Battery reactivation processing method and system based on life prediction

Abstract

The present invention discloses a battery reactivation processing method and system based on life prediction, which relates to the field of battery technology. The method comprises: determining the operating state of a target battery in a preset detection window in combination with a battery detection instrument, analyzing the shedding of active substances, and obtaining the performance coefficient of the positive plate and the performance coefficient of the negative plate; obtaining the performance coefficient of the electrolyte; obtaining the performance coefficient of the separator; calling the life prediction network layer for analysis and prediction, and obtaining the predicted life coefficient; obtaining the first reactivation time; optimizing the reactivation parameters, and obtaining the target reactivation parameters; and reactivating the target battery according to the target discharge current and the target reactivation time at the first reactivation time. The present invention solves the technical problem in the prior art that the timing of battery reactivation processing is separated from the actual state of each component of the battery, resulting in low reactivation processing quality, and achieves the technical effect of improving the quality of battery reactivation processing.

Description

Technical Field

[0001] The present invention relates to the technical field of storage batteries, and in particular to a storage battery reactivation processing method and system based on life prediction. Background Art

[0002] At present, in many battery maintenance technologies, the execution of reactivation treatment often relies on a preset time period or power threshold, while ignoring the actual aging and failure status of internal battery components such as separators and electrode plates. For example, some systems may start the reactivation procedure when the battery power drops to a certain fixed percentage. In fact, if the separator has been severely hardened or the electrode plate has been irreversibly vulcanized, reactivation will not only fail to effectively restore the battery capacity, but may also aggravate component damage, resulting in poor reactivation quality and even shortening the overall service life of the battery. The prior art has the technical problem that the timing of battery reactivation treatment is out of touch with the actual status of each component of the battery, resulting in low reactivation quality. Summary of the invention

[0003] The present application provides a battery reactivation processing method and system based on life prediction, which is used to solve the technical problem in the prior art that the timing of battery reactivation processing is out of touch with the actual status of each component of the battery, resulting in low reactivation processing quality.

[0004] In view of the above problems, the present application provides a battery reactivation processing method and system based on life prediction.

[0005] In a first aspect of the present application, a battery reactivation processing method based on life prediction is provided, the method is applied to a battery reactivation processing system, the battery reactivation processing system is communicatively connected to a battery detection instrument, the method comprising:

[0006] Determine the operating state of the target battery in the preset detection window in combination with the battery detection instrument, analyze the active material shedding situation in combination with the surface state of the positive plate and the negative plate of the target battery, and obtain the positive plate performance coefficient and the negative plate performance coefficient;

[0007] Sampling and testing the electrolyte of the target battery according to a preset sampling and testing scheme, performing comprehensive parameter analysis on the sampling and testing results, and obtaining the electrolyte performance coefficient;

[0008] Monitoring the operating status of the separator of the target battery to obtain a separator performance coefficient;

[0009] Calling the life prediction network layer to analyze and predict the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient to obtain the predicted life coefficient of the target battery;

[0010] Determine whether a reactivation condition is met based on the predicted life coefficient, and if so, obtain a first reactivation opportunity;

[0011] Optimizing reactivation parameters based on the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient, and the separator performance coefficient to obtain target reactivation parameters, wherein the target reactivation parameters include a target discharge current and a target reactivation time;

[0012] At the first reactivation opportunity, a reactivation process is performed on the target storage battery according to the target discharge current and the target reactivation time.

[0013] A second aspect of the present application provides a battery reactivation processing system based on life prediction, the system comprising:

[0014] The plate performance coefficient acquisition module is used to determine the operating state of the target battery in combination with the battery detection instrument in the preset detection window, analyze the active material shedding situation in combination with the surface state of the positive plate and the negative plate of the target battery, and obtain the positive plate performance coefficient and the negative plate performance coefficient;

[0015] An electrolyte performance coefficient acquisition module is used to perform sampling and testing on the electrolyte of the target battery according to a preset sampling and testing scheme, and perform parameter comprehensive analysis on the sampling and testing results to obtain the electrolyte performance coefficient;

[0016] A separator performance coefficient obtaining module, used to monitor the operating status of the separator of the target battery and obtain the separator performance coefficient;

[0017] A predicted life coefficient acquisition module, used for calling the life prediction network layer to analyze and predict the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient to obtain the predicted life coefficient of the target battery;

[0018] A first reactivation opportunity obtaining module, used to determine whether a reactivation condition is met based on the predicted life coefficient, and if so, obtain a first reactivation opportunity;

[0019] a target reactivation parameter acquisition module, for optimizing the reactivation parameters based on the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient, and obtaining the target reactivation parameters, wherein the target reactivation parameters include a target discharge current and a target reactivation time;

[0020] A reactivation processing module is used to perform reactivation processing on the target battery according to the target discharge current and the target reactivation time at the first reactivation opportunity.

