Sodium-ion battery state-of-charge prediction method, apparatus and device, and storage medium
By collecting and processing multi-source heterogeneous data of sodium ion batteries, using singular value decomposition method to extract key features and train prediction models, the problem of insufficient accuracy and response speed of traditional prediction methods is solved, and more efficient state of charge prediction is achieved.
Patent Information
- Application Number
- CN202411830883.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-12
- Publication Date
- 2025-03-04
AI Technical Summary
The traditional sodium ion battery state of charge prediction methods have problems such as insufficient prediction accuracy and slow response.
By collecting multi-source heterogeneous data of the battery, including battery voltage, battery current, battery temperature and historical state of charge, the target-related data is determined using the preset singular value decomposition method, the initial prediction model is trained, the target prediction model is obtained, and the real-time data is input to the model to predict the state of charge.
It improves the accuracy and response speed of state-of-charge prediction of sodium ion batteries, reduces the computational amount of model training, and enhances the accuracy and generalization capabilities of the model.
Smart Images
Figure CN119556176A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of sodium ion batteries, and in particular to a method, device, equipment and storage medium for predicting the state of charge of a sodium ion battery. Background Art
[0002] In battery management systems, accurately predicting the battery's state of charge (SOC) still faces major challenges. Traditional SOC prediction methods generally have problems such as insufficient prediction accuracy and slow response speed, which limits the performance optimization of battery management systems and the efficient operation of electronic devices.
[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention
[0004] The main purpose of the present application is to provide a sodium ion battery state of charge prediction method, device, equipment and storage medium, aiming to solve the technical problems of insufficient prediction accuracy and slow response speed commonly found in traditional SOC prediction methods.
[0005] To achieve the above objectives, the present application proposes a method for predicting the state of charge of a sodium ion battery, the method comprising:
[0006] Collecting multi-source heterogeneous battery data, wherein the multi-source heterogeneous battery data includes battery voltage, battery current, battery temperature, and historical state of charge;
[0007] Determine the target related data in the multi-source heterogeneous data of the battery according to a preset singular value decomposition method;
[0008] Based on the target related data, an initial prediction model is trained to obtain a target prediction model;
[0009] The real-time battery data is input into the target prediction model to obtain a sodium ion battery state of charge prediction result, wherein the real-time battery data includes battery voltage, battery current and battery temperature.
[0010] In one embodiment, the step of collecting multi-source heterogeneous data of batteries includes:
[0011] Collect multi-source heterogeneous data of raw batteries;
[0012] Performing data cleaning on the original battery multi-source heterogeneous data to obtain cleaned data;
[0013] Normalizing the cleaned data to obtain normalized data;
[0014] Based on the interpolation method or the median method, the outliers in the normalized data are replaced to obtain multi-source heterogeneous data of batteries.
[0015] In one embodiment, the step of determining the target related data in the battery multi-source heterogeneous data according to a preset singular value decomposition method includes:
[0016] Dividing the battery multi-source heterogeneous data into target matrices according to input quantities;
[0017] Decomposing the target matrix into a left singular value vector matrix, a singular value matrix and a right singular value vector matrix by a singular value decomposition method, wherein the singular values in the singular value matrix are used to reflect the importance of the target matrix in different directions;
[0018] Performing dimension reduction on the target matrix according to a preset singular value threshold to obtain a target left singular value vector matrix, a target singular value matrix, and a target right singular value vector matrix;
[0019] Target related data is determined according to the target left singular value vector matrix, the target singular value matrix and the target right singular value vector matrix.
[0020] In one embodiment, the step of training the initial prediction model based on the target-related data to obtain the target prediction model includes:
[0021] Based on the target left singular value vector matrix, the target singular value matrix, and the target right singular value vector matrix, determine a plurality of triplets, and determine a target importance score for each triplet, wherein each triplet includes a column vector of the target left singular value vector matrix, a singular value of the target singular value matrix, and a row vector of the target right singular value vector matrix;
[0022] Determining a weight value of each vector in the target-related data according to the target importance score;
[0023] Based on the weight values and the target related data, the initial prediction model is trained to obtain a target prediction model.
