rate are accurately extracted, and the NARX dynamic neural network is combined to realize the prediction of the thermal effect state at the next moment. The system can still accurately warn of thermal runaway risks under rapidly changing working conditions.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A battery charge and discharge status monitoring system, comprising a data acquisition module, a data calculation module, an algorithm prediction module and a thermal runaway warning module;

[0007] The data acquisition module is used to collect the current battery voltage, current and temperature.

[0008] The data calculation module is used to perform corresponding calculations on the collected data by establishing electrochemical and thermal effect models to extract the electrochemical data and thermal effect data of the battery during the charging and discharging process;

[0009] Preferably, the electrochemical data includes the internal resistance and state of charge of the battery; and the thermal effect data includes the total heat generation of the battery.

[0010] Preferably, the specific calculation process of establishing the electrochemical model includes:

[0011] Establishing electrochemical model: Establishing electrochemical model based on equivalent circuit method; calculating internal resistance and state of charge (SOC) of battery;

[0012] Among them, the calculation formula of the internal resistance of the battery is:

[0013]

[0014] Where ΔV is the voltage change of the battery during the overcharge current interruption period; I is the current of the battery; R b is the current internal resistance of the battery;

[0015] The formula for calculating the battery's state of charge is:

[0016]

[0017] In the formula, C c is the current charging capacity of the battery, obtained by the current-time integration method; C n is the rated capacity of the battery.

[0018] Preferably, the specific calculation process of establishing the thermal effect model includes:

[0019] A thermal effect model is established based on the thermal balance equation of the battery to calculate the total heat generation of the battery; the thermal balance equation of the battery is expressed as:

[0020]

[0021] In the formula, is the battery temperature change rate per unit time; Q is the total heat generated by the battery per unit time; M is the mass of the battery; C p is the specific heat capacity of the battery (constant).

[0022] The algorithm prediction module is used to train the NARX dynamic neural network with electrochemical data and thermal effect data to predict the thermal effect data at the next moment;

[0023] Preferably, the specific implementation process of the algorithm prediction module includes:

[0024] S1) Data acquisition: Collect time series data of electrochemical and thermal effects of the battery at different SOCs;

[0025] S2) Data preprocessing: remove outliers and normalize the collected data;

[0026] S3) Constructing a NARX dynamic neural network: selecting electrochemical data and thermal effect data at an initial moment as the input layer of the NARX network; selecting thermal effect data at the next moment as the output layer of the NARX network; setting 1-2 hidden layers, and the number of nodes in each layer is determined by experiments;

[0027] Define the delay sequence of input variables (current, voltage, etc.) to capture dynamic historical data; define the delay sequence of output variables (such as temperature) to model time correlation; use the sine-cosine optimization (SCA) algorithm to optimize the parameters of the NARX dynamic neural network;

[0028] Use LM algorithm to update the weight and bias parameters of the network;

[0029] S4)NARX Network Application:

[0030] The electrochemical data and thermal effect data of the battery at the current moment are input into the NARX network to predict the thermal effect data of the battery at the next moment.

[0031] Preferably, the electrochemical data include the voltage, current, internal resistance and state of charge of the battery; the thermal effect data include the temperature change rate and total heat generation of the battery per unit time.

[0032] Preferably, the data preprocessing further comprises dividing the long time series into multiple subsequences according to the same window step size.

[0033] The thermal runaway warning module is used to monitor whether the battery has a thermal runaway risk based on the thermal effect data output by the algorithm prediction module and set the risk threshold, and issue a warning in a timely manner.

[0034] Preferably, the specific implementation process of the thermal runaway warning module includes:

[0035] The risk threshold of total heat generation is set according to the material and structural characteristics of the battery to determine the thermal high temperature state;

[0036] At the same time, a critical value of the temperature change rate is set to judge the tendency of thermal runaway;

[0037] If the total heat generated by the current battery exceeds the risk threshold, the battery is judged to have entered a hot and high temperature state;

[0038] The battery temperature change rate is further calculated to determine whether it exceeds a critical value. If the temperature change rate is higher than the critical value, the battery is judged to be at risk of thermal runaway.

