Methods, devices, electronic equipment, and storage media for predicting the operating conditions of automotive batteries
By combining historical and real-time data using a Markov chain model, the problem of inaccurate battery condition prediction in existing technologies is solved, achieving accurate prediction of battery conditions and reducing the time required.
Patent Information
- Application Number
- CN202210923731.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-08-02
- Publication Date
- 2025-11-14
- Estimated Expiration
- 2042-08-02
AI Technical Summary
Existing automotive battery condition prediction methods have long prediction times and cannot accurately predict actual changes in battery conditions during normal use. They also ignore changes in battery terminal voltage under actual vehicle conditions, resulting in inaccurate prediction results.
A Markov chain model is used to combine historical and real-time driving data. A state space for predicting operating conditions is constructed through smoothing and cluster analysis. The Markov chain model is then used to predict battery operating conditions, including data filtering, clustering, and calculation of the state transition probability matrix.
It enables accurate prediction of vehicle battery operating conditions, shortens prediction time, and improves the accuracy of prediction results.
Smart Images
Figure CN115270481B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of battery technology, and more specifically, to a method, apparatus, electronic device, and computer-readable storage medium for predicting the operating conditions of an automotive battery. Background Technology
[0002] Most current methods for predicting the operating conditions of automotive batteries are defined as predicting the power state of the battery. This method refers to the maximum power that the power battery can release or absorb under different constraints (voltage, SOC, temperature, and available capacity, etc.) within a predetermined time interval. It is mainly used to evaluate the ultimate capabilities of the power battery. The goal is to optimally match the relationship between the power battery system and the vehicle's power performance in order to meet the acceleration and climbing performance of electric vehicles and maximize the regenerative braking performance of the motor.
[0003] However, this prediction method has several drawbacks. For example, it only assesses the battery's maximum power capacity under extreme conditions such as acceleration, hill climbing, and regenerative braking, while ignoring the changes in the battery's voltage under the actual operating conditions of the vehicle during normal use. The prediction time is relatively long, and as time progresses, the information in the historical-current time domain becomes richer, while the future prediction time domain gradually shortens, making accurate prediction impossible. Summary of the Invention
[0004] The purpose of this application is to provide a method, apparatus, electronic device, and computer-readable storage medium for predicting the operating condition of an automotive battery, which can accurately predict the operating condition of the automotive battery, shorten the prediction time, and make the prediction results more accurate.
[0005] In a first aspect, embodiments of this application provide a method for predicting the operating conditions of an automotive battery, the method comprising:
[0006] Obtain the historical driving data and real-time driving data of the vehicle battery;
[0007] Based on the historical driving data, predictive state space data for operating conditions is obtained.
[0008] A Markov chain model is constructed based on the real-time driving data and the predicted state space data of the operating conditions.
[0009] Battery operating conditions are predicted based on the Markov chain model, and the prediction results are obtained.
[0010] In the above implementation process, the operating condition prediction state space data is obtained based on historical driving data, and then a Markov chain model is constructed based on real-time driving data and operating condition prediction state space data. This enables the Markov chain model to accurately express the state of the battery, accurately predict the operating condition of the car battery, shorten the prediction time, and make the prediction results more accurate.
[0011] Furthermore, the step of obtaining the operating condition prediction state space data based on the historical driving data includes:
[0012] The historical driving data is smoothed to obtain smoothed historical driving data;
[0013] Clustering is performed on the smoothed historical driving data to obtain the working condition prediction state space data.
[0014] In the above implementation process, the historical driving data is smoothed to reduce the error generated during the clustering process, making the obtained working condition prediction state space data more accurate.
[0015] Further, the step of constructing a Markov chain model based on the real-time driving data and the working condition prediction state space data includes:
[0016] The real-time driving data is filtered to obtain data sample points;
[0017] Obtain the initial state space with the smallest distance from the center of each state space in the predicted state space data of the working condition;
[0018] The data sample points are distributed into the initial state space to obtain the state space;
[0019] The Markov chain model is constructed based on the state space.
