A lithium battery state prediction method and storage medium

Abstract

The present invention discloses a lithium battery state prediction method and storage medium, the method comprising: obtaining battery operation data and a state recognition model of a target lithium battery at multiple moments, wherein the state recognition model is obtained based on deep learning model training, and the state recognition model comprises at least a gating module and a multi-task prediction module, the gating module is used to determine the weight of input features, and the multi-task prediction module is used to predict more than two battery state parameters; the battery operation data is input into the state recognition model to obtain prediction parameters related to the lithium battery operation state, wherein the prediction parameters include at least remaining life, health status and charge state, thereby improving the efficiency and accuracy of battery management, helping to optimize battery use and maintenance, and thus extending battery service life.

Description

Technical Field

[0001] The present invention relates to the technical field of lithium battery health detection, and in particular to a lithium battery state prediction method and a storage medium. Background Art

[0002] Accurately assessing and predicting the operating status of lithium batteries faces many challenges. The electrochemical reaction mechanism inside the battery is complex, and the operating status is affected by multiple factors such as temperature, charge and discharge current, degree of aging, state of charge, and health status. Existing related technologies are difficult to fully capture the complex nonlinear relationship between factors affecting the operating status of lithium batteries. Although traditional physical model-based methods can construct models based on the internal reaction mechanism of the battery, due to the complexity of the internal battery reaction, the model parameters are difficult to accurately obtain and update in real time, and there are great limitations in practical applications. In response to the above technical problems, there is an urgent need to develop a more mature lithium battery status prediction method. Summary of the Invention

[0003] The present invention provides a lithium battery state prediction method and a storage medium to solve the problem in the related art that the prediction model can only predict a single battery state parameter.

[0004] According to one aspect of the present invention, a method for predicting a lithium battery state is provided, comprising:

[0005] Obtaining battery operating data and a state recognition model of a target lithium battery at multiple times, wherein the state recognition model is trained based on a deep learning model and includes at least a gating module and a multi-task prediction module, wherein the gating module is used to determine the weight of input features, and the multi-task prediction module is used to predict two or more battery state parameters;

[0006] The battery operation data is input into a state recognition model to obtain prediction parameters related to the lithium battery operation state, wherein the prediction parameters at least include remaining life, health state and charge state.

[0007] According to another aspect of the present invention, a lithium battery state prediction device is provided, the device comprising:

[0008] An acquisition module, configured to acquire battery operating data and a state recognition model of a target lithium battery at multiple times, wherein the state recognition model is trained based on a deep learning model and includes at least a gating module and a multi-task prediction module. The gating module is configured to determine the weights of input features, and the multi-task prediction module is configured to predict two or more battery state parameters.

[0009] A prediction parameter determination module is used to input the battery operation data into a state recognition model to obtain prediction parameters related to the lithium battery operation state, wherein the prediction parameters at least include remaining life, health state and charge state.

[0010] According to another aspect of the present invention, an electronic device is provided, comprising:

[0011] at least one processor;

[0012] and a memory communicatively coupled to the at least one processor;

[0013] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the lithium battery state prediction method described in any embodiment of the present invention.

[0014] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the lithium battery state prediction method described in any embodiment of the present invention when executed.

[0015] The technical solution of the embodiment of the present invention obtains the battery operation data and state recognition model of the target lithium battery at multiple moments. Since the state recognition model is obtained based on deep learning model training, the state recognition model includes at least a gating module and a multi-task prediction module. The gating module is used to determine the weight of the input feature, and the multi-task prediction module is used to predict more than two battery state parameters, which can provide sufficient data support and tools for the state prediction of the lithium battery; the battery operation data is input into the state recognition model to obtain prediction parameters related to the lithium battery operation state, wherein the prediction parameters include at least remaining life, health state and charge state, which can realize accurate prediction of multiple state parameters of the lithium battery, solves the problem in the related technology that the prediction model can only predict a single battery state parameter, improves the efficiency and accuracy of battery management, and helps optimize battery use and maintenance, thereby extending the battery life.

[0016] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] 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.

[0018] Figure 1 This is a flow chart of a lithium battery status prediction method provided according to the first embodiment of the present invention;

[0019] Figure 2 This is a schematic structural diagram of a lithium battery status prediction device provided according to a third embodiment of the present invention;

[0020] Figure 3 2 is a schematic structural diagram of a state recognition model in a lithium battery state prediction method provided by an embodiment of the present invention;

[0021] Figure 4 1 is a GRU schematic diagram of a state recognition model in a lithium battery state prediction method provided by an embodiment of the present invention;

[0022] Figure 5 2 is a schematic diagram of a temporal convolutional network of a state recognition model in a lithium battery state prediction method provided by an embodiment of the present invention;

[0023] FIG6 (a) is a schematic diagram of the SOH prediction result of the state recognition model in a lithium battery state prediction method provided in an embodiment of the present invention;