[0039] The thermal runaway warning module sends warning information to the background monitoring terminal.

[0040] Preferably, a feedback control module is also included, which is used to execute the following process:

[0041] If the battery enters a hot and high temperature state, start the heat dissipation device (such as air cooling or liquid cooling) to reduce the battery temperature; if the battery is at risk of thermal runaway, disconnect the battery from the charging power source or load to prevent the thermal runaway from worsening.

[0042] Beneficial effects of the present invention:

[0043] 1. The present invention uses electrochemical and thermal effect models to accurately extract key characteristics of the battery state based on real-time data collection, and then predicts the thermal effect state of the battery at the next moment through the NARX dynamic neural network; the system can warn of thermal runaway risks in advance, significantly improving the safety of battery operation.

[0044] 2. The NARX network utilizes delayed sequences of inputs and outputs to fully consider the impact of historical characteristics on current predictions, allowing the system to accurately warn of thermal runaway risks under rapidly changing operating conditions.

[0045] 3. The thermal runaway warning module sets multi-level threshold risk assessment, and the feedback control module makes different emergency responses (starting the heat dissipation device or disconnecting the power supply) under high temperature and thermal runaway conditions; the system can effectively prevent the deterioration of battery thermal runaway and ensure the smooth and safe operation of the battery and its application system. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0047] Figure 1 The present invention is a structural framework diagram of a battery charging and discharging status monitoring system.

[0048] Figure 2 The present invention is a flowchart of an algorithm prediction module in a battery charge and discharge status monitoring system.

[0049] Figure 3 This is a flow chart of a thermal runaway warning module in a battery charge and discharge status monitoring system of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] See also Figure 1-Figure 3 As shown, a battery charge and discharge status monitoring system includes a data acquisition module, a data calculation module, an algorithm prediction module and a thermal runaway warning module;

[0052] The data acquisition module is used to collect the current battery voltage, current and temperature.

[0053] The data calculation module is used to perform corresponding calculations on the collected data by establishing electrochemical and thermal effect models to extract the electrochemical data and thermal effect data of the battery during the charging and discharging process;

[0054] Furthermore, the electrochemical data includes the internal resistance and state of charge of the battery; and the thermal effect data includes the total heat generation of the battery.

[0055] Furthermore, the specific calculation process of establishing the electrochemical model includes:

[0056] Establishing electrochemical model: Establishing electrochemical model based on equivalent circuit method; calculating internal resistance and state of charge (SOC) of battery;

[0057] Among them, the calculation formula of the internal resistance of the battery is:

[0058]

[0059] Where ΔV is the voltage change of the battery during the overcharge current interruption period; I is the current of the battery; R b is the current internal resistance of the battery;

[0060] The formula for calculating the battery's state of charge is:

[0061]

[0062] In the formula, C c is the current charging capacity of the battery, obtained by integrating the current over time; C n is the rated capacity of the battery.

[0063] Furthermore, the specific calculation process of establishing the thermal effect model includes:

[0064] Based on the thermal balance equation of the battery, the total heat generation of the battery is calculated; the thermal balance equation of the battery is expressed as:

[0065]

[0066] In the formula, is the battery temperature change rate per unit time; Q is the total heat generated by the battery per unit time; M is the mass of the battery; C p is the specific heat capacity of the battery (constant).

[0067] Specifically, in order to construct the electrochemical and thermal effect model of lithium batteries, the electrochemical model quantifies the state of the battery's charge and discharge process through the battery's electrochemical parameters (such as current and voltage). Based on the equivalent circuit theory, the relationship between transient voltage and current changes is used to calculate the battery's internal resistance, and the SOC is analyzed by the current-time integration method; reflecting the state changes of the battery during the charge and discharge process.

[0068] The thermal effect model is based on the principle of thermal balance to describe the heat generated by the battery during the charging and discharging process; as well as the influence of electrochemical parameters (internal resistance, SOC, etc.) on the thermal effect.

