Solid-state battery vehicle fault prediction method and system

Abstract

The invention discloses a solid-state battery vehicle fault prediction method and system, and the method comprises the steps: obtaining the alarm message data of a solid-state battery vehicle, and carrying out the analysis of the alarm message data, and obtaining a solid-state battery vehicle fault data set; preprocessing the vehicle fault data set, and constructing a model sample library according to the preprocessed data; constructing a GRU model, and training and evaluating the GRU model according to the model sample library to obtain a final solid-state battery vehicle fault prediction model; and inputting real-time solid-state battery vehicle alarm message data into the solid-state battery vehicle fault prediction model, and predicting the solid-state battery vehicle fault. The problems that in the prior art, manual fault collection and analysis work is complex, and errors are likely to be generated are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle fault prediction, and in particular to a method and system for predicting faults of solid-state battery vehicles. Background Art

[0002] With the popularity of electric vehicles, solid-state batteries, as a new generation of battery technology, have gradually become an important development direction for electric vehicle power batteries due to their advantages such as high energy density, long cycle life and safety. However, solid-state batteries may still face a variety of faults during use, such as capacity decay, internal short circuit, external short circuit, overcharge or over discharge, etc. These faults not only affect battery performance, but may also pose a threat to vehicle safety. Therefore, a method and system for predicting solid-state battery vehicle faults is urgently needed to solve this problem. Summary of the invention

[0003] In view of the above problems, the present invention is proposed to provide a method and system for solid-state battery vehicle fault prediction that overcomes the above problems or at least partially solves the above problems.

[0004] In order to solve the above technical problems, the embodiments of the present application disclose the following technical solutions:

[0005] In a first aspect, an embodiment of the present invention discloses a method for predicting faults of a solid-state battery vehicle, comprising:

[0006] S100. Acquire alarm message data of solid-state battery vehicles, parse the alarm message data, and obtain a fault data set of solid-state battery vehicles;

[0007] S200. Preprocessing the vehicle fault data set, and building a model sample library based on the preprocessed data;

[0008] S300. Construct a GRU model, train and evaluate the GRU model according to the model sample library, and obtain a final solid-state battery vehicle fault prediction model;

[0009] S400. Input the real-time solid-state battery vehicle alarm message data into the solid-state battery vehicle fault prediction model to predict the solid-state battery vehicle fault.

[0010] Furthermore, in S100, the solid-state battery vehicle fault data set includes at least: vehicle number, data reception time, vehicle speed, vehicle cumulative mileage, battery remaining capacity, vehicle total voltage, vehicle total current, battery cell voltage minimum value and battery cell voltage maximum value.

[0011] Furthermore, in S200, the vehicle fault data set is preprocessed, specifically including eliminating invalid data and processing abnormal data; wherein, the invalid data is eliminated by a specific method including: first checking whether there are missing values ​​in the data set, and filling the data with missing values ​​by an interpolation method; then verifying the integrity of the data, verifying whether each record contains all necessary fields, including at least a timestamp, a vehicle ID, an alarm type, and a fault code; finally, verifying the rationality of the business logic, including checking whether the timestamp is reasonable, whether the vehicle ID is unique, and whether the fault code exists in a known fault code list.

[0012] Furthermore, in S200, the abnormal data is processed, and the specific method includes: first, the outliers are identified, and statistical methods are used to identify the outliers in the data. When the value of a data point is far higher or lower than the mean of the data set plus or minus several standard deviations, the data point is confirmed as an outlier; then the data point is processed by deletion, replacement and retention methods.

[0013] Furthermore, in S200, a model sample library is constructed based on the preprocessed data, and the specific method includes: first, selecting sample features based on the vehicle fault data set type and the observation time window; then, performing one-hot encoding and label encoding on the labels, and pairing the features and labels; finally, resampling the samples, dividing the resampled data into a training set, a test set, and a validation set, to obtain a model sample library.