[0021] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0022] The present application determines the operating state of the target battery in combination with a battery testing instrument in a preset detection window, analyzes the shedding of active substances in combination with the surface states of the positive plate and the negative plate of the target battery, obtains the positive plate performance coefficient and the negative plate performance coefficient, then samples and tests the electrolyte of the target battery according to a preset sampling and testing scheme, performs a comprehensive parameter analysis on the sampling and testing results, obtains the electrolyte performance coefficient, and then monitors the operating state of the separator of the target battery to obtain the separator performance coefficient, then calls the life prediction network layer to analyze and predict the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient to obtain the predicted life coefficient of the target battery, matches the reactivation timing based on the predicted life coefficient to obtain the first reactivation timing, then optimizes the reactivation parameters based on the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient to obtain the target reactivation parameters, wherein the target reactivation parameters include a target discharge current and a target reactivation time, and then reactivates the target battery according to the target discharge current and the target reactivation time at the first reactivation timing. The technical effect of improving the quality of battery reactivation treatment and extending the battery service life is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A schematic flow chart of a battery reactivation method based on life prediction provided in an embodiment of the present application;

[0025] Figure 2 A schematic diagram of the structure of a battery reactivation processing system based on life prediction provided in an embodiment of the present application.

[0026] Explanation of the reference numerals: plate performance coefficient obtaining module 11, electrolyte performance coefficient obtaining module 12, electrolyte performance coefficient obtaining module 13, predicted life coefficient obtaining module 14, first reactivation timing obtaining module 15, target reactivation parameter obtaining module 16, reactivation processing module 17. DETAILED DESCRIPTION

[0027] The present application provides a battery reactivation processing method and system based on life prediction, which is used to solve the technical problem in the prior art that the timing of battery reactivation processing is out of touch with the actual status of each component of the battery, resulting in low reactivation processing quality.

[0028] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings 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 ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0030] Embodiment 1

[0031] like Figure 1 As shown, the present application provides a battery reactivation processing method based on life prediction, wherein the method is applied to a battery reactivation processing system, the battery reactivation processing system is communicatively connected with a battery detection instrument, and the method comprises:

[0032] S100: determining the operating state of the target battery in a preset detection window in combination with a battery detection instrument, analyzing the shedding of active materials in combination with the surface states of the positive plate and the negative plate of the target battery, and obtaining the performance coefficient of the positive plate and the performance coefficient of the negative plate;

[0033] Further, in the preset detection window, the operating state of the target battery is determined in combination with the battery detection instrument, and the active material shedding is analyzed in combination with the surface state of the positive plate and the negative plate of the target battery to obtain the positive plate performance coefficient and the negative plate performance coefficient. The step S100 of the embodiment of the present application also includes:

[0034] Collecting the operating parameters of the target battery using a battery testing instrument in a preset testing window to obtain a battery operating parameter set;

[0035] Collecting the plate surface images of the positive plate and the negative plate respectively to obtain the positive plate surface image and the negative plate surface image;

[0036] Performing lead flocculant distribution feature recognition on the positive plate surface image and the negative plate surface image to obtain the positive plate lead flocculant distribution feature and the negative plate lead flocculant distribution feature;

[0037] Performing positive plate performance analysis according to the battery operating parameter set and the lead floc distribution characteristics of the positive plate to obtain the positive plate performance coefficient;

[0038] The negative plate performance is analyzed according to the battery operation parameter set and the lead floc distribution characteristics of the negative plate to obtain the negative plate performance coefficient.

[0039] Furthermore, the battery operating parameter set includes operating voltage, operating current and operating resistance.

[0040] In a possible embodiment, the battery detection instrument is a device for detecting the current, voltage and resistance in the target battery. The preset detection window is a time period preset for battery performance detection. The target battery is any battery that needs to be reactivated. The components of the target battery include positive plates, negative plates, electrolytes, separators, etc. In order to improve the performance and service life of the target battery, it is necessary to reactivate the battery. At the same time, the performance status of each component of the battery (such as the positive electrode, negative electrode, electrolyte, separator, etc.) is analyzed, and then the overall life of the target battery is predicted, and then the time point for reactivating the battery is determined according to the predicted life of the target battery. The technical effect of combining the performance of each component of the battery, determining the timing and parameters of battery reactivation, improving the fit between the battery reactivation and the actual operation, and extending the battery life is achieved.

