Battery liquid leakage detection method, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a battery liquid leakage detection method, electronic equipment and a storage medium. The battery liquid leakage detection method comprises the following steps: acquiring sample battery data when a sample battery leaks liquid; performing standardization processing on the sample battery data, and dividing the processed sample battery data into a training set and a test set; training a preset long-short-term memory model based on the training set, and determining a liquid leakage detection model in the trained long-short-term memory model according to the test set; and performing battery liquid leakage detection on the to-be-detected battery according to the liquid leakage detection model. According to the scheme, the timeliness of battery liquid leakage detection can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of battery testing, and in particular to a battery leakage detection method, an electronic device and a storage medium. Background Art

[0002] Lithium iron phosphate batteries have become the mainstream choice in the market for energy storage systems due to their high energy density, mature mass production technology, long cycle life, and deep discharge depth. Battery energy storage systems are generally 20-foot standard containers. In a limited space, a large number of batteries are connected in series and parallel to form battery packs. The energy storage capacity of the battery packs is often at the MWh level, and the conversion power is from hundreds of KW to MW. The DC side battery energy storage system has the characteristics of high voltage, high operating power, and deep charging and discharging, all of which put higher requirements on the safe operation of the battery in the battery energy storage system.

[0003] The energy storage container is equipped with a fire protection system, which can monitor and respond quickly to fires inside the container in real time. The fire protection system uses multiple sensors such as smoke, temperature, and gas. When the battery leaks, the positive and negative electrolytes react to generate VOC gases, which can be detected by the sensors. However, when VOC gas is detected, it means that the gas has spread into the container and the battery leakage is very serious. The fire protection system is mainly to ensure the fire safety at the energy storage system level. Battery leakage is an aspect that needs to be considered in fire safety. In fact, during the charging and discharging process of the battery pack, the leakage of the battery cell cannot be detected in time by the fire protection system. It can be seen that the current battery leakage detection scheme has the problem of poor timeliness. Summary of the invention

[0004] The embodiments of the present application provide a battery leakage detection method, an electronic device, and a storage medium, which can improve the timeliness of battery leakage detection.

[0005] The present application provides a battery leakage detection method, comprising:

[0006] Acquire sample battery data when the sample battery has battery leakage;

[0007] Standardizing the sample battery data, and dividing the processed sample battery data into a training set and a test set;

[0008] Training a preset long short-term memory model based on the training set, and determining a leakage detection model in the trained long short-term memory model according to the test set;

[0009] The battery to be tested is subjected to battery leakage detection according to the leakage detection model.

[0010] Optionally, in some embodiments of the present application, training a preset long short-term memory model based on the training set, and determining a leakage detection model in the trained long short-term memory model according to the test set, includes:

[0011] Get the preset long short-term memory model;

[0012] Using the training set to train the long short-term memory model;

[0013] Saving the model weights of the long short-term memory model during training according to a preset callback function;

[0014] A liquid leakage detection model is determined in the trained long short-term memory model based on the model weights and the test set.

[0015] Optionally, in some embodiments of the present application, determining a leakage detection model in a trained long short-term memory model based on the model weight and the test set includes:

[0016] Determine the model weight and model loss of the long short-term memory model at the nth moment, where n is an integer greater than 0;

[0017] Updating the model weight of the long short-term memory model at the n+1th moment, and training the long short-term memory model after the weight update based on the training set;

[0018] Determine the model loss corresponding to the long short-term memory model at the n+1th moment based on the test set;

[0019] According to the model loss of the long short-term memory model at the nth moment and the model loss at the (n+1)th moment, a leakage detection model is determined in the trained long short-term memory model.

[0020] Optionally, in some embodiments of the present application, determining the liquid leakage detection model in the trained long short-term memory model according to the model loss of the long short-term memory model at the nth time and the model loss at the n+1th time includes:

[0021] Comparing the size of the model loss of the long short-term memory model at the nth moment and the model loss at the n+1th moment;

[0022] The long short-term memory model with the smallest model loss is determined as the leakage detection model.