[0020] In the above implementation process, the data sample points are distributed into the initial state space so that the resulting state space can represent the distribution of the data sample points, and better reflect the state of the battery in the Markov chain model.
[0021] Further, the step of constructing the Markov chain model based on the state space includes:
[0022] Obtain the discharge time of the car battery;
[0023] The power change data during the discharge process of the vehicle battery is obtained based on the discharge time;
[0024] A power state sequence is obtained based on the power change data and the state space;
[0025] The Markov chain model is constructed based on the power state sequence.
[0026] In the above implementation process, power change data is obtained based on the discharge time, and then the power state sequence is obtained based on the power change data and the state space, so that the constructed Markov chain model can include the situation of power change.
[0027] Further, the step of predicting battery operating conditions based on the Markov chain model to obtain the prediction result includes:
[0028] Obtain the state transition data of the state space;
[0029] The transition data is input into the Markov chain model to obtain the state transition probability matrix;
[0030] The power prediction value is obtained based on the state transition probability matrix;
[0031] The predicted battery operating condition is obtained based on the predicted power value.
[0032] In the above implementation process, the power prediction value is obtained based on the state transition probability matrix, which makes the prediction result more accurate and can effectively shorten the prediction time.
[0033] Secondly, embodiments of this application also provide a device for predicting the operating condition of an automotive battery, the device comprising:
[0034] The acquisition module is used to acquire historical driving data and real-time driving data of the vehicle battery.
[0035] The data acquisition module is used to obtain the operating condition prediction state space data based on the historical driving data;
[0036] The module is used to construct a Markov chain model based on the real-time driving data and the working condition prediction state space data;
[0037] The prediction module is used to predict battery operating conditions based on the Markov chain model and obtain the prediction results.
[0038] In the above implementation process, the operating condition prediction state space data is obtained based on historical driving data, and then a Markov chain model is constructed based on real-time driving data and operating condition prediction state space data. This enables the Markov chain model to accurately express the state of the battery, accurately predict the operating condition of the car battery, shorten the prediction time, and make the prediction results more accurate.
[0039] Furthermore, the data acquisition module is also used for:
[0040] The historical driving data is smoothed to obtain smoothed historical driving data;
[0041] Clustering is performed on the smoothed historical driving data to obtain the working condition prediction state space data.
[0042] In the above implementation process, the historical driving data is smoothed to reduce the error generated during the clustering process, making the obtained working condition prediction state space data more accurate.
[0043] Furthermore, the building module is also used for:
[0044] The real-time driving data is filtered to obtain data sample points;
[0045] Obtain the initial state space with the smallest distance from the center of each state space in the predicted state space data of the working condition;
[0046] The data sample points are distributed into the initial state space to obtain the state space;
[0047] The Markov chain model is constructed based on the state space.
[0048] In the above implementation process, the data sample points are distributed into the initial state space so that the resulting state space can represent the distribution of the data sample points, and better reflect the state of the battery in the Markov chain model.
[0049] Thirdly, an electronic device provided in this application includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method as described in any of the first aspects.
[0050] Fourthly, embodiments of this application provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method described in any of the first aspects.
[0051] Fifthly, embodiments of this application provide a computer program product that, when run on a computer, causes the computer to perform the method described in any of the first aspects.
[0052] Other features and advantages of this disclosure will be set forth in the following description, or some features and advantages may be inferred from the description or determined without doubt, or may be learned by practicing the techniques described above.
[0053] It can be implemented in accordance with the contents of the specification. The preferred embodiments of this application are described in detail below with reference to the accompanying drawings. Attached Figure Description
[0054] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0055] Figure 1 A flowchart illustrating the method for predicting the operating conditions of an automotive battery provided in an embodiment of this application;
[0056] Figure 2 A schematic diagram illustrating the structural composition of the vehicle battery condition prediction device provided in this application embodiment;
[0057] Figure 3 This is a schematic diagram of the structural composition of the electronic device provided in the embodiments of this application. Detailed Implementation
[0058] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.