[0041] In one embodiment, the positive plate performance coefficient is used to describe the operating performance of the positive plate of the target battery. When the active material of the positive plate is largely shed, and the voltage, current and resistance of the target battery during operation reflect that the overall performance of the battery is degraded, the positive plate performance will be degraded. The negative plate performance coefficient is used to describe the operating performance of the positive plate of the target battery. When the active material of the negative plate is largely shed, and the voltage, current and resistance of the target battery during operation reflect that the overall performance of the battery is degraded, the negative plate performance will be degraded.

[0042] Optionally, within a preset detection window, a battery detection instrument is used to collect operating parameters of a target battery to obtain a battery operating parameter set, wherein the battery operating parameter set reflects the performance of the target battery in an actual working process. The battery operating parameter set includes operating voltage, operating current and operating resistance.

[0043] A high-definition camera or a dedicated scanning device is used to obtain the surface images of the positive plate and the negative plate, that is, the positive plate surface image and the negative plate surface image. The positive plate surface image reflects the distribution of lead flocs on both sides of the positive plate. The negative plate surface image reflects the distribution of lead flocs on both sides of the negative plate. The positive plate surface image and the negative plate surface image are used for subsequent lead floc distribution feature recognition.

[0044] The collected plate surface images are processed and analyzed to identify the distribution characteristics of lead flocs. The positive plate lead floc distribution characteristics and the negative plate lead floc distribution characteristics reflect information such as the density, shape, and distribution area of ​​the lead flocs, which are used to evaluate the plate performance. Optionally, by constructing a lead floc feature recognition network layer, the positive plate surface image and the negative plate surface image are input into the lead floc feature recognition network layer for feature analysis to obtain the positive plate lead floc distribution characteristics and the negative plate lead floc distribution characteristics.

[0045] Optionally, multiple sample plate surface images and multiple sample plate lead floccules distribution features are obtained as construction data, and the framework constructed based on the convolutional neural network is supervised and trained using the construction data until convergence is reached, thereby obtaining the trained lead floccules feature recognition network layer. The positive plate surface image and the negative plate surface image are input into the lead floccules feature recognition network layer for recognition, thereby obtaining the positive plate lead floccules distribution features and the negative plate lead floccules distribution features.

[0046] The battery performance analysis is performed based on the battery operating parameter set. Optionally, a preset parameter-performance mapping table (a table for analyzing battery performance constructed by a person skilled in the art) is obtained, and the battery operating parameter set is input into the preset parameter-performance mapping table for mapping and acquisition to obtain the window operating performance of the target battery. The window operating performance and the lead floc distribution characteristics of the positive plate are comprehensively analyzed to obtain the positive plate performance coefficient. Optionally, multiple sample battery operating parameter sets, multiple sample plate lead floc distribution characteristics, and multiple sample plate performance coefficients are obtained as training data sets, and the training data sets are used to supervise the training of the framework constructed based on the feedforward neural network, and the mapping relationship between the battery operating parameters and the plate lead floc distribution characteristics and the plate performance coefficient is learned until the model converges to obtain a trained plate performance analysis network layer. The battery operating parameter set and the positive plate lead floc distribution characteristics are sent to the plate performance analysis network layer for analysis to obtain the positive plate performance coefficient. Based on the same principle, the battery operation parameter set and the lead floc distribution characteristics of the negative plate are sent to the plate performance analysis network layer for analysis to obtain the negative plate performance coefficient.

[0047] By obtaining the positive plate performance coefficient and the negative plate performance coefficient, the performance status of the positive and negative plates can be intuitively grasped, providing a basis for subsequent life prediction and reactivation treatment.

[0048] S200: performing sampling inspection on the electrolyte of the target battery according to a preset sampling inspection scheme, performing comprehensive parameter analysis on the sampling inspection results, and obtaining an electrolyte performance coefficient;

[0049] In one possible embodiment, an appropriate sampling method is selected, such as random sampling, stratified sampling or systematic sampling, to ensure the representativeness and reliability of the sample. At the same time, the frequency, quantity and location of the sampling are determined, such as extracting electrolyte samples from different heights or different positions of the battery, so as to obtain the preset sampling detection scheme. Extract electrolyte samples from the target battery according to the preset sampling method and location. Pay attention to safety protection during operation to avoid direct contact of the electrolyte with the skin or eyes. According to the detection requirements, the extracted electrolyte samples are subjected to necessary pretreatment, such as filtration, dilution or neutralization, to ensure the accuracy of the test results. Use the prepared detection tools to detect the treated electrolyte samples, record various test data, and obtain the sampling test results. Among them, the sampling test results include electrolyte color, turbidity and impurity distribution.