[0024] FIG6 (b) is a schematic diagram of an error in the SOH prediction result of a state recognition model in a lithium battery state prediction method provided by an embodiment of the present invention;

[0025] FIG6 (c) is a schematic diagram of the SOH prediction result of the long short-term memory network (LSTM) lithium battery state prediction method provided according to an embodiment of the present invention;

[0026] FIG6( d ) is a schematic diagram of the SOH prediction result error of the long short-term memory network (LSTM) lithium battery state prediction method provided according to an embodiment of the present invention;

[0027] FIG6( e ) is a schematic diagram of the SOH prediction result of the lithium battery state prediction method using a convolutional long short-term memory fusion network (CNN-LSTM) according to an embodiment of the present invention;

[0028] FIG6( f ) is a schematic diagram of the SOH prediction result error of the lithium battery state prediction method using a convolutional long short-term memory fusion network (CNN-LSTM) according to an embodiment of the present invention;

[0029] FIG6( g ) is a schematic diagram of the SOH prediction result of the gated recurrent unit (GRU) lithium battery state prediction method provided according to an embodiment of the present invention;

[0030] FIG6( h ) is a schematic diagram of the SOH prediction result error of the gated recurrent unit (GRU) lithium battery state prediction method provided according to an embodiment of the present invention;

[0031] FIG6 (i) is a schematic diagram of the SOH prediction result of the recurrent neural network (RNN) lithium battery state prediction method provided according to an embodiment of the present invention;

[0032] FIG6( j ) is a schematic diagram of the SOH prediction result error of the recurrent neural network (RNN) lithium battery state prediction method provided according to an embodiment of the present invention;

[0033] FIG7 (a) is a schematic diagram of a RUL prediction result of a state recognition model in a lithium battery state prediction method provided in accordance with an embodiment of the present invention;

[0034] FIG7 (b) is a schematic diagram of the RUL prediction result error of the state recognition model in a lithium battery state prediction method provided by an embodiment of the present invention;

[0035] FIG7 (c) is a schematic diagram of the RUL prediction result of the long short-term memory network (LSTM) lithium battery status prediction method provided according to an embodiment of the present invention;

[0036] FIG7( d ) is a schematic diagram of the RUL prediction result error of the long short-term memory network (LSTM) lithium battery status prediction method provided according to an embodiment of the present invention;

[0037] FIG7 (e) is a schematic diagram of the RUL prediction result of the lithium battery status prediction method using a convolutional long short-term memory fusion network (CNN-LSTM) according to an embodiment of the present invention;

[0038] FIG7( f ) is a schematic diagram of the RUL prediction result error of the lithium battery state prediction method using a convolutional long short-term memory fusion network (CNN-LSTM) according to an embodiment of the present invention;

[0039] FIG7( g ) is a schematic diagram of the RUL prediction result of the gated recurrent unit (GRU) lithium battery status prediction method provided according to an embodiment of the present invention;

[0040] FIG7 (h) is a schematic diagram of the RUL prediction result error of the gated recurrent unit (GRU) lithium battery status prediction method provided according to an embodiment of the present invention;

[0041] FIG7 (i) is a schematic diagram of the RUL prediction result of the recurrent neural network (RNN) lithium battery status prediction method provided according to an embodiment of the present invention;

[0042] FIG7( j ) is a schematic diagram of the RUL prediction result error of the recurrent neural network (RNN) lithium battery state prediction method provided according to an embodiment of the present invention;

[0043] Figure 8 2 is a schematic diagram of a prediction result of SOC in a lithium battery state prediction method provided by an embodiment of the present invention;

[0044] Figure 9 It is a structural diagram of an electronic device for implementing the lithium battery state prediction method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0046] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0047] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0048] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0049] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0050] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0051] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0052] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0053] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0054] Example 1: Figure 1 A flowchart of a lithium battery status prediction method is provided for the first embodiment of the present invention. This embodiment is applicable to situations where real-time detection and accurate prediction of the lithium battery status are required. The method can be performed by a lithium battery status prediction device, which can be implemented in the form of hardware and / or software. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, PC or server, etc.

[0055] like Figure 1 As shown, the method may specifically include:

[0056] S110. Obtain battery operation data and a state recognition model of the target lithium battery at multiple moments, wherein the state recognition model is obtained based on deep learning model training, and the state recognition model includes at least a gating module and a multi-task prediction module, the gating module is used to determine the weight of the input feature, and the multi-task prediction module is used to predict more than two battery state parameters.

[0057] The target lithium battery can be understood as a specific lithium-ion battery that is the subject of inspection or analysis. The target lithium battery can be used for energy storage and power supply and is a key component of electronic devices such as electric vehicles. By collecting and analyzing the battery operating data of the target lithium battery, its performance can be evaluated and its future state predicted. The battery operating data can be understood as various data generated during the use of the target lithium battery, including but not limited to voltage, current, and temperature. This battery operating data is used to detect the operating state of the lithium battery and provide basic data information for subsequent state identification. The state identification model can be understood as a model built based on deep learning technology, which is used to determine the current battery state based on the battery operating data. By analyzing the battery operating data, the state identification model can predict important parameters such as the health status, remaining life, and state of charge of the lithium battery, helping to optimize battery management and maintenance plans. The gating module can be understood as a mechanism in deep learning models, such as the GRU (Gated Recurrent Unit), which is used to control information flow. The gating module can learn to determine which input features are more important and adjust the weights of the input features, helping to improve the state identification model's ability to understand time series data. The multi-task prediction module can be understood as a model component that can predict multiple related output variables.