[0014] Furthermore, in S300, a GRU model is constructed, and the specific method includes:

[0015] Define the structure of the GRU model, including the specific configuration of the input layer, hidden layer, and output layer;

[0016] Initialize the model's parameters, including weights and biases, which will be updated during training using the back-propagation algorithm;

[0017] The forward propagation is set up so that the input sequence will be forward propagated through the input layer, hidden layer, and output layer in the order of time steps. At each time step, the GRU unit will calculate the output of the update gate and reset gate based on the current input and the hidden state of the previous time step, and update the hidden state accordingly;

[0018] Set the loss function and optimizer. The loss function is used to calculate the difference between the model prediction result and the actual result, and the optimizer is used to update the model parameters according to the gradient of the loss function.

[0019] Furthermore, in S300, the GRU model is trained and evaluated according to the model sample library to obtain a final solid-state battery vehicle fault prediction model, and the specific method includes:

[0020] Load the training data in the model sample library into the GRU model, train the model through multiple iterations, each iteration will traverse the entire training set, at each time step, the model will calculate the output based on the input and the current hidden state, and update the model parameters to minimize the loss function; load the test data in the model sample library into the GRU model, and use the test set to evaluate the performance of the model. According to the previously defined evaluation indicators, calculate the performance indicators of the model, which include at least accuracy, F1 score and mean square error; adjust the hyperparameters of the model according to the evaluation results, which include at least the learning rate, the number of units and the number of layers of the GRU layer, and tune the model to finally obtain a solid-state battery vehicle fault prediction model.

[0021] Furthermore, in S400, the real-time solid-state battery vehicle alarm message data is input into the solid-state battery vehicle fault prediction model to predict the solid-state battery vehicle fault. The specific method includes: inputting the real-time solid-state battery vehicle alarm message data into the trained solid-state battery vehicle fault prediction model to ensure that the format of the input data is consistent with the data format used during model training. The model will calculate and output the fault prediction results based on the input data, including the probability of the fault and the remaining service life; according to the output of the model, analyze and determine whether the solid-state battery vehicle has a fault risk; if the prediction result shows that there is a fault risk, generate corresponding alarm information and trigger the corresponding emergency response mechanism.

[0022] In a second aspect, an embodiment of the present invention discloses a system for predicting faults of solid-state battery vehicles, including: a solid-state battery vehicle fault data set acquisition unit, a model sample library construction unit, a solid-state battery vehicle fault prediction model construction unit, and a solid-state battery vehicle fault prediction unit, wherein:

[0023] A solid-state battery vehicle fault data set acquisition unit, used to acquire solid-state battery vehicle alarm message data, and parse the alarm message data to obtain a solid-state battery vehicle fault data set;

[0024] A model sample library construction unit, used to preprocess the vehicle fault data set and construct a model sample library based on the preprocessed data;

[0025] A solid-state battery vehicle fault prediction model construction unit is used to construct a GRU model, train and evaluate the GRU model according to the model sample library, and obtain a final solid-state battery vehicle fault prediction model;

[0026] The solid-state battery vehicle fault prediction unit is used to input real-time solid-state battery vehicle alarm message data into the solid-state battery vehicle fault prediction model to predict solid-state battery vehicle faults.

[0027] In a third aspect, an embodiment of the present invention discloses an electronic device, including:

[0028] one or more processors;

[0029] A memory for storing one or more programs;

[0030] When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle fault prediction method.

[0031] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least:

[0032] The embodiment of the present invention discloses a method for predicting faults of solid-state battery vehicles, including: obtaining alarm message data of solid-state battery vehicles, parsing the alarm message data to obtain a solid-state battery vehicle fault data set; preprocessing the vehicle fault data set, and building a model sample library based on the preprocessed data; building a GRU model, training and evaluating the GRU model based on the model sample library to obtain a final solid-state battery vehicle fault prediction model; inputting real-time solid-state battery vehicle alarm message data into the solid-state battery vehicle fault prediction model to predict solid-state battery vehicle faults. The present invention solves the problem that the manual collection and analysis of faults in the prior art is complicated and prone to errors.

[0033] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0035] Figure 1 This is a flow chart of a method for predicting faults of solid-state battery vehicles in Embodiment 1 of the present invention;

[0036] Figure 2 The TBOX collection fields and corresponding meaning analysis table in Embodiment 1 of the present invention;

[0037] Figure 3 This is a schematic diagram of the structure of an electronic device in Example 3 of the present invention. DETAILED DESCRIPTION

[0038] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0039] In order to solve the problems existing in the prior art, an embodiment of the present invention provides a method and system for predicting faults of a solid-state battery vehicle.