[0050] Optionally, a person skilled in the art constructs an electrolyte performance mapping table, inputs the electrolyte color, turbidity and impurity distribution in the sampling test results into the electrolyte performance mapping table, and obtains the electrolyte performance coefficient by mapping and searching. Thus, the goal of providing data support for subsequent battery reactivation treatment analysis from the perspective of electrolyte performance analysis is achieved.

[0051] S300: monitoring the operating status of the separator of the target battery to obtain a separator performance coefficient;

[0052] Furthermore, step S300 of the embodiment of the present application further includes:

[0053] Invoking a sensor integrated device to monitor the separator of the target battery in real time according to a preset separator influence index to obtain a real-time monitoring result of the separator status;

[0054] Performing non-destructive testing on the partition by using X-ray testing in a preset testing window to determine the surface morphology of the partition and obtain the surface deformation characteristics of the partition;

[0055] The real-time monitoring results of the partition state and the deformation characteristics of the partition surface are comprehensively analyzed to obtain the partition performance coefficient.

[0056] In one embodiment, the separator is located between the positive plate and the negative plate of the battery to prevent a direct short circuit between the positive and negative electrodes. Therefore, the performance status of the separator is crucial to whether the battery needs to be reactivated.

[0057] Optionally, the preset separator influence index is resistivity, thickness, mechanical strength, etc. The sensor integrated device is used to monitor the separator state of the target battery, and can work continuously to collect various data of the separator operation state in real time, including temperature sensor, thickness sensor, etc. The sensor integrated device is called according to the preset separator influence index to monitor the separator of the target battery in real time, and obtain the real-time monitoring result of the separator state. Among them, the real-time monitoring result of the separator state reflects the real-time state of the separator of the target battery.

[0058] Optionally, since X-rays can penetrate the partition material and reveal its internal microstructure and surface morphology, an X-ray detection image can be obtained by performing non-destructive detection on the partition using X-ray detection equipment in a preset detection window. The X-ray detection image is intelligently analyzed using a surface deformation feature identifier to determine the surface morphology of the partition and obtain the surface deformation characteristics of the partition. The surface deformation characteristics of the partition include cracks, depressions, and expansions, which reflect the physical damage of the partition during long-term use. Preferably, the real-time monitoring results of the partition state and the surface deformation characteristics of the partition are input into a partition performance identifier to obtain the partition performance coefficient. The partition performance identifier is used to intelligently perform a comprehensive analysis of the real-time monitoring results of the partition state and the surface deformation characteristics of the partition to obtain the partition performance coefficient. Optionally, the partition performance identifier is constructed based on a convolutional neural network, a neural network model that takes the real-time monitoring results of the partition state and the surface deformation characteristics of the partition as input and takes the partition performance coefficient as output.

[0059] S400: calling the life prediction network layer to analyze and predict the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient to obtain the predicted life coefficient of the target battery;

[0060] Furthermore, step S400 in the embodiment of the present application further includes:

[0061] Acquire multiple sample positive plate performance coefficients, multiple sample negative plate performance coefficients, multiple sample electrolyte performance coefficients, multiple sample separator performance coefficients, and multiple sample predicted life coefficients as training data, and perform data identification on the multiple sample predicted life coefficients;

[0062] The training data is used to train a framework built based on a convolutional neural network, and during the training process, the life prediction coefficients of the multiple samples after data identification are used for supervision. The network parameters are updated according to the supervision results until convergence is reached, thereby obtaining the trained life prediction network layer.

[0063] In one embodiment of the present application, the life prediction network layer is a network model for comprehensively analyzing the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient to determine the overall life of the battery. The positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient are input into the life prediction network layer for analysis to obtain the predicted life coefficient of the target battery. The predicted life coefficient of the target battery reflects the life of the target battery.