[0058] On the basis of the above scheme, optionally, before obtaining the battery operation data of the target lithium battery at multiple moments, it also includes: obtaining the acquisition data of the target lithium battery at multiple moments, post-processing the acquisition data to obtain post-processing analysis data; and determining the battery operation data based on the acquisition data and the post-processing analysis data.

[0059] The collected data may be understood as data collected from the target lithium battery at different time points, including but not limited to voltage, current, and temperature, etc. The post-processing includes methods such as obtaining the maximum value, average value, skewness, and kurtosis.

[0060] Based on the above method, optionally, the acquisition of the collected data of the target lithium battery at multiple moments includes: acquiring the collected data through the sensor of the lithium battery pack; or transmitting the operating data on the remote device to the central server through wireless communication technology to obtain the collected data; or, in response to a data upload operation, acquiring the uploaded collected data; or, pulling data from a preset battery operation database to obtain the collected data, etc., which are not specifically limited here.

[0061] Based on the above method, optionally, the collected data includes at least: charging voltage, discharging voltage, charging current, discharging current, rated voltage, rated capacity, charging capacity (acceptable capacity under charging conditions), discharging capacity (capacity that can be released under discharging conditions), charging time, discharging time and ambient temperature, etc. corresponding to several charging and discharging cycles before the charging and discharging cycle.

[0062] By adopting this technical solution, useful information can be determined by post-processing the collected data of the target lithium battery, thereby accurately determining the battery operation data. This not only improves the accuracy of battery status assessment, but also enhances the reliability of predicting remaining life and health status, helps to optimize battery management and maintenance strategies and extend battery service life.

[0063] Based on the above scheme, optionally, the state recognition model also includes a first feature extraction module and a second feature extraction module; the multi-task prediction module includes a first prediction unit, a second prediction unit and a third prediction unit; the first feature extraction module, the second feature extraction module, the first prediction unit, the second prediction unit and the third prediction unit are all connected to the gating module; and the second feature extraction module is connected to the second prediction unit.

[0064] The first feature extraction module and the second feature extraction module can be understood as a part of the state recognition model, which is responsible for extracting features from the input data. The first prediction unit, the second prediction unit and the third prediction unit can be understood as subcomponents of the multi-task prediction module, which are used to predict the remaining life, health status and charge status respectively. An optional implementation method, such as Figure 3 As shown, the first prediction unit, the second prediction unit and the third prediction unit have the same structure, including at least a time convolutional network (structure as shown in FIG. Figure 5 described) and the Gated Recurrent Unit (GRU) (structure as Figure 4 shown) network, etc. Normalized feature sets for health status and remaining useful life, is the state of charge normalized feature set, H k , H k+1 , · · ·，H k+w-1 The features extracted from the normalized feature set by the shared layer, SOC t-1 To predict the target's previous SOC, SOC t To predict the target time SOC, SOC t+1 , is the predicted target SOC at the next moment.

[0065] For a temporal convolutional network, suppose we have the input sequence , and hope to predict the corresponding output at each time point . It generates the following mapping:

[0066]

[0067] In order to increase the receptive field without increasing the number of parameters, TCN uses dilated convolution. Dilated convolution, also known as hole convolution, is a form of convolution that inserts gaps between convolution kernels (i.e., skips some input units). This technique allows the model to capture a larger receptive field without increasing the number of parameters, thereby better understanding the contextual information in the input data. The dilation factor determines the spacing between elements in the convolution kernel. For example, if the dilation factor is 2, the elements in the convolution kernel will be separated by one input unit. Mathematical representation of dilated convolution:

[0068] in, f is the convolution kernel, k is the convolution kernel size, x is the input sequence, d is the expansion rate.

[0069] For the gated recurrent unit, assuming x t Input information for the current moment, h t-1 is the hidden state at the previous moment. The hidden state acts as the memory of the neural network, which contains information about the data that the node has seen before. t is the hidden state passed to the next moment. Then:

[0070] in: is a candidate hidden state, To reset the gate, To update the gate, The sigmoid function converts data into a value between 0 and 1. The tanh activation function converts data into a value between -1 and 1.

[0071] By adopting this technical solution, each component can handle specific prediction tasks through structured model design, thereby improving the performance and prediction accuracy of the overall model.

[0072] Based on the above scheme, optionally, the target loss in the state recognition model training process includes a first target loss and a second target loss, the first target loss is used to adjust the model parameters of the first prediction unit and the second prediction unit, and the second target loss is used to adjust the model parameters of the third prediction unit.