[0069] By building electrochemical and thermal effect models, more characteristic parameters are calculated and extracted; at the same time, more comprehensive data is collected for the next step of training the NARX dynamic neural network, so as to specifically describe and quantify the electrochemical behavior and thermal effect behavior of the battery. Including the following data:

[0070] Electrochemical data:

[0071] Battery voltage (V): The terminal voltage of a battery can provide information about the change in potential during the charge and discharge process of the battery and is an important indicator of the kinetics of electrochemical reactions.

[0072] Battery current (I): It is used to describe the charge and discharge current of the battery, which is directly related to the battery charging process, the ion flow within the battery and its thermal effect.

[0073] Battery internal resistance (R): The internal resistance of a battery reflects the electrochemical and physical properties inside the battery, affecting the battery's energy conversion and heat generation.

[0074] Battery State of Charge (SOC): The battery SOC is usually estimated by the current integration method. The electrochemical model maps the battery voltage, current, temperature and other information to the SOC, and obtains the battery state of charge through reverse calculation.

[0075] Electrochemical reaction rates and lithium ion diffusion coefficients: electrochemical constants of the battery at different temperatures; these constants are used to build an electrochemical model of the battery.

[0076] Thermal effect data:

[0077] Battery temperature (T): The operating temperature of the battery affects the electrochemical performance of the battery and the probability of thermal runaway, and is a critical parameter in the thermal effect model.

[0078] Total heat generation (Q): The sum of all heat generated by the battery during operation, reflecting the comprehensive characteristics of the internal and external thermal effects of the battery. It is an important parameter for assessing the risk of thermal runaway of the battery, including reversible heat, irreversible heat, ohmic heat, chemical reaction heat, and heat dissipation.

[0079] Specific heat capacity and thermal conductivity of battery materials: Thermophysical parameters of battery materials determine the distribution and propagation of heat in the battery.

[0080] As an optional implementation, the thermal effect data may also include Ohmic heat (Qo): the heat caused by the flow of current inside the battery, which is generally proportional to the internal resistance of the battery and the current.

[0081] Chemical reaction heat (Qr): The heat caused by the chemical reactions inside the battery, mainly involving the insertion / deinsertion process of lithium ions, changes in the SE I film, manganese dissolution, etc.

[0082] Phase change heat: During the charging process, the battery materials may undergo phase changes, such as structural changes in the positive electrode material, which may also release or absorb heat.

[0083] Heat dissipation of the battery: The heat exchange between the battery and the external environment is mainly related to the cooling or heat dissipation method outside the battery.

[0084] The total heat production is calculated as:

[0085] Q=Q o +Q r -Q d ;

[0086] In the formula, Q o is ohmic heat; Q r is the heat of chemical reaction; Q d is the heat dissipation;

[0087] Among them, ohmic heat is mainly generated by the internal resistance of the battery, and the formula is:

[0088] Q o =I 2 ·R b ;

[0089] In the formula, R b is the current internal resistance of the battery; I is the current battery current.

[0090] Therefore, the data calculation module extracts electrochemical data (such as internal resistance, SOC) and thermal effect data (such as total heat production, temperature change rate) through real-time acquisition and model calculation, providing high-quality input data for subsequent prediction and early warning of the system.

[0091] The algorithm prediction module is used to train the NARX dynamic neural network with electrochemical data and thermal effect data to predict the thermal effect data at the next moment;

[0092] Furthermore, the specific implementation process of the algorithm prediction module includes:

[0093] S1) Data acquisition: Collect time series data of electrochemical and thermal effects of the battery at different SOCs;

[0094] S2) Data preprocessing: Remove outliers and normalize the collected data; remove outliers in the collected data to ensure the reliability of the input data. Scale data of different dimensions to the same range to improve the training stability of the model.

[0095] Furthermore, the data preprocessing also includes dividing the long time series into multiple subsequences according to the same window step size.