[0064] Optionally, collect the positive plate performance coefficient, negative plate performance coefficient, electrolyte performance coefficient, separator performance coefficient and the corresponding predicted life coefficient from multiple battery samples. These data may come from experimental tests and historical records. Clean the collected data to remove outliers, missing values ​​or erroneous data. Standardize or normalize the data to ensure that data of different dimensions and ranges can be compared and analyzed on the same scale. Design a convolutional neural network (CNN) structure suitable for processing multi-dimensional inputs (such as multiple performance coefficients), including multiple convolutional layers, pooling layers, fully connected layers, etc. Initialize the weights and biases in the network. This is usually done by random initialization or using pre-trained weights. Input the pre-processed training data (multiple sample positive plate performance coefficients, multiple sample negative plate performance coefficients, multiple sample electrolyte performance coefficients, multiple sample separator performance coefficients and multiple sample predicted life coefficients) into the CNN framework. Each sample includes the positive plate performance coefficient, negative plate performance coefficient, electrolyte performance coefficient, separator performance coefficient as input features, and the predicted life coefficient as the target output. The data is forward propagated through each layer of CNN, and the output of each layer is calculated. In the last layer (usually a fully connected layer), the error between the predicted life coefficient and the actual life coefficient is calculated (such as using the mean square error MSE as the loss function). According to the gradient of the loss function, the weights and biases in the network are updated through the back propagation algorithm until the model reaches convergence, and the trained life prediction network layer is obtained.

[0065] S500: determining whether a reactivation condition is met based on the predicted life coefficient, and if so, obtaining a first reactivation opportunity;

[0066] In a possible embodiment, the reactivation condition is that the predicted life coefficient is less than or equal to a life coefficient threshold (a minimum life coefficient set by a person skilled in the art when no battery reactivation is required). When the predicted life coefficient is less than or equal to the life coefficient threshold, the reactivation condition is met, and the battery reactivation process is required at this time, and the end time point of the preset detection window is used as the first reactivation opportunity. When the predicted life coefficient does not meet the reactivation condition, it indicates that the battery reactivation process is not required at this time. In this way, the technical effect of improving the reliability of the battery reactivation process time node and extending the battery life is achieved.

[0067] S600: Optimizing reactivation parameters based on the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient, and the separator performance coefficient to obtain target reactivation parameters, wherein the target reactivation parameters include a target discharge current and a target reactivation time;

[0068] S700: reactivating the target battery according to the target discharge current and the target reactivation time at the first reactivation opportunity.

[0069] Furthermore, step S600 in the embodiment of the present application further includes:

[0070] Inputting the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient into the reactivation parameter optimization space to obtain initial reactivation parameters, wherein the initial reactivation parameters include an initial discharge current and an initial reactivation time;

[0071] evaluating the processing quality of the target battery reactivation process by the initial reactivation parameters to obtain the initial parameter fitness;

[0072] Adjusting the initial reactivation parameters according to a preset adjustment method to obtain stage reactivation parameters;

[0073] evaluating the quality of the target battery reactivation process by the stage reactivation parameters to obtain the stage parameter fitness;

[0074] Determine that the fitness of the stage parameter is greater than or equal to the fitness of the initial parameter. If so, take the stage reactivation parameter as an adjustment object and adjust it according to the preset adjustment method until the preset adjustment times are met to obtain the target discharge current and the target reactivation time;

[0075] The target discharge current and the target reactivation time are used as the target reactivation parameters.

[0076] Furthermore, the preset adjustment method is to increase or decrease the initial discharge current according to a preset current adjustment step, and to increase or decrease the initial reactivation time according to a preset time adjustment step.

[0077] In a possible embodiment, the positive plate performance coefficient, negative plate performance coefficient, electrolyte performance coefficient and separator performance coefficient respectively reflect the performance of the positive plate, negative plate, electrolyte and separator, and at this time, the reactivation parameters are optimized according to the actual conditions of the components to obtain the target reactivation parameters, wherein the target reactivation parameters include the target discharge current and the target reactivation time. The technical effect of improving the degree of fit between the reactivation parameters and the actual operation of the target battery is achieved.

[0078] Furthermore, at the first reactivation opportunity, the target battery is reactivated according to the target discharge current and the target reactivation time, thereby achieving the technical effect of reliably extending the battery life and improving the quality of battery reactivation.

[0079] In one possible embodiment, the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient are input into the reactivation parameter optimization space to obtain the initial reactivation parameters, wherein the initial reactivation parameters include the initial discharge current and the initial reactivation time. The reactivation parameter optimization space stores a data storage space for multiple historical reactivation records. The positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient are input into the reactivation parameter optimization space for interpolation extraction to obtain the initial reactivation parameters. The initial reactivation parameters include the initial discharge current and the initial reactivation time. The initial reactivation time is the duration of the reactivation process.

[0080] Combine the positive plate performance coefficient, negative plate performance coefficient, electrolyte performance coefficient and separator performance coefficient, and the initial reactivation parameters to evaluate the processing quality of the target battery reactivation process and obtain the initial parameter fitness. Based on the same construction principle as the life prediction network layer, construct a parameter fitness analysis network layer. Input the positive plate performance coefficient, negative plate performance coefficient, electrolyte performance coefficient and separator performance coefficient, and the initial reactivation parameters into the parameter fitness analysis network layer for analysis to obtain the initial parameter fitness. Among them, the initial parameter fitness reflects the degree of adaptability of the initial reactivation parameters to the actual situation of the target battery.