[0023] Optionally, in some embodiments of the present application, it further includes:

[0024] Performing validity testing on model training according to the model loss of the long short-term memory model at the nth moment and the model loss at the n+1th moment;

[0025] If the detection result is valid, then calculating the error between the estimated leakage data corresponding to the sample battery estimated by the latest long short-term memory model and the actual leakage data corresponding to the sample battery;

[0026] When the error meets the preset condition, the latest long short-term memory model is determined as the leakage detection model.

[0027] Optionally, in some embodiments of the present application, the training of the long short-term memory model using the training set includes:

[0028] estimating the estimated leakage data corresponding to the training set based on the long short-term memory model;

[0029] The long short-term memory model is trained according to the real leakage data and the estimated leakage data corresponding to the training set.

[0030] Optionally, in some embodiments of the present application, the standardizing the sample battery data includes:

[0031] determining an average value of the sample battery data when leaking as a first preset value, and;

[0032] The variance of the sample battery data when leaking is determined as a second preset value.

[0033] Optionally, in some embodiments of the present application, performing battery leakage detection on the battery to be detected according to the leakage detection model includes:

[0034] Acquiring battery data of the battery to be detected by means of a sensor disposed inside the battery to be detected;

[0035] Processing the battery data according to the leakage detection model to estimate whether the battery to be detected is in a leakage state;

[0036] If the battery to be detected is in a leakage state, the battery to be monitored is controlled to stop charging and discharging, and fault information corresponding to the battery leakage is output.

[0037] Correspondingly, the present application also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the steps of any of the above methods when executing the program.

[0038] The present application also provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0039] The embodiment of the present application provides a battery leakage detection method, an electronic device, and a storage medium. After obtaining the sample battery data when the sample battery has battery leakage, the sample battery data is standardized, and the processed sample battery data is divided into a training set and a test set. Then, a preset long-short term memory model is trained based on the training set, and a leakage detection model is determined in the trained long-short term memory model according to the test set. Finally, a battery leakage detection is performed on the battery to be detected according to the leakage detection model. The battery leakage detection scheme provided by the present application uses the sample battery data when the sample battery has battery leakage in advance to train the preset long-short term memory model, and determines the leakage detection model in the trained long-short term memory model according to the test set. When the battery leakage detection is actually performed, the trained leakage detection model can be directly used to perform battery leakage detection on the battery to be detected, thereby improving the timeliness of battery leakage detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 is a flow chart of a battery leakage detection method provided in an embodiment of the present application;

[0042] Figure 2 is a structural schematic diagram of a battery leakage detection system provided in an embodiment of the present application;

[0043] Figure 3 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0045] Embodiments of the present application provide a battery leakage detection method, an electronic device, and a storage medium.

[0046] Among them, the battery leakage detection method can be specifically applied in a terminal, which may include a tablet computer or a personal computer (PC). The terminal can establish a wired or wireless connection with a server. The server may include an independently running server or a distributed server, or may include a server cluster consisting of multiple servers.

[0047] It should be noted that the order of description of the following embodiments is not intended to limit the priority order of the embodiments.

[0048] A battery leakage detection method comprises: obtaining sample battery data when the sample battery has battery leakage; performing standardization processing on the sample battery data, and dividing the processed sample battery data into a training set and a test set; training a preset long short-term memory model based on the training set, and determining a leakage detection model in the trained long short-term memory model according to the test set; and performing battery leakage detection on a battery to be detected according to the leakage detection model.

[0049] See also Figure 1 , Figure 1 A schematic diagram of the process of a battery leakage detection method provided in an embodiment of the present application. The specific process of the battery leakage detection method can be as follows:

[0050] 101. Obtain sample battery data when the sample battery leaks.

[0051] For example, data of the battery in normal operation and leakage is collected from the battery energy storage system, such as parameters such as the battery voltage, temperature and pressure. In order to ensure that the collected data can accurately reflect whether the battery is leaking. Sample battery testing or actual leakage events are required, or leakage is simulated under laboratory conditions. Specifically, a data recording device or system can be used to capture battery data, including voltage, current, temperature, pressure, etc. Then, the collected data is organized into a format suitable for analysis, such as time series data, in which each time point has a corresponding parameter value. Optionally, in some embodiments of the present application, the data can be preprocessed, such as removing noise, filling missing values, smoothing, etc., to ensure the quality of the data. In addition, the data can also be labeled to mark which data is the data when the battery is operating normally and which is the data when the battery is leaking.