[0073] Among them, the target loss can be understood as a metric used to quantify the error size of the model prediction, and is the target to be optimized during the training process. The training process of the state recognition model aims to minimize the target loss. The target loss includes at least a first target loss and a second target loss. The first target loss can be understood as a loss function set for the first prediction unit (such as state of charge SOC prediction) and the second prediction unit (such as state of health SOH prediction), which is used to evaluate the accuracy of the prediction results of the two units. The second target loss can be understood as a loss function set for the third prediction unit, which is used to evaluate the accuracy of the prediction results of the third prediction unit. The model parameters can be understood as adjustable variables in the multi-task prediction module, which determine how the multi-task prediction module converts inputs into outputs. During the training process, the target loss is reduced by adjusting the model parameters, so that the state recognition model can better fit the training data and improve the prediction accuracy.

[0074] This technical solution allows the state recognition model to be optimized for different prediction tasks separately through a hierarchical target loss design, thereby improving the pertinence and accuracy of the overall prediction performance of the state recognition model. It can not only improve the prediction effect of a single prediction parameter, but also enhance the state recognition model's understanding and adaptability to complex battery state changes.

[0075] Based on the above scheme, optionally, the first target loss is determined based on the following manner: respectively determining a first loss related to the remaining life and a second loss related to the health status; determining a fourth weight and a fifth weight based on the first loss and the second loss, wherein the fourth weight and the fifth weight are positively correlated with the values ​​of the first loss and the second loss; determining the first target loss based on the first loss, the second loss, the fourth weight and the fifth weight.

[0076] Among them, the first loss can be understood as a metric for measuring the accuracy of the state recognition model for the remaining life (RUL) prediction results. The second loss can be understood as a metric for measuring the accuracy of the state recognition model for the state of health (SOH) prediction results. The fourth weight can be understood as a weight coefficient associated with the first loss, which is used to balance the impact of the first loss in the first target loss. If the value of the fourth weight is positively correlated with the first loss, then when the first loss is large, it is determined to assign a higher weight to emphasize the need for improvement of the first loss. The fifth weight can be understood as a weight coefficient associated with the second loss, which is used to balance the impact of the second loss in the first target loss. If the value of the fifth weight is positively correlated with the second loss, then when the second loss is large, it is determined to assign a higher weight to emphasize the need for improvement of the first loss.

[0077] The values ​​of the first loss and the second loss are determined based on the ratio with the result of the previous iteration. The loss of each prediction parameter is compared with the result of the previous iteration to calculate the ratio. When the ratio is high, it indicates that the prediction parameter is more challenging to optimize. In this way, the optimization difficulty of the task of each prediction parameter can be quantitatively evaluated. In the backpropagation stage, based on the evaluation results, the loss corresponding to the prediction task with greater optimization difficulty is multiplied by a larger weight factor, thereby enhancing its role in parameter updating. Correspondingly, the loss corresponding to the prediction task with less optimization difficulty is multiplied by a smaller weight factor to reduce the impact on parameter updating.

[0078] Based on the above solution, optionally, determining the first target loss according to the first loss, the second loss, the fourth weight, and the fifth weight may be determined based on the following formula:

[0079] ;

[0080] in, represents the first target loss, represents the fourth weight, represents the first loss, represents the fifth weight, Indicates the second loss.

[0081] By adopting this technical solution, the loss weights of different prediction parameters are dynamically adjusted, so that the state recognition model can respond to different prediction tasks more flexibly and automatically adjust the degree of attention to each prediction task, thereby improving the overall prediction performance of the state recognition model.

[0082] Based on the above scheme, optionally, the second target loss is determined based on the following method: determining multiple third losses corresponding to the state of charge at multiple moments adjacent to the predicted moment and earlier than the predicted moment; respectively determining the sixth weights of the multiple third losses, and determining the second target loss based on the multiple third losses and their corresponding sixth weights, wherein the sixth weight is positively correlated with the value of the third loss.

[0083] The third loss can be understood as a metric for measuring the accuracy of the state recognition model's state-of-charge (SOC) prediction results, primarily relative to multiple time points adjacent to and prior to the prediction moment. This is calculated by comparing the difference between the SOC value predicted by the state recognition model and the actual value, helping to optimize the portion of the model related to SOC prediction. Each time point has a corresponding third loss. The sixth weight can be understood as a weight coefficient associated with each third loss, used to balance the impact of the third loss at each time point on the second target loss. The sixth weight is positively correlated with the corresponding third loss, meaning that a larger third loss at a certain time point is assigned a greater weight.

[0084] Based on the above solution, optionally, the second target loss is determined according to the plurality of third losses and their corresponding sixth weights, and can be determined based on the following formula:

[0085] ;

[0086] in, represents the second target loss, Represents the weight coefficient of the two moments before the prediction moment, Represents the loss two moments before the prediction moment, It represents the load weight coefficient at the moment before the prediction moment, represents the loss at the moment before the prediction moment, Represents the weight coefficient at the prediction moment, represents the loss at the prediction moment.

