Vehicle gear shifting optimization adjusting system and method based on fuzzy control

Abstract

The invention relates to the technical field of vehicle control systems, provides a fuzzy control-based vehicle gear shifting optimization adjustment system and method, solves the problems of large rule matching workload and low decision-making speed in fuzzy control, and provides a fuzzy control-based vehicle gear shifting optimization adjustment system and method by collecting vehicle real-time data and utilizing a random forest model to carry out gear shifting simulation. And gear shifting parameter errors are detected according to a preset error range. And for the data exceeding the error range, the system extracts data features, matches and trains a model suitable for the current scene, optimizes the model by using a genetic algorithm, and outputs optimized gear shifting parameters, so that the real-time performance, the accuracy and the adaptive capacity of gear shifting control are improved, the gear shifting strategy is optimized, and the vehicle driving performance is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle control systems, and in particular to a vehicle gear shift optimization adjustment system and method based on fuzzy control. Background Art

[0002] Fuzzy control is applied to the vehicle automatic shifting system and is suitable for establishing accurate mathematical models, nonlinear and large-lag controlled processes. During vehicle shifting, the fuzzy control system collects various shifting parameters of the vehicle's real-time state, such as engine speed, engine torque, transmission output shaft speed, vehicle speed, etc., and combines the driver's operating intentions and the vehicle's operating environment. It uses fuzzy control rules for reasoning and decision-making to achieve intelligent control of the shifting process. The control method can more accurately reflect the driver's intentions and vehicle dynamics.

[0003] The vehicle shift optimization adjustment based on fuzzy control collects the vehicle's operating status data in real time through sensors. The vehicle's operating status data is input into the fuzzy controller, which fuzzifies these imprecise and nonlinear input information according to the preset fuzzy rules and membership functions. Subsequently, the fuzzy controller generates a fuzzy shift decision output by comprehensively considering factors such as driving intention, road condition changes, and vehicle power performance through the fuzzy reasoning mechanism. This output is then converted into a specific shift instruction, such as upshift, downshift, or maintain the current gear, through the defuzzification process.

[0004] The following technical pain points exist in the vehicle gear shift optimization adjustment process of fuzzy control. In fuzzy control, input information needs to be matched with the rules in the fuzzy rule base to find applicable control rules. When the search range of the fuzzy rules is too large, the input information needs to be matched with more rules, which increases the workload of rule matching. In real-time vehicle gear shift control, the increase in the workload of rule matching leads to a decrease in decision-making speed. To solve this technical problem, the present invention provides a vehicle gear shift optimization adjustment system and method based on fuzzy control. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a vehicle gear shift optimization adjustment system and method based on fuzzy control, which solves the problem that when the search range of fuzzy rules is too large, the input information needs to be matched with more rules, which increases the workload of rule matching. In real-time vehicle gear shift control, the increase in the workload of rule matching leads to a decrease in decision-making speed.