[0081] The initial reactivation parameter is adjusted according to a preset adjustment method to obtain a stage reactivation parameter, wherein the preset adjustment method is to increase or decrease the initial discharge current according to a preset current adjustment step, and to increase or decrease the initial reactivation time according to a preset time adjustment step.

[0082] Optionally, based on the same principle as the initial parameter fitness, the quality of the target battery reactivation process is evaluated according to the stage reactivation parameters to obtain the stage parameter fitness, wherein the stage parameter fitness reflects the degree of adaptability of the stage reactivation parameters to the actual situation of the target battery.

[0083] It is determined that the fitness of the stage parameter is greater than or equal to the fitness of the initial parameter. If so, the stage reactivation parameter is taken as the adjustment object and adjusted according to the preset adjustment method until a preset adjustment number (a maximum adjustment number pre-set by a person skilled in the art, such as 30 times, etc.) is met to obtain the target discharge current and the target reactivation time. The target discharge current and the target reactivation time are taken as the target reactivation parameters.

[0084] In summary, the embodiments of the present application have at least the following technical effects:

[0085] The present application determines the operating state of the target battery in a preset detection window in combination with a battery detection instrument, analyzes the shedding of active substances in combination with the surface state of the positive plate and the negative plate of the target battery, obtains the performance coefficient of the positive plate and the performance coefficient of the negative plate, and achieves the goal of determining the state of the positive plate and the negative plate. Then, the electrolyte of the target battery is sampled and tested according to the preset sampling detection scheme, and the parameters of the sampling detection results are comprehensively analyzed to obtain the electrolyte performance coefficient. Then, the operating state of the separator of the target battery is monitored to obtain the separator performance coefficient, and then the life prediction network is called. The performance coefficient of the positive plate, the performance coefficient of the negative plate, the performance coefficient of the electrolyte and the performance coefficient of the separator are analyzed and predicted to obtain the predicted life coefficient of the target battery, realizing the goal of intelligently predicting the life of the target battery, matching the reactivation timing based on the predicted life coefficient, obtaining the first reactivation timing, and then optimizing the reactivation parameters based on the performance coefficient of the positive plate, the performance coefficient of the negative plate, the performance coefficient of the electrolyte and the performance coefficient of the separator to obtain the target reactivation parameters, and then reactivating the target battery according to the target discharge current and the target reactivation time at the first reactivation timing. The technical effect of improving the accuracy of the battery reactivation treatment, effectively avoiding the situation of inaccurate treatment timing, and extending the battery life is achieved.

[0086] Embodiment 2

[0087] Based on the same inventive concept as the battery reactivation processing method based on life prediction in the aforementioned embodiment, Figure 2 As shown, the present application provides a battery reactivation processing system based on life prediction, and the system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0088] The plate performance coefficient obtaining module 11 is used to determine the operating state of the target battery in combination with the battery testing instrument in the preset detection window, analyze the active material shedding situation in combination with the surface state of the positive plate and the negative plate of the target battery, and obtain the positive plate performance coefficient and the negative plate performance coefficient;

[0089] The electrolyte performance coefficient obtaining module 12 is used to perform sampling inspection on the electrolyte of the target battery according to a preset sampling inspection scheme, perform parameter comprehensive analysis on the sampling inspection results, and obtain the electrolyte performance coefficient;

[0090] A separator performance coefficient obtaining module 13 is used to monitor the operating status of the separator of the target battery and obtain the separator performance coefficient;

[0091] The predicted life coefficient obtaining module 14 is used to call the life prediction network layer to analyze and predict the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient to obtain the predicted life coefficient of the target battery;

[0092] A first reactivation opportunity obtaining module 15, for determining whether a reactivation condition is met based on the predicted life coefficient, and if so, obtaining a first reactivation opportunity;

[0093] A target reactivation parameter acquisition module 16 is used to optimize the reactivation parameters based on the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient to obtain the target reactivation parameters, wherein the target reactivation parameters include a target discharge current and a target reactivation time;

[0094] The reactivation processing module 17 is used to perform a reactivation process on the target battery according to the target discharge current and the target reactivation time at the first reactivation opportunity.

