A battery thermal runaway state monitoring and evaluation method based on linear discriminant analysis

Abstract

The present disclosure is about a battery thermal runaway state monitoring and evaluation method based on linear discriminant analysis. The method includes: obtaining the operating state data of the battery to be monitored; obtaining the historical operating state data of the battery to be monitored in a first time period, and determining the characteristic gas concentration change rate, pressure change rate, temperature change rate and volume change rate of the battery to be monitored in the first time period based on the historical operating state data; using the operating state data to determine the thermal runaway risk index value of the battery to be monitored; inputting the operating state data, concentration change rate, pressure change rate and temperature change rate into a first prediction model to obtain the volume prediction value and volume change rate prediction value in the second time period; determining a first weight value based on a first mapping relationship; determining the product of the thermal runaway risk index value and the first weight value to obtain a comprehensive risk index value, and outputting corresponding early warning information based on the comprehensive risk index value. This solution improves the timeliness of monitoring the thermal runaway state of the battery.

Description

Technical Field

[0001] The present disclosure relates to the technical field of battery safety monitoring, and in particular to a battery thermal runaway state monitoring and evaluation method based on linear discriminant analysis. Background Art

[0002] Batteries are widely used in energy storage and power applications. As battery energy density increases, the energy released after thermal runaway also increases, which can easily lead to serious consequences. Current firefighting detection methods for battery thermal runaway typically use the characteristic gases produced after thermal runaway to determine whether thermal runaway has occurred. However, batteries are often stored in relatively confined spaces, which causes the characteristic gases to accumulate and increase in concentration, easily exceeding the detector's range limit. Consequently, it is impossible to effectively determine whether the subsequent battery thermal runaway will continue to intensify. Firefighting actions can only be provided based on a countdown strategy based on empirical data, resulting in poor timeliness and accuracy in monitoring the battery thermal runaway state. Summary of the Invention

[0003] In order to overcome the problems existing in the related art, the present disclosure provides a battery thermal runaway state monitoring and evaluation method based on linear discriminant analysis.

[0004] According to a first aspect of an embodiment of the present disclosure, a method for monitoring and evaluating a battery thermal runaway state based on linear discriminant analysis is provided, comprising:

[0005] Acquiring operating status data inside the battery to be monitored; the operating status data includes characteristic gas concentration, pressure value, temperature value and sound data;

[0006] Determining a thermal runaway risk index value of the battery to be monitored using the characteristic gas concentration, pressure value, temperature value, and sound data;

[0007] Obtaining historical operating status data of the battery to be monitored within a first time period, and determining, based on the historical operating status data, a characteristic gas concentration change rate, a pressure change rate, a temperature change rate, and a volume change rate within the battery to be monitored within the first time period, respectively; the first time period being a time period corresponding to a first preset time length before a current time node;

[0008] Inputting the characteristic gas concentration, pressure value, temperature value, sound data, temperature change rate, pressure change value, characteristic gas concentration change rate, and volume change rate into a trained first prediction model, obtaining a volume prediction value and a volume change rate prediction value within a second time period output by the first prediction model; the second time period being a time period corresponding to a second preset time length after the current time node;

[0009] Determining a first weight value that matches the volume prediction value and the volume change rate prediction value based on a preset first mapping relationship; wherein the first mapping relationship includes a mapping relationship between the volume value, the volume change rate, and the weight value;

[0010] The product of the thermal runaway risk index value and the first weight value is determined to obtain a comprehensive risk index value, and corresponding warning information is output based on the comprehensive risk index value.

[0011] In some embodiments of the present disclosure, determining the thermal runaway risk index value of the battery to be monitored by using the characteristic gas concentration, pressure value, temperature value, and sound data includes:

[0012] Extracting at least one high-dimensional feature from the sound data, and performing dimensionality reduction processing on the at least one high-dimensional feature using linear discriminant analysis to obtain a target feature;

[0013] The characteristic gas concentration, pressure value, temperature value and the target feature are input into the trained thermal runaway prediction model to obtain a thermal runaway risk index value output by the thermal runaway prediction model.

[0014] In some embodiments of the present disclosure, the first prediction model is trained using the following steps:

[0015] Acquire battery operating status data samples within a third time period; the battery operating status data samples include characteristic gas concentration samples, pressure value samples, temperature value samples, and sound sample data; the third time period is a time period corresponding to a first preset time length before the battery operating status data samples are collected;

[0016] Determine, based on the operating status data samples, a sample characteristic gas concentration change rate, a sample pressure change rate, a sample temperature change rate, and a sample volume change rate within the third time period;

[0017] Inputting the characteristic gas concentration samples, pressure value samples, temperature value samples, sound sample data, sample characteristic gas concentration change rate, sample pressure change rate, sample temperature change rate, and sample volume change rate into a neural network model to be trained, and obtaining a volume prediction value and a volume change rate prediction value within a fourth time period output by the neural network model; the fourth time period being a time period corresponding to a second preset time length after collecting the battery operating status data samples;

[0018] Calculating a loss function between the volume prediction value and the sound sample data to obtain a first loss value;

[0019] Calculating a loss function between the volume change rate prediction value and the sample volume change rate to obtain a second loss value;

[0020] When the first loss value does not meet the first preset condition and / or the second loss value does not meet the second preset condition, the first loss value and the second loss value are used to adjust the parameters of the neural network model, and the step of obtaining the battery operating status data sample within the third time period is returned to execute until the first loss value meets the first preset condition and the second loss value meets the second preset condition, thereby obtaining the first prediction model.

[0021] In some embodiments of the present disclosure, after inputting the characteristic gas concentration, pressure value, temperature value, concentration change rate, pressure change rate, and temperature change rate into the trained first prediction model to obtain the volume prediction value and volume change rate prediction value for the second time period output by the first prediction model, the method further includes:

[0022] Acquiring target sound data within the second time period, and determining an actual volume and an actual volume change rate of the battery to be monitored within the second time period based on the target sound data;

[0023] Calculating a loss function between the actual volume and the predicted volume value to obtain a third loss value;

[0024] calculating a loss function between the volume prediction value and the volume change rate prediction value to obtain a fourth loss value;

[0025] When the third loss value does not satisfy the first preset condition and / or the fourth loss value does not satisfy the second preset condition, the first prediction model is adjusted using the third loss value and the fourth loss value.

[0026] In some embodiments of the present disclosure, determining a first weight value that matches the volume prediction value and the volume change rate prediction value based on a preset first mapping relationship includes:

[0027] Acquire multiple volume value intervals and multiple volume change rate intervals from the first mapping relationship;

[0028] determining a target volume value interval to which the volume prediction value belongs from the plurality of volume value intervals, and determining a target volume change rate interval to which the volume change rate prediction value belongs from the plurality of volume change rate intervals;

[0029] A weight value that matches both the target volume value interval and the target volume change rate interval is determined from the first mapping relationship to obtain the first weight value.