[0006] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows: In a first aspect, the present invention provides a vehicle shift optimization adjustment system based on fuzzy control, comprising: A data acquisition module is used to acquire vehicle historical data, which includes historical vehicle operation data, historical vehicle shifting data, historical driver operation intention data, historical vehicle operation environment data, and historical vehicle load data. The historical vehicle shifting data, historical driver operation intention data, historical vehicle operation environment data, and historical vehicle load data are used as training data to train a random forest model, and the historical vehicle operation data is used as verification data to obtain a vehicle shifting simulation model. A data acquisition module is used to collect real-time vehicle data, substitute the real-time vehicle data into a vehicle shift simulation model, output a vehicle shift simulation result, group the vehicle shift simulation result according to time periods to obtain vehicle shift simulation group data, substitute the vehicle shift simulation group data into a preset vehicle shift parameter knowledge base in sequence for matching, obtain a preset shift parameter corresponding to each vehicle shift simulation group, align the real-time vehicle data with the vehicle shift simulation group in units of time to obtain the real-time vehicle group data, compare the real-time vehicle group data with the preset shift parameter corresponding to each vehicle shift simulation group, and obtain real-time vehicle shift parameter error data; A gear shift data detection module, used for receiving a preset vehicle gear shift error range value, comparing the real-time vehicle gear shift parameter error data with the preset vehicle gear shift error range value, and if the real-time vehicle gear shift parameter error data exceeds the preset vehicle gear shift error range value, marking the real-time vehicle gear shift parameter error data exceeding the preset vehicle gear shift error range value as data to be corrected; A data processing module is used to align the preset shift parameters corresponding to each vehicle shift simulation group with the data to be corrected based on time to obtain the preset shift parameters corresponding to the data to be corrected, retrieve the vehicle real-time data corresponding to the data to be corrected, extract data features of the vehicle real-time data corresponding to the data to be corrected, obtain data features of the data to be corrected, match the data features of the data to be corrected in a preset model knowledge base, obtain a model corresponding to the data features of the corrected data, use the vehicle real-time data corresponding to the data to be corrected to train the model, use the preset shift parameters corresponding to the data to be corrected as verification data, and obtain a shift simulation model of the data to be corrected; The optimization module is used to substitute the real-time vehicle data corresponding to the data to be corrected into the shift parameter simulation model of the data to be corrected to obtain the shift parameter simulation parameters corresponding to the data to be corrected, use the shift parameter simulation parameters corresponding to the corrected data as the shift parameters to be used, substitute the shift parameters to be used into a preset vehicle operation simulation model to obtain the vehicle operation data simulated by the shift parameters to be used, send the shift parameters to be used to the shift device, receive the data fed back by the shift device, compare the data fed back by the shift device with the vehicle operation data simulated by the shift parameters to be used, if the vehicle operation data error data is higher than the preset vehicle operation error range, use the genetic algorithm to optimize the shift simulation model of the data to be corrected to obtain the optimized shift simulation model of the data to be corrected, use the shift simulation model of the data to be corrected to output the optimized shift parameter simulation parameters corresponding to the data to be corrected, and use the optimized shift parameter simulation parameters corresponding to the data to be corrected as the shift execution parameters.

[0007] Furthermore, in the vehicle shift optimization adjustment system based on fuzzy control of the present invention, the data acquisition module is also used for: According to time, the vehicle real-time data is divided into the same time period as the vehicle shift simulation grouping to form vehicle real-time grouping data. Each real-time data point can correspond to a simulation grouping to determine the time period to which each real-time data point belongs; For each vehicle real-time grouped data, the gear shift parameters are extracted, and the gear shift parameters include engine speed, vehicle speed and accelerator pedal position; The real-time vehicle data is compared with the preset shift parameters in the vehicle shift simulation grouping within the corresponding time period. For each compared parameter, the difference between the real-time parameter and the preset parameter is calculated, and the difference is the real-time vehicle shift parameter error data.

[0008] Furthermore, in the vehicle shift optimization adjustment system based on fuzzy control of the present invention, the shift data detection module is also used for: Obtaining a preset vehicle shift error range value from a system configuration or a database to determine whether a real-time shift parameter deviates from an acceptable range; The real-time vehicle shift parameter error data includes the error between the real-time value and the preset value of the engine speed data, the vehicle speed data, and the accelerator pedal position data; For each real-time error data point, compare each real-time error data point with a preset vehicle shift error range value to check whether the absolute value of the error is less than or equal to the upper limit of the preset range; If the value of each real-time error data point exceeds the preset vehicle shift error range value, that is, the absolute value of the error is greater than the upper limit of the preset range, each real-time error data point is marked as data to be corrected; If the error is within the preset range, the data point is usable; A data set to be corrected is formed for the data points marked as to be corrected, and the data set to be corrected is used to correct the shift parameters that deviate from the preset range.

[0009] Furthermore, in the vehicle shift optimization adjustment system based on fuzzy control of the present invention, the data processing module is also used for: Extracting data features from the data to be corrected, wherein the data features extracted from the data to be corrected include a timestamp, a vehicle speed, an engine speed, an accelerator pedal position, and a vehicle load; The extracted data features are input into a preset model knowledge base, which includes a neural network, a decision tree, and a support vector machine. Each model in the preset model knowledge base is suitable for different data features and shift control scenarios; Using the real-time vehicle data corresponding to the data to be corrected as the input part of the training data set, and using the training data model for training, so that the model can learn the mapping relationship between the vehicle shift parameters and the real-time data; The preset shift parameters corresponding to the data to be corrected are used as the output part of the verification data set, i.e., the target value. The trained model is applied to the input part of the verification data set, i.e., the real-time vehicle data corresponding to the data to be corrected, and the prediction result is output.