[0059] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0060] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are used to illustrate this application, but are not intended to limit the scope of this application.
[0061] Example 1
[0062] Figure 1 This is a flowchart illustrating the method for predicting the operating conditions of an automotive battery provided in an embodiment of this application. Figure 1 As shown, the method includes:
[0063] S1, acquire historical and real-time driving data of the vehicle battery;
[0064] S2, obtains the working condition prediction state space data based on historical driving data;
[0065] S3, construct a Markov chain model based on real-time driving data and working condition prediction state space data;
[0066] S4. Battery operating conditions are predicted based on the Markov chain model, and the prediction results are obtained.
[0067] In the above implementation process, the operating condition prediction state space data is obtained based on historical driving data, and then a Markov chain model is constructed based on real-time driving data and operating condition prediction state space data. This enables the Markov chain model to accurately express the state of the battery, accurately predict the operating condition of the car battery, shorten the prediction time, and make the prediction results more accurate.
[0068] In S1, historical driving data and real-time driving data are acquired. For example, historical driving data and real-time driving data are data obtained according to time periods. Real-time driving data is acquired in the current period, and historical driving data is acquired in the previous time period. As time changes continuously, after a time period, real-time driving data becomes historical driving data.
[0069] Furthermore, S2 includes:
[0070] Smooth the historical driving data to obtain smoothed historical driving data;
[0071] Clustering is performed on the smoothed historical driving data to obtain the state space data for driving condition prediction.
[0072] In the above implementation process, the historical driving data is smoothed to reduce the error generated during the clustering process, making the obtained working condition prediction state space data more accurate.
[0073] The method in this application embodiment is based on the cumulative historical power data, i.e., historical driving data, of the driving cycle on the electric vehicle. After first-order inertial data filtering, the fuzzy C-means clustering algorithm is used to automatically identify the types and quantities of states to obtain the operating condition prediction state space data, and the operating condition prediction state space data is applied to the operating condition prediction of the current driving cycle. If there is no historical data for the first run, a default initial operating condition prediction state needs to be set (based on experience).
[0074] First, the historical driving data is smoothed using a first-order inertial filter. For ease of engineering implementation, the discrete first-order inertial filter model is adopted as follows:
[0075]
[0076] Where x(n) is the actual sampled value at the current time, y(n-1) is the filtered value at the previous time, y(n) is the filtered value at the current time, and T s Where τ is the sampling frequency, and RC is the time constant of the first-order inertial filter.
[0077] Then, the filtered historical driving data is clustered using the fuzzy C-means clustering algorithm to automatically identify the states it contains, thereby obtaining the state space data for driving condition prediction.
[0078] Fuzzy C-means clustering is an algorithm that uses membership degree to determine the degree of clustering: the similarity between sample points is represented by the square of the Euclidean distance, the category is represented by the cluster center, and the sum of the distances between a sample point and its center is used as the optimization objective function.
[0079] For example, assuming that the historical driving data of a certain driving cycle covers the power battery discharge power from 0kW to 80kW, then according to the vehicle application scenario and the characteristics of the power battery, the clustering algorithm can be used to obtain a set of state spaces divided into four states: A, B, C, and D.
[0080] Table 1 State Space Set
[0081]
[0082]
[0083] Furthermore, S3 includes:
[0084] Data sample points are obtained by filtering the real-time driving data.
[0085] Obtain the initial state space with the smallest distance from the center of each state space in the working condition prediction state space data;
[0086] The data sample points are distributed into the initial state space to obtain the state space;
[0087] Construct a Markov chain model based on the state space.
[0088] In the above implementation process, the data sample points are distributed into the initial state space so that the resulting state space can represent the distribution of the data sample points, and better reflect the state of the battery in the Markov chain model.