[0030] In some embodiments of the present disclosure, outputting corresponding warning information based on the comprehensive risk indicator value includes:

[0031] Obtain multiple preset comprehensive risk indicator intervals;

[0032] Selecting the comprehensive risk indicator interval to which the comprehensive risk indicator value belongs from the multiple comprehensive risk indicator intervals to obtain a target comprehensive risk indicator interval;

[0033] Determine the warning level associated with the target comprehensive risk indicator interval;

[0034] The warning information is output according to the warning level.

[0035] In some embodiments of the present disclosure, after obtaining the operating status data of the battery to be monitored, the method further includes:

[0036] When it is detected that at least one of the characteristic gas concentration sensor for obtaining the characteristic gas concentration, the pressure sensor for obtaining the pressure value, and the temperature sensor for obtaining the temperature value exceeds a range limit, the sensor that exceeds the range limit is determined as a target sensor;

[0037] determining target operating state data collected by the target sensor from the operating state data;

[0038] Acquire historical target operating status data collected by the target sensor within a first historical time period; the first historical time period is a time period corresponding to a preset time length before the target sensor exceeds a range limit;

[0039] Generating a first trend graph using the historical target operating status data, and performing trend prediction on the first trend graph using a curve analysis algorithm to obtain predicted operating status data corresponding to the current time node;

[0040] Replacing the target operating state data with the predicted operating state data to obtain updated operating state data;

[0041] Determining the thermal runaway risk index value of the battery to be monitored by using the characteristic gas concentration, pressure value, temperature value, and sound data includes:

[0042] Determining a thermal runaway risk index value of the battery to be monitored using the updated characteristic gas concentration, pressure value, temperature value, and sound data;

[0043] The step of inputting the characteristic gas concentration, pressure value, temperature value, concentration change rate, pressure change rate, and temperature change rate into the trained first prediction model to obtain a volume prediction value and a volume change rate prediction value within a second time period output by the first prediction model includes:

[0044] The updated characteristic gas concentration, pressure value, temperature value, concentration change rate, pressure change rate and temperature change rate are input into the first prediction model that has completed training to obtain the volume prediction value and volume change rate prediction value within the second time period output by the first prediction model.

[0045] According to a second aspect of an embodiment of the present disclosure, a battery thermal runaway state monitoring and evaluation device based on linear discriminant analysis is provided, comprising:

[0046] A first acquisition module is used to acquire operating status data inside the battery to be monitored; the operating status data includes characteristic gas concentration, pressure value, temperature value and sound data;

[0047] a second determination module, configured to determine a thermal runaway risk index value of the battery to be monitored by using the characteristic gas concentration, pressure value, temperature value, and sound data;

[0048] a first determining module, configured to obtain historical operating status data of the battery to be monitored within a first time period, and determine, based on the historical operating status data, a characteristic gas concentration change rate, a pressure change rate, a temperature change rate, and a volume change rate within the battery to be monitored within the first time period; the first time period being a time period corresponding to a first preset time length before a current time node;

[0049] a prediction module, configured to input the characteristic gas concentration, pressure value, temperature value, sound data, temperature change rate, pressure change value, characteristic gas concentration change rate, and volume change rate into a trained first prediction model, and obtain a volume prediction value and a volume change rate prediction value within a second time period output by the first prediction model; the second time period being a time period corresponding to a second preset time length after the current time node;

[0050] a third determining module, configured to determine a first weight value that matches the volume prediction value and the volume change rate prediction value based on a preset first mapping relationship, wherein the first mapping relationship includes a mapping relationship between the volume value, the volume change rate, and the weight value;

[0051] The output module is used to determine the product of the thermal runaway risk index value and the first weight value to obtain a comprehensive risk index value, and output corresponding warning information based on the comprehensive risk index value.

[0052] According to a third aspect of an embodiment of the present disclosure, an electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described in any one of the first aspects is implemented.

[0053] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method according to any one of the first aspects is implemented.

[0054] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the method as described in any one of the first aspects when executed by a processor.

[0055] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: by obtaining the operating status data inside the battery to be monitored; obtaining the historical operating status data of the battery to be monitored within a first time period, and determining the characteristic gas concentration change rate, pressure change rate, temperature change rate and volume change rate inside the battery to be monitored within the first time period based on the historical operating status data; determining the thermal runaway risk index value of the battery to be monitored using the characteristic gas concentration, pressure value, temperature value and sound data; inputting the characteristic gas concentration, pressure value, temperature value, concentration change rate, pressure change rate and temperature change rate into the first prediction model that has been trained to obtain the volume prediction value and volume change rate prediction value within the second time period output by the first prediction model; based on a preset first mapping relationship, determining a first weight value that matches the volume prediction value and the volume change rate prediction value; determining the product of the thermal runaway risk index value and the first weight value to obtain a comprehensive risk index value, and outputting corresponding warning information based on the comprehensive risk index value. Based on the correlation between the concentration of characteristic gases, pressure values, temperature values ​​and sound data inside the battery, the first prediction model is used to predict the volume value and volume change rate within a preset time period in the future. The operating status data before the range limit of the data acquisition equipment is exceeded and the volume prediction data are used to effectively estimate the thermal runaway state of the battery in advance. This avoids the problem of the actual operating status data exceeding the range limit and making it impossible to monitor the thermal runaway state of the battery in a timely manner, thereby improving the timeliness and accuracy of the monitoring results.

[0056] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0058] Figure 1 The present invention is a flowchart of a method for monitoring and evaluating a battery thermal runaway state based on linear discriminant analysis according to an exemplary embodiment.

[0059] Figure 2The present invention is a block diagram of a battery thermal runaway state monitoring and evaluation device based on linear discriminant analysis according to an exemplary embodiment.

[0060] Figure 3 The present invention is a block diagram of an apparatus for a method for monitoring and evaluating a battery thermal runaway state based on linear discriminant analysis according to an exemplary embodiment. DETAILED DESCRIPTION

[0061] Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. In the following description, when referring to the drawings, like numbers in different figures represent like or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present invention, as detailed in the appended claims.

[0062] The terms used in the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure. The singular forms "a", "an" and "the" used in the present disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0063] It should be understood that although the terms first, second, third, etc. may be used to describe various information in the embodiments of the present disclosure, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of the embodiments of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0064] Furthermore, the various forms of processes shown in the embodiments of this disclosure may be used to reorder, add, or delete steps. For example, the steps described in this application may be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0065] Batteries are widely used in energy storage and power applications. As battery energy density increases, the energy released after thermal runaway also increases, which can easily lead to serious consequences. Current firefighting detection methods for battery thermal runaway typically use the characteristic gases produced after thermal runaway to determine whether thermal runaway has occurred. However, batteries are often stored in relatively confined spaces, which causes the characteristic gases to accumulate and increase in concentration, easily exceeding the detector's range limit. Consequently, it is impossible to effectively determine whether the subsequent battery thermal runaway will continue to intensify. Firefighting actions can only be provided based on a countdown strategy based on empirical data, resulting in poor timeliness and accuracy in monitoring the battery thermal runaway state.