[0010] In a second aspect, a vehicle shift optimization adjustment method based on fuzzy control is applied to the vehicle shift optimization adjustment system based on fuzzy control, comprising: Step S101, obtaining vehicle historical data, the vehicle historical data including historical vehicle operation data, historical vehicle shifting data, historical driver operation intention data, historical vehicle operation environment data and historical vehicle load data, using the historical vehicle shifting data, historical driver operation intention data, historical vehicle operation environment data and historical vehicle load data as training data to train a random forest model, using the historical vehicle operation data as verification data to obtain a vehicle shifting simulation model; Step S102, collecting vehicle real-time data, substituting the vehicle real-time data into a vehicle shift simulation model, outputting a vehicle shift simulation result, grouping the vehicle shift simulation result according to time periods to obtain vehicle shift simulation group data, substituting the vehicle shift simulation group data into a preset vehicle shift parameter knowledge base in sequence for matching to obtain preset shift parameters corresponding to each vehicle shift simulation group, aligning the vehicle real-time data with the vehicle shift simulation group in units of time to obtain vehicle real-time group data, comparing the vehicle real-time group data with the preset shift parameters corresponding to each vehicle shift simulation group to obtain real-time vehicle shift parameter error data; Step S103, receiving a preset vehicle gear shift error range value, comparing the real-time vehicle gear shift parameter error data with the preset vehicle gear shift error range value, and if the real-time vehicle gear shift parameter error data exceeds the preset vehicle gear shift error range value, marking the real-time vehicle gear shift parameter error data exceeding the preset vehicle gear shift error range value as data to be corrected; Step S104, aligning the preset shift parameters corresponding to each vehicle shift simulation group with the data to be corrected based on time to obtain the preset shift parameters corresponding to the data to be corrected, retrieving the vehicle real-time data corresponding to the data to be corrected, extracting data features of the vehicle real-time data corresponding to the data to be corrected to obtain data features of the data to be corrected, matching the data features of the data to be corrected in a preset model knowledge base to obtain a model corresponding to the data features of the corrected data, using the vehicle real-time data corresponding to the data to be corrected to train the model, using the preset shift parameters corresponding to the data to be corrected as verification data, and obtaining a shift simulation model of the data to be corrected; Step S105, substitute the real-time vehicle data corresponding to the data to be corrected into the shift parameter simulation model of the data to be corrected to obtain the shift parameter simulation parameters corresponding to the data to be corrected, use the shift parameter simulation parameters corresponding to the corrected data as the shift parameters to be used, substitute the shift parameters to be used into the preset vehicle operation simulation model to obtain the vehicle operation data simulated by the shift parameters to be used, send the shift parameters to be used to the shift device, receive the data fed back by the shift device, compare the data fed back by the shift device with the vehicle operation data simulated by the shift parameters to be used, if the error data of the vehicle operation data is higher than the preset vehicle operation error range, use the genetic algorithm to optimize the shift simulation model of the data to be corrected to obtain the optimized shift simulation model of the data to be corrected, use the shift simulation model of the data to be corrected to output the optimized shift parameter simulation parameters corresponding to the data to be corrected, and use the optimized shift parameter simulation parameters corresponding to the data to be corrected as the shift execution parameters.

[0011] Furthermore, the vehicle shift optimization adjustment method based on fuzzy control described in the present invention, step S102 includes: According to time, the vehicle real-time data is divided into the same time period as the vehicle shift simulation grouping to form vehicle real-time grouping data. Each real-time data point can correspond to a simulation grouping to determine the time period to which each real-time data point belongs; For each vehicle real-time grouped data, the gear shift parameters are extracted, and the gear shift parameters include engine speed, vehicle speed and accelerator pedal position; The real-time vehicle data is compared with the preset shift parameters in the vehicle shift simulation grouping within the corresponding time period. For each compared parameter, the difference between the real-time parameter and the preset parameter is calculated, and the difference is the real-time vehicle shift parameter error data.