[0096] S3) constructing a NARX dynamic neural network: selecting electrochemical data and thermal effect data at an initial moment as the input layer of the NARX network; selecting thermal effect data at the next moment as the output layer of the NARX network;

[0097] In the specific implementation process, according to the data dimension and the window step, the number of input layer nodes is m×n; where m is the data dimension (such as the number of characteristics such as voltage and current), and n is the window step.

[0098] Similarly, the data dimension of each output layer (such as temperature change rate and total heat generation) corresponds to a window step.

[0099] There are 1-2 hidden layers, and the number of nodes in each layer is determined by experiments; usually between 10-50.

[0100] Define the delay sequence of input variables (current, voltage, etc.) to capture dynamic historical data; define the delay sequence of output variables (such as temperature) to model time correlation; use the sine-cosine optimization (SCA) algorithm to optimize the parameters of the NARX dynamic neural network to avoid falling into the local optimal solution.

[0101] The LM algorithm is used to update the weight and bias parameters of the network and improve the fitting accuracy.

[0102] S4)NARX Network Application:

[0103] The electrochemical data and thermal effect data of the battery at the current moment are input into the NARX network to predict the thermal effect data of the battery at the next moment.

[0104] Furthermore, the electrochemical data includes the voltage, current, internal resistance and state of charge of the battery; and the thermal effect data includes the temperature and total heat generation of the battery.

[0105] The design concept principle of the present invention is that the NARX dynamic neural network is a recursive neural network for time series modeling, which can capture complex dynamic nonlinear relationships through delayed sequences of inputs and outputs. It can use the input and output information of the previous moment to predict the output at the current moment. In the prediction of the thermal effect of the battery, based on the time series data of electrochemical and thermal effects, the NARX dynamic neural network is used to model the dynamic association between electrochemical parameters and thermal effects. There is a strong coupling and dynamic correlation between the electrochemical data and the thermal effect data. The input and output delay characteristics of the NARX network can accurately model this relationship. The NARX network uses delayed sequences of inputs and outputs to fully consider the impact of historical characteristics on current predictions, which is suitable for the dynamic prediction scenario of battery thermal effect data.

[0106] In the specific implementation process, the NARX network can learn the evolution law between the electrochemical data and thermal effects of the battery based on experimental data or historical data. The NARX network updates the network weights, bias parameters and time delay network through self-learning to learn and train the network with the current and historical information of the input layer and the historical information of the output layer.

[0107] When the NARX dynamic neural network is used to construct a battery dynamic system model, the input delay, output delay and number of hidden layer nodes affect the estimation performance of the neural network. The present invention uses the sine-cosine optimization algorithm (SCA) to optimize the input delay, feedback delay and number of hidden layer nodes of the NARX dynamic neural network. The specific implementation method is as follows:

[0108] 1. Determine the optimization goal: Use the mean square error (MSE) as the fitness function of the NARX dynamic neural network. The goal is to find a set of NARX dynamic neural network parameters that minimizes the mean square error.

[0109] 2. Initialize the sine-cosine algorithm parameters: Set the search population number of the sine-cosine optimization algorithm to 20 and the maximum number of iterations to 50.

[0110] 3. Set the parameter search range: Set the search range of input delay, output delay and number of hidden layer nodes to.

[0111] 4. Iterative optimization:

[0112] a) Randomly generate a set of initial solutions within the set parameter search range, representing the input delay, output delay and number of hidden layer nodes of the NARX dynamic neural network.

[0113] b) Substitute the generated solution into the NARX dynamic neural network model for training and calculate the mean square error (MSE) of the model.

[0114] c) Update the value of each solution according to the update formula of the sine-cosine algorithm.

[0115] Repeat steps b) and c) until the maximum number of iterations is reached.

[0116] 5. Output the optimal solution: After the iteration, the solution with the smallest fitness value is output, which is the optimal parameter of the NARX dynamic neural network.

[0117] The algorithm prediction module is an important component of the system. It predicts the thermal effect data (such as temperature change rate and total heat generation) at the next moment through the NARX dynamic neural network, provides prior information for the thermal runaway warning module, and supports timely risk assessment. The time delay structure and nonlinear modeling capabilities of the NARX network provide a technical basis for the expansion of the system.

