Vehicle power battery temperature early warning method and device, electronic equipment and storage medium
By generating a feature matrix and using the LSTM model for temperature prediction, the problems of low warning accuracy and poor adaptability in existing technologies are solved, achieving more accurate temperature warnings and ensuring vehicle safety.
Patent Information
- Application Number
- CN202510872236.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-26
- Publication Date
- 2025-09-26
AI Technical Summary
Existing vehicle power battery high temperature warning technology relies on a single data source, with low warning accuracy, short warning time, and poor adaptability, and cannot effectively deal with the high temperature risks of vehicle power batteries.
By generating the first feature matrix and combining different types of data to increase feature dimensions and weight features, the LSTM model is used to capture long-term time series features and nonlinear relationships to perform temperature prediction and issue temperature warnings.
The accuracy of temperature prediction and early warning is improved, ensuring vehicle safety and avoiding potential dangers caused by high temperatures.
Smart Images
Figure CN120709557A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of vehicle power battery diagnosis, and in particular to a vehicle power battery temperature early warning method, device, electronic equipment and storage medium. Background Art
[0002] Vehicle power batteries may generate high temperatures during operation due to a variety of reasons, including internal short circuits, overcharging, over-discharging, high ambient temperatures, and poor heat dissipation. High temperatures not only accelerate battery aging and degrade performance, but can also cause thermal runaway, resulting in fire or even explosion, seriously threatening the safety of the vehicle and passengers.
[0003] Existing vehicle power battery high temperature warning technologies mainly rely on a single data source (such as temperature sensor data) or simple machine learning models. These methods have the following limitations: low warning accuracy, short warning time, poor adaptability, and insufficient data utilization. Summary of the Invention
[0004] The present invention provides a vehicle power battery temperature early warning method, device, electronic equipment and storage medium to solve the problem of low power battery temperature early warning accuracy.
[0005] According to one aspect of the present invention, a vehicle power battery temperature early warning method is provided, comprising:
[0006] A first feature matrix is generated based on the first data and the second data; the first data is used to describe the operating state of the vehicle within a first preset time period; the second data is used to characterize the state change of the vehicle's power battery within the first preset time period; the first feature matrix is a feature obtained by increasing the feature dimension and weighting the first data and the second data;
[0007] Predicting the temperature of the vehicle power battery within a second preset time period according to the first characteristic matrix to obtain third data; wherein the second preset time period is after the first preset time period;
[0008] A temperature warning is issued according to the third data.
[0009] According to another aspect of the present invention, a vehicle power battery temperature warning device is provided, comprising:
[0010] A first feature data determination module is configured to generate a first feature matrix based on first data and second data; the first data is configured to describe the operating state of the vehicle within a first preset time period; the second data is configured to characterize a change in the state of the vehicle's power battery within the first preset time period; the first feature matrix is a feature matrix obtained by increasing the feature dimension and weighting the first and second data;
[0011] a third data determination module, configured to predict the temperature of the vehicle power battery within a second preset time period according to the first characteristic matrix to obtain third data; the second preset time period being after the first preset time period;
[0012] The temperature warning module is used to issue a temperature warning based on the third data.
[0013] According to another aspect of the present invention, an electronic device is provided, comprising:
[0014] at least one processor; and
[0015] a memory communicatively connected to the at least one processor; wherein,
[0016] 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 vehicle power battery temperature warning method described in any embodiment of the present invention.
[0017] 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 vehicle power battery temperature warning method described in any embodiment of the present invention when executed.
[0018] The technical solution of the embodiment of the present invention generates a first feature matrix based on the first data and the second data. The generation of the first data feature includes different types of data, which can make up for the low prediction accuracy caused by relying on a single data source for prediction, and can also improve the adaptability of the first model; the temperature of the vehicle power battery in the second preset time period is predicted based on the first feature matrix to obtain third data, and the prediction is made through the first data feature, which can improve the accuracy of the first model prediction; and a temperature warning is made based on the third data. This method makes up for the problem of the limitations of single data prediction by increasing the feature dimensions and fusing the features of different types of data. The temperature prediction is made based on the fused features, which can improve the accuracy of temperature prediction. The improvement of the accuracy of temperature prediction can also improve the accuracy of temperature warning, thereby ensuring the safety of the vehicle.
