Vehicle motor system efficiency prediction method, system, device and medium
By generating nonlinear features and using random forest algorithms to train the motor system efficiency prediction model, the problem of insufficient accuracy and reliability of motor system efficiency prediction in the prior art is solved, and more efficient motor system efficiency prediction and vehicle energy consumption optimization are achieved.
Patent Information
- Application Number
- CN202510294902.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-12
- Publication Date
- 2025-06-20
AI Technical Summary
When the prior art predicts the efficiency of motor systems of new energy vehicles, it is difficult to accurately express complex nonlinear relationships, resulting in insufficient accuracy and reliability of the prediction results.
By obtaining motor running data, nonlinear features are generated, a large-contribution feature set is selected, and a random forest algorithm is used to train the motor system efficiency prediction model, and the motor speed and torque are input to predict the motor system efficiency.
It improves the accuracy and reliability of motor system efficiency prediction, can more accurately evaluate vehicle energy consumption, optimize operational efficiency and support personalized services.
Smart Images
Figure CN120180092A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of vehicles, and particularly to a method, system, device and medium for predicting the efficiency of a motor system of a vehicle. Background Art
[0002] In the rapid development process of new energy vehicles, the optimization of the motor system efficiency has become an important research direction for driving behavior analysis. The motor system efficiency of vehicles such as new energy heavy truck models is comprehensively affected by many complex factors, and the non-linear interaction between speed and torque has a particularly significant impact on the motor system efficiency. At present, the existing technologies mainly adopt linear modeling methods, lacking sufficient expression ability for these complex non-linear relationships, resulting in insufficient accuracy and reliability of the motor efficiency prediction results.
[0003] In addition, when the existing models process data in the high-efficiency region, they usually allocate insufficient weights to the data in these key regions and fail to fully explore the characteristics of the high-efficiency region, which further limits the performance of the models in practical applications. At the same time, with the explosive growth of vehicle data, the existing data processing and model training technologies fail to efficiently adapt to the big data distributed computing environment, restricting the large-scale application of the motor system efficiency calculation. Summary of the Invention
[0004] Based on this, in view of the above technical problems, it is necessary to provide a method, system, device and medium for predicting the efficiency of a motor system of a vehicle, obtain the motor speed and torque of the vehicle, and input the motor speed and torque into a pre-trained motor system efficiency prediction model to obtain the motor system efficiency predicted by the motor system efficiency prediction model. Since the motor system efficiency prediction model is trained by using non-linear features extracted from motor operation data, etc., it has the advantages of high accuracy and high reliability of the motor system efficiency prediction results.
[0005] In a first aspect, a training method for a motor system efficiency prediction model is provided, including:
[0006] Obtain motor operation data, where the motor operation data includes motor speed, torque and motor efficiency, and repeatedly add the motor operation data in the high-efficiency region;
[0007] Generate non-linear features according to the motor operation data, where the non-linear features include the square of the motor speed, the square of the torque and the interaction term of the speed and the torque;
[0008] Based on the contribution index, screen the non-linear features to obtain a feature set;
[0009] Set parameters, and train the motor system efficiency prediction model using the random forest algorithm according to the set parameters. Among them, the trained motor system efficiency prediction model takes the motor speed and torque as inputs and the motor efficiency as the prediction result.
[0010] In some examples, based on the contribution index, filter the non-linear features to obtain a feature set, including:
[0011] Evaluate the importance of non-linear features through information gain to filter out features whose contribution to the target variable is greater than a predetermined index, and obtain the feature set.
[0012] In some examples, the setting of parameters and the training of the motor system efficiency prediction model using the random forest algorithm according to the set parameters include:
[0013] Set parameters, where the set parameters include the number of trees, the maximum depth, the number of random features, and the random seed;
[0014] Use the random forest algorithm to train the motor system efficiency prediction model, and use the grid search method to optimize the hyperparameters to select the parameter combination with the best performance.
[0015] In some examples, after the trained motor system efficiency prediction model, it further includes:
[0016] Adopt 10-fold cross-validation to evaluate the performance of the motor system efficiency prediction model.