[0024] In one embodiment, the step of determining the target importance score of each triplet includes:
[0025] Determine the first importance score mean of all elements in the column vector of the target left singular value vector matrix;
[0026] Determine the importance scores of the singular values of the target singular value matrix;
[0027] Determine the second importance score mean of all elements in the column vector of the target right singular value vector matrix;
[0028] A target importance score for each triple is determined based on the first importance score mean, the importance score, and the second importance score mean.
[0029] In one embodiment, the step of training the initial prediction model based on the target-related data to obtain the target prediction model includes:
[0030] Inputting the target related data into the initial prediction model to obtain a target output value;
[0031] Determining a loss value based on the target output value and the historical state of charge;
[0032] The parameters in the initial prediction model are updated according to the loss value to obtain a target prediction model.
[0033] In one embodiment, the method further comprises:
[0034] When the time interval between the current time and the previous update time is greater than or equal to the model update period, new battery multi-source heterogeneous data is acquired, and the target prediction model is updated based on the new battery multi-source heterogeneous data; and / or,
[0035] Collect user feedback information on the target prediction model, and optimize the target prediction model according to the feedback information.
[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a sodium ion battery state of charge prediction device, the sodium ion battery state of charge prediction device comprising:
[0037] A collection module, used for collecting multi-source heterogeneous data of batteries, wherein the multi-source heterogeneous data of batteries include battery voltage, battery current, battery temperature and historical state of charge;
[0038] A determination module, used for determining target related data in the battery multi-source heterogeneous data according to a preset singular value decomposition method;
[0039] A training module, used to train an initial prediction model based on the target-related data to obtain a target prediction model;
[0040] The input module is used to input real-time battery data into the target prediction model to obtain a prediction result of the state of charge of the sodium ion battery, wherein the real-time battery data includes battery voltage, battery current and battery temperature.
[0041] In addition, to achieve the above-mentioned purpose, the present application also proposes a sodium ion battery state of charge prediction device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the sodium ion battery state of charge prediction method as described above.
[0042] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the sodium ion battery state of charge prediction method as described above are implemented.
[0043] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the sodium ion battery state of charge prediction method as described above are implemented.
[0044] One or more technical solutions proposed in this application have at least the following technical effects:
[0045] The sodium ion battery state of charge prediction method, device, equipment and storage medium proposed in the present application collect battery multi-source heterogeneous data, wherein the battery multi-source heterogeneous data includes battery voltage, battery current, battery temperature and historical state of charge; determine the target related data in the battery multi-source heterogeneous data according to a preset singular value decomposition method; train an initial prediction model based on the target related data to obtain a target prediction model; input real-time battery data into the target prediction model to obtain a sodium ion battery state of charge prediction result, wherein the real-time battery data includes battery voltage, battery current and battery temperature, solves the technical problems of insufficient prediction accuracy and slow response speed commonly existing in traditional SOC prediction methods. Compared with the prior art, the present application extracts the most valuable features in multi-source heterogeneous data through a preset singular value decomposition method, thereby realizing dimensionality reduction of battery multi-source heterogeneous data, which can not only reduce the amount of calculation in the target prediction model training process, but also effectively improve the accuracy and generalization ability of the target prediction model. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0048] Figure 1 A schematic diagram of a flow chart provided for the first embodiment of the method for predicting the state of charge of a sodium ion battery of the present application;
[0049] Figure 2 A schematic diagram of a flow chart provided for the second embodiment of the method for predicting the state of charge of a sodium ion battery of the present application;
[0050] Figure 3 A decomposition schematic diagram provided for Example 2 of the method for predicting the state of charge of a sodium ion battery of the present application;
[0051] Figure 4 This is a schematic diagram of the module structure of the sodium ion battery charge state prediction device according to an embodiment of the present application;
[0052] Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the sodium ion battery charge state prediction method in the embodiment of the present application.