[0012] Furthermore, the vehicle shift optimization adjustment method based on fuzzy control described in the present invention, step S103, includes: Obtaining a preset vehicle shift error range value from a system configuration or a database to determine whether a real-time shift parameter deviates from an acceptable range; The real-time vehicle shift parameter error data includes the error between the real-time value and the preset value of the engine speed data, the vehicle speed data, and the accelerator pedal position data; For each real-time error data point, compare each real-time error data point with a preset vehicle shift error range value to check whether the absolute value of the error is less than or equal to the upper limit of the preset range; If the value of each real-time error data point exceeds the preset vehicle shift error range value, that is, the absolute value of the error is greater than the upper limit of the preset range, each real-time error data point is marked as data to be corrected; If the error is within the preset range, the data point is usable; A data set to be corrected is formed for the data points marked as to be corrected, and the data set to be corrected is used to correct the shift parameters that deviate from the preset range.

[0013] Furthermore, the vehicle shift optimization adjustment method based on fuzzy control described in the present invention, step S104 includes: Extracting data features from the data to be corrected, wherein the data features extracted from the data to be corrected include a timestamp, a vehicle speed, an engine speed, an accelerator pedal position, and a vehicle load; The extracted data features are input into a preset model knowledge base, which includes a neural network, a decision tree, and a support vector machine. Each model in the preset model knowledge base is suitable for different data features and shift control scenarios; Using the real-time vehicle data corresponding to the data to be corrected as the input part of the training data set, and using the training data model for training, so that the model can learn the mapping relationship between the vehicle shift parameters and the real-time data; The preset shift parameters corresponding to the data to be corrected are used as the output part of the verification data set, i.e., the target value. The trained model is applied to the input part of the verification data set, i.e., the real-time vehicle data corresponding to the data to be corrected, and the prediction result is output.

[0014] Beneficial effects of the present invention: The present invention reduces the reliance on real-time fuzzy rule matching by introducing a random forest model to simulate vehicle shifting, significantly reduces the workload caused by the excessive search range of fuzzy rules, and thus improves the real-time performance of shift control. Through the steps of real-time data collection, simulation grouping and matching with preset shift parameters, error detection and correction, it can more accurately reflect the driver's intention and vehicle dynamics, and improve the accuracy of shift control.

[0015] The system can automatically detect and correct shift parameters that deviate from the preset range based on real-time vehicle operation data and preset error range values, ensuring that the shift decision is adapted to the current vehicle state and driving environment. Through the model knowledge base selection and data feature extraction in the data processing module, the system can select appropriate models for training and optimization according to different data features and shift control scenarios, enhancing the system's adaptive ability.

[0016] The genetic algorithm is used to optimize the gear shift simulation model, which further improves the prediction accuracy and generalization ability of the model, making the gear shift control strategy more scientific and reasonable. By using the optimized gear shift parameter simulation parameters as the gear shift execution parameters, the smoothness and comfort of the gear shift process are improved, and the vehicle performance degradation or safety hazards caused by improper gear shifting are reduced.

[0017] Intelligent shift control makes the driving process smoother and more natural, improving the driving experience. Optimized shift control strategy can reduce fuel consumption and emissions, extend vehicle life, and reduce maintenance costs, thereby improving the overall performance and economy of the vehicle.

[0018] In summary, the present invention realizes intelligent control of the vehicle shifting process by introducing advanced technologies such as random forest model, real-time data acquisition and processing, error detection and correction, and model optimization, and significantly improves the real-time, accuracy, and adaptability of the shifting control. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on the drawings without paying any creative labor.

[0020] Figure 1 A schematic diagram of functional modules in a vehicle gear shift optimization adjustment system based on fuzzy control provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments 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 creative work are within the scope of protection of the present invention. The technical solutions provided by the embodiments of the present invention are described in detail below in conjunction with the drawings.

[0022] In order to better understand the purpose of the present invention, the present invention is described in further detail below.