[0017] In some examples, it further includes:
[0018] When the performance of the motor system efficiency prediction model does not meet the requirements, fine-tune the motor system efficiency prediction model again until the performance of the motor system efficiency prediction model meets the requirements.
[0019] In a second aspect, a method for predicting the efficiency of a motor system of a vehicle is provided, including:
[0020] Obtain the motor speed and torque of the vehicle;
[0021] Input the motor speed and torque into a pre-trained motor system efficiency prediction model to obtain the motor system efficiency predicted by the motor system efficiency prediction model, where the motor system efficiency prediction model is a motor system efficiency prediction model trained according to the training method of the motor system efficiency prediction model described in the first aspect above.
[0022] In a third aspect, a system for predicting the efficiency of a motor system of a vehicle is provided, including:
[0023] An acquisition module for obtaining the motor speed and torque of the vehicle;
[0024] A prediction module, configured to input the motor speed and torque into a pre-trained motor system efficiency prediction model to obtain the motor system efficiency predicted by the motor system efficiency prediction model, where the motor system efficiency prediction model is a motor system efficiency prediction model trained according to the training method of the motor system efficiency prediction model described in the first aspect above. Fourth aspect, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the vehicle's motor system efficiency prediction method in the second aspect above are implemented.
[0025] Fifth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the steps of the vehicle's motor system efficiency prediction method in the second aspect above are implemented.
[0026] Sixth aspect, a computer program product is provided, on which a computer program is stored. When the program is executed by a processor, the steps of the vehicle's motor system efficiency prediction method in the second aspect above are implemented.
[0027] By adopting the embodiments of the present application, the motor speed and torque of the vehicle are obtained, and the motor speed and torque are input into a pre-trained motor system efficiency prediction model to obtain the motor system efficiency predicted by the motor system efficiency prediction model. Since the motor system efficiency prediction model is trained by using non-linear features extracted from motor operation data, etc., therefore, it has the advantages of high accuracy and high reliability of the motor system efficiency prediction result. Description of the Drawings
[0028] By reading the detailed description of the non-restrictive embodiments with reference to the following drawings, other features, objects, and advantages of the present application will become more obvious:
[0029] Figure 1 It is a flowchart of the training of the motor system efficiency prediction model provided by the embodiment of the present application;
[0030] Figure 2 It is an application schematic diagram of the vehicle's motor system efficiency prediction method provided by the embodiment of the present application;
[0031] Figure 3 It is a structural block diagram of the vehicle's motor system efficiency prediction system provided by the embodiment of the present application;
[0032] Figure 4 It is a structural block diagram of the computer device provided by the embodiment of the present application. Detailed Embodiments
[0033] The present application will be further described in detail below in conjunction with embodiments and the accompanying drawings. It can be understood that the specific embodiments described herein are only used to explain the related application, rather than limiting the application. Additionally, it should be noted that for the convenience of description, only the parts related to the application are shown in the drawings.
[0034] It should be noted that, without conflict, the embodiments and features of the embodiments in the present application can be combined with each other. The present application will be described in detail below with reference to the drawings and in conjunction with embodiments.
[0035] The method, system, device, and medium for predicting the efficiency of the motor system of a vehicle according to an embodiment of the present application will be described in detail below with reference to the drawings.
[0036] Figure 1 is a flowchart of a method for training a motor system efficiency prediction model according to an embodiment of the present application. As Figure 1 shown, the method for training a motor system efficiency prediction model according to an embodiment of the present application includes the following steps:
[0037] S101: Obtain motor operation data, where the motor operation data includes motor speed, torque, and motor efficiency, and repeatedly add the motor operation data in the high-efficiency region.
[0038] S102: Generate non-linear features according to the motor operation data, where the non-linear features include the square of the motor speed, the square of the torque, and the interaction term of the speed and the torque.
[0039] S103: Screen the non-linear features based on the contribution index to obtain a feature set.
[0040] In an embodiment of the present application, screening the non-linear features based on the contribution index to obtain a feature set includes: evaluating the importance of the non-linear features through information gain to screen out the features whose contribution to the target variable is greater than a predetermined index to obtain the feature set.