[0040] Example 1

[0041] The present invention discloses a method for predicting faults of solid-state battery vehicles. Figure 1 ,include:

[0042] S100. Obtain the alarm message data of the solid-state battery vehicle, parse the alarm message data, and obtain the fault data set of the solid-state battery vehicle; specifically, receive the message data reported by the TBOX on the solid-state battery vehicle, wherein the vehicle's TBOX (Telemetry BOX) data refers to the vehicle-related information collected, processed and transmitted by the on-board TBOX device. TBOX is a key component in modern cars. It plays the role of a bridge connecting the vehicle to the external network, communicates with the cloud in real time through wireless networks, and provides a variety of convenient services for car owners.

[0043] according to Figure 2 The parsing table parses out a solid-state battery vehicle fault data set, which includes at least: vehicle number, data reception time, vehicle speed, vehicle cumulative mileage, battery remaining capacity, vehicle total voltage, vehicle total current, battery cell voltage minimum value and battery cell voltage maximum value.

[0044] S200. Preprocess the vehicle fault data set and build a model sample library based on the preprocessed data; Preprocessing the vehicle fault data set and building a model sample library is a key step in a machine learning or data analysis project. This process aims to ensure the quality of the data and improve the accuracy and efficiency of the model.

[0045] In S200 of this embodiment, the vehicle fault data set is preprocessed, specifically including the removal of invalid data and the processing of abnormal data; wherein, the specific method for removing invalid data includes: firstly checking whether there are missing values ​​in the data set, and filling the data with missing values ​​by interpolation method; then verifying the integrity of the data, verifying whether each record contains all necessary fields, including at least timestamp, vehicle ID, alarm type, and fault code; finally verifying the rationality of the business logic, including checking whether the timestamp is reasonable, whether the vehicle ID is unique, and whether the fault code exists in the known fault code list. Through the above steps, a high-quality vehicle fault data set sample library suitable for model training can be constructed, laying a solid foundation for subsequent model development and deployment.

[0046] In S200 of this embodiment, the abnormal data is processed, and the specific method includes: first, the abnormal values ​​are identified, and statistical methods are used to identify the abnormal values ​​in the data. When the value of a data point is far higher or lower than the mean of the data set plus or minus several standard deviations, the data point is confirmed as an abnormal value; then the data point is processed by deletion, replacement and retention methods. The model sample library is constructed based on the preprocessed data, and the specific method includes: first, the sample features are selected according to the vehicle fault data set type and the observation time window; then the labels are uniquely encoded and the labels are encoded, and the features and labels are paired; finally, the samples are resampled, and the resampled data is divided into a training set, a test set and a validation set to obtain a model sample library.

[0047] S300. Construct a GRU model, train and evaluate the GRU model according to the model sample library, and obtain the final solid-state battery vehicle fault prediction model; wherein, the GRU (Gated Recurrent Unit) model, that is, the gated recurrent unit structure, is a variant of the traditional RNN (recurrent neural network). Similar to LSTM (long short-term memory network), the GRU model can also effectively capture the semantic associations between long sequences and alleviate the phenomenon of gradient disappearance or explosion. However, compared with LSTM, the structure and calculation of GRU are simpler, and its core structure is mainly composed of two gates: Update Gate and Reset Gate.

[0048] The function of the Update Gate is to control the extent to which the state information of the previous moment is brought into the current state. The larger the value of the Update Gate, the more state information of the previous moment is brought in. Use the current moment input x(t) and the hidden state h(t-1) of the previous moment to splice, and after linear transformation, use the sigmoid activation function to get the gate value z(t) of the Update Gate. The function of the Reset Gate is to control how much information of the previous state is written to the current candidate set h'(t) (or called the internal state). The smaller the reset gate, the less information of the previous state is written. Similarly, use x(t) and h(t-1) for splicing, linear transformation, and use the sigmoid activation function to get the gate value r(t) of the Reset Gate. Then, the reset gate value r(t) will act on h(t-1) to get the "reset" h(t-1).