[0118] As an optional implementation, the input layer of the NARX dynamic neural network can further improve the prediction accuracy by adding more feature dimensions (such as ambient temperature and material properties) to enhance the system's adaptability to different types of batteries.

[0119] As an optional implementation,

[0120] The thermal runaway warning module is used to monitor whether the battery has a thermal runaway risk and issue a warning in a timely manner based on the thermal effect data output by the algorithm prediction module by setting a reasonable risk threshold.

[0121] Furthermore, the specific implementation process of the thermal runaway warning module includes:

[0122] The risk threshold of total heat generation is set according to the material and structural characteristics of the battery to determine the thermal high temperature state;

[0123] At the same time, a critical value of the temperature change rate is set to judge the tendency of thermal runaway;

[0124] If the total heat generated by the current battery exceeds the risk threshold, the battery is judged to have entered a hot and high temperature state;

[0125] The battery temperature change rate is further calculated to determine whether it exceeds a critical value. If the temperature change rate is higher than the critical value, the battery is judged to be at risk of thermal runaway.

[0126] The thermal runaway warning module sends warning information to the background monitoring terminal.

[0127] Specifically, the thermal effect of the battery is closely related to its internal chemical composition and structure. For example, the electrolyte, negative electrode (graphite), and positive electrode materials (such as LiCoO2, LiFePO4, etc.) used in lithium-ion batteries have different thermal characteristics. Different types of batteries will have different heat generation. For common lithium-ion batteries, the maximum safe working risk threshold is set at 70-80°C. If the total heat generation Q exceeds the set risk threshold, it is determined that the battery has entered a hot high temperature state and enters the next judgment step.

[0128] Temperature change rate A critical value of the temperature change rate can be set based on experimental data or battery safety standards. For common lithium-ion batteries, when the temperature change rate exceeds 5-10℃ / min, the battery may enter a thermal runaway state. Therefore, if the battery temperature change rate exceeds this critical value, it means that the battery temperature changes too quickly and there is a risk of thermal runaway.

[0129] Furthermore, it also includes a feedback control module for executing the following process: if the battery enters a hot and high temperature state, the heat dissipation device (such as air cooling or liquid cooling) is started to reduce the battery temperature; if the battery has a risk of thermal runaway, the battery is disconnected from the charging power supply or load to prevent the thermal runaway from worsening.

[0130] Specifically, when the battery is determined to be in a thermal runaway risk state, the thermal runaway warning module generates warning information, which generally includes the current temperature of the battery, the temperature change rate, the heat generation, and the risk level.

[0131] The early warning information is sent to the background monitoring terminal through the communication system, and the maintenance personnel or monitoring personnel are notified in time so that corresponding emergency measures can be taken, such as cutting off the power supply, reducing the load, starting the cooling system, etc.

[0132] In summary, the battery charge and discharge status monitoring system of the present invention realizes real-time monitoring of the battery operating status and effective prevention of thermal runaway risks through the coordinated work of data acquisition, modeling calculation and algorithm prediction, risk warning and feedback control. It can be widely used in lithium battery management systems (BMS), energy storage systems, electric vehicles, smart grids and other fields to solve the thermal runaway problem in the battery charge and discharge process, improve the safety, stability and service life of the battery system, and is of great significance to the development of battery technology and new energy fields.

[0133] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system and module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0134] In the several embodiments provided in the present application, it should be understood that the disclosed systems, modules and processes can be implemented in other ways. For example, the module embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules 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 an indirect coupling or communication connection through some interfaces, devices or units.

[0135] If the module 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 all or 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 a number of 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, random access memory), disk or optical disk and other media that can store program code.