[0019] 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
[0020] 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.
[0021] Figure 1 A flow chart of a vehicle power battery temperature early warning method provided by an embodiment of the present invention;
[0022] Figure 2 A schematic structural diagram of a vehicle power battery temperature warning device provided by an embodiment of the present invention;
[0023] Figure 3 A schematic structural diagram of an electronic device for implementing the vehicle power battery temperature warning method according to an embodiment of the present invention. DETAILED DESCRIPTION
[0024] 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.
[0025] 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.
[0026] Figure 1 This is a flow chart of a vehicle power battery temperature warning method provided by an embodiment of the present invention. This embodiment is applicable to situations where a warning is provided for the temperature of a power battery. The method can be executed by a vehicle power battery temperature warning device. The vehicle power battery temperature warning device can be implemented in the form of hardware and / or software. The vehicle power battery temperature warning device can be configured in any electronic device with network communication function. Figure 1As shown, the method includes:
[0027] S110. Generate a first feature matrix based on the first data and the second data; the first data is used to describe the operating status of the vehicle within a first preset time period; the second data is used to characterize the state change of the vehicle's power battery within the first preset time period; the first feature matrix is the features obtained by increasing the feature dimension and weighting the features of the first data and the second data.
[0028] The first data is collected by sensors installed on the vehicle and includes at least one of the following: vehicle speed, engine speed, ambient temperature and humidity, etc.
[0029] The second data is collected by a sensor configured on the power battery, and includes at least one of the following: the voltage of the power battery, the current of the power battery, and the temperature within a first preset time period.
[0030] The first feature matrix is obtained by performing dimension mapping on the first data and the second data using a kernel function to increase the feature dimensions of the first data and the second data, and weighting them. The kernel function is used to map data in a low-dimensional space to a high-dimensional feature space.
[0031] Specifically, different kernel functions are matched according to the data types of the first data and the second data, and feature mapping is performed on the first data and the second data respectively using the kernel functions to obtain different kernel matrices. The kernel matrices are weighted to obtain the first feature matrix.
[0032] Furthermore, feature mapping is performed on the first data and the second data respectively through the kernel function, and it is necessary to ensure that the dimensions of the kernel matrices obtained by the mapping are uniform.
[0033] Furthermore, different kernel functions are matched according to the data types of the first data and the second data, including: since the first data is used to characterize the operating status of the vehicle within a first preset time period and there is a nonlinear relationship, a polynomial kernel function is used; the voltage, current and temperature in the second data belong to a complex nonlinear scenario, so an RBF kernel function is used.
[0034] S120. Predict the temperature of the vehicle power battery within a second preset time period according to the first characteristic matrix to obtain third data; the second preset time period is after the first preset time period.
[0035] Specifically, the LSTM layer in the first model extracts time series features from the first feature matrix, capturing the relationship between data and time, as well as the nonlinear relationship between data, in the first feature matrix. The output layer in the first model then generates the temperature of the vehicle's power battery within a second preset time period based on the time series features, generating third data.
[0036] The first model can use an LSTM model as its framework. Within this framework, the depth and number of neurons in the LSTM layer are increased to better capture long-term time series features and the temporal dependencies within them. Furthermore, an input layer is added after the LSTM layer to generate the power battery temperature value or the probability of exceeding the temperature limit based on the data features extracted by the LSTM layer.
[0037] In the above steps, the use of the first model can better capture long-term time series features and the dependencies between long-term time series features, thereby avoiding the problems of short temperature warning time and low accuracy.
[0038] S130: Issue a temperature warning based on the third data.
[0039] Specifically, the third data is traversed and compared with the preset temperature threshold. If the third data contains temperature data exceeding the temperature threshold, a temperature over-limit warning is issued; if the third data does not contain temperature data exceeding the temperature threshold, data collection continues.
[0040] Furthermore, after obtaining the temperature data of the power battery in the second time period, the temperature data is compared with the third data, and the first model is modified according to the comparison result to ensure the real-time performance and adaptability of the first model.