[0052] 102. Standardize the sample battery data and divide the processed sample battery data into a training set and a test set.

[0053] Data normalization is to scale the data so that it falls into a small specific interval, the most common of which is the [0,1] interval. For battery data, the details are as follows:

[0054] a. Calculate mean and standard deviation

[0055] Mean: Calculates the average value of all sample data.

[0056] Standard Deviation: Calculates the degree of dispersion of data, that is, the width of the data distribution.

[0057] b. Apply the standardized formula

[0058] For each data point x, apply the following formula to normalize:

[0059] Where x' is the standardized value, μ is the mean, and σ is the standard deviation.

[0060] Additionally, any missing data points need to be processed or filled before standardization to avoid problems when calculating the mean and standard deviation.

[0061] Optionally, in some embodiments of the present application, the step of “standardizing the sample battery data” may specifically include:

[0062] determining an average value of the sample battery data when leaking as a first preset value, and;

[0063] The variance of the sample battery data when leaking is determined as a second preset value.

[0064] The sample battery data may specifically include voltage, temperature and pressure. When the battery leaks, the mean values ​​of the voltage, temperature and pressure data may be calculated respectively, and the mean value of the voltage, the mean value of the temperature and the mean value of the pressure may be determined as a first preset value (such as 0), which represents the typical values ​​of these parameters under the leakage condition. Similarly, when the battery leaks, the variance of the voltage, temperature and pressure data may be calculated respectively, and the variance of the voltage, the variance of the temperature and the variance of the pressure may be determined as a second preset value (such as 1), respectively.

[0065] After standardization, the processed data is divided into a training set and a test set, wherein the ratio of the training set to the test set can be 7:3, i.e., 70% of the data is used for training and 30% is used for testing, but this ratio can be adjusted according to the specific situation. The data set can be divided into a training set and a test set using a random sampling method to ensure that the samples in each set are randomly selected to avoid any potential bias. Optionally, in some embodiments of the present application, after dividing the data set, additional processing can be performed, such as:

[0066] Data augmentation: If the amount of data is small, you can consider using data augmentation techniques to increase the number of samples.

[0067] Feature selection: Determine which features are most important for training the model, which may require removing some irrelevant or redundant features.

[0068] 103. The preset long short-term memory model is trained based on the training set, and the leakage detection model is determined in the trained long short-term memory model according to the test set.

[0069] The Long Short-Term Memory (LSTM) model is a special recurrent neural network (RNN) architecture that performs well in processing sequence data, especially time series analysis. The original intention of LSTM was to solve the problem of gradient vanishing or gradient exploding when traditional RNN processes long sequence data, which enables LSTM to capture long-term dependencies.

[0070] First, a pre-set LSTM can be obtained. The architecture of the LSTM may include one or more LSTM layers and a final output layer. The activation function of the output layer depends on the nature of the problem (for example, for a binary classification problem, a sigmoid activation function is usually used). Then, the data of the training set is used as input features, and the corresponding leakage label is used as the target output. During the training process, a callback function (such as ModelCheckpoint) can be used to save the weight of the model. This callback function can be set to save the current best model weight after each epoch if the performance on the validation set is improved. That is, optionally, in some embodiments of the present application, the step of "training a preset long short-term memory model based on the training set, and determining a leakage detection model in the trained long short-term memory model according to the test set" may specifically include:

[0071] Get the preset long short-term memory model;

[0072] Use the training set to train the long short-term memory model;

[0073] The model weights of the long short-term memory model during training are saved according to the preset callback function;

[0074] The leakage detection model is determined in the trained long short-term memory model based on the model weights and the test set.