[0066] In order to solve the above problems, the present disclosure provides a battery thermal runaway state monitoring and evaluation method based on linear discriminant analysis, which obtains the operating state data inside the battery to be monitored; obtains the historical operating state data of the battery to be monitored in a first time period, and determines the characteristic gas concentration change rate, pressure change rate, temperature change rate and volume change rate inside the battery to be monitored in the first time period based on the historical operating state data; uses the characteristic gas concentration, pressure value, temperature value and sound data to determine the thermal runaway risk index value of the battery to be monitored; inputs the characteristic gas concentration, pressure value, temperature value, concentration change rate, pressure change rate and temperature change rate into a first prediction model that has been trained to obtain a volume prediction value and a volume change rate prediction value in a second time period output by the first prediction model; based on a preset first mapping relationship, determines a first weight value that matches the volume prediction value and the volume change rate prediction value; determines the product of the thermal runaway risk index value and the first weight value to obtain a comprehensive risk index value, and outputs corresponding warning information based on the comprehensive risk index value. Based on the correlation between the concentration of characteristic gases, pressure values, temperature values ​​and sound data inside the battery, the first prediction model is used to predict the volume value and volume change rate within a preset time period in the future. The operating status data before the range limit of the data acquisition equipment is exceeded and the volume prediction data are used to effectively estimate the thermal runaway state of the battery in advance. This avoids the problem of the actual operating status data exceeding the range limit and making it impossible to monitor the thermal runaway state of the battery in a timely manner, thereby improving the timeliness and accuracy of the monitoring results.

[0067] Figure 1 FIG. 1 is a flow chart of a method for monitoring and evaluating a battery thermal runaway state based on linear discriminant analysis according to an exemplary embodiment. Figure 1 As shown, it should be noted that the battery thermal runaway state monitoring and evaluation method based on linear discriminant analysis of the embodiment of the present disclosure is applied to the battery thermal runaway state monitoring and evaluation device based on linear discriminant analysis. Figure 1 As shown, the method may include the following steps:

[0068] Step 101: Acquire the internal operating status data of the battery to be monitored.

[0069] The operating status data includes characteristic gas concentration, pressure value, temperature value and sound data.

[0070] It can be understood that battery thermal runaway refers to a chain reaction that occurs in the battery under specific conditions, causing the temperature to rise sharply and possibly causing fire or explosion.

[0071] During the battery charging process, if the battery is overcharged, the internal electrolyte will decompose and produce a large amount of gas, which will increase the internal pressure of the battery and cause the battery shell to swell and bulge. In addition, as the internal pressure of the battery continues to increase, the battery shell will gradually deform and even bulge. If the pressure continues to increase, the battery shell may rupture. In addition, during the charging process, if the battery is overcharged, the internal electrolyte will decompose and produce gas, which will further increase the internal pressure, causing the battery to swell or even burst. In addition, high temperature will also affect the safety performance of the battery, which may cause the battery to bulge or even burst.

[0072] Therefore, the characteristic gas concentration, pressure value, temperature value and sound data inside the monitored battery can be collected in real time to assess the possibility of thermal runaway risk in the battery.

[0073] In one example, the characteristic gas may be any one or more of VOC, CO, CO2, H2, HF, and CH4. Furthermore, the sound data may be the sound data of a pressure relief valve rupturing corresponding to the monitored battery, or the sound data of a bulging or bursting battery casing.

[0074] In one embodiment, the characteristic gas can be collected by a gas sensor; the above pressure value can be collected by an air pressure sensor; the above temperature value can be collected by a temperature sensor; and the above sound data can be collected by a sound sensor.

[0075] In another example, the above-mentioned operating status data can be collected by using a pack detector that integrates a gas sensor, a gas sensor, a temperature sensor, and a sound sensor.

[0076] Step 102 : Determine the thermal runaway risk index value of the battery to be monitored using characteristic gas concentration, pressure value, temperature value, and sound data.

[0077] In one embodiment, the characteristic gas concentration, pressure value, temperature value and sound data collected by the monitored battery at the current time node can be used to conduct a preliminary assessment of whether the battery has a thermal runaway risk and obtain a thermal runaway risk index value.

[0078] It is understandable that, since the current node may be in the early stage of thermal runaway, the sound data of the pressure relief valve bursting or the sound data of the battery casing to be monitored bulging or bursting may be 0 or have a low volume.

[0079] In some embodiments of the present application, step 102 may specifically include the following steps:

[0080] Extracting at least one high-dimensional feature from the sound data, and performing dimensionality reduction processing on the at least one high-dimensional feature using linear discriminant analysis to obtain a target feature;

[0081] The characteristic gas concentration, pressure value, temperature value and operating status data target features are input into the trained thermal runaway prediction model to obtain the thermal runaway risk index value output by the thermal runaway prediction model.

[0082] In one embodiment, the above-mentioned high-dimensional features may include time domain features and frequency domain features. Based on the signal processing methods of time domain, frequency domain and time-frequency domain, feature indicators that can characterize the battery status information are extracted to construct a high-dimensional mixed domain feature set of training samples and a high-dimensional mixed domain feature set of test samples.

[0083] Furthermore, the sound data can be analyzed in the time domain, and the extracted time domain features may include maximum value, standard deviation, root mean square value, mean, skewness, kurtosis, peak index, margin index and pulse index; the sound data can be analyzed in the frequency domain, and the extracted frequency domain features may include mean frequency, frequency standard deviation, root mean square frequency and other indicators that can reflect the degree of spectrum dispersion and the position of the main frequency band; the sound data can be analyzed in the time-frequency domain, and the sound data can be subjected to variational mode decomposition, and then the energy entropy value of each component signal can be calculated and used as the characteristic index of the time-frequency domain to obtain a variety of high-dimensional features.

[0084] As an example of an implementation, after obtaining the above-mentioned multiple high-dimensional features, all the extracted high-dimensional features can be analyzed for their distinguishing effects on different state information, and high-dimensional features with better distinguishing effects can be selected. The selected high-dimensional features can be normalized to complete the construction of the high-dimensional mixed domain feature set.

[0085] It should be noted that the specific implementation of using linear discriminant analysis to perform dimensionality reduction processing on at least one high-dimensional feature is an existing technology and will not be described in detail here.