[0053] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0054] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0055] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0056] The main solution of the embodiment of the present application is: collecting multi-source heterogeneous data of batteries, wherein the multi-source heterogeneous data of batteries include battery voltage, battery current, battery temperature and historical state of charge; determining target-related data in the multi-source heterogeneous data of batteries according to a preset singular value decomposition method; training an initial prediction model based on the target-related data to obtain a target prediction model; inputting real-time battery data into the target prediction model to obtain a prediction result of the state of charge of a sodium ion battery, wherein the real-time battery data include battery voltage, battery current and battery temperature.
[0057] It can be seen from the above embodiments that the present application collects multi-source heterogeneous data of batteries, wherein the multi-source heterogeneous data of batteries include battery voltage, battery current, battery temperature and historical state of charge; determines the target-related data in the multi-source heterogeneous data of batteries according to a preset singular value decomposition method; trains an initial prediction model based on the target-related data to obtain a target prediction model; inputs real-time battery data into the target prediction model to obtain a prediction result of the state of charge of a sodium-ion battery, wherein the real-time battery data include battery voltage, battery current and battery temperature, solves the technical problems of insufficient prediction accuracy and slow response speed commonly existing in traditional SOC prediction methods. Compared with the prior art, the present application extracts the most valuable features in multi-source heterogeneous data through a preset singular value decomposition method, thereby realizing dimensionality reduction of multi-source heterogeneous data of batteries, which can not only reduce the amount of calculation in the training process of the target prediction model, but also effectively improve the accuracy and generalization ability of the target prediction model.
[0058] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a sodium ion battery state of charge prediction device, etc. The following takes the sodium ion battery state of charge prediction device as an example to illustrate this embodiment and the following embodiments.
[0059] Based on this, the present application embodiment provides a method for predicting the state of charge of a sodium ion battery, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for predicting the state of charge of a sodium ion battery of the present application.
[0060] In this embodiment, the sodium ion battery state of charge prediction method includes steps S10 to S40:
[0061] Step S10, collecting multi-source heterogeneous battery data, wherein the multi-source heterogeneous battery data includes battery voltage, battery current, battery temperature, and historical state of charge;
[0062] In a feasible implementation, the step of collecting multi-source heterogeneous battery data includes: collecting original multi-source heterogeneous battery data; performing data cleaning on the original multi-source heterogeneous battery data to obtain cleaned data; performing data normalization on the cleaned data to obtain normalized data; and replacing outliers in the normalized data based on interpolation or median method to obtain multi-source heterogeneous battery data.
[0063] It should be noted that data cleaning: identify and delete or correct errors, duplicates or missing values in the data, and remove data columns that are irrelevant or have little impact on SOC estimation; data normalization: convert data of different dimensions to the same dimension for subsequent processing. Normalization helps to speed up model training and improve model performance; outlier processing: use interpolation or replace outliers with median values to reduce noise and uncertainty in the data. Interpolation can estimate outliers based on the values of adjacent data points, while median replacement is a robust outlier processing method.
[0064] Step S20, determining target related data in the battery multi-source heterogeneous data according to a preset singular value decomposition method;
[0065] It should be noted that the preset singular value decomposition method can be used to retain the data that has the greatest impact on SOC, select the most representative features, discard those irrelevant phases, and finally leave the target-related data.
[0066] Step S30, training an initial prediction model based on the target related data to obtain a target prediction model;
[0067] In a feasible implementation manner, the step of training an initial prediction model based on the target-related data to obtain a target prediction model includes: inputting the target-related data into the initial prediction model to obtain a target output value; determining a loss value based on the target output value and the historical state of charge; and updating parameters in the initial prediction model according to the loss value to obtain a target prediction model.