[0087] By adopting this technical solution, by assigning different weights to losses at different times, the state recognition model not only focuses on the accuracy of the current prediction moment, but also on the losses along the entire time path, thereby improving the model's adaptability to dynamic changes, especially for parameters such as the state of charge that fluctuate greatly over time, which helps to improve the overall prediction accuracy and reliability of the state recognition model.

[0088] S120: Input the battery operation data into a state recognition model to obtain prediction parameters related to the lithium battery operation state, wherein the prediction parameters at least include remaining life, health state, and charge state.

[0089] Among them, the remaining useful life (RUL) can be understood as the time or number of cycles from the current working state of the lithium battery to the time when it can no longer meet the specified performance standards. It can provide users or management systems with information about when the lithium battery needs to be replaced, which is helpful for maintenance and replacement of batteries. The state of health (SOH) can be understood as an indicator that describes the overall condition of the lithium battery and reflects the degree of aging of the lithium battery. The state of charge (SOC) can be understood as the ratio of the current storage capacity of the battery to the maximum capacity. The state of charge (SOC) can be used to manage the charging and discharging process of the lithium battery and avoid overcharging and over-discharging, which directly affects the safety of the lithium battery.

[0090] On the basis of the above scheme, optionally, when the prediction parameter is the remaining life, the battery operation data includes voltage data; the inputting of the battery operation data into the state recognition model to obtain the prediction parameter related to the lithium battery operation state includes: inputting the voltage data into the first feature extraction module for feature extraction to obtain first operation feature data; inputting the voltage data into the gating module to determine the first weight of the first operation feature data; and inputting the result of the weighted sum of the first operation feature data and the first weight into the first prediction unit to obtain the remaining life related to the lithium battery operation state.

[0091] The first operating characteristic data can be understood as characteristic information obtained by processing the voltage data by the first feature extraction module. The first operating characteristic data can be used to reflect the state of the battery, such as changes in its internal chemical reactions. The first weight can be understood as the weight of the first operating characteristic data determined by the gating module.

[0092] By adopting this technical solution, the first operating characteristic data is extracted from the voltage data, the weight of the first operating characteristic data is determined through the gating module, and finally the weighted characteristics are input into the first prediction unit to predict the remaining life of the lithium battery. This not only improves the accuracy of the prediction, but also better adapts to the battery characteristics under different working conditions.

[0093] On the basis of the above scheme, optionally, when the prediction parameter is a health state, the battery operation data includes voltage data; the inputting of the battery operation data into the state recognition model to obtain a prediction parameter related to the lithium battery operation state includes: inputting the voltage data into the first feature extraction module for feature extraction to obtain second operation feature data; inputting the voltage data into the gating module to determine a second weight of the second operation feature data; and inputting the result of the weighted sum of the second operation feature data and the second weight into the second prediction unit to obtain a health state related to the lithium battery operation state.

[0094] The second operating characteristic data can be understood as characteristic information obtained by processing the voltage data by the first characteristic extraction module, which is used for health status assessment. The second weight can be understood as the weight of the second operating characteristic data determined by the gating module.

[0095] By adopting this technical solution, the second operating characteristic data is extracted from the voltage data, the weight of the second operating characteristic data is determined through the gating module, and finally the weighted characteristics are input into the second prediction unit to predict the health status of the lithium battery. This not only improves the accuracy of the prediction, but also better adapts to the battery characteristics under different working conditions, helps to timely discover battery aging problems and take corresponding maintenance measures.

[0096] On the basis of the above scheme, optionally, when the prediction parameter is the state of charge, the battery operation data includes voltage data, current data and temperature data; the battery operation data is input into the state recognition model to obtain the prediction parameters related to the lithium battery operation state, including: inputting the voltage data, the current data, the temperature data and the health state into the second feature extraction module for feature extraction to obtain third operation feature data; inputting the voltage data, the current data, the temperature data and the health state into the gating module to determine the third weight of the third operation feature data; inputting the result of the weighted sum of the third operation feature data and the third weight into the third prediction unit to obtain the state of charge related to the lithium battery operation state.

[0097] The third operating characteristic data can be understood as features derived by the second feature extraction module after processing multi-source input data (such as voltage data, current data, temperature data, and health status). These features are used for state of charge assessment and reflect the battery's current charge level and its changing trend over time, facilitating more accurate state of charge prediction. The third weight can be understood as the weight of the third operating characteristic data determined by the gating module.