[0086] In one embodiment, the thermal runaway prediction model may adopt a particle swarm optimization support vector machine model. Specifically, the following steps may be used to construct the particle swarm optimization support vector machine model:

[0087] Initialize the basic parameters of the particle swarm and determine the fitness function in the optimization process; generate a particle population, use the parameter combination that affects the classification performance of the support vector machine as the position of the particle, and randomly generate a certain number of influencing parameter combinations as the initial position of the particle; train the support vector machine under different particle position conditions and calculate the fitness value of each particle; by comparing the size of the fitness value, update the individual optimal solution and the global optimal solution of the particle swarm, and then determine the position coordinates of the next movement of the particle; if the expected accuracy is not achieved or the set number of cycles is not completed, return to the step of training the support vector machine under different particle position conditions and calculating the fitness value of each particle. If the expected accuracy is achieved or the set number of cycles is completed, the cycle can be stopped, and the particle position corresponding to the obtained global optimal solution is the optimal parameter combination of the support vector machine.

[0088] In some embodiments of the present application, after step 101, the method may further include the following steps:

[0089] When it is detected that at least one of the characteristic gas concentration sensor for obtaining characteristic gas concentration, the pressure sensor for obtaining pressure value, and the temperature sensor for obtaining temperature value exceeds the range limit, the sensor that exceeds the range limit is determined as the target sensor;

[0090] determining target operating state data collected by a target sensor from the operating state data;

[0091] Acquire historical target operating status data collected by the target sensor within a first historical time period; the first historical time period is a time period corresponding to a preset time length before the target sensor exceeds a range limit;

[0092] Generate a first trend chart using historical target operating status data, and use a curve analysis algorithm to perform trend prediction on the first trend chart to obtain predicted operating status data corresponding to the current time node;

[0093] Replacing the target operating status data with the predicted operating status data to obtain updated operating status data;

[0094] Step 102 may specifically include: using the updated operating status data (i.e., using the updated characteristic gas concentration, pressure value, temperature value, and sound data), determining a thermal runaway risk index value of the battery to be monitored;

[0095] Step 104 may specifically include: inputting the updated characteristic gas concentration, pressure value, temperature value, sound data, temperature change rate, pressure change value, characteristic gas concentration change rate and volume change rate into the first prediction model that has completed training, and obtaining the volume prediction value and volume change rate prediction value within the second time period output by the first prediction model.

[0096] It should be noted that in order to ensure that the thermal runaway risk can continue to be monitored when the sensor exceeds the range limit, a first trend graph including historical data and acquisition time can be generated based on the historical data collected by the sensor, and the operating status data of the current time node can be predicted based on the first trend graph. The thermal runaway risk index value is determined based on the predicted operating status data, and the volume prediction value and the volume change rate prediction value are predicted based on the operating status data, so as to maintain the accuracy of the thermal runaway risk index value and the accuracy of the predicted volume prediction value and the volume change rate prediction value.

[0097] Step 103 : Obtain historical operating status data of the battery to be monitored within a first time period, and determine the characteristic gas concentration change rate, pressure change rate, and temperature change rate inside the battery to be monitored within the first time period based on the historical operating status data.

[0098] The first time period is a time period corresponding to a first preset time length before the current time node.

[0099] It should be noted that when a large amount of characteristic gas is generated inside the battery, the internal pressure of the battery will gradually increase, and the battery shell will gradually deform with the increase of pressure and change of temperature, and may even bulge or rupture. In other words, the above-mentioned sound data may not be detected in the initial stage when no deformation occurs. The enrichment of characteristic gas and the surge in concentration can easily exceed the range limit of the detector. Therefore, it is difficult to comprehensively and accurately monitor thermal runaway by relying solely on the collected original operating status data.

[0100] It can be understood that the characteristic gas concentration, temperature and pressure of the battery have an impact on the bulging and rupture of the battery. That is, there is a correlation between the characteristic gas concentration, temperature and pressure of the battery and the sound data generated by bulging and rupture. Moreover, the faster the characteristic gas concentration, temperature and pressure increase, the louder the volume will be, and the faster the volume will increase. Therefore, the characteristic gas concentration, temperature and pressure and their corresponding rates of change can be used to predict the sound data for a period of time in the future, so that the risk of thermal runaway of the battery can be assessed in advance.

[0101] Step 104: Input the characteristic gas concentration, pressure value, temperature value, sound data, temperature change rate, pressure change value, characteristic gas concentration change rate and volume change rate into the trained first prediction model to obtain the volume prediction value and volume change rate prediction value within the second time period output by the first prediction model.

[0102] The second time period is a time period corresponding to a second preset time length after the current time node.

[0103] In one embodiment, the first prediction model may adopt a neural network model.

[0104] It can be understood that since the characteristic gas concentration, pressure value, temperature value and their respective change rates are correlated with the volume, the characteristic gas concentration, pressure value, temperature value, sound data, temperature change rate, pressure change value, characteristic gas concentration change rate and volume change rate can be input into the first prediction model that has completed training. The first prediction model uses the characteristic gas concentration, pressure value, temperature value, sound data, temperature change rate, pressure change value, characteristic gas concentration change rate and volume change rate to predict the volume and volume change rate in a preset time period in the future to obtain a volume prediction value and a volume change rate prediction value.

[0105] In one embodiment, the volume prediction value and volume change rate prediction value within the above-mentioned second time period can be multiple volume prediction values ​​and volume change rate prediction values ​​corresponding to different preset time nodes in the second time period, or can be the average volume prediction value and average volume change rate prediction value in the second time period.

[0106] In some embodiments of the present application, the first prediction model is trained using the following steps:

[0107] Step a1: Obtain battery operating status data samples within a third time period.

[0108] Among them, the battery operation status data samples include characteristic gas concentration samples, pressure value samples, temperature value samples and sound sample data; the third time period is the time period corresponding to the first preset time length before collecting the battery operation status data samples.

[0109] In one embodiment, the battery operation sample data may be obtained based on historical operation status data of a plurality of batteries.

[0110] Step a2: determining the sample characteristic gas concentration change rate, the sample pressure change rate, the sample temperature change rate, and the sample volume change rate within a third time period based on the operating status data sample.

[0111] Step a3: Input the characteristic gas concentration samples, pressure value samples, temperature value samples, sound sample data, sample characteristic gas concentration change rate, sample pressure change rate, sample temperature change rate and sample volume change rate into the neural network model to be trained, and obtain the volume prediction value and volume change rate prediction value within the fourth time period output by the neural network model.

[0112] The fourth time period is a time period corresponding to the second preset time length after the battery operating status data sample is collected.

[0113] Step a4: Calculate the loss function between the volume prediction value and the sound sample data to obtain a first loss value.

[0114] Step a5: Calculate the loss function between the volume change rate prediction value and the sample volume change rate to obtain a second loss value.