[0041] Optionally, generating a first feature matrix according to the first data and the second data includes steps A1-A3:
[0042] Step A1: Match a first kernel function from candidate kernel functions according to the first data, and perform dimension mapping on the first data according to the first kernel function to obtain a first feature vector.
[0043] The candidate kernel functions include at least a linear kernel function, a polynomial kernel function, an RBF kernel function and a sigmoid kernel function.
[0044] Among them, the linear kernel function is suitable for linearly separable data; the polynomial kernel function is suitable for data with nonlinear relationships; the RBF kernel function is suitable for complex nonlinear scenarios; and the sigmoid kernel function is suitable for neural network models.
[0045] Specifically, a data type is determined based on the first data, a corresponding kernel function is matched from candidate kernel functions based on the data type to serve as the first kernel function, and the first data is input into the first kernel function for dimension increase to obtain a first eigenvector.
[0046] Furthermore, since the first data is nonlinear data, the first matching kernel function is a polynomial kernel function.
[0047] Among them, the polynomial kernel function can be expressed as:
[0048] KPoly(x,y)=(<x,y> +1) d ;
[0049] Among them, x and y are data samples in the sample pair, and the sample pair is composed of different data in the first data; d is a parameter.
[0050] Furthermore, before the first data is input into the first kernel function for dimension increase, the method includes: generating at least one set of sample pairs (x i , x j ), where i, j = 1, 2, ..., n. Each pair of samples is input into the first kernel function for calculation to increase the feature dimension.
[0051] Step A2: Match a second kernel function from the candidate kernel functions according to the second data, and perform dimension mapping on the second data according to the second kernel function to obtain a second feature vector.
[0052] Specifically, the data type is determined based on the second data, a corresponding processing kernel function is matched from the candidate kernel functions based on the data type to serve as the second kernel function, and the second data is input into the second kernel function for dimension increase to obtain a second eigenvector.
[0053] Furthermore, since the second data is complex nonlinear scene data, the second kernel function to be matched is the RBF kernel function.
[0054] Among them, the RBF kernel function can be expressed as:
[0055] KRBF(x,y)=exp(-γ||xy||2);
[0056] Wherein, x and y are data samples in a sample pair, and the sample pair is composed of different data in the first data; γ is a parameter.
[0057] Step A3: Perform weighted summation on the first eigenvector and the second eigenvector to obtain a first eigenmatrix.
[0058] Specifically, the first eigenvector and the second eigenvector are multiplied by a preset weight group and then added to obtain a first eigenmatrix.
[0059] The preset weight group is dynamically selected according to actual needs. For example, the preset weight group may be [0.5, 0.5].
[0060] For example, assuming that the preset weights are [0.5, 0.5], the first feature matrix can be expressed as:
[0061] KCombined=0.5KRBF+0.5Kpoly.
[0062] Optionally, matching a first kernel function from candidate kernel functions according to the first data, and performing dimension mapping on the first data according to the first kernel function to obtain a first feature vector includes steps B1-B4:
[0063] Step B1: Generate sample pairs according to the first data.
[0064] Specifically, the data dimension of the first data and the number of data contained in the first data are determined according to the composition of the first data, and at least one set of sample pairs is generated according to the data dimension and the number of data.
[0065] Among them, the sample pair is represented as: (x i , x j ), where i, j = 1, 2, ..., n.
[0066] Step B3: Determine at least one set of first features based on the sample pairs using a kernel function.
[0067] The first feature represents the similarity of the data samples in the sample pair in the feature space.
[0068] Specifically, each sample pair data is input into the kernel function for calculation to obtain at least one set of first features.
[0069] Step B4: Combine at least one set of first features to obtain a first feature vector.
[0070] Specifically, the subscript of the first element in the sample pair is used as the column order of the first eigenvector; the subscript of the second element in the sample pair is used as the row order of the first eigenvector. At least one set of first features is sorted according to the obtained column order and row order to obtain the first eigenvector.
[0071] Optionally, predicting the temperature of the vehicle power battery within a second preset time period according to the first characteristic matrix to obtain third data includes steps C1-C2:
[0072] Step C1: Use the first model to extract time series features from the first feature matrix to obtain second features.