[0049] In S300 of this embodiment, a GRU model is constructed, and the specific method includes:

[0050] Define the structure of the GRU model, including the specific configuration of the input layer, hidden layer, and output layer;

[0051] Initialize the model's parameters, including weights and biases, which will be updated during training using the back-propagation algorithm;

[0052] The forward propagation is set up so that the input sequence will be forward propagated through the input layer, hidden layer, and output layer in the order of time steps. At each time step, the GRU unit will calculate the output of the update gate and reset gate based on the current input and the hidden state of the previous time step, and update the hidden state accordingly;

[0053] The loss function and optimizer are set, where the loss function is used to calculate the difference between the model prediction result and the actual result, and the optimizer is used to update the model parameters according to the gradient of the loss function; in this embodiment, the mean square error is used as the loss function, and the Adam optimization algorithm is used for training. The number of hidden layer units is 100, the batch size is 32, and the learning rate is 0.001.

[0054] In S300 of this embodiment, the GRU model is trained and evaluated according to the model sample library to obtain a final solid-state battery vehicle fault prediction model. The specific method includes:

[0055] Load the training data in the model sample library into the GRU model, train the model through multiple iterations, each iteration will traverse the entire training set, at each time step, the model will calculate the output based on the input and the current hidden state, and update the model parameters to minimize the loss function; load the test data in the model sample library into the GRU model, and use the test set to evaluate the performance of the model. According to the previously defined evaluation indicators, calculate the performance indicators of the model, which include at least accuracy, F1 score and mean square error; adjust the hyperparameters of the model according to the evaluation results, which include at least the learning rate, the number of units and the number of layers of the GRU layer, and tune the model to finally obtain a solid-state battery vehicle fault prediction model.

[0056] S400. Input the real-time solid-state battery vehicle alarm message data into the solid-state battery vehicle fault prediction model to predict the solid-state battery vehicle fault.

[0057] In S400 of the present embodiment, real-time solid-state battery vehicle alarm message data is input into the solid-state battery vehicle fault prediction model to predict the solid-state battery vehicle fault. The specific method includes: inputting the real-time solid-state battery vehicle alarm message data into the trained solid-state battery vehicle fault prediction model to ensure that the format of the input data is consistent with the data format used in model training. The model will calculate and output the fault prediction results based on the input data, including the probability of the fault and the remaining service life; according to the output of the model, analyze and determine whether the solid-state battery vehicle has a fault risk; if the prediction result shows that there is a fault risk, generate corresponding alarm information and trigger the corresponding emergency response mechanism.

[0058] This embodiment discloses a method for predicting faults of solid-state battery vehicles, including: obtaining alarm message data of solid-state battery vehicles, parsing the alarm message data to obtain a solid-state battery vehicle fault data set; preprocessing the vehicle fault data set, and building a model sample library based on the preprocessed data; building a GRU model, training and evaluating the GRU model based on the model sample library to obtain a final solid-state battery vehicle fault prediction model; inputting real-time solid-state battery vehicle alarm message data into the solid-state battery vehicle fault prediction model to predict solid-state battery vehicle faults. The present invention solves the problem that the manual collection and analysis of faults in the prior art is complicated and prone to errors.

[0059] Example 2

[0060] Based on the same inventive concept, the disclosed embodiment also provides a system for predicting faults of solid-state battery vehicles, characterized in that it includes: a solid-state battery vehicle fault data set acquisition unit, a model sample library construction unit, a solid-state battery vehicle fault prediction model construction unit and a solid-state battery vehicle fault prediction unit, wherein:

[0061] A solid-state battery vehicle fault data set acquisition unit, used to acquire solid-state battery vehicle alarm message data, and parse the alarm message data to obtain a solid-state battery vehicle fault data set;

[0062] A model sample library construction unit, used to preprocess the vehicle fault data set and construct a model sample library based on the preprocessed data;

[0063] A solid-state battery vehicle fault prediction model construction unit is used to construct a GRU model, train and evaluate the GRU model according to the model sample library, and obtain a final solid-state battery vehicle fault prediction model;

[0064] The solid-state battery vehicle fault prediction unit is used to input real-time solid-state battery vehicle alarm message data into the solid-state battery vehicle fault prediction model to predict solid-state battery vehicle faults.