[0068] It should be noted that the target output value is the predicted value, and the historical state of charge is the label value. The loss value can be determined based on the predicted value and the label value, and finally the model parameters in the initial prediction model are adjusted based on the loss value, thereby realizing the training of the initial prediction model.
[0069] In the specific implementation, you can choose a suitable loss function such as mse or rmse, set the learning rate, so as to quickly reduce the gradient and make the target prediction model converge quickly.
[0070] Step S40, inputting the real-time battery data into the target prediction model to obtain a sodium ion battery state of charge prediction result, wherein the real-time battery data includes battery voltage, battery current and battery temperature.
[0071] It should be noted that the target prediction model refers to the trained initial prediction model, which can be directly used to predict the state of charge of sodium-ion batteries.
[0072] In a feasible implementation, the method further includes: when the time interval between the current time and the previous update time is greater than or equal to the model update cycle, acquiring new battery multi-source heterogeneous data, and updating the target prediction model based on the new battery multi-source heterogeneous data; and / or, collecting user feedback information on the target prediction model, and optimizing the target prediction model based on the feedback information.
[0073] It should be noted that new battery multi-source heterogeneous data is extracted at regular intervals (such as weekly or monthly) to update the target prediction model, and the target prediction model is incrementally trained using online learning methods so that it can quickly adapt to the new data distribution. The prediction error of the target prediction model on the new data after real-time update continues to remain at a low level; the model can also be further optimized by collecting user feedback to discover.
[0074] This embodiment collects multi-source heterogeneous data of batteries, wherein the multi-source heterogeneous data of batteries include battery voltage, battery current, battery temperature and historical state of charge; determines target-related data in the multi-source heterogeneous data of batteries according to a preset singular value decomposition method; trains an initial prediction model based on the target-related data to obtain a target prediction model; inputs real-time battery data into the target prediction model to obtain a prediction result of the state of charge of a sodium-ion battery, wherein the real-time battery data include battery voltage, battery current and battery temperature, solves the technical problems of insufficient prediction accuracy and slow response speed commonly existing in traditional SOC prediction methods. Compared with the prior art, this application extracts the most valuable features in multi-source heterogeneous data through a preset singular value decomposition method, thereby achieving dimensionality reduction of multi-source heterogeneous data of batteries, which can not only reduce the amount of calculation in the training process of the target prediction model, but also effectively improve the accuracy and generalization ability of the target prediction model.
[0075] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , step S20 includes steps S201 to S204:
[0076] Step S201, dividing the battery multi-source heterogeneous data into a target matrix according to the input amount;
[0077] It should be noted that the collected battery multi-source heterogeneous data (which may include multiple types of data from different sensors and at different time points) are organized and divided into a target matrix, and each row or column of this target matrix may represent different data features or data points.
[0078] Step S202, decomposing the target matrix into a left singular value vector matrix, a singular value matrix and a right singular value vector matrix by singular value decomposition method, wherein the singular values in the singular value matrix are used to reflect the importance of the target matrix in different directions;
[0079] It should be noted that if Figure 3 As shown in Figure 1, singular value decomposition is a matrix decomposition method that decomposes a matrix into the product of three matrices: a left singular value vector matrix, a singular value matrix, and a right singular value vector matrix. These matrices provide important information about the structure of the original matrix. The singular values in the singular value matrix (also called the singular spectrum) reflect the importance or energy distribution of the target matrix in different directions. Larger singular values correspond to more important directions or components in the matrix.
[0080] Step S203, reducing the dimension of the target matrix according to a preset singular value threshold to obtain a target left singular value vector matrix, a target singular value matrix and a target right singular value vector matrix;
[0081] It should be noted that, according to the preset singular value threshold, the singular values in the target singular value matrix that are greater than the preset singular value threshold and their corresponding left singular value vectors and right singular value vectors can be selected. In this way, those components that contribute less to the target matrix can be removed, thereby achieving dimensionality reduction, and obtaining the target left singular value vector matrix, the target singular value matrix, and the target right singular value vector matrix after dimensionality reduction.