[0023] like Figure 1 As shown, in the first aspect, the present invention provides a vehicle shift optimization adjustment system based on fuzzy control, comprising: A data acquisition module is used to acquire vehicle historical data, which includes historical vehicle operation data, historical vehicle shifting data, historical driver operation intention data, historical vehicle operation environment data, and historical vehicle load data. The historical vehicle shifting data, historical driver operation intention data, historical vehicle operation environment data, and historical vehicle load data are used as training data to train a random forest model, and the historical vehicle operation data is used as verification data to obtain a vehicle shifting simulation model. The data acquisition module is responsible for collecting and processing the historical data of the vehicle, which is the basis for the subsequent establishment and optimization of the vehicle shift simulation model. By collecting comprehensive historical data, the vehicle shift simulation model can learn the shift rules under various driving scenarios and conditions, thereby improving the accuracy and intelligence of the shift control.

[0024] Historical vehicle operation data: including vehicle speed, acceleration, mileage and other operating parameters in different time periods.

[0025] Historical vehicle gear shift data: records the actual gear shifting time, gear positions before and after the gear shift, and other information during the vehicle's past driving.

[0026] Historical driver operation intention data: data collected through sensors or driver assistance systems, reflecting the driver's operation intentions such as acceleration, deceleration, and overtaking.

[0027] Historical vehicle operating environment data: including external environmental factors such as road type (such as highways, urban roads, mountain roads, etc.), traffic conditions, and weather conditions.

[0028] Historical vehicle load data: records the load of vehicles at different points in time, including the number of passengers and cargo weight.

[0029] Clean and organize the collected raw data, remove outliers and missing values, and ensure the integrity of the data. Normalize or standardize the data so that data of different dimensions can be compared and analyzed on the same scale.

[0030] Historical vehicle shifting data, historical driver operation intention data, historical vehicle operating environment data, and historical vehicle load data are used as training data. The random forest model is selected as the learning algorithm. Random forest is an ensemble learning method that improves the stability of the model by building multiple decision trees and combining their prediction results. The random forest model is trained to enable it to learn the complex relationship between vehicle shifting and driver operation intention, vehicle operating environment, and vehicle load.

[0031] Use historical vehicle operation data as validation data to validate the trained random forest model. Evaluate the model's prediction performance by comparing the model's prediction results with actual vehicle operation data. Adjust the model's parameters and structure based on the validation results to further improve the model's prediction accuracy and generalization ability.

[0032] A data acquisition module is used to collect real-time vehicle data, substitute the real-time vehicle data into a vehicle shift simulation model, output a vehicle shift simulation result, group the vehicle shift simulation result according to time periods to obtain vehicle shift simulation group data, substitute the vehicle shift simulation group data into a preset vehicle shift parameter knowledge base in sequence for matching, obtain a preset shift parameter corresponding to each vehicle shift simulation group, align the real-time vehicle data with the vehicle shift simulation group in units of time to obtain the real-time vehicle group data, compare the real-time vehicle group data with the preset shift parameter corresponding to each vehicle shift simulation group, and obtain real-time vehicle shift parameter error data; The data acquisition module collects the vehicle's operating data in real time in the vehicle shift optimization adjustment system based on fuzzy control, and substitutes the data into the pre-trained vehicle shift simulation model to output the simulated shift results. The following are the specific workflow and steps of the data acquisition module: The data acquisition module obtains the vehicle's operating status data in real time through various sensors installed on the vehicle. These data include but are not limited to engine speed, vehicle speed, transmission output shaft speed, accelerator pedal position, brake pedal status, etc. Real-time data reflects the vehicle's current operating status and the driver's operating intentions.

[0033] The collected real-time vehicle data is substituted into a pre-trained vehicle shift simulation model. This model is based on a large amount of historical vehicle data and is trained through machine learning algorithms (such as random forests) to simulate the vehicle's shifting behavior under different conditions.

[0034] The vehicle shift simulation model outputs simulated shift results based on the input real-time data. These results include recommended shift timing, target gear position and other information.

[0035] The simulated shift results are grouped according to time periods to obtain a series of vehicle shift simulation group data. Each vehicle shift simulation group data is sequentially substituted into a preset vehicle shift parameter knowledge base for matching. This knowledge base contains shift parameter standards or empirical values ​​under various driving scenarios. Through matching, the corresponding preset shift parameters are found for each vehicle shift simulation group.