[0065] Among them, the specific working methods of the solid-state battery vehicle fault data set acquisition unit, the model sample library construction unit, the solid-state battery vehicle fault prediction model construction unit and the solid-state battery vehicle fault prediction unit have been recorded in detail in Example 1, and will not be repeated in this embodiment.

[0066] Example 3

[0067] Based on the same inventive concept, an embodiment of the present disclosure also provides an electronic device. Figure 3 FIG. 1 is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. Figure 3 As shown, an embodiment of the present disclosure provides an electronic device including: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement any optimization method in the above embodiments; the one or more I / O interfaces 103 are connected between the processor and the memory, and are configured to implement information interaction between the processor and the memory.

[0068] Among them, the processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU), etc.; the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH); the I / O interface (read-write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus), etc.

[0069] In some embodiments, the processor 101 , the memory 102 , and the I / O interface 103 are connected to each other via a bus 104 , and further connected to other components of the computing device.

[0070] In some embodiments, the one or more processors 101 include a field programmable gate array.

[0071] According to an embodiment of the present disclosure, a computer-readable medium is further provided, wherein a computer program is stored on the computer-readable medium, wherein when the program is executed by a processor, the steps in any optimization method in the above-mentioned embodiment are implemented.

[0072] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.

[0073] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are clearly stated in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0074] Those skilled in the art will also appreciate that the various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the embodiments herein can all be implemented as electronic hardware, computer software, or a combination thereof. In order to clearly illustrate the interchangeability between hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above around their functions. Whether such functions are implemented as hardware or software depends on specific applications and the design constraints imposed on the entire system. A skilled person can implement the described functions in an alternative manner for each specific application, but such implementation decisions should not be interpreted as departing from the scope of protection of the present disclosure.

[0075] The steps of the method or algorithm described in conjunction with the embodiments herein may be directly embodied as hardware, a software module executed by a processor, or a combination thereof. The software module may be located in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a mobile disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium may also be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The ASIC may be located in a user terminal. Of course, the processor and the storage medium may also be present in a user terminal as discrete components.

[0076] For software implementation, the techniques described in this application can be implemented with modules (e.g., procedures, functions, etc.) that perform the functions described in this application. These software codes can be stored in a memory unit and executed by a processor. The memory unit can be implemented within the processor or outside the processor. In the latter case, it is coupled to the processor in a communication manner via various means, which are well known in the art.

[0077] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments may be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," is explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to mean "non-exclusive or".

Claims

1. A method for predicting faults of solid-state battery vehicles, characterized in that: include: S100. Acquire alarm message data of solid-state battery vehicles, parse the alarm message data, and obtain a fault data set of solid-state battery vehicles; S200. Preprocessing the vehicle fault data set, and building a model sample library based on the preprocessed data; S300. Construct a GRU model, train and evaluate the GRU model according to the model sample library, and obtain a final solid-state battery vehicle fault prediction model; S400. Input the real-time solid-state battery vehicle alarm message data into the solid-state battery vehicle fault prediction model to predict the solid-state battery vehicle fault.

2. A method for predicting faults of solid-state battery vehicles as claimed in claim 1, characterized in that: In S100, the solid-state battery vehicle fault data set includes at least: vehicle number, data reception time, vehicle speed, vehicle cumulative mileage, battery remaining capacity, vehicle total voltage, vehicle total current, battery cell voltage minimum value and battery cell voltage maximum value.

3. A method for predicting faults of solid-state battery vehicles as claimed in claim 1, characterized in that: In S200, the vehicle fault data set is preprocessed, specifically including eliminating invalid data and processing abnormal data; wherein, the invalid data is eliminated by a specific method including: firstly checking whether there are missing values ​​in the data set, and filling the data with missing values ​​by interpolation method; then verifying the integrity of the data, verifying whether each record contains all necessary fields, including at least timestamp, vehicle ID, alarm type, and fault code; finally, verifying the rationality of the business logic, including checking whether the timestamp is reasonable, whether the vehicle ID is unique, and whether the fault code exists in the known fault code list.