[0082] Step S204, determining target related data according to the target left singular value vector matrix, the target singular value matrix and the target right singular value vector matrix.
[0083] It should be noted that the reduced-dimensional matrix information can be used to reconstruct the reduced-dimensional target-related data, which retains important information in the multi-source heterogeneity of batteries but has a lower dimension and is therefore easier to process and analyze.
[0084] In a feasible implementation manner, the step of training an initial prediction model based on the target-related data to obtain a target prediction model includes: determining multiple triplets based on the target left singular value vector matrix, the target singular value matrix, and the target right singular value vector matrix, and determining a target importance score for each triplet, wherein each triplet includes a column vector of a target left singular value vector matrix, a singular value of a target singular value matrix, and a row vector of a target right singular value vector matrix; determining a weight value of each vector in the target-related data according to the target importance score; and training the initial prediction model based on the weight value and the target-related data to obtain a target prediction model.
[0085] In the specific implementation, multiple triplets are determined: after singular value decomposition (SVD), we get three matrices: target left singular value vector matrix, target singular value matrix and target right singular value vector matrix. Each triplet consists of the following three parts: a column of the target left singular value vector matrix (representing a left singular vector), a singular value in the target singular value matrix (representing the importance or energy in that direction), and a row of the target right singular value vector matrix (representing a right singular vector), where each triplet captures the information of multi-source heterogeneous data of batteries in a specific direction. Then determine the target importance score of each triplet, and finally determine the weight value of each vector in the target-related data based on the target importance score. After determining the weight value, we can use these weight values and the target-related data (possibly after preprocessing and feature extraction) to train the initial prediction model. During the training process, the model will learn how to use the input features (i.e., weighted target-related data).
[0086] In a feasible implementation, the step of determining the target importance score of each triple includes: determining the first importance score mean of all elements in the column vector of the target left singular value vector matrix; determining the importance scores of the singular values of the target singular value matrix; determining the second importance score mean of all elements in the column vector of the target right singular value vector matrix; and determining the target importance score of each triple based on the first importance score mean, the importance score and the second importance score mean.
[0087] In the specific implementation, the first importance score mean of all elements in the column vector of the target left singular value vector matrix is determined (that is, the value obtained by averaging the single parameter importance scores of all elements in the column vector of the i-th column of the target left singular value vector matrix); the second importance score mean of all elements in the row vector of the target right singular value vector matrix is determined (that is, the value obtained by averaging the single parameter importance scores of all elements in the row vector of the i-th column of the target right singular value vector matrix).
[0088] This embodiment divides the battery multi-source heterogeneous data into target matrices according to the input amount; decomposes the target matrix into a left singular value vector matrix, a singular value matrix and a right singular value vector matrix by singular value decomposition method, wherein the singular values in the singular value matrix are used to reflect the importance of the target matrix in different directions; reduces the dimension of the target matrix according to a preset singular value threshold to obtain a target left singular value vector matrix, a target singular value matrix and a target right singular value vector matrix; determines the target related data according to the target left singular value vector matrix, the target singular value matrix and the target right singular value vector matrix. In the above manner, the data with the greatest impact on the battery state of charge can be screened out as target related data, thereby reducing the amount of calculation of the target prediction model during the training process.
[0089] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the method for predicting the state of charge of a sodium ion battery of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.
[0090] The present application also provides a sodium ion battery charge state prediction device, please refer to Figure 4 , the sodium ion battery charge state prediction device comprises:
[0091] The acquisition module 10 is used to acquire multi-source heterogeneous battery data, wherein the multi-source heterogeneous battery data includes battery voltage, battery current, battery temperature and historical state of charge;
[0092] A determination module 20, configured to determine target related data in the battery multi-source heterogeneous data according to a preset singular value decomposition method;
[0093] A training module 30, for training an initial prediction model based on the target-related data to obtain a target prediction model;
[0094] The input module 40 is used to input real-time battery data into the target prediction model to obtain a sodium ion battery state of charge prediction result, wherein the real-time battery data includes battery voltage, battery current and battery temperature.