[0041] S104: Set parameters, and according to the set parameters, use the random forest algorithm to train the motor system efficiency prediction model, where the trained motor system efficiency prediction model takes the motor speed and torque as inputs and the motor efficiency as the prediction result.
[0042] In an embodiment of the present application, setting the parameters and using the random forest algorithm to train the motor system efficiency prediction model according to the set parameters includes: setting parameters, where the set parameters include the number of trees, the maximum depth, the number of random features, and the random seed; using the random forest algorithm to train the motor system efficiency prediction model, and using the grid search method to optimize the hyperparameters and select the parameter combination with the best performance.
[0043] In one embodiment of the present application, after the trained motor system efficiency prediction model, it further includes: evaluating the performance of the motor system efficiency prediction model using 10-fold cross-validation.
[0044] In one embodiment of the present application, the training method of the motor system efficiency prediction model further includes: when the performance of the motor system efficiency prediction model does not meet the requirements, fine-tuning the motor system efficiency prediction model again until the performance of the motor system efficiency prediction model meets the requirements.
[0045] As a specific example, in combination with Figure 2 as shown, the training process is as follows:
[0046] 1. Data loading and preprocessing:
[0047] Use the operating data recorded through motor calibration and experiments, including key variables such as speed, torque, and motor efficiency, as the data set.
[0048] Generate non-linear features, including the square of speed, the square of torque, and the interaction term of speed and torque.
[0049] Repeat adding data in the high-efficiency region to balance the data distribution and improve the sensitivity of the model to the high-efficiency region.
[0050] 2. Non-linear feature enhancement:
[0051] Feature generation: Construct non-linear features based on speed and torque, including interaction terms, square terms, etc.
[0052] Feature screening: Evaluate the importance of features through information gain, and screen the feature set that contributes the most to the target variable.
[0053] 3. Model construction and training:
[0054] Use the random forest algorithm for model training, and set parameters such as the number of trees (100), the maximum depth (10), the number of random features (3), and the random seed (42).
[0055] Use the grid search method to optimize the hyperparameters and select the parameter combination with the best performance.
[0056] Adopt 10-fold cross-validation to evaluate the model performance.
[0057] 4. Big data encapsulation:
[0058] Use the big data distributed database to encapsulate the algorithms for generating features such as the square of speed, the square of torque, and interaction terms as the calculation model to improve the calculation performance of the motor system efficiency.
[0059] After training the motor system efficiency prediction model, an embodiment of the present application further provides a method for predicting the motor system efficiency of a vehicle. The method includes: obtaining the motor speed and torque of the vehicle; inputting the motor speed and torque into a pre-trained motor system efficiency prediction model to obtain the motor system efficiency predicted by the motor system efficiency prediction model, where the motor system efficiency prediction model is a motor system efficiency prediction model trained according to the training method of the motor system efficiency prediction model described in the above embodiment.
[0060] Combined with Figure 2 As shown, after training the motor system efficiency prediction model, for new motor speed and torque data on the vehicle, corresponding non-linear features are generated and instances are constructed, and then the motor system efficiency prediction model trained by the random forest algorithm is used to predict the motor system efficiency.
[0061] According to the method for predicting the motor system efficiency of a vehicle in an embodiment of the present application, the motor speed and torque of the vehicle are obtained, and the motor speed and torque are input into a pre-trained motor system efficiency prediction model to obtain the motor system efficiency predicted by the motor system efficiency prediction model. Since the motor system efficiency prediction model is trained using non-linear features extracted from motor operation data, etc., it has the advantages of high accuracy and high reliability in the prediction result of the motor system efficiency.
[0062] In an embodiment of the present application, based on the random forest algorithm and non-linear feature enhancement technology, the accuracy and reliability of the motor system efficiency prediction of vehicles such as new energy heavy truck vehicles are significantly improved, and it plays an important role in optimizing operation efficiency, supporting personalized services, and strengthening energy consumption management in high-efficiency regions. By accurately evaluating the vehicle energy consumption, the embodiments of the present application can help optimize driving routes, loading configurations, and scheduling strategies, achieve energy conservation and emission reduction goals, and contribute to the development of green logistics. At the same time, it can be deeply integrated with the vehicle networking platform to provide customized click efficiency reports and driving energy consumption optimization suggestions, evaluate driving behaviors, and promote the intelligent and green process of the logistics transportation industry.