[0115] Step a6: When the first loss value does not meet the first preset condition and / or the second loss value does not meet the second preset condition, the neural network model is adjusted using the first loss value and the second loss value, and the step of obtaining the battery operating status data sample within the third time period is returned to execute until the first loss value meets the first preset condition and the second loss value meets the second preset condition, thereby obtaining the first prediction model.

[0116] In one embodiment, the operating status data samples, the sample characteristic gas concentration change rate, the sample pressure change rate, the sample temperature change rate, and the sample volume change rate can be divided into a training set and a test set; wherein the training set is used to train the neural network model, and the test set is used to evaluate the performance of the model;

[0117] Determine the structure of the neural network model and the number of input layer nodes of the neural network to 8 (including characteristic gas concentration samples, pressure value samples, temperature value samples, sound sample data, sample characteristic gas concentration change rate, sample pressure change rate, sample temperature change rate and sample volume change rate). Each node corresponds to a sample feature. Determine the number of hidden layers in the neural network and the number of neurons in each hidden layer, and configure a Sigmoid activation function for each neuron. Select the stochastic gradient descent algorithm to train the neural network model.

[0118] As a possible example, the weights and biases can be initialized according to the number of nodes in each layer of the neural network model structure, the weights can be randomly sampled from the standard normal distribution, the biases can be initialized to zero, the feature data of the training set can be input into the network, the activation value of each neuron can be calculated through the parameters of each layer, and this forward propagation process can be performed between the hidden layer and the output layer.

[0119] In one embodiment, after completing the forward propagation process, a loss function between the volume prediction value and the sound sample data can be calculated to obtain a first loss value, and a loss function between the volume change rate prediction value and the sample volume change rate can be calculated to obtain a second loss value. The first and second loss values ​​are then propagated from the output layer to the hidden layer using a backpropagation algorithm, and the gradient of each parameter can be calculated using the chain rule. The backpropagation algorithm and the chain rule are conventional techniques and are not described in detail here.

[0120] Furthermore, a stochastic gradient descent algorithm can be used to update the weights and biases between layers based on the calculated gradients; the stochastic gradient descent algorithm is a conventional technique and is therefore not specifically described in this embodiment. If the first loss value does not satisfy the first preset condition and / or the second loss value does not satisfy the second preset condition (i.e., the number of iterations is less than the preset number of iterations, or the first loss value does not satisfy the convergence condition, and / or the second loss value does not satisfy the convergence condition), the feature data in the training set is re-inputted into the neural network model until the first loss value satisfies the first preset condition and the second loss value satisfies the second preset condition, thereby obtaining a first prediction model.

[0121] As an example, the test set can be used to evaluate the performance of the first prediction model, including accuracy, precision, and recall metrics, and the network architecture and hyperparameters can be adjusted based on the evaluation results to optimize the performance of the first prediction model.

[0122] In some embodiments of the present application, after step 104, the method may further include the following steps:

[0123] Step b1, acquiring target sound data within a second time period, and determining the actual volume and actual volume change rate of the battery to be monitored within the second time period based on the target sound data;

[0124] Step b2, calculating a loss function between the actual volume and the predicted volume value to obtain a third loss value;

[0125] Step b3, calculating a loss function between the volume prediction value and the volume change rate prediction value to obtain a fourth loss value;

[0126] Step b4: When the third loss value does not meet the first preset condition and / or the fourth loss value does not meet the second preset condition, the third loss value and the fourth loss value are used to adjust the parameters of the first prediction model.

[0127] It should be noted that, in order to continuously improve the accuracy of the prediction results of the first prediction model, after the first prediction model is put into use, the first prediction model can be continuously optimized based on the loss between the predicted results and the actual volume and the actual volume change rate, thereby continuously improving the performance of the first prediction model. In addition, the actual operating environment of the battery may change over time. Continuous optimization of the first prediction model allows the first prediction model to adapt to the changing operating environment, thereby avoiding inaccurate prediction results due to environmental changes.

[0128] In one embodiment, the above-mentioned method of adjusting the parameters of the first prediction model is the same as the parameter adjustment method proposed in the embodiment corresponding to steps a1-a6, and will not be repeated here.

[0129] Step 105 : Determine a first weight value that matches the volume prediction value and the volume change rate prediction value based on a preset first mapping relationship.

[0130] The first mapping relationship includes a mapping relationship between a volume value, a volume change rate, and a weight value.

[0131] In one embodiment, the first mapping relationship can be pre-set according to actual needs. In the first mapping relationship, the weight value can be an integer greater than 1, and the weight value is proportional to the volume prediction value and the volume change rate. That is, the larger the volume prediction value and the volume change rate, the larger the weight value, and the larger the comprehensive risk index value obtained after multiplying the first weight value and the thermal runaway risk index value.

[0132] In some embodiments of the present application, step 105 may specifically include the following steps:

[0133] Acquire multiple volume value intervals and multiple volume change rate intervals from the first mapping relationship;

[0134] Determining a target volume value interval to which the volume prediction value belongs from a plurality of volume value intervals, and determining a target volume change rate interval to which the volume change rate prediction value belongs from a plurality of volume change rate intervals;

[0135] A weight value that matches both the target volume value interval and the target volume change rate interval in the first mapping relationship is determined to obtain a first weight value.

[0136] In an example of a possible implementation, multiple volume value intervals can be used as the horizontal axis, and multiple volume change rate intervals can be used as the vertical axis. Points in the coordinate system corresponding to different volume value intervals and different volume change rate intervals can be assigned values, that is, each point corresponds to the first weight value.

[0137] In one embodiment, after determining the volume prediction value and the volume change rate prediction value, the volume value interval within which the volume prediction value falls is determined to obtain a target volume value interval, and the volume change rate interval within which the volume change rate prediction value falls is determined to obtain a target volume change rate interval. A target point is determined using the target volume value interval as the horizontal coordinate and the target volume change rate interval as the vertical coordinate, and the weight value corresponding to the target point is determined as the first weight value.

[0138] Step 106 : Determine the product of the thermal runaway risk index value and the first weight value to obtain a comprehensive risk index value, and output corresponding warning information based on the comprehensive risk index value.

[0139] In one embodiment, the thermal runaway risk index value is multiplied by the first weight value to obtain a comprehensive risk index value, a warning level is determined according to the size of the comprehensive risk index value, and warning information is output based on the warning level.

[0140] In some embodiments of the present application, step 106 may specifically include the following steps:

[0141] Obtain multiple preset comprehensive risk indicator intervals;

[0142] Selecting a comprehensive risk indicator interval to which the comprehensive risk indicator value belongs from a plurality of comprehensive risk indicator intervals determined from the operating status data to obtain a target comprehensive risk indicator interval;

[0143] Determine the warning level associated with the target comprehensive risk indicator interval;

[0144] Output warning information according to the warning level.