[0095] The sodium ion battery state of charge prediction device provided by the present application adopts the sodium ion battery state of charge prediction method in the above embodiment, which can solve the technical problems of insufficient prediction accuracy and slow response speed commonly existing in traditional SOC prediction methods. Compared with the prior art, the beneficial effects of the sodium ion battery state of charge prediction device provided by the present application are the same as the beneficial effects of the sodium ion battery state of charge prediction method provided by the above embodiment, and the other technical features in the sodium ion battery state of charge prediction device are the same as the features disclosed in the above embodiment method, which will not be repeated here.
[0096] The present application provides a sodium ion battery state of charge prediction device, the sodium ion battery state of charge prediction device comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the sodium ion battery state of charge prediction method in the above-mentioned embodiment 1.
[0097] Reference below Figure 5 , which shows a schematic diagram of the structure of a sodium ion battery state of charge prediction device suitable for implementing an embodiment of the present application. The sodium ion battery state of charge prediction device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The sodium ion battery state of charge prediction device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0098] like Figure 5As shown, the sodium ion battery state of charge prediction device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the sodium ion battery state of charge prediction device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the sodium ion battery state of charge prediction device to communicate wirelessly or wired with other devices to exchange data. Although the sodium ion battery state of charge prediction device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.
[0099] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0100] The sodium ion battery state of charge prediction device provided by the present application adopts the sodium ion battery state of charge prediction method in the above embodiment, which can solve the technical problems of insufficient prediction accuracy and slow response speed commonly existing in traditional SOC prediction methods. Compared with the prior art, the beneficial effects of the sodium ion battery state of charge prediction device provided by the present application are the same as the beneficial effects of the sodium ion battery state of charge prediction method provided by the above embodiment, and the other technical features in the sodium ion battery state of charge prediction device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.
[0101] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0102] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0103] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the sodium ion battery state of charge prediction method in the above-mentioned embodiment.
[0104] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with 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 above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.
[0105] The computer-readable storage medium may be included in the sodium-ion battery state of charge prediction device; or may exist independently without being assembled into the sodium-ion battery state of charge prediction device.
[0106] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the sodium-ion battery state of charge prediction device, the sodium-ion battery state of charge prediction device: collects multi-source heterogeneous data of the battery, wherein the multi-source heterogeneous data of the battery includes battery voltage, battery current, battery temperature and historical state of charge; determines target-related data in the multi-source heterogeneous data of the battery according to a preset singular value decomposition method; trains an initial prediction model based on the target-related data to obtain a target prediction model; inputs real-time battery data into the target prediction model to obtain a sodium-ion battery state of charge prediction result, wherein the real-time battery data includes battery voltage, battery current and battery temperature.
[0107] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0108] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0109] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0110] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned sodium-ion battery state of charge prediction method, which can solve the technical problems of insufficient prediction accuracy and slow response speed commonly found in traditional SOC prediction methods. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the sodium-ion battery state of charge prediction method provided in the above-mentioned embodiment, and will not be elaborated here.
[0111] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the sodium ion battery state of charge prediction method as described above.
[0112] The computer program product provided by the present application can solve the technical problems of insufficient prediction accuracy and slow response speed commonly found in traditional SOC prediction methods. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the sodium ion battery state of charge prediction method provided by the above embodiment, and will not be elaborated here.