[0095] Furthermore, the plate performance coefficient obtaining module 11 is used to perform the following steps:

[0096] Collecting the operating parameters of the target battery using a battery testing instrument in a preset testing window to obtain a battery operating parameter set;

[0097] Collecting the plate surface images of the positive plate and the negative plate respectively to obtain the positive plate surface image and the negative plate surface image;

[0098] Performing lead flocculant distribution feature recognition on the positive plate surface image and the negative plate surface image to obtain the positive plate lead flocculant distribution feature and the negative plate lead flocculant distribution feature;

[0099] Performing positive plate performance analysis according to the battery operating parameter set and the lead floc distribution characteristics of the positive plate to obtain the positive plate performance coefficient;

[0100] The negative plate performance is analyzed according to the battery operation parameter set and the lead floc distribution characteristics of the negative plate to obtain the negative plate performance coefficient.

[0101] Furthermore, the battery operating parameter set includes operating voltage, operating current and operating resistance.

[0102] Furthermore, the partition performance coefficient obtaining module 13 is used to perform the following steps:

[0103] Invoking a sensor integrated device to monitor the separator of the target battery in real time according to a preset separator influence index to obtain a real-time monitoring result of the separator status;

[0104] Performing non-destructive testing on the partition by using X-ray testing in a preset testing window to determine the surface morphology of the partition and obtain the surface deformation characteristics of the partition;

[0105] The real-time monitoring results of the partition state and the deformation characteristics of the partition surface are comprehensively analyzed to obtain the partition performance coefficient.

[0106] Furthermore, the predicted life coefficient obtaining module 14 is used to perform the following steps:

[0107] Acquire multiple sample positive plate performance coefficients, multiple sample negative plate performance coefficients, multiple sample electrolyte performance coefficients, multiple sample separator performance coefficients, and multiple sample predicted life coefficients as training data, and perform data identification on the multiple sample predicted life coefficients;

[0108] The training data is used to train a framework built based on a convolutional neural network, and during the training process, the life prediction coefficients of the multiple samples after data identification are used for supervision. The network parameters are updated according to the supervision results until convergence is reached, thereby obtaining the trained life prediction network layer.

[0109] Furthermore, the target reactivation parameter obtaining module 16 is used to perform the following steps:

[0110] Inputting the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient into the reactivation parameter optimization space to obtain initial reactivation parameters, wherein the initial reactivation parameters include an initial discharge current and an initial reactivation time;

[0111] evaluating the processing quality of the target battery reactivation process by the initial reactivation parameters to obtain the initial parameter fitness;

[0112] Adjusting the initial reactivation parameters according to a preset adjustment method to obtain stage reactivation parameters;

[0113] evaluating the quality of the target battery reactivation process by the stage reactivation parameters to obtain the stage parameter fitness;

[0114] Determine that the fitness of the stage parameter is greater than or equal to the fitness of the initial parameter. If so, take the stage reactivation parameter as an adjustment object and adjust it according to the preset adjustment method until the preset adjustment times are met to obtain the target discharge current and the target reactivation time;

[0115] The target discharge current and the target reactivation time are used as the target reactivation parameters.

[0116] Furthermore, the preset adjustment method is to increase or decrease the initial discharge current according to a preset current adjustment step, and to increase or decrease the initial reactivation time according to a preset time adjustment step.