[0089] Predictive state-space data refers to dividing the battery operating conditions into several states based on the actual operating scenarios of electric vehicles, and assuming that the battery is in the same state within the target time scale. As the battery discharges, the battery's discharge power will jump between the various states in the state space.
[0090] For each data sample point, the K-means clustering algorithm is applied to assign each data sample point to the state in the predicted state space data that has the smallest distance to the center of each state, which is then used as the initial state space. The objective function of the K-means clustering algorithm is:
[0091]
[0092] Where k is the number of state categories in the state-space data for load condition prediction, x iFor data sample points, m l The center point for different state categories.
[0093] Furthermore, the steps for constructing a Markov chain model based on the state space include:
[0094] Obtain the discharge time of the car battery;
[0095] Data on power changes during the discharge process of a car battery are obtained based on the discharge time.
[0096] The power state sequence is obtained based on power change data and state space;
[0097] Construct a Markov chain model based on the power state sequence.
[0098] In the above implementation process, power change data is obtained based on the discharge time, and then the power state sequence is obtained based on the power change data and the state space, so that the constructed Markov chain model can include the situation of power change.
[0099] Real-time battery characteristic data (voltage, current, temperature, and remaining charge (SOC), etc.) are collected and smoothed using first-order inertial filtering. The average power is calculated based on a set prediction target time scale (e.g., predicting a power value every 2 minutes). Then, a K-means clustering algorithm is used to determine which state in the operating condition prediction state space the current average power belongs to. This process continues, and a power state sequence is obtained as the discharge time increases. When the power state sequence reaches a certain sample size (determined based on operating condition coverage testing), a Markov chain model for operating condition prediction and the corresponding state transition probability matrix can be obtained.
[0100] Furthermore, S4 includes:
[0101] Obtain the state transition data in the state space;
[0102] Input the transition data into the Markov chain model to obtain the state transition probability matrix;
[0103] The predicted power value is obtained based on the state transition probability matrix;
[0104] The predicted battery operating conditions are obtained based on the predicted power values.
[0105] In the above implementation process, the power prediction value is obtained based on the state transition probability matrix, which makes the prediction result more accurate and can effectively shorten the prediction time.
[0106] As the discharge time increases, multiple real-time driving data points can be obtained, resulting in multiple state spaces. These state spaces are then constructed based on the corresponding power change data. When the power state sequence reaches a certain sample size, a Markov chain model can be obtained, and different states transition to each other with certain probabilities. The state transition data of the state space during this process can be obtained, and the corresponding state transition probability matrix can be derived from the state transition data.
[0107] For example, in a Markov chain model, if the power battery discharge power was in state i in the previous calculation cycle, and it moves to state j at the current moment, then the transition probability is denoted as:
[0108] p ij (X t =i|X t-1 = j), i = A, B, C, D; j = A, B, C, D;
[0109] And satisfy p ij ≥0, ∑ i p ij =1, represented by a matrix, that is:
[0110]
[0111] Based on the data sample points and state transition probability matrix of the current time period, the predicted power value for the next time period can be:
[0112] X′ t+1 =P*X t ;
[0113] As the discharge proceeds, the time period changes continuously, and the measured power value X can be obtained from the real-time data. t+1 Meanwhile, the predicted value is compared with the measured value, and the error tolerance threshold is assumed to be δ.
[0114] If |X t+1 -X′ t+1 If | ≤ δ, then continue to update the current power state sequence with the measured values and make predictions for the next time period; if |X t+1 -X′ t+1 If |>δ, it indicates that the actual operating conditions have changed significantly and the current Markov chain model is not applicable to the new operating conditions. Therefore, the operating condition prediction is paused, a new Markov chain model is reconstructed, and then the new model is used for operating condition prediction. This process is repeated.
[0115] Example 2
[0116] To implement the method corresponding to Embodiment 1 above and achieve the corresponding functions and technical effects, a vehicle battery operating condition prediction device is provided below, such as... Figure 2 As shown, the device includes:
[0117] Module 1 is used to acquire historical and real-time driving data of the vehicle battery.