[0136] In the description of the specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0137] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. A battery charge and discharge status monitoring system, characterized in that: It includes data acquisition module, data calculation module, algorithm prediction module and thermal runaway warning module; The data acquisition module is used to collect the current battery voltage, current and temperature; The data calculation module is used to perform corresponding calculations on the collected data by establishing electrochemical and thermal effect models to extract the electrochemical data and thermal effect data of the battery during the charging and discharging process; The algorithm prediction module is used to train the NARX dynamic neural network with electrochemical data and thermal effect data to predict the thermal effect data at the next moment; The thermal runaway warning module is used to monitor whether the battery has a thermal runaway risk based on the thermal effect data output by the algorithm prediction module and set the risk threshold, and issue a warning in a timely manner.

2. A battery charge and discharge status monitoring system according to claim 1, characterized in that: The electrochemical data include the internal resistance and state of charge of the battery; and the thermal effect data include the total heat generation of the battery.

3. A battery charge and discharge status monitoring system according to claim 1, characterized in that: The specific calculation process of the electrochemical model includes: Establishing electrochemical model: Establishing electrochemical model based on equivalent circuit method; calculating internal resistance and state of charge of battery; Among them, the calculation formula of the internal resistance of the battery is: Where ΔV is the voltage change of the battery during the overcharge current interruption period; I is the current of the battery; R b is the current internal resistance of the battery; The formula for calculating the battery's state of charge is: In the formula, C c is the current charging capacity of the battery, obtained by the current-time integration method; C n is the rated capacity of the battery.

4. A battery charge and discharge status monitoring system according to claim 1, characterized in that: The specific calculation process of the thermal effect model includes: A thermal effect model is established based on the thermal balance equation of the battery to calculate the total heat generation of the battery; the thermal balance equation of the battery is expressed as: In the formula, is the battery temperature change rate per unit time; Q is the total heat generated by the battery per unit time; M is the mass of the battery; C p is the specific heat capacity of the battery.

5. A battery charge and discharge status monitoring system according to claim 1, characterized in that: The specific implementation process of the algorithm prediction module includes: S1) Data acquisition: Collect time series data of electrochemical and thermal effects of the battery at different SOCs; S2) Data preprocessing: remove outliers and normalize the collected data; S3) Constructing a NARX dynamic neural network: selecting electrochemical data and thermal effect data at an initial moment as the input layer of the NARX network; selecting thermal effect data at the next moment as the output layer of the NARX network; setting 1-2 hidden layers, and the number of nodes in each layer is determined by experiments; Define the delayed sequence of input variables to capture dynamic historical data; define the delayed sequence of output variables to model time correlation; use the sine-cosine optimization algorithm to optimize the parameters of the NARX dynamic neural network; Use LM algorithm to update the weight and bias parameters of the network; S4) NARX network application: The electrochemical data and thermal effect data of the battery at the current moment are input into the NARX network to predict the thermal effect data of the battery at the next moment.

6. A battery charge and discharge status monitoring system according to claim 5, characterized in that: The electrochemical data include the voltage, current, internal resistance and state of charge of the battery; the thermal effect data include the temperature change rate and total heat generation of the battery per unit time.

7. A battery charge and discharge status monitoring system according to claim 5, characterized in that: The data preprocessing step S2) further includes: dividing the long time series into multiple subsequences according to the same window step size.

8. A battery charge and discharge status monitoring system according to claim 1, characterized in that: The specific implementation process of the thermal runaway warning module includes: The risk threshold of total heat generation is set according to the material and structural characteristics of the battery to determine the thermal high temperature state; At the same time, a critical value of the temperature change rate is set to judge the tendency of thermal runaway; If the total heat generated by the current battery exceeds the risk threshold, the battery is judged to have entered a hot and high temperature state; The battery temperature change rate is further calculated to determine whether it exceeds a critical value. If the temperature change rate is higher than the critical value, the battery is judged to be at risk of thermal runaway. The thermal runaway warning module sends warning information to the background monitoring terminal.

9. A battery charge and discharge status monitoring system according to claim 8, characterized in that: It also includes a feedback control module to perform the following processes: If the battery enters a hot state, the heat dissipation device is activated to reduce the battery temperature; If there is a risk of thermal runaway of the battery, disconnect the battery from the charging source or load.

Images