[0117] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0118] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0119] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A battery reactivation method based on life prediction, characterized in that: The method is applied to a battery reactivation processing system, wherein the battery reactivation processing system is communicatively connected to a battery detection instrument, and the method comprises: Determine the operating state of the target battery in the preset detection window in combination with the battery detection instrument, analyze the active material shedding situation in combination with the surface state of the positive plate and the negative plate of the target battery, and obtain the positive plate performance coefficient and the negative plate performance coefficient; Sampling and testing the electrolyte of the target battery according to a preset sampling and testing scheme, performing comprehensive parameter analysis on the sampling and testing results, and obtaining the electrolyte performance coefficient; Monitoring the operating status of the separator of the target battery to obtain a separator performance coefficient; Calling the life prediction network layer to analyze and predict the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient to obtain the predicted life coefficient of the target battery; Determine whether a reactivation condition is met based on the predicted life coefficient, and if so, obtain a first reactivation opportunity; Optimizing reactivation parameters based on the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient, and the separator performance coefficient to obtain target reactivation parameters, wherein the target reactivation parameters include a target discharge current and a target reactivation time; reactivating the target battery according to the target discharge current and the target reactivation time at the first reactivation opportunity; Among them, a battery testing instrument is used to perform multi-dimensional testing on the active materials of the positive plate and the negative plate of the target battery in a preset testing window, and the test results are analyzed to obtain the positive plate performance coefficient and the negative plate performance coefficient, including: Collecting the operating parameters of the target battery using a battery testing instrument in a preset testing window to obtain a battery operating parameter set; Collecting the plate surface images of the positive plate and the negative plate respectively to obtain the positive plate surface image and the negative plate surface image; Performing lead flocculant distribution feature recognition on the positive plate surface image and the negative plate surface image to obtain the positive plate lead flocculant distribution feature and the negative plate lead flocculant distribution feature; Performing positive plate performance analysis according to the battery operating parameter set and the lead floc distribution characteristics of the positive plate to obtain the positive plate performance coefficient; Performing negative plate performance analysis according to the battery operating parameter set and the lead floc distribution characteristics of the negative plate to obtain the negative plate performance coefficient; Wherein, the method further comprises: Invoking a sensor integrated device to monitor the separator of the target battery in real time according to a preset separator influence index to obtain a real-time monitoring result of the separator status; Performing non-destructive testing on the partition by using X-ray testing in a preset testing window to determine the surface morphology of the partition and obtain the surface deformation characteristics of the partition; Comprehensively analyzing the real-time monitoring results of the partition state and the deformation characteristics of the partition surface to obtain the partition performance coefficient; Wherein, the method further comprises: Inputting the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient into the reactivation parameter optimization space to obtain initial reactivation parameters, wherein the initial reactivation parameters include an initial discharge current and an initial reactivation time; evaluating the processing quality of the target battery reactivation process by the initial reactivation parameters to obtain the initial parameter fitness; Adjusting the initial reactivation parameters according to a preset adjustment method to obtain stage reactivation parameters; evaluating the quality of the target battery reactivation process by the stage reactivation parameters to obtain the stage parameter fitness; Determine that the fitness of the stage parameter is greater than or equal to the fitness of the initial parameter. If so, take the stage reactivation parameter as an adjustment object and adjust it according to the preset adjustment method until the preset adjustment times are met to obtain the target discharge current and the target reactivation time; The target discharge current and the target reactivation time are used as the target reactivation parameters.

2. The battery reactivation method based on life prediction according to claim 1, characterized in that: The battery operating parameter set includes operating voltage, operating current and operating resistance.

3. The battery reactivation method based on life prediction according to claim 1, characterized in that: include: Acquire multiple sample positive plate performance coefficients, multiple sample negative plate performance coefficients, multiple sample electrolyte performance coefficients, multiple sample separator performance coefficients, and multiple sample predicted life coefficients as training data, and perform data identification on the multiple sample predicted life coefficients; The training data is used to train a framework built based on a convolutional neural network, and during the training process, the life prediction coefficients of the multiple samples after data identification are used for supervision. The network parameters are updated according to the supervision results until convergence is reached, thereby obtaining the trained life prediction network layer.

4. The battery reactivation method based on life prediction according to claim 1, characterized in that: The preset adjustment method is to increase or decrease the initial discharge current according to a preset current adjustment step, and to increase or decrease the initial reactivation time according to a preset time adjustment step.

5. A battery reactivation system based on life prediction, characterized in that: The system is used to implement the battery reactivation treatment method based on life prediction according to any one of claims 1 to 4, and the system comprises: The plate performance coefficient acquisition module is used to perform multi-dimensional detection of the active materials of the positive plate and the negative plate of the target battery using a battery detection instrument in a preset detection window, and analyze the detection results to obtain the positive plate performance coefficient and the negative plate performance coefficient; An electrolyte performance coefficient acquisition module is used to perform sampling and testing on the electrolyte of the target battery according to a preset sampling and testing scheme, and perform parameter comprehensive analysis on the sampling and testing results to obtain the electrolyte performance coefficient; A separator performance coefficient obtaining module, used to monitor the operating status of the separator of the target battery and obtain the separator performance coefficient; A predicted life coefficient acquisition module, used for calling the life prediction network layer to analyze and predict the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient to obtain the predicted life coefficient of the target battery; A first reactivation opportunity obtaining module, used to determine whether a reactivation condition is met based on the predicted life coefficient, and if so, obtain a first reactivation opportunity; a target reactivation parameter acquisition module, for optimizing the reactivation parameters based on the positive plate performance coefficient, the negative plate performance coefficient, the electrolyte performance coefficient and the separator performance coefficient, and obtaining the target reactivation parameters, wherein the target reactivation parameters include a target discharge current and a target reactivation time; A reactivation processing module is used to perform reactivation processing on the target battery according to the target discharge current and the target reactivation time at the first reactivation opportunity.

Images