[0118] Data acquisition module 2 is used to obtain working condition prediction state space data based on historical driving data;
[0119] Module 3 is used to build a Markov chain model based on real-time driving data and working condition prediction state space data;
[0120] Prediction module 4 is used to predict battery operating conditions based on the Markov chain model and obtain the prediction results.
[0121] In the above implementation process, the operating condition prediction state space data is obtained based on historical driving data, and then a Markov chain model is constructed based on real-time driving data and operating condition prediction state space data. This enables the Markov chain model to accurately express the state of the battery, accurately predict the operating condition of the car battery, shorten the prediction time, and make the prediction results more accurate.
[0122] Furthermore, data acquisition module 2 is also used for:
[0123] Smooth the historical driving data to obtain smoothed historical driving data;
[0124] Clustering is performed on the smoothed historical driving data to obtain the state space data for driving condition prediction.
[0125] In the above implementation process, the historical driving data is smoothed to reduce the error generated during the clustering process, making the obtained working condition prediction state space data more accurate.
[0126] Furthermore, Module 3 is also used for:
[0127] Data sample points are obtained by filtering the real-time driving data.
[0128] Obtain the initial state space with the smallest distance from the center of each state space in the working condition prediction state space data;
[0129] The data sample points are distributed into the initial state space to obtain the state space;
[0130] Construct a Markov chain model based on the state space.
[0131] In the above implementation process, the data sample points are distributed into the initial state space so that the resulting state space can represent the distribution of the data sample points, and better reflect the state of the battery in the Markov chain model.
[0132] Furthermore, Module 3 is also used for:
[0133] Obtain the discharge time of the car battery;
[0134] Data on power changes during the discharge process of a car battery are obtained based on the discharge time.
[0135] The power state sequence is obtained based on power change data and state space;
[0136] Construct a Markov chain model based on the power state sequence.
[0137] Furthermore, prediction module 4 is also used for:
[0138] Obtain the state transition data in the state space;
[0139] Input the transition data into the Markov chain model to obtain the state transition probability matrix;
[0140] The predicted power value is obtained based on the state transition probability matrix;
[0141] The predicted battery operating conditions are obtained based on the predicted power values.
[0142] The aforementioned vehicle battery operating condition prediction device can implement the method of Embodiment 1. The options in Embodiment 1 also apply to this embodiment, and will not be described in detail here.
[0143] The remaining contents of this embodiment can be referred to the contents of Embodiment 1 above, and will not be repeated in this embodiment.
[0144] Example 3
[0145] This application provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor runs the computer program to enable the electronic device to perform the automotive battery condition prediction method of Embodiment 1.
[0146] Alternatively, the aforementioned electronic device may be a server.
[0147] Please see Figure 3 , Figure 3 This is a schematic diagram illustrating the structural composition of an electronic device provided in an embodiment of this application. The electronic device may include a processor 31, a communication interface 32, a memory 33, and at least one communication bus 34. The communication bus 34 is used to enable direct communication between these components. In this embodiment, the communication interface 32 is used for signaling or data communication with other node devices. The processor 31 may be an integrated circuit chip with signal processing capabilities.
[0148] The processor 31 described above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor, or the processor 31 can be any conventional processor.
[0149] The memory 33 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc. The memory 33 stores computer-readable instructions. When these computer-readable instructions are executed by the processor 31, the device can perform the aforementioned operations. Figure 1 The various steps involved in the method implementation examples.
[0150] Optionally, the electronic device may also include a storage controller and an input / output unit. The memory 33, storage controller, processor 31, peripheral interface, and input / output unit are electrically connected directly or indirectly to each other to achieve data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses 34. The processor 31 is used to execute executable modules stored in the memory 33, such as software function modules or computer programs included in the device.