[0145] It should be noted that the comprehensive risk indicator interval can be pre-set according to actual needs, and a corresponding warning level can be configured for each comprehensive risk indicator interval according to actual needs.

[0146] In one embodiment, in order to quickly determine the degree of thermal runaway risk of the battery to be monitored, the comprehensive risk index value can be compared with multiple comprehensive risk index intervals to obtain the target comprehensive risk index interval to which the comprehensive risk index value belongs. The warning level associated with the target comprehensive risk index interval is used as the warning level of the current battery to be monitored, and the corresponding warning information is output according to the warning level, so that the degree of thermal runaway risk of the battery can be accurately and intuitively determined.

[0147] According to the battery thermal runaway state monitoring and evaluation method based on linear discriminant analysis proposed in an embodiment of the present disclosure, the operating state data of the battery to be monitored is obtained; the historical operating state data of the battery to be monitored in a first time period is obtained, and the characteristic gas concentration change rate, pressure change rate, temperature change rate and volume change rate inside the battery to be monitored in the first time period are determined based on the historical operating state data; the thermal runaway risk index value of the battery to be monitored is determined using the characteristic gas concentration, pressure value, temperature value and sound data; the characteristic gas concentration, pressure value, temperature value, concentration change rate, pressure change rate and temperature change rate are input into a first prediction model that has been trained to obtain a volume prediction value and a volume change rate prediction value in a second time period output by the first prediction model; based on a preset first mapping relationship, a first weight value that matches the volume prediction value and the volume change rate prediction value is determined; the product of the thermal runaway risk index value and the first weight value is determined to obtain a comprehensive risk index value, and corresponding warning information is output based on the comprehensive risk index value. Based on the correlation between the concentration of characteristic gases, pressure values, temperature values ​​and sound data inside the battery, the first prediction model is used to predict the volume value and volume change rate within a preset time period in the future. The operating status data before the range limit of the data acquisition equipment is exceeded and the volume prediction data are used to effectively estimate the thermal runaway state of the battery in advance. This avoids the problem of the actual operating status data exceeding the range limit and making it impossible to monitor the thermal runaway state of the battery in a timely manner, thereby improving the timeliness and accuracy of the monitoring results.

[0148] Figure 2 This is a block diagram of a battery thermal runaway state monitoring and evaluation device based on linear discriminant analysis according to an exemplary embodiment. Figure 2 The device includes a first acquisition module 201, a first determination module 202, a second determination module 203, a prediction module 204, a third determination module 205 and an output module 206.

[0149] The first acquisition module 201 is used to acquire the operating status data of the battery to be monitored; the operating status data includes characteristic gas concentration, pressure value, temperature value and sound data;

[0150] A first determination module 202 is configured to determine a thermal runaway risk index value of a battery to be monitored using characteristic gas concentration, pressure value, temperature value, and sound data of the operating status data;

[0151] A second determining module 203 is configured to obtain historical operating status data of the battery to be monitored within a first time period, and determine, based on the historical operating status data, the rate of change of characteristic gas concentration, the rate of change of pressure, and the rate of change of temperature within the battery to be monitored within the first time period; the first time period being a time period corresponding to a first preset time length before the current time node;

[0152] Prediction module 204 is configured to input the characteristic gas concentration, pressure value, temperature value, sound data, temperature change rate, pressure change value, characteristic gas concentration change rate, and volume change rate into the trained first prediction model to obtain a volume prediction value and a volume change rate prediction value for a second time period output by the first prediction model; the second time period being a time period corresponding to a second preset time length after the current time node;

[0153] A third determining module 205 is configured to determine a first weight value that matches the volume prediction value and the volume change rate prediction value based on a preset first mapping relationship; the first mapping relationship includes a mapping relationship between the volume value, the volume change rate, and the weight value;

[0154] The output module 206 is configured to determine the product of the thermal runaway risk index value and the first weight value to obtain a comprehensive risk index value, and output corresponding warning information based on the comprehensive risk index value.

[0155] In some embodiments of the present application, the first determining module 202 may be specifically configured to:

[0156] Extracting at least one high-dimensional feature from the sound data, and performing dimensionality reduction processing on the at least one high-dimensional feature using linear discriminant analysis to obtain a target feature;

[0157] The characteristic gas concentration, pressure value, temperature value and target feature are input into the trained thermal runaway prediction model to obtain the thermal runaway risk index value output by the thermal runaway prediction model.

[0158] In some embodiments of the present application, the apparatus further includes a training module, which can be specifically used to:

[0159] The first prediction model is trained using the following steps:

[0160] Obtaining battery operating status data samples within a third time period; the battery operating status data samples include characteristic gas concentration samples, pressure value samples, temperature value samples, and sound sample data; the third time period is a time period corresponding to the first preset time length before collecting the battery operating status data samples;

[0161] determining, based on the operating status data samples, a sample characteristic gas concentration change rate, a sample pressure change rate, a sample temperature change rate, and a sample volume change rate within a third time period;

[0162] Inputting characteristic gas concentration samples, pressure value samples, temperature value samples, sound sample data, sample characteristic gas concentration change rate, sample pressure change rate, sample temperature change rate, and sample volume change rate into the neural network model to be trained, and obtaining a volume prediction value and a volume change rate prediction value within a fourth time period output by the neural network model; the fourth time period is a time period corresponding to the second preset time length after the battery operating status data sample is collected;

[0163] Calculating a loss function between the volume prediction value and the sound sample data to obtain a first loss value;

[0164] Calculating a loss function between the volume change rate prediction value and the sample volume change rate to obtain a second loss value;

[0165] When the first loss value does not meet the first preset condition and / or the second loss value does not meet the second preset condition, the neural network model is adjusted using the first loss value and the second loss value, and the step of executing the operating status data to obtain the battery operating status data sample within the third time period is returned until the first loss value meets the first preset condition and the second loss value meets the second preset condition, thereby obtaining a first prediction model for the operating status data.

[0166] In some embodiments of the present application, the training module may also be used to:

[0167] Acquire target sound data within a second time period, and determine an actual volume and an actual volume change rate of the battery to be monitored within the second time period based on the target sound data;

[0168] Calculate the loss function between the actual volume and the predicted volume value to obtain a third loss value;

[0169] Calculating a loss function between the volume prediction value and the volume change rate prediction value to obtain a fourth loss value;

[0170] When the third loss value does not satisfy the first preset condition and / or the fourth loss value does not satisfy the second preset condition, the third loss value and the fourth loss value are used to adjust the parameters of the first prediction model.

[0171] In some embodiments of the present application, the third determining module 205 may be specifically configured to:

[0172] Acquire multiple volume value intervals and multiple volume change rate intervals from the first mapping relationship;

[0173] Determining a target volume value interval to which the volume prediction value belongs from a plurality of volume value intervals, and determining a target volume change rate interval to which the volume change rate prediction value belongs from a plurality of volume change rate intervals;

[0174] A weight value that matches both the target volume value interval and the target volume change rate interval in the first mapping relationship is determined to obtain a first weight value.