[0073] The first model can use an LSTM model as its framework. Within this framework, the depth and number of neurons in the LSTM layer are increased to better capture long-term time series features and the temporal dependencies within them. Furthermore, an input layer is added after the LSTM layer to generate the power battery temperature value and / or the probability of exceeding the temperature limit based on the data features extracted by the LSTM layer.
[0074] Specifically, the time series features of the first feature matrix are extracted through the LSTM layer in the first model to capture the relationship between data and time and the nonlinear relationship between data in the first feature matrix to obtain the second feature.
[0075] Step C2: using the first model to predict the temperature of the vehicle power battery within a second preset time period according to the second feature to obtain third data.
[0076] Specifically, the output layer in the first model is used to generate the temperature of the vehicle power battery within the second preset time period according to the second feature to obtain the third data.
[0077] Furthermore, the output layer can also output the probability of the power battery temperature exceeding the limit.
[0078] Furthermore, after obtaining the third data, the third data is compared with the temperature data of the power battery collected within the second preset time period to determine a prediction error, and the first model is further adjusted according to the prediction error.
[0079] Optionally, at least one construction method of the first model includes steps D1-D4:
[0080] Step D1, determine the second characteristic matrix and the fourth data; the second characteristic matrix is a characteristic matrix generated by the vehicle's operating status data and the vehicle's power battery status change data within a third preset time period; the fourth data is the vehicle's power battery temperature change data within the third preset time period; the third preset time period is located before the first preset time period.
[0081] Specifically, the third data and the fourth data are obtained from the data storage module, and the second characteristic matrix is generated according to the third data and the fourth data using the same generation method as the first characteristic matrix.
[0082] The data storage module is used to store the third data and the fourth data. The data storage module is configured in a cloud server or in the vehicle.
[0083] Step D2: Input the second characteristic matrix into the second model to predict the temperature of the vehicle power battery within the third preset time period to obtain fifth data; the second model and the first model have the same model structure but different model parameters.
[0084] Specifically, the LSTM layer in the second model extracts time series features from the second feature matrix, capturing the relationship between data and time, as well as the nonlinear relationship between data, to obtain the third feature. The output layer in the second model then generates the temperature of the vehicle's power battery within a third preset time period based on the third feature, to obtain the fifth data.
[0085] Step D3: Determine a first error according to the fifth data and the fourth data.
[0086] Specifically, error evaluation is performed on the temperature data in the fifth data and the fourth data to obtain the first data.
[0087] Furthermore, the error evaluation may adopt the mean absolute error or the mean absolute percentage error.
[0088] Step D4: Correct the second model according to the first error to obtain the first model.
[0089] Specifically, the model structure and model parameters of the second model are modified according to the first data to obtain the first model.
[0090] Optionally, performing a temperature warning according to the third data includes steps E1-E3:
[0091] Step E1: Compare the third data with a preset temperature threshold.
[0092] Specifically, the third data is traversed and compared with the preset temperature thresholds respectively.
[0093] Step E2: If the temperature exceeds the preset threshold, a temperature over-limit warning is issued.
[0094] Specifically, if the third data includes temperature data exceeding a temperature threshold, a temperature over-limit warning is issued.
[0095] Step E3: If the value does not exceed the preset threshold, continue data collection.
[0096] Specifically, if there is no temperature data exceeding the temperature threshold in the third data, data collection continues.
[0097] The technical solution of this embodiment generates a first feature matrix based on the first data and the second data. The generation of the first data feature includes different types of data, which can make up for the low prediction accuracy caused by relying on a single data source for prediction and improve the adaptability of the first model; the temperature of the vehicle power battery in the second preset time period is predicted based on the first feature matrix to obtain third data. The prediction is made through the first data feature, which can improve the accuracy of the first model prediction; and a temperature warning is issued based on the third data. This method compensates for the limitations of single data prediction by increasing the feature dimensions and fusing the features of different types of data. Temperature prediction is performed based on the fused features, which can improve the accuracy of temperature prediction. The improvement of the accuracy of temperature prediction can also improve the accuracy of temperature warning, thereby ensuring the safety of the vehicle.