4. A method for predicting faults of solid-state battery vehicles as claimed in claim 1, characterized in that: In S200, the abnormal data is processed. The specific method includes: first, the outliers are identified, and statistical methods are used to identify the outliers in the data. When the value of a data point is far higher or lower than the mean of the data set plus or minus several standard deviations, the data point is confirmed as an outlier; then the data point is processed by deletion, replacement and retention methods.

5. A method for predicting faults of solid-state battery vehicles as claimed in claim 1, characterized in that: In S200, a model sample library is constructed based on the preprocessed data. The specific method includes: first, selecting sample features based on the vehicle fault data set type and the observation time window; then, performing one-hot encoding and label encoding on the labels, and pairing the features and labels; finally, resampling the samples, dividing the resampled data into a training set, a test set, and a validation set, to obtain a model sample library.

6. A method for predicting faults of solid-state battery vehicles as claimed in claim 1, characterized in that: In S300, a GRU model is constructed. The specific method includes: Define the structure of the GRU model, including the specific configuration of the input layer, hidden layer, and output layer; Initialize the model's parameters, including weights and biases, which will be updated during training using the back-propagation algorithm; The forward propagation is set up so that the input sequence is forward propagated through the input layer, hidden layer, and output layer in the order of time steps. At each time step, the GRU unit calculates the output of the update gate and reset gate based on the current input and the hidden state of the previous time step, and updates the hidden state accordingly. The loss function and optimizer are set, where the loss function is used to calculate the difference between the model's predicted results and the actual results, and the optimizer is used to update the model parameters according to the gradient of the loss function.

7. A method for predicting faults of solid-state battery vehicles as claimed in claim 1, characterized in that: In S300, the GRU model is trained and evaluated according to the model sample library to obtain a final solid-state battery vehicle fault prediction model. The specific method includes: The training data in the model sample library is loaded into the GRU model, and the model is trained through multiple iterations. Each iteration traverses the entire training set. At each time step, the model calculates the output based on the input and the current hidden state, and updates the model parameters to minimize the loss function; the test data in the model sample library is loaded into the GRU model, and the performance of the model is evaluated using the test set; the performance indicators of the model are calculated according to the previously defined evaluation indicators, and the indicators include at least accuracy, F1 score and mean square error; the hyperparameters of the model are adjusted according to the evaluation results, and the parameters include at least the learning rate, the number of units and the number of layers of the GRU layer, and the model is tuned to finally obtain a solid-state battery vehicle fault prediction model.

8. A method for predicting faults of solid-state battery vehicles as claimed in claim 1, characterized in that: In S400, the real-time solid-state battery vehicle alarm message data is input into the solid-state battery vehicle fault prediction model to predict the solid-state battery vehicle fault. The specific method includes: inputting the real-time solid-state battery vehicle alarm message data into the trained solid-state battery vehicle fault prediction model to ensure that the format of the input data is consistent with the data format used when the model is trained. The model will calculate and output the fault prediction results based on the input data, including the probability of the fault and the remaining service life; according to the output of the model, analyze and determine whether the solid-state battery vehicle has a fault risk; if the prediction result shows that there is a fault risk, generate corresponding alarm information and trigger the corresponding emergency response mechanism.

9. A system for predicting faults of solid-state battery vehicles, characterized in that: include: A solid-state battery vehicle fault data set acquisition unit, a model sample library construction unit, a solid-state battery vehicle fault prediction model construction unit and a solid-state battery vehicle fault prediction unit, wherein: A solid-state battery vehicle fault data set acquisition unit, used to acquire solid-state battery vehicle alarm message data, and parse the alarm message data to obtain a solid-state battery vehicle fault data set; A model sample library construction unit, used to preprocess the vehicle fault data set and construct a model sample library based on the preprocessed data; A solid-state battery vehicle fault prediction model construction unit is used to construct a GRU model, train and evaluate the GRU model according to the model sample library, and obtain a final solid-state battery vehicle fault prediction model; The solid-state battery vehicle fault prediction unit is used to input real-time solid-state battery vehicle alarm message data into the solid-state battery vehicle fault prediction model to predict solid-state battery vehicle faults.

10. An electronic device, comprising: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle fault prediction method in claims 1-8.

Images