[0113] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A method for predicting the state of charge of a sodium ion battery, characterized in that: The method comprises: Collecting multi-source heterogeneous battery data, wherein the multi-source heterogeneous battery data includes battery voltage, battery current, battery temperature, and historical state of charge; Determine the target related data in the multi-source heterogeneous data of the battery according to a preset singular value decomposition method; Based on the target related data, an initial prediction model is trained to obtain a target prediction model; The real-time battery data is input into the target prediction model to obtain a sodium ion battery state of charge prediction result, wherein the real-time battery data includes battery voltage, battery current and battery temperature.
2. The method according to claim 1, characterized in that The step of collecting multi-source heterogeneous data of batteries includes: Collect multi-source heterogeneous data of raw batteries; Performing data cleaning on the original battery multi-source heterogeneous data to obtain cleaned data; Normalizing the cleaned data to obtain normalized data; Based on the interpolation method or the median method, the outliers in the normalized data are replaced to obtain multi-source heterogeneous data of batteries.
3. The method according to claim 1, characterized in that The step of determining the target related data in the battery multi-source heterogeneous data according to a preset singular value decomposition method comprises: Dividing the battery multi-source heterogeneous data into target matrices according to input quantities; Decomposing the target matrix into a left singular value vector matrix, a singular value matrix and a right singular value vector matrix by a singular value decomposition method, wherein the singular values in the singular value matrix are used to reflect the importance of the target matrix in different directions; Performing dimension reduction on the target matrix according to a preset singular value threshold to obtain a target left singular value vector matrix, a target singular value matrix, and a target right singular value vector matrix; Target related data is determined according to the target left singular value vector matrix, the target singular value matrix and the target right singular value vector matrix.
4. The method according to claim 3, characterized in that The step of training the initial prediction model based on the target related data to obtain the target prediction model comprises: Based on the target left singular value vector matrix, the target singular value matrix, and the target right singular value vector matrix, determine a plurality of triplets, and determine a target importance score for each triplet, wherein each triplet includes a column vector of the target left singular value vector matrix, a singular value of the target singular value matrix, and a row vector of the target right singular value vector matrix; Determining a weight value of each vector in the target-related data according to the target importance score; Based on the weight values and the target related data, the initial prediction model is trained to obtain a target prediction model.
5. The method according to claim 4, characterized in that The step of determining the target importance score of each triplet comprises: Determine the first importance score mean of all elements in the column vector of the target left singular value vector matrix; Determine the importance scores of the singular values of the target singular value matrix; Determine the second importance score mean of all elements in the column vector of the target right singular value vector matrix; A target importance score for each triple is determined based on the first importance score mean, the importance score, and the second importance score mean.
6. The method according to claim 1, characterized in that The step of training the initial prediction model based on the target related data to obtain the target prediction model comprises: Inputting the target related data into the initial prediction model to obtain a target output value; Determining a loss value based on the target output value and the historical state of charge; The parameters in the initial prediction model are updated according to the loss value to obtain a target prediction model.
7. The method according to claim 1, characterized in that The method further comprises: When the time interval between the current time and the previous update time is greater than or equal to the model update period, new battery multi-source heterogeneous data is acquired, and the target prediction model is updated based on the new battery multi-source heterogeneous data; and / or, Collect user feedback information on the target prediction model, and optimize the target prediction model according to the feedback information.
8. A sodium ion battery charge state prediction device, characterized in that: The device comprises: A collection module, used for collecting multi-source heterogeneous battery data, wherein the multi-source heterogeneous battery data includes battery voltage, battery current, battery temperature and historical state of charge; A determination module, used to determine target related data in the battery multi-source heterogeneous data according to a preset singular value decomposition method; A training module, used to train an initial prediction model based on the target-related data to obtain a target prediction model; The input module is used to input real-time battery data into the target prediction model to obtain a sodium ion battery state of charge prediction result, wherein the real-time battery data includes battery voltage, battery current and battery temperature.
9. A sodium ion battery state of charge prediction device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for predicting the state of charge of a sodium ion battery according to any one of claims 1 to 7.
10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for predicting the state of charge of a sodium ion battery according to any one of claims 1 to 7 are implemented.