[0098] Figure 2This is a schematic diagram of the structure of a vehicle power battery temperature warning device provided by an embodiment of the present invention. This embodiment is applicable to the case of warning the temperature of the power battery. The vehicle power battery temperature warning device can be implemented in the form of hardware and / or software. The vehicle power battery temperature warning device can be configured in any electronic device with network communication function. Figure 2 As shown, the device includes: a first characteristic data determination module 210, a third data determination module 220 and a temperature warning module 230, wherein:
[0099] First feature data determination module 210: used to generate a first feature matrix based on first data and second data; the first data is used to describe the operating state of the vehicle within a first preset time period; the second data is used to characterize the state change of the vehicle's power battery within the first preset time period; the first feature matrix is the features obtained by increasing the feature dimension and weighting the first data and the second data;
[0100] The third data determination module 220 is configured to predict the temperature of the vehicle power battery within a second preset time period according to the first characteristic matrix to obtain third data; the second preset time period is after the first preset time period;
[0101] The temperature warning module 230 is used to issue a temperature warning according to the third data.
[0102] Optionally, the first feature data determination module includes:
[0103] A first feature vector determining unit is configured to match a first kernel function from candidate kernel functions according to the first data, and perform dimension mapping on the first data according to the first kernel function to obtain a first feature vector;
[0104] A second eigenvector determining unit is configured to match a second kernel function from the candidate kernel functions according to the second data, and perform dimension mapping on the second data according to the second kernel function to obtain a second eigenvector;
[0105] The first characteristic data determining unit is configured to perform weighted summation on the first characteristic vector and the second characteristic vector to obtain a first characteristic matrix.
[0106] Optionally, the first feature vector determining unit includes:
[0107] A sample pair determination subunit: configured to generate a sample pair according to the first data;
[0108] A first feature determination subunit: configured to determine at least one set of first features according to the sample pairs through a kernel function;
[0109] The first feature vector determining subunit is configured to combine at least one set of first features to obtain a first feature vector.
[0110] Optionally, the third data determination module 220 includes:
[0111] A second feature determination unit is configured to extract time series features from the first feature matrix using the first model to obtain a second feature;
[0112] The third data determination unit is configured to use the first model to predict the temperature of the vehicle power battery within a second preset time period according to the second feature to obtain third data.
[0113] Optionally, the second feature determination unit includes:
[0114] Data determination subunit: used to determine a second characteristic matrix and fourth data; the second characteristic matrix is a characteristic matrix generated by the operating status data of the vehicle and the status change data of the vehicle power battery within a third preset time period; the fourth data is the temperature change data of the vehicle power battery within the third preset time period; the third preset time period is before the first preset time period;
[0115] a fifth data determination subunit configured to input the second characteristic matrix into the second model to predict the temperature of the vehicle power battery within a third preset time period to obtain fifth data; the second model and the first model have the same model structure but different model parameters;
[0116] A first error determining subunit: configured to determine a first error according to the fifth data and the fourth data;
[0117] The first model determination subunit is configured to correct the second model according to the first error to obtain the first model.
[0118] Optionally, the temperature warning module 230 includes:
[0119] Comparison unit: used for comparing the third data with a preset temperature threshold;
[0120] Early warning unit: used to issue a temperature over-limit warning if the preset temperature threshold is exceeded;
[0121] Data determination unit: used to continue data collection if the preset threshold is not exceeded.
[0122] The vehicle power battery temperature warning device provided in the embodiment of the present invention can execute the vehicle power battery temperature warning method provided in any embodiment of the present invention mentioned above, and has the corresponding functions and beneficial effects of executing the vehicle power battery temperature warning method. For detailed process, please refer to the relevant operations of the vehicle power battery temperature warning method in the aforementioned embodiment.
[0123] Figure 3A schematic structural diagram of an electronic device for implementing a vehicle power battery temperature warning method according to an embodiment of the present invention. 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 may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, 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 required herein.
[0124] like Figure 3 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0125] 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.
[0126] 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 that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the vehicle power battery temperature warning method.
[0127] In some embodiments, the vehicle power battery temperature warning 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 vehicle power battery temperature warning method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the vehicle power battery temperature warning method in any other appropriate manner (for example, by means of firmware).