[0175] In some embodiments of the present application, the output module 206 may be specifically used to:

[0176] Obtain multiple preset comprehensive risk indicator intervals;

[0177] Selecting a comprehensive risk indicator interval to which the comprehensive risk indicator value belongs from the determined multiple comprehensive risk indicator intervals to obtain a target comprehensive risk indicator interval;

[0178] Determine the warning level associated with the target comprehensive risk indicator interval;

[0179] Output warning information according to the warning level.

[0180] In some embodiments of the present application, the apparatus may further include:

[0181] a third determining module, configured to, upon detecting that at least one of the characteristic gas concentration sensor for obtaining characteristic gas concentration, the pressure sensor for obtaining pressure values, and the temperature sensor for obtaining temperature values ​​exceeds a range limit, determine the sensor that exceeds the range limit as a target sensor;

[0182] a fourth determining module, configured to determine target operating state data collected by a target sensor from the operating state data;

[0183] The second acquisition module is used to obtain historical target operating status data collected by the target sensor within a first historical time period; the first historical time period is a time period corresponding to a preset time length before the target sensor exceeds the range limit;

[0184] A trend prediction module is used to generate a first trend chart using historical target operating status data, and perform trend prediction on the first trend chart using a curve analysis algorithm to obtain predicted operating status data corresponding to a current time node;

[0185] An updating module, configured to replace the target operating status data with the predicted operating status data to obtain updated operating status data;

[0186] The first determining module 202 may be specifically configured to:

[0187] Using the updated characteristic gas concentration, pressure value, temperature value and sound data, determine the thermal runaway risk index value of the battery to be monitored;

[0188] The prediction module 204 can be specifically used to:

[0189] The updated characteristic gas concentration, pressure value, temperature value, concentration change rate, pressure change rate and temperature change rate are input into the first prediction model that has completed training to obtain the volume prediction value and volume change rate prediction value in the second time period output by the first prediction model.

[0190] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0191] According to the battery thermal runaway state monitoring and evaluation device based on linear discriminant analysis proposed in the embodiment of the present disclosure, the operating state data of the battery to be monitored is obtained; the historical operating state data of the battery to be monitored in a first time period is obtained, and the characteristic gas concentration change rate, pressure change rate, temperature change rate and volume change rate inside the battery to be monitored in the first time period are determined based on the historical operating state data; the thermal runaway risk index value of the battery to be monitored is determined by using the characteristic gas concentration, pressure value, temperature value and sound data; the characteristic gas concentration, pressure value, temperature value, concentration change rate, pressure change rate and temperature change rate are input into a first prediction model that has been trained to obtain a volume prediction value and a volume change rate prediction value in a second time period output by the first prediction model; based on a preset first mapping relationship, a first weight value that matches the volume prediction value and the volume change rate prediction value is determined; the product of the thermal runaway risk index value and the first weight value is determined to obtain a comprehensive risk index value, and corresponding warning information is output based on the comprehensive risk index value. Based on the correlation between the concentration of characteristic gases, pressure values, temperature values ​​and sound data inside the battery, the first prediction model is used to predict the volume value and volume change rate within a preset time period in the future. The operating status data before the range limit of the data acquisition equipment is exceeded and the volume prediction data are used to effectively estimate the thermal runaway state of the battery in advance. This avoids the problem of the actual operating status data exceeding the range limit and making it impossible to monitor the thermal runaway state of the battery in a timely manner, thereby improving the timeliness and accuracy of the monitoring results.

[0192] Figure 3 This is a block diagram illustrating an apparatus for a method for monitoring and assessing battery thermal runaway conditions based on linear discriminant analysis, according to an exemplary embodiment. For example, apparatus 300 may be an electronic device, such as a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0193] Reference Figure 3, apparatus 300 may include one or more of the following components: a processing component 302 , a memory 304 , a power component 306 , a multimedia component 308 , an audio component 310 , an input / output (I / O) interface 312 , a sensor component 314 , and a communication component 316 .

[0194] The processing component 302 generally controls the overall operation of the device 300, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 302 may include one or more processors 320 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 302 may include one or more modules to facilitate interaction between the processing component 302 and other components. For example, the processing component 302 may include a multimedia module to facilitate interaction between the multimedia component 308 and the processing component 302.

[0195] The memory 304 is configured to store various types of data to support operations on the device 300. Examples of such data include instructions for any application or method operating on the device 300, contact data, phone book data, messages, pictures, videos, etc. The memory 304 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0196] The power component 306 provides power to the various components of the device 300. The power component 306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 300.

[0197] The multimedia component 308 includes a screen that provides an output interface between the device 300 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, it may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensors can not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide action. In some embodiments, the multimedia component 308 includes a front-facing camera and / or a rear-facing camera. When the device 300 is in an operating mode, such as a capture mode or a video mode, the front-facing camera and / or the rear-facing camera can receive external multimedia data. Each front-facing camera and the rear-facing camera can have a fixed optical lens system or have focal length and optical zoom capabilities.

[0198] The audio component 310 is configured to output and / or input audio signals. For example, the audio component 310 includes a microphone (MIC) that is configured to receive external audio signals when the device 300 is in an operating mode, such as a call mode, a recording mode, or a speech recognition mode. The received audio signals may be further stored in the memory 304 or transmitted via the communication component 316. In some embodiments, the audio component 310 also includes a speaker for outputting audio signals.

[0199] I / O interface 312 provides an interface between processing component 302 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0200] Sensor assembly 314 includes one or more sensors for providing various status assessments of device 300. For example, sensor assembly 314 can detect the open / closed state of device 300, the relative positioning of components, such as the display and keypad of device 300. Sensor assembly 314 can also detect changes in the position of device 300 or a component of device 300, the presence or absence of user contact with device 300, the orientation or acceleration / deceleration of device 300, and changes in the temperature of device 300. Sensor assembly 314 can be a pressure sensor or a temperature sensor.

[0201] The communication component 316 is configured to facilitate wired or wireless communication between the apparatus 300 and other devices. The apparatus 300 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 316 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 316 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0202] In an exemplary embodiment, the apparatus 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0203] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 304 including instructions. The instructions can be executed by the processor 320 of the apparatus 300 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0204] In an exemplary embodiment, a computer program product is also provided, comprising a computer program, which implements the above method when executed by the processor 320 of the apparatus 300 .

[0205] Other embodiments of the present invention will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the invention that follow from the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the invention being indicated by the following claims.