[0098] In an optional embodiment, for voltage and current data, a feature extraction module can be used to obtain voltage / current characteristic values, including maximum value, average value, skewness, and kurtosis. Therefore, for charging voltage, the characteristic values ​​can be selected from the maximum charging voltage, the average charging voltage, the charging voltage skewness, and / or the charging voltage kurtosis; for discharging voltage, the characteristic values ​​can be selected from the maximum discharge voltage, the average discharge voltage, the discharge voltage skewness, and / or the discharge voltage kurtosis; for charging current, the characteristic values ​​can be selected from the maximum charging current, the average charging current, the charging current skewness, and / or the charging current kurtosis; and for discharging current, the characteristic values ​​can be selected from the maximum discharge current, the average discharge current, the discharge current skewness, and / or the discharge current kurtosis.

[0099] By adopting this technical solution, through comprehensive analysis of various data such as voltage, current, temperature and health status, the third operating characteristic data related to the state of charge is extracted, and the weight of the third operating characteristic data is determined through the gating module. Finally, the weighted characteristics are input into the third prediction unit to predict the state of charge of the lithium battery. This not only improves the accuracy of the prediction, but also better adapts to the battery characteristics under different working conditions, which helps to achieve more efficient and safe battery management.

[0100] On the basis of the above scheme, optionally, the training method of the state recognition model includes: obtaining historical operation detection data of the lithium battery; preprocessing the historical operation detection data of the lithium battery, the preprocessing at least including data cleaning, missing value filling and abnormal data processing; forming a feature set with the historical operation detection data of the lithium battery, and at the same time making battery state labels, the feature set and the corresponding labels constitute a training data set; dividing the training data set into a training set and a test set according to a preset ratio; normalizing the data in the training set and the test set respectively; using the training set to train the state prediction model, and obtaining the target loss of the state prediction model, and optimizing the parameters of the state prediction model according to the target loss; using the test set data to verify and test the trained state prediction model.

[0101] The technical solution of the embodiment of the present invention obtains the battery operation data and state recognition model of the target lithium battery at multiple moments. Since the state recognition model is obtained based on deep learning model training, the state recognition model includes at least a gating module and a multi-task prediction module. The gating module is used to determine the weight of the input feature, and the multi-task prediction module is used to predict more than two battery state parameters, which can provide sufficient data support and tools for the state prediction of the lithium battery; the battery operation data is input into the state recognition model to obtain prediction parameters related to the lithium battery operation state, wherein the prediction parameters include at least remaining life, health state and charge state, which can realize accurate prediction of multiple state parameters of the lithium battery, solves the problem in the related technology that the prediction model can only predict a single battery state parameter, improves the efficiency and accuracy of battery management, and helps optimize battery use and maintenance, thereby extending the battery life.

[0102] Example 2: Using the method of Example 1, a material is predicted to be LiNi 0.83 Co 0.11 Mn 0.06 The specifications of the tested NCM batteries are shown in Table 1. The charging process includes a combination of constant current and constant voltage (CC and CV) modes at a charging rate of 0.5C, followed by a 30-min relaxation period and a 1C discharge at an ambient temperature of 25°C.

[0103] Table 1 Detailed specifications of test samples

[0104]

[0105] Table 2 shows the statistical errors of battery SOH predictions using different models. The lithium battery state prediction method achieves a mean absolute error (MAE) of 0.00243 and a root mean square error (RMSE) of 0.00312, both lower than the results of other models. Therefore, the lithium battery state prediction method proposed in this paper demonstrates robustness and excellent prediction accuracy for batteries operating at different temperatures, demonstrating its suitability for battery SOH prediction. Figures 6(a)-6(j) provide a more intuitive display of the SOH prediction results.

[0106] Table 2 Statistical error of battery SOH prediction under different models

[0107]

[0108] The RUL of the battery is predicted, and the prediction curve is shown in Figure 7.

[0109] Table 3 Comparison of RUL estimation results of different models

[0110]

[0111] As can be seen from Table 3, the estimated values ​​of the four single-task learning models are quite close, with MAE errors greater than 3. However, the MAE and RMSE errors of the proposed method are significantly smaller than those of the other models, indicating that the proposed lithium battery state prediction method has high accuracy and strong adaptability. Figures 7(a)-7(j) more intuitively show the RUL prediction results.

[0112] Table 4 Comparison of SOC estimation results of different models

[0113]

[0114] Table 4 shows the statistical errors of battery SOC prediction by different models. The mean absolute error (MAE) of the lithium battery state prediction method is 0.00241, and the root mean square error (RMSE) is 0.00338, both of which are lower than the results of other models. Figure 8 The SOC prediction results are more intuitively displayed. Figure 8 (a) shows that the model of the present invention, which includes SOH as one of the input features, exhibits excellent prediction ability throughout the battery's service life. The orange line (predicted by the model of the present invention, with SOH as a feature) almost coincides with the blue line (actual SOC). However, the model of the present invention, which does not include SOH, performs slightly worse throughout the battery's service life, as shown by the green line. More importantly, Figure 8 (b) in Figure 3 clearly shows that the time required to reach a specific state of charge is shorter at an SOH of 0.85 than at an SOH of 0.90, which can be seen from the capacity at an SOH of 0.90 (red line) being consistently higher than that at an SOH of 0.85 (purple line). Figure 8 (c) in Figure 3 demonstrates that using SOH as an input feature can significantly improve the accuracy of SOC estimation.