[0075] For example, specifically, when the long short-term memory model is trained using the data in the training set, the long short-term memory model learns the relationship between the input data and the leakage label. In addition, during the training process, a callback function (such as ModelCheckpoint in TensorFlow or Keras) is used to save the weights of the model. This callback function can be set to save the current best model weights after each epoch if the performance on the validation set improves. In this way, even if the training process is interrupted, training can continue from the saved best weights without starting from scratch. Finally, the saved best model weights are used to initialize a new or the same LSTM model. The model loaded with the best weights is evaluated on the test set to determine its performance. Since the test set is data that is not used in the training process, it can provide important information about the generalization ability of the model. Specifically, the final leakage detection model can be determined based on performance indicators on the test set (such as accuracy, recall, F1 score, etc.).

[0076] Optionally, in some embodiments of the present application, the step of “training the long short-term memory model using the training set” may specifically include:

[0077] The estimated leakage data corresponding to the training set is estimated based on the long short-term memory model;

[0078] The long short-term memory model is trained based on the actual leakage data and estimated leakage data corresponding to the training set.

[0079] For example, generate preliminary estimated leakage data based on the training set features, then generate the loss of the long short-term memory model based on the actual leakage data and the estimated leakage data corresponding to the training set, and adjust the model weight of the long short-term memory model based on the loss. At the same time, use callback functions such as EarlyStopping or ModelCheckpoint to save the model with the best performance during the training process. Evaluate the performance of the model on the validation set to check whether there is overfitting or underfitting. According to the results of the performance evaluation, adjust the model's hyperparameters, such as the learning rate, batch size, number of LSTM layers or number of units, etc.

[0080] Optionally, in some embodiments of the present application, the step of “determining a leakage detection model in a trained long short-term memory model based on the model weight and the test set” may specifically include:

[0081] Determine the model weight and model loss of the long short-term memory model at the nth moment, where n is an integer greater than 0;

[0082] Update the model weight of the long short-term memory model at the n+1th moment, and train the long short-term memory model after the weight update based on the training set;

[0083] Determine the model loss corresponding to the long short-term memory model at the n+1th moment based on the test set;

[0084] According to the model loss of the long short-term memory model at the nth moment and the model loss at the n+1th moment, a leakage detection model is determined in the trained long short-term memory model.

[0085] The model weight is a collection of internal parameters of the model, which determines how the model maps input data to output. Model loss is an indicator that measures the difference between the model prediction and the true label, such as mean square error or cross entropy loss. For example, at the end of the first training cycle (epoch), the model weight and loss on the validation set are recorded. Then, the model weight at the second moment is updated according to the model loss, and the long short-term memory model after the weight update is trained based on the training set, and the model loss corresponding to the long short-term memory model at the second moment is determined based on the test set; if the model loss at the second moment is reduced compared to the model loss at the first moment, this indicates that the model is learning and improving its performance. If the model loss decreases, continue the training process; if the model loss increases or no longer decreases significantly, the model can be adjusted or training can be stopped to avoid overfitting. Optionally, in some embodiments of the present application, when the number of iterations meets the preset conditions, if the model loss remains unchanged, the long short-term memory model trained for the last time is determined as the leakage detection model.

[0086] Optionally, in some embodiments of the present application, the step of “determining a liquid leakage detection model in a trained long short-term memory model according to a model loss of the long short-term memory model at the nth moment and a model loss at the n+1th moment” may specifically include:

[0087] Compare the size of the model loss of the long short-term memory model at the nth moment and the n+1th moment;

[0088] The long short-term memory model with the smallest model loss is determined as the leakage detection model.

[0089] For example, at the end of the nth training cycle, record the loss of the model on the validation set, denoted as L n ; At the end of the n+1th training cycle, the loss of the model on the validation set is recorded again, denoted as L n+1 If L n >L n+1 , it indicates that the model performance has improved in the new training cycle. n+1 >L n , it indicates that the model performance has not improved or there is a risk of overfitting.

[0090] By comparing the model losses of different training cycles, the model with the smallest model loss is selected as the best model, and the model weights with the lowest loss are saved at the end of each training cycle. In this way, even if the training process is interrupted, training can continue from the best model weights, or the best model can be used directly for prediction.