[0206] It should be understood that the present invention is not limited to the exact construction described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A battery thermal runaway state monitoring and evaluation method based on linear discriminant analysis, characterized in that: include: Obtaining the internal operating status data of the battery to be monitored; The operating status data includes characteristic gas concentration, pressure value, temperature value and sound data; Determining a thermal runaway risk index value of the battery to be monitored using the characteristic gas concentration, pressure value, temperature value, and sound data; Obtaining historical operating status data of the battery to be monitored within a first time period, and determining, based on the historical operating status data, a characteristic gas concentration change rate, a pressure change rate, a temperature change rate, and a volume change rate within the battery to be monitored within the first time period, respectively; the first time period being a time period corresponding to a first preset time length before a current time node; Inputting the characteristic gas concentration, pressure value, temperature value, sound data, temperature change rate, pressure change value, characteristic gas concentration change rate, and volume change rate into a trained first prediction model, obtaining a volume prediction value and a volume change rate prediction value within a second time period output by the first prediction model; the second time period being a time period corresponding to a second preset time length after the current time node; Determining a first weight value that matches the volume prediction value and the volume change rate prediction value based on a preset first mapping relationship; wherein the first mapping relationship includes a mapping relationship between the volume value, the volume change rate, and the weight value; The product of the thermal runaway risk index value and the first weight value is determined to obtain a comprehensive risk index value, and corresponding warning information is output based on the comprehensive risk index value.

2. The battery thermal runaway state monitoring and evaluation method based on linear discriminant analysis according to claim 1, characterized in that: Determining the thermal runaway risk index value of the battery to be monitored by using the characteristic gas concentration, pressure value, temperature value, and sound data includes: Extracting at least one high-dimensional feature from the sound data, and performing dimensionality reduction processing on the at least one high-dimensional feature using linear discriminant analysis to obtain a target feature; The characteristic gas concentration, pressure value, temperature value and the target feature are input into the trained thermal runaway prediction model to obtain a thermal runaway risk index value output by the thermal runaway prediction model.

3. The battery thermal runaway state monitoring and evaluation method based on linear discriminant analysis according to claim 1, characterized in that: The first prediction model is trained using the following steps: Acquire battery operating status data samples within a third time period; the battery operating status data samples include characteristic gas concentration samples, pressure value samples, temperature value samples, and sound sample data; the third time period is a time period corresponding to a first preset time length before the battery operating status data samples are collected; Determine, based on the operating status data samples, a sample characteristic gas concentration change rate, a sample pressure change rate, a sample temperature change rate, and a sample volume change rate within the third time period; Inputting the characteristic gas concentration samples, pressure value samples, temperature value samples, sound sample data, sample characteristic gas concentration change rate, sample pressure change rate, sample temperature change rate, and sample volume change rate into a neural network model to be trained, and obtaining a volume prediction value and a volume change rate prediction value within a fourth time period output by the neural network model; the fourth time period being a time period corresponding to a second preset time length after collecting the battery operating status data samples; Calculating a loss function between the volume prediction value and the sound sample data to obtain a first loss value; Calculating a loss function between the volume change rate prediction value and the sample volume change rate to obtain a second loss value; When the first loss value does not meet the first preset condition and / or the second loss value does not meet the second preset condition, the first loss value and the second loss value are used to adjust the parameters of the neural network model, and the step of obtaining the battery operating status data sample within the third time period is returned to execute until the first loss value meets the first preset condition and the second loss value meets the second preset condition, thereby obtaining the first prediction model.

4. The battery thermal runaway state monitoring and evaluation method based on linear discriminant analysis according to claim 3 is characterized in that: After inputting the characteristic gas concentration, pressure value, temperature value, sound data, temperature change rate, pressure change value, characteristic gas concentration change rate, and volume change rate into the trained first prediction model and obtaining the volume prediction value and volume change rate prediction value for the second time period output by the first prediction model, the method further includes: Acquiring target sound data within the second time period, and determining an actual volume and an actual volume change rate of the battery to be monitored within the second time period based on the target sound data; Calculating a loss function between the actual volume and the predicted volume value to obtain a third loss value; calculating a loss function between the volume change rate and the predicted value of the volume change rate to obtain a fourth loss value; When the third loss value does not satisfy the first preset condition and / or the fourth loss value does not satisfy the second preset condition, the first prediction model is adjusted using the third loss value and the fourth loss value.

5. The battery thermal runaway state monitoring and evaluation method based on linear discriminant analysis according to claim 1, characterized in that: The determining, based on a preset first mapping relationship, a first weight value that matches the volume prediction value and the volume change rate prediction value includes: Acquire multiple volume value intervals and multiple volume change rate intervals from the first mapping relationship; determining a target volume value interval to which the volume prediction value belongs from the plurality of volume value intervals, and determining a target volume change rate interval to which the volume change rate prediction value belongs from the plurality of volume change rate intervals; A weight value that matches both the target volume value interval and the target volume change rate interval is determined from the first mapping relationship to obtain the first weight value.

6. The battery thermal runaway state monitoring and evaluation method based on linear discriminant analysis according to claim 1, characterized in that: Outputting corresponding warning information based on the comprehensive risk indicator value includes: Obtain multiple preset comprehensive risk indicator intervals; Selecting the comprehensive risk indicator interval to which the comprehensive risk indicator value belongs from the multiple comprehensive risk indicator intervals to obtain a target comprehensive risk indicator interval; Determine the warning level associated with the target comprehensive risk indicator interval; The warning information is output according to the warning level.

7. A battery thermal runaway state monitoring and evaluation device based on linear discriminant analysis, characterized in that: include: A first acquisition module is used to obtain the internal operating status data of the battery to be monitored; The operating status data includes characteristic gas concentration, pressure value, temperature value and sound data; A first determination module is configured to determine a thermal runaway risk index value of the battery to be monitored by using the characteristic gas concentration, pressure value, temperature value, and sound data; a second determining module, configured to obtain historical operating status data of the battery to be monitored within a first time period, and determine, based on the historical operating status data, a characteristic gas concentration change rate, a pressure change rate, a temperature change rate, and a volume change rate within the battery to be monitored within the first time period; the first time period being a time period corresponding to a first preset time length before a current time node; a prediction module, configured to input the characteristic gas concentration, pressure value, temperature value, sound data, temperature change rate, pressure change value, characteristic gas concentration change rate, and volume change rate into a trained first prediction model, and obtain a volume prediction value and a volume change rate prediction value within a second time period output by the first prediction model; the second time period being a time period corresponding to a second preset time length after the current time node; a third determining module, configured to determine a first weight value that matches the volume prediction value and the volume change rate prediction value based on a preset first mapping relationship, wherein the first mapping relationship includes a mapping relationship between the volume value, the volume change rate, and the weight value; The output module is used to determine the product of the thermal runaway risk index value and the first weight value to obtain a comprehensive risk index value, and output corresponding warning information based on the comprehensive risk index value.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that The computer program implements the method according to any one of claims 1 to 6 when executed by a processor.

Images