[0128] Various embodiments of the systems and techniques described herein 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 comprising 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.
[0129] 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.
[0130] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0131] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: 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).
[0132] 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.
[0133] 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.
[0134] 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.
[0135] 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 vehicle power battery temperature early warning method, characterized in that: include: generating a first characteristic matrix according to the first data and the second data; The first data is used to describe the running status of the vehicle within a first preset time period; The second data is used to characterize the state change of the vehicle power battery within a first preset time period; the first feature matrix is a feature obtained by increasing the feature dimension and weighting the first data and the second data; Predicting the temperature of the vehicle power battery within a second preset time period according to the first characteristic matrix to obtain third data; wherein the second preset time period is after the first preset time period; A temperature warning is issued according to the third data.
2. The method according to claim 1, characterized in that The generating of the first characteristic matrix according to the first data and the second data includes: Matching a first kernel function from candidate kernel functions according to the first data, and performing dimension mapping on the first data according to the first kernel function to obtain a first feature vector; Matching a second kernel function from the candidate kernel functions according to the second data, and performing dimension mapping on the second data according to the second kernel function to obtain a second feature vector; A weighted sum is performed on the first eigenvector and the second eigenvector to obtain a first eigenmatrix.
3. The method according to claim 2, characterized in that The matching of the first kernel function from the candidate kernel functions according to the first data, and dimension mapping of the first data according to the first kernel function to obtain a first feature vector includes: generating sample pairs according to the first data; Determine at least one set of first features according to the sample pairs by using a kernel function; The at least one set of first features is combined to obtain a first feature vector.
4. The method according to claim 1, wherein The step of predicting the temperature of the vehicle power battery within a second preset time period according to the first characteristic matrix to obtain third data includes: Using the first model to extract time series features from the first feature matrix to obtain the second feature; The first model is used to predict the temperature of the vehicle power battery within a second preset time period according to the second feature to obtain third data.
5. The method according to claim 4, characterized in that At least one construction method of the first model includes: Determine a second characteristic matrix and fourth data; the second characteristic matrix is a characteristic matrix generated by the operating state data of the vehicle and the state change data of the vehicle power battery within a third preset time period; the fourth data is the temperature change data of the vehicle power battery within the third preset time period; the third preset time period is before the first preset time period; Inputting the second characteristic matrix into a second model to predict the temperature of the vehicle power battery within a third preset time period to obtain fifth data; the second model and the first model have the same model structure but different model parameters; determining a first error based on the fifth data and the fourth data; The second model is corrected according to the first error to obtain a first model.
6. The method according to claim 1, characterized in that The performing of temperature warning according to the third data includes: comparing the third data with a preset temperature threshold; If the preset temperature threshold is exceeded, a temperature over-limit warning will be issued; If the preset threshold is not exceeded, data collection continues.
7. A vehicle power battery temperature warning device, characterized in that: include: A first characteristic data determination module, configured to generate a first characteristic matrix based on the first data and the second data; The first data is used to describe the operating state of the vehicle within a first preset time period; the second data is used to characterize the state change of the vehicle's power battery within the first preset time period; the first feature matrix is a feature obtained by increasing the feature dimension and weighting the first data and the second data; a third data determination module, configured to predict the temperature of the vehicle power battery within a second preset time period according to the first characteristic matrix to obtain third data; the second preset time period being after the first preset time period; The temperature warning module is used to issue a temperature warning based on the third data.
8. The device according to claim 7, characterized in that The first feature data determination module includes: a first feature vector determining unit, configured to match a first kernel function from candidate kernel functions according to the first data, and perform dimension mapping on the first data according to the first kernel function to obtain a first feature vector; a second eigenvector determining unit, configured to match a second kernel function from the candidate kernel functions according to the second data, and perform dimension mapping on the second data according to the second kernel function to obtain a second eigenvector; The first feature data determining unit is configured to perform weighted summation on the first feature vector and the second feature vector to obtain a first feature matrix.
9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, 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 vehicle power battery temperature warning method according to any one of claims 1 to 6.
10. 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 vehicle power battery temperature warning method according to any one of claims 1 to 6 when executed.