[0063] In addition, the modeling ability for the non-linear relationship between speed and torque is effectively improved. By repeatedly adding data in the high-efficiency region, the prediction ability of the model for the high-efficiency region is significantly enhanced. A motor system efficiency prediction calculation model adapted to the distributed computing framework and suitable for real-time and offline processing and analysis of large-scale data is developed. It can be extended to other vehicle performance prediction tasks and provides a reliable solution for energy consumption optimization in driving behavior analysis.
[0064] Figure 3 is a structural block diagram of a motor system efficiency prediction system of a vehicle according to an embodiment of the present application. As Figure 3As shown, the motor system efficiency prediction system of a vehicle according to an embodiment of the present application includes: an acquisition module 310 and a prediction module 320, where:
[0065] The acquisition module 310 is configured to obtain the motor speed and torque of the vehicle;
[0066] The prediction module 320 is configured to input the motor speed and torque into a pre-trained motor system efficiency prediction model to obtain the motor system efficiency predicted by the motor system efficiency prediction model, where the motor system efficiency prediction model is a motor system efficiency prediction model trained according to the training method of the motor system efficiency prediction model according to any one of claims 1-4.
[0067] The motor system efficiency prediction system of a vehicle according to an embodiment of the present application obtains the motor speed and torque of the vehicle, inputs the motor speed and torque into a pre-trained motor system efficiency prediction model, and obtains the motor system efficiency predicted by the motor system efficiency prediction model. Since the motor system efficiency prediction model is trained by using non-linear features extracted from motor operation data, etc., it has the advantages of high accuracy and high reliability of the motor system efficiency prediction result.
[0068] In the embodiments of the present application, based on the random forest algorithm and the non-linear feature enhancement technology, the accuracy and reliability of the motor system efficiency prediction of vehicles such as new energy heavy truck vehicles are significantly improved, and it plays an important role in optimizing operation efficiency, supporting personalized services, and strengthening high-efficiency regional energy consumption management. By accurately evaluating the vehicle energy consumption, the embodiments of the present application can help optimize driving routes, loading configurations, and scheduling strategies, achieve energy conservation and emission reduction goals, and contribute to the development of green logistics. At the same time, it can be deeply integrated with the vehicle networking platform to provide customized click efficiency reports and driving energy consumption optimization suggestions, evaluate driving behaviors, and promote the intelligent and green process of the logistics transportation industry.
[0069] For the specific limitations on the motor system efficiency prediction system of the vehicle, reference can be made to the limitations on the motor system efficiency prediction method of the vehicle described above, which will not be elaborated here. Each module of the above-mentioned motor system efficiency prediction system of the vehicle can be implemented in whole or in part by software, hardware, and their combinations. The above-mentioned each module can be embedded in the processor of the computer device in the form of hardware or independent of it, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned each module.
[0070] In one embodiment, a computer device is provided. Figure 4 This is the structural block diagram of the computer device provided in the embodiments of the present application. Refer to Figure 4The computer device includes a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the embodiments of the method for predicting the efficiency of the motor system of the vehicle described above are implemented. For example, it performs: obtaining the motor speed and torque of the vehicle; inputting the motor speed and torque into a pre-trained motor system efficiency prediction model to obtain the motor system efficiency predicted by the motor system efficiency prediction model, where the motor system efficiency prediction model is a motor system efficiency prediction model trained according to the training method of the motor system efficiency prediction model described in the above embodiments.
[0071] In an embodiment of the present application, there is also provided a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the processor executes the computer program, the embodiments of the method for predicting the efficiency of the motor system of the vehicle described above are implemented. For example, it performs: obtaining the motor speed and torque of the vehicle; inputting the motor speed and torque into a pre-trained motor system efficiency prediction model to obtain the motor system efficiency predicted by the motor system efficiency prediction model, where the motor system efficiency prediction model is a motor system efficiency prediction model trained according to the training method of the motor system efficiency prediction model described in the above embodiments.