[0091] Optionally, in some embodiments of the present application, the battery leakage detection method of the present application may further include:

[0092] The effectiveness of model training is tested based on the model loss of the long short-term memory model at the nth moment and the model loss at the n+1th moment;

[0093] If the test result is valid, the error between the estimated leakage data corresponding to the sample battery estimated by the latest long short-term memory model and the actual leakage data corresponding to the sample battery is calculated;

[0094] When the error meets the preset conditions, the latest long short-term memory model is determined as the leakage detection model.

[0095] For example, after training, plot the curves of training loss and validation loss as the number of training rounds changes. If the loss curve shows a decreasing trend, it means that the training is effective, and the model is saved and output. If the loss curve shows a non-decreasing trend, it means that the training is invalid, and the model needs to be retrained. Calculate the root mean square error (RMSE) and mean absolute percentage error (MAPE) between the leakage data estimated by the model and the actual leakage data. The smaller the error, the higher the accuracy of the model.

[0096] 104. Perform battery leakage detection on the battery to be detected according to the leakage detection model.

[0097] For example, specifically, real-time data of the battery to be tested is collected, including parameters such as voltage, temperature and pressure. The real-time data is input into the leakage detection model, and the leakage detection model estimates whether the battery to be tested is in a leakage state. If leakage is detected, an alarm can be triggered or maintenance personnel can be notified to take corresponding measures. That is, optionally, in some embodiments of the present application, the step of "performing battery leakage detection on the battery to be tested according to the leakage detection model" can specifically include:

[0098] Acquiring battery data of the battery to be detected by means of a sensor disposed inside the battery to be detected;

[0099] Process the battery data according to the leakage detection model to estimate whether the battery to be tested is in a leakage state;

[0100] If the battery to be detected is in a leakage state, the battery to be monitored is controlled to stop charging and discharging, and fault information corresponding to the battery leakage is output.

[0101] For example, specifically, a sensor is deployed inside the battery to be tested to monitor the key parameters of the battery such as voltage, temperature and pressure in real time. Then, the trained leakage detection model is loaded and the data is input into the leakage detection model. The leakage detection model will estimate whether the battery is in a leakage state based on the input data. If the battery is determined to be in a leakage state, a control instruction is sent to the battery management system (BMS) to instruct it to stop the charging and discharging operations of the battery. At the same time, the corresponding fault information is output, including leakage alarm, battery identification, timestamp, sensor reading, etc.

[0102] The battery energy storage system BMS has a three-level architecture, consisting of the main control MBMU, the master control SBMU and the slave control VCMU. The slave control VCMU collects the temperature and voltage of the battery cell and uploads the data to the main control and the master control, which determine the battery cell status and faults and issue control instructions.

[0103] When a battery cell leaks, the negative aluminum foil is corroded and the voltage of the single cell drops. When leaking, a chemical reaction occurs inside the cell, releasing a large amount of heat and causing the cell temperature to rise. The normal pressure inside the cell is 101.325 kPa. The chemical reaction also generates VOC gas, causing the gas pressure inside the cell to increase. Based on the phenomenon of battery cell leakage, sensors are added at the location of the battery cell explosion-proof valve to collect the voltage, temperature and internal pressure of the battery cell. Based on these three data, an intelligent algorithm is developed to determine whether the battery cell is leaking. Based on this, the present application provides a battery leakage detection system, such as Figure 2 As shown in the figure, the battery leakage detection system includes a main control Bluetooth module, a battery pack and a battery cell. The BMS can detect battery cell leakage at any time. Through Bluetooth technology, the sensor sends the collected data to the paired Bluetooth receiving board in the battery pack. Given that the reliability and stability of Bluetooth communication are related to the communication distance, the Bluetooth receiving board and VCMU are both in the battery pack, and short-range Bluetooth communication is more reliable to ensure that the battery cell data is not lost. It should be noted that the function of VCMU is to collect the temperature and voltage of the battery cell. The data collected by the sensor is not output as the temperature and voltage of the battery cell, but is only used to determine whether the battery cell is leaking. Therefore, the Bluetooth receiving board will transmit the data to the Bluetooth module designed by the VCMU software through the CAN communication line in real time without filtering. VCMU sends this part of the data to the Bluetooth module of the main control SBMU software, and the SBMU determines the leakage status of the battery cell.