[0151] Input / output units are used to enable users to create tasks and set optional start periods or preset execution times for those tasks, facilitating user-server interaction. Input / output units can be, but are not limited to, a mouse and keyboard.
[0152] Understandable. Figure 3 The structure shown is for illustrative purposes only; the electronic device may also include components that are more advanced than those shown. Figure 3 The more or fewer components shown, or having the same Figure 3 The different configurations shown. Figure 3The components shown can be implemented using hardware, software, or a combination thereof.
[0153] In addition, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for predicting the operating conditions of an automotive battery according to Embodiment 1.
[0154] This application also provides a computer program product that, when run on a computer, causes the computer to perform the method described in the method embodiment.
[0155] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using dedicated hardware-based apparatus that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
[0156] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.
[0157] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, external hard drives, ROM, RAM, magnetic disks, or optical disks.
[0158] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.
[0159] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
[0160] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
Claims
1. A method for predicting the operating conditions of an automotive battery, characterized in that, The method includes: Obtain the historical driving data and real-time driving data of the vehicle battery; Based on the historical driving data, predictive state space data for operating conditions is obtained. A Markov chain model is constructed based on the real-time driving data and the predicted state space data of the operating conditions. Battery operating conditions are predicted based on the Markov chain model, and the prediction results are obtained. The step of constructing a Markov chain model based on the real-time driving data and the working condition prediction state space data includes: The real-time driving data is filtered to obtain data sample points; Obtain the initial state space with the smallest distance from the center of each state space in the predicted state space data of the working condition; The data sample points are distributed into the initial state space to obtain the target state space; Construct the Markov chain model based on the target state space; The step of obtaining the operating condition prediction state space data based on the historical driving data includes: The historical driving data is smoothed to obtain smoothed historical driving data; Clustering is performed on the smoothed historical driving data to obtain the working condition prediction state space data; The step of constructing the Markov chain model based on the target state space includes: Obtain the discharge time of the car battery; The power change data during the discharge process of the vehicle battery is obtained based on the discharge time; A power state sequence is obtained based on the power change data and the target state space; Construct the Markov chain model based on the power state sequence; The step of predicting battery operating conditions based on the Markov chain model and obtaining the prediction result includes: Obtain the state transition data of the target state space; The state transition data is input into the Markov chain model to obtain the state transition probability matrix; The power prediction value is obtained based on the state transition probability matrix; The predicted battery operating condition is obtained based on the predicted power value.
2. A device for predicting the operating condition of an automotive battery, characterized in that, The device includes: The acquisition module is used to acquire historical driving data and real-time driving data of the vehicle battery; The data acquisition module is used to obtain the operating condition prediction state space data based on the historical driving data; The module is used to construct a Markov chain model based on the real-time driving data and the working condition prediction state space data; The prediction module is used to predict battery operating conditions based on the Markov chain model and obtain the prediction results. The building module is also used for: The real-time driving data is filtered to obtain data sample points; Obtain the initial state space with the smallest distance from the center of each state space in the predicted state space data of the working condition; The data sample points are distributed into the initial state space to obtain the target state space; Construct the Markov chain model based on the target state space; The data acquisition module is also used for: The historical driving data is smoothed to obtain smoothed historical driving data; Clustering is performed on the smoothed historical driving data to obtain the working condition prediction state space data; The building module is also used for: Obtain the discharge time of the car battery; The power change data during the discharge process of the vehicle battery is obtained based on the discharge time; A power state sequence is obtained based on the power change data and the target state space; Construct the Markov chain model based on the power state sequence; The prediction module is also used for: Obtain the state transition data of the target state space; The state transition data is input into the Markov chain model to obtain the state transition probability matrix; The power prediction value is obtained based on the state transition probability matrix; The predicted battery operating condition is obtained based on the predicted power value.
3. An electronic device, characterized in that, The device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to enable the electronic device to perform the automotive battery condition prediction method according to claim 1.
4. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the automotive battery condition prediction method as described in claim 1.