[0115] Example 3: Figure 2 This is a schematic diagram of the structure of a lithium battery status prediction device provided by the third embodiment of the present invention. Figure 2 As shown, the device includes: an acquisition module 210 and a prediction parameter determination module 220. The acquisition module 210 is used to obtain battery operation data and a state recognition model of the target lithium battery at multiple times. The state recognition model is obtained based on deep learning model training. The state recognition model includes at least a gating module and a multi-task prediction module. The gating module is used to determine the weight of input features, and the multi-task prediction module is used to predict two or more battery state parameters. The prediction parameter determination module 220 is used to input the battery operation data into the state recognition model to obtain prediction parameters related to the lithium battery operation state, wherein the prediction parameters include at least remaining life, health state, and state of charge.

[0116] The technical solution of the embodiment of the present invention obtains the battery operation data and state recognition model of the target lithium battery at multiple moments through the acquisition module 210. Since the state recognition model is obtained based on deep learning model training, the state recognition model includes at least a gating module and a multi-task prediction module. The gating module is used to determine the weight of the input feature, and the multi-task prediction module is used to predict more than two battery state parameters, which can provide sufficient data support and tools for the state prediction of the lithium battery; the battery operation data is input into the state recognition model through the prediction parameter determination module 220 to obtain prediction parameters related to the lithium battery operation state, wherein the prediction parameters include at least remaining life, health status and charge state, which can realize accurate prediction of multiple state parameters of the lithium battery, solves the problem in the related technology that the prediction model can only predict a single battery state parameter, improves the efficiency and accuracy of battery management, and helps optimize battery use and maintenance, thereby extending the battery life.

[0117] Based on the above scheme, optionally, the state recognition model also includes a first feature extraction module and a second feature extraction module; the multi-task prediction module includes a first prediction unit, a second prediction unit and a third prediction unit; the first feature extraction module, the second feature extraction module, the first prediction unit, the second prediction unit and the third prediction unit are all connected to the gating module; and the second feature extraction module is connected to the second prediction unit.

[0118] Based on the above solution, optionally, the prediction parameter includes a remaining lifespan; the battery operating data includes voltage data; and the prediction parameter determination module includes a remaining lifespan prediction unit. The remaining lifespan prediction unit is configured to input the voltage data into the first feature extraction module for feature extraction to obtain first operating characteristic data; input the voltage data into the gating module to determine a first weight for the first operating characteristic data; and input a weighted sum of the first operating characteristic data and the first weight into the first prediction unit to obtain a remaining lifespan related to the operating state of the lithium battery.

[0119] Based on the above solution, optionally, the prediction parameter includes a health state; the battery operating data includes voltage data; and the prediction parameter determination module includes a health state prediction unit. The health state prediction unit is configured to input the voltage data into the first feature extraction module for feature extraction to obtain second operating characteristic data; input the voltage data into the gating module to determine a second weight for the second operating characteristic data; and input a weighted sum of the second operating characteristic data and the second weight into the second prediction unit to obtain a health state related to the lithium battery operating state.

[0120] Based on the above solution, optionally, the prediction parameter includes state of charge; the battery operation data includes voltage data, current data, and temperature data; and the prediction parameter determination module includes: a state of charge prediction unit. The state of charge prediction unit is configured to input the voltage data, current data, temperature data, and health status into the second feature extraction module for feature extraction to obtain third operation feature data; input the voltage data, current data, temperature data, and health status into the gating module to determine a third weight for the third operation feature data; and input a weighted sum of the third operation feature data and the third weight into the third prediction unit to obtain a state of charge related to the operation status of the lithium battery.

[0121] Based on the above scheme, optionally, the target loss in the state recognition model training process includes a first target loss and a second target loss, the first target loss is used to adjust the model parameters of the first prediction unit and the second prediction unit, and the second target loss is used to adjust the model parameters of the third prediction unit.

[0122] Based on the above scheme, optionally, the first target loss is determined based on the following manner: respectively determining a first loss related to the remaining life and a second loss related to the health status; determining a fourth weight and a fifth weight based on the first loss and the second loss, wherein the fourth weight and the fifth weight are positively correlated with the values ​​of the first loss and the second loss; determining the first target loss based on the first loss, the second loss, the fourth weight and the fifth weight.

[0123] Based on the above scheme, optionally, the second target loss is determined based on the following method: determining multiple third losses corresponding to the state of charge at multiple moments adjacent to the predicted moment and earlier than the predicted moment; respectively determining the sixth weights of the multiple third losses, and determining the second target loss based on the multiple third losses and their corresponding sixth weights, wherein the sixth weight is positively correlated with the value of the third loss.