[0104] The sensor is located inside the battery cell and collects the battery cell voltage, internal temperature, and internal pressure every 1000ms. A Bluetooth transmitter is designed on each sensor and paired with the corresponding Bluetooth receiver board. The collected data will be transmitted to the Bluetooth receiver board inside the battery pack through the Bluetooth transmitter. The Bluetooth receiver board then transmits the data to the VCMU through CAN communication, and the Bluetooth module of the VCMU software sends the data to the main control. In order to reflect the true status of each battery cell, the data is not processed in any way. It is directly sent to the Bluetooth module of the main control SBMU, and the SBMU determines whether the battery cell is leaking. If there is no leakage, the system charges and discharges normally; if there is leakage, the main control MBMU issues a command, the battery pack where the leaking battery cell is located stops charging and discharging, and a battery cell leakage fault message is issued.

[0105] A Bluetooth module has been added to the VCMU and SBMU software. The Bluetooth module of the VCMU receives the battery leakage data, checks the voltage, temperature and pressure data of each battery, and corresponds to the battery number; if the data is lost, this set of data will not be sent out, and the next set of collected data will overwrite this set of data and send it to the SBMU. The SBMU has a new Bluetooth module to receive this part of the data. There is an intelligent algorithm code in the Bluetooth module to determine whether there is a leakage based on the battery data. If it is determined to be a leakage, the battery leakage fault will be reported. If there is no leakage, the system will operate normally.

[0106] After obtaining the sample battery data when the sample battery has battery leakage, the embodiment of the present application performs standardization processing on the sample battery data, and divides the processed sample battery data into a training set and a test set, then trains the preset long-short term memory model based on the training set, and determines the leakage detection model in the trained long-short term memory model according to the test set, and finally, performs battery leakage detection on the battery to be detected according to the leakage detection model. The battery leakage detection scheme provided by the present application pre-trains the preset long-short term memory model using the sample battery data when the sample battery has battery leakage, and determines the leakage detection model in the trained long-short term memory model according to the test set, and when actually performing battery leakage detection, the trained leakage detection model can be directly used to perform battery leakage detection on the battery to be detected, thereby improving the timeliness of battery leakage detection.

[0107] In addition, the present application also provides an electronic device, such as Figure 3 As shown, it shows a schematic diagram of the structure of the electronic device involved in the embodiment of the present application, specifically:

[0108] The electronic device may include components such as a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, a power supply 303, and an input unit 304. Those skilled in the art will appreciate that Figure 3The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0109] The processor 301 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 302 and calling data stored in the memory 302, it executes various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 301.

[0110] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and battery leakage detection by running the software programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0111] The electronic device also includes a power supply 303 for supplying power to each component. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, so that the power management system can manage charging, discharging, power consumption and other functions. The power supply 303 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0112] The electronic device may further include an input unit 304, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0113] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 301 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302, thereby realizing various functions, as follows:

[0114] Acquire sample battery data when the sample battery has battery leakage; standardize the sample battery data and divide the processed sample battery data into a training set and a test set; train a preset long short-term memory model based on the training set, and determine a leakage detection model in the trained long short-term memory model according to the test set; perform battery leakage detection on the battery to be detected according to the leakage detection model.

[0115] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0116] After obtaining the sample battery data when the sample battery has battery leakage, the embodiment of the present application performs standardization processing on the sample battery data, and divides the processed sample battery data into a training set and a test set, then trains the preset long-short term memory model based on the training set, and determines the leakage detection model in the trained long-short term memory model according to the test set, and finally, performs battery leakage detection on the battery to be detected according to the leakage detection model. The battery leakage detection scheme provided by the present application pre-trains the preset long-short term memory model using the sample battery data when the sample battery has battery leakage, and determines the leakage detection model in the trained long-short term memory model according to the test set, and when actually performing battery leakage detection, the trained leakage detection model can be directly used to perform battery leakage detection on the battery to be detected, thereby improving the timeliness of battery leakage detection.