[0072] In an embodiment of the present application, there is provided a computer program product. The computer program product includes instructions. When the instructions are run, the method described in the embodiments of the present application is executed. For example, it can execute Figure 1 each step of the method for predicting the efficiency of the motor system of the vehicle shown, for example, it performs: obtaining the motor speed and torque of the vehicle; inputting the motor speed and torque into a pre-trained motor system efficiency prediction model to obtain the motor system efficiency predicted by the motor system efficiency prediction model, where the motor system efficiency prediction model is a motor system efficiency prediction model trained according to the training method of the motor system efficiency prediction model described in the above embodiments.
[0073] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.
[0074] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.
[0075] The above embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.
Claims
1. A training method for a motor system efficiency prediction model, characterized in that: include: Obtaining motor operation data, wherein the motor operation data includes motor speed, torque and motor efficiency, and repeatedly adding motor operation data in a high efficiency area; Generating a nonlinear feature according to the motor operation data, wherein the nonlinear feature includes a square of motor speed, a square of torque, and an interaction term between speed and torque; Based on the contribution index, the nonlinear features are screened to obtain a feature set; Parameters are set, and according to the set parameters, a motor system efficiency prediction model is trained using a random forest algorithm, wherein the trained motor system efficiency prediction model takes motor speed and torque as inputs, and takes motor efficiency as a prediction result.
2. The training method of the motor system efficiency prediction model according to claim 1, characterized in that: The nonlinear features are screened based on the contribution index to obtain a feature set, including: The importance of nonlinear features is evaluated by information gain to screen out features whose contribution to the target variable is greater than a predetermined index, thereby obtaining the feature set.
3. The training method of the motor system efficiency prediction model according to claim 1, characterized in that: The setting of parameters and training the motor system efficiency prediction model using a random forest algorithm according to the set parameters include: Setting parameters, wherein the set parameters include the number of trees, the maximum depth, the number of random features, and the random seed; The motor system efficiency prediction model is trained using the random forest algorithm, and the grid search method is used to optimize the hyperparameters and select the parameter combination with the best performance.
4. The training method of the motor system efficiency prediction model according to any one of claims 1 to 3, characterized in that: After the motor system efficiency prediction model is trained, it also includes: A 10-fold cross validation was used to evaluate the performance of the motor system efficiency prediction model.
5. The training method of the motor system efficiency prediction model according to claim 4, characterized in that: Also includes: When the performance of the motor system efficiency prediction model does not meet the requirement, the motor system efficiency prediction model is fine-tuned again until the performance of the motor system efficiency prediction model meets the requirement.
6. A method for predicting the efficiency of a motor system of a vehicle, characterized in that: include: Get the motor speed and torque of the vehicle; The motor speed and torque are input into a pre-trained motor system efficiency prediction model to obtain the motor system efficiency predicted by the motor system efficiency prediction model, wherein the motor system efficiency prediction model is a motor system efficiency prediction model trained according to the training method of the motor system efficiency prediction model according to any one of claims 1-4.
7. A vehicle motor system efficiency prediction system, characterized in that: include: An acquisition module, used to obtain the motor speed and torque of the vehicle; A prediction module is used to input the motor speed and torque into a pre-trained motor system efficiency prediction model to obtain the motor system efficiency predicted by the motor system efficiency prediction model, wherein the motor system efficiency prediction model is a motor system efficiency prediction model trained according to the training method of the motor system efficiency prediction model according to any one of claims 1-5.
8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for predicting the efficiency of the motor system of the vehicle according to claim 6 is implemented.
9. A computer-readable storage medium, comprising a memory and a computer program stored in the memory and executable on a processor, characterized in that: When the program is executed by a processor, the method for predicting the efficiency of a motor system of a vehicle according to claim 6 is implemented.
10. A computer program product, comprising a memory and a computer program stored in the memory and executable on a processor, characterized in that: When the program is executed by a processor, the method for predicting the efficiency of a motor system of a vehicle according to claim 6 is implemented.