[0124] Based on the above solution, the lithium battery state prediction device may optionally further include a battery operation data determination module. The battery operation data determination module is configured to, before obtaining the battery operation data of the target lithium battery at multiple moments, obtain collected data of the target lithium battery at multiple moments, post-process the collected data to obtain post-processed analysis data, and determine the battery operation data based on the collected data and the post-processed analysis data.

[0125] The lithium battery state prediction device provided in the embodiment of the present invention can execute the lithium battery state prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0126] Example 4: Figure 9 A schematic diagram of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0127] like Figure 9 As shown, electronic device 10 includes at least one processor 11 and memory, such as read-only memory (ROM) 12 and random access memory (RAM) 13, communicatively connected to at least one processor 11. The memory stores computer programs executable by the at least one processor. Processor 11 can perform various appropriate actions and processes based on the computer programs stored in ROM 12 or loaded from storage unit 18 into RAM 13. RAM 13 can also store various programs and data required for the operation of electronic device 10. Processor 11, ROM 12, and RAM 13 are interconnected via bus 14. An input / output (I / O) interface 15 is also connected to bus 14.

[0128] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0129] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a lithium battery state prediction method.

[0130] In some embodiments, a lithium battery state prediction method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the lithium battery state prediction method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform a lithium battery state prediction method in any other appropriate manner (for example, by means of firmware).

[0131] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0132] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0133] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or apparatus. A computer-readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0134] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device that has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0135] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0136] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0137] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0138] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A lithium battery status prediction method, characterized in that: include: Obtaining battery operating data and a state recognition model of a target lithium battery at multiple times, wherein the state recognition model is trained based on a deep learning model and includes at least a gating module and a multi-task prediction module, wherein the gating module is used to determine the weight of input features, and the multi-task prediction module is used to predict two or more battery state parameters; Inputting the battery operating data into a state recognition model to obtain prediction parameters related to the lithium battery operating state, wherein the prediction parameters include at least remaining life, health state, and state of charge; The state recognition model further includes a first feature extraction module and a second feature extraction module; the multi-task prediction module includes a first prediction unit, a second prediction unit, and a third prediction unit; the first feature extraction module, the second feature extraction module, the first prediction unit, the second prediction unit, and the third prediction unit are all connected to the gating module; and the second feature extraction module is connected to the third prediction unit; The prediction parameters include the remaining life; the battery operation data includes voltage data; the battery operation data is input into the state recognition model to obtain prediction parameters related to the lithium battery operation state, including: Inputting the voltage data into the first feature extraction module for feature extraction to obtain first operation feature data; Inputting the voltage data into the gating module to determine a first weight of the first operating characteristic data; Inputting a weighted sum of the first operating characteristic data and the first weight into the first prediction unit to obtain a remaining life related to the operating state of the lithium battery; The prediction parameters include health status; the battery operation data includes voltage data; the battery operation data is input into the state recognition model to obtain prediction parameters related to the lithium battery operation status, including: Inputting the voltage data into the first feature extraction module for feature extraction to obtain second operation feature data; inputting the voltage data into the gating module to determine a second weight of the second operating characteristic data; Inputting a weighted sum of the second operating characteristic data and the second weight into the second prediction unit to obtain a health state related to the operating state of the lithium battery; The prediction parameters include the state of charge; the battery operation data includes voltage data, current data and temperature data; the battery operation data is input into the state recognition model to obtain prediction parameters related to the lithium battery operation state, including: Inputting the voltage data, the current data, the temperature data, and the health status into the second feature extraction module for feature extraction to obtain third operation feature data; inputting the voltage data, the current data, the temperature data, and the health status into the gating module to determine a third weight of the third operating characteristic data; Inputting a weighted sum of the third operating characteristic data and the third weight into the third prediction unit to obtain a state of charge related to the operating state of the lithium battery; The target loss in the state recognition model training process includes a first target loss and a second target loss, the first target loss is used to adjust the model parameters of the first prediction unit and the second prediction unit, and the second target loss is used to adjust the model parameters of the third prediction unit; The first target loss is determined based on the following method: respectively determining a first loss associated with the remaining life span and a second loss associated with the health status; determining a fourth weight and a fifth weight according to the first loss and the second loss, wherein the fourth weight and the fifth weight are positively correlated with the values ​​of the first loss and the second loss; determining a first target loss according to the first loss, the second loss, the fourth weight, and the fifth weight; The second target loss is determined based on the following method: determining a plurality of third losses corresponding to the state of charge at a plurality of times adjacent to the predicted time and earlier than the predicted time; The sixth weights of the plurality of third losses are determined respectively, and the second target loss is determined according to the plurality of third losses and their corresponding sixth weights, wherein the sixth weight is positively correlated with the value of the third loss.

2. The method according to claim 1, characterized in that Before acquiring the battery operation data of the target lithium battery at multiple moments, the method further includes: Acquire collected data of a target lithium battery at multiple times, and post-process the collected data to obtain post-processed analysis data; The battery operation data is determined according to the collected data and the post-processing analysis data.

3. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the lithium battery state prediction method according to any one of claims 1 to 2 when executed.

Images