[0117] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0118] To this end, an embodiment of the present application provides a storage medium in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any of the battery leakage detection methods provided in the embodiments of the present application. For example, the instructions can execute the following steps:

[0119] Acquire sample battery data when the sample battery has battery leakage; standardize the sample battery data and divide the processed sample battery data into a training set and a test set; train a preset long short-term memory model based on the training set, and determine a leakage detection model in the trained long short-term memory model according to the test set; perform battery leakage detection on the battery to be detected according to the leakage detection model.

[0120] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0121] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0122] Since the instructions stored in the storage medium can execute the steps in any battery leakage detection method provided in the embodiments of the present application, the beneficial effects that can be achieved by any battery leakage detection method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0123] The above is a detailed introduction to a battery leakage detection method, an electronic device, and a storage medium provided in an embodiment of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A battery leakage detection method, characterized in that: include: Acquire sample battery data when the sample battery has battery leakage; Standardizing the sample battery data, and dividing the processed sample battery data into a training set and a test set; Training a preset long short-term memory model based on the training set, and determining a leakage detection model in the trained long short-term memory model according to the test set; The battery to be tested is subjected to battery leakage detection according to the leakage detection model.

2. The battery leakage detection method according to claim 1, characterized in that: The step of training a preset long short-term memory model based on the training set and determining a leakage detection model in the trained long short-term memory model according to the test set includes: Get the preset long short-term memory model; Using the training set to train the long short-term memory model; Saving the model weights of the long short-term memory model during training according to a preset callback function; A liquid leakage detection model is determined in the trained long short-term memory model based on the model weights and the test set.

3. The battery leakage detection method according to claim 2, characterized in that: Determining the leakage detection model in the trained long short-term memory model based on the model weight and the test set includes: Determine the model weight and model loss of the long short-term memory model at the nth moment, where n is an integer greater than 0; Updating the model weight of the long short-term memory model at the n+1th moment, and training the long short-term memory model after the weight update based on the training set; Determine the model loss corresponding to the long short-term memory model at the n+1th moment based on the test set; According to the model loss of the long short-term memory model at the nth moment and the model loss at the (n+1)th moment, a leakage detection model is determined in the trained long short-term memory model.

4. The battery leakage detection method according to claim 3, characterized in that: Determining a liquid leakage detection model in the trained long short-term memory model according to the model loss of the long short-term memory model at the nth moment and the model loss at the n+1th moment includes: Comparing the size of the model loss of the long short-term memory model at the nth moment and the model loss at the n+1th moment; The long short-term memory model with the smallest model loss is determined as the leakage detection model.

5. The battery leakage detection method according to claim 4, characterized in that: Also includes: Performing validity testing on model training according to the model loss of the long short-term memory model at the nth moment and the model loss at the n+1th moment; If the detection result is valid, then calculating the error between the estimated leakage data corresponding to the sample battery estimated by the latest long short-term memory model and the actual leakage data corresponding to the sample battery; When the error meets the preset condition, the latest long short-term memory model is determined as the leakage detection model.

6. The battery leakage detection method according to claim 2, characterized in that: The step of training the long short-term memory model using the training set includes: estimating the estimated leakage data corresponding to the training set based on the long short-term memory model; The long short-term memory model is trained according to the real leakage data and the estimated leakage data corresponding to the training set.

7. The battery leakage detection method according to any one of claims 1 to 6, characterized in that: The standardization process of the sample battery data includes: determining an average value of the sample battery data when leaking as a first preset value, and; The variance of the sample battery data when leaking is determined as a second preset value.

8. The battery leakage detection method according to any one of claims 1 to 6, characterized in that: The performing battery leakage detection on the battery to be detected according to the leakage detection model comprises: Acquiring battery data of the battery to be detected by means of a sensor disposed inside the battery to be detected; Processing the battery data according to the leakage detection model to estimate whether the battery to be detected is in a leakage state; If the battery to be detected is in a leakage state, the battery to be monitored is controlled to stop charging and discharging, and fault information corresponding to the battery leakage is output. The detection module is used to perform battery leakage detection on the battery to be detected according to the leakage detection model.

9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the battery leakage detection method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, wherein when the computer program is executed by a processor, the steps of the battery leakage detection method according to any one of claims 1 to 8 are implemented.

Images