[0036] The real-time vehicle data and the vehicle shift simulation grouping are aligned in time units to ensure that each group of real-time data can be compared with the corresponding simulation grouping data. For each real-time data group, the relevant shift parameters (such as engine speed, vehicle speed, etc.) are extracted and compared with the corresponding preset shift parameters. The difference between the real-time parameters and the preset parameters is calculated to obtain the real-time vehicle shift parameter error data. These error data reflect the difference between the current vehicle shift state and the ideal state.

[0037] The data acquisition module is the key link between the real-time status of the vehicle and the gear shift simulation model. By collecting vehicle data in real time and accurately, and substituting it into the model for analysis and prediction, it provides strong data support for subsequent gear shift decisions. At the same time, by comparing the error between real-time data and preset parameters, the deviation in the gear shift process can be discovered and corrected in time, thereby improving the accuracy and efficiency of gear shift control.

[0038] A gear shift data detection module, used for receiving a preset vehicle gear shift error range value, comparing the real-time vehicle gear shift parameter error data with the preset vehicle gear shift error range value, and if the real-time vehicle gear shift parameter error data exceeds the preset vehicle gear shift error range value, marking the real-time vehicle gear shift parameter error data exceeding the preset vehicle gear shift error range value as data to be corrected; The shift data detection module receives the preset vehicle shift error range value in the vehicle shift optimization adjustment system based on fuzzy control, and compares the real-time vehicle shift parameter error data with the preset range to determine whether the real-time error of the shift parameter is within an acceptable range. The following is the specific work flow and details of the shift data detection module: The shift data detection module first obtains the preset vehicle shift error range value from the system configuration or database. These preset values ​​are determined based on factors such as vehicle performance characteristics, driver's driving habits and road conditions, and are used to determine whether the real-time shift parameters deviate from the acceptable range.

[0039] The module receives the real-time vehicle shift parameter error data provided by the data acquisition module. These data are the difference between the real-time vehicle operating parameters and the parameters predicted by the shift simulation model, reflecting the difference between the actual shift state and the simulated state.

[0040] Each real-time error data point is compared to a preset vehicle shift error range value. This typically involves checking whether the absolute value of the error is less than or equal to the upper limit of the preset range.

[0041] If the value of a real-time error data point exceeds the preset vehicle shift error range (i.e. the absolute value of the error is greater than the upper limit of the preset range), the data point is marked as data to be corrected. This means that the current shift parameters are significantly different from the ideal state and require further adjustment and optimization. If the error is within the preset range, the data point is considered usable and does not need to be corrected.

[0042] All the data points marked as to be corrected are collected to form a data set to be corrected. This data set will be used in the subsequent model training and parameter correction process to improve the accuracy and efficiency of the shift control.

[0043] The importance of the shift data detection module lies in its ability to detect deviations in the shift process in a timely manner, providing clear guidance for subsequent parameter correction and optimization. By setting a reasonable error range value, the shift data detection module can ensure the stability of the shift control and avoid vehicle performance degradation or safety hazards caused by improper shifting. At the same time, the shift data detection module also provides data support for the continuous optimization and improvement of the system.

[0044] A data processing module is used to align the preset shift parameters corresponding to each vehicle shift simulation group with the data to be corrected based on time to obtain the preset shift parameters corresponding to the data to be corrected, retrieve the vehicle real-time data corresponding to the data to be corrected, extract data features of the vehicle real-time data corresponding to the data to be corrected, obtain data features of the data to be corrected, match the data features of the data to be corrected in a preset model knowledge base, obtain a model corresponding to the data features of the corrected data, use the vehicle real-time data corresponding to the data to be corrected to train the model, use the preset shift parameters corresponding to the data to be corrected as verification data, and obtain a shift simulation model of the data to be corrected; The data processing module first obtains the preset shift parameters corresponding to each vehicle shift simulation group, and then aligns these preset shift parameters with the data to be corrected (i.e., the data marked as needing correction by the shift data detection module) based on time.

[0045] For each data point to be corrected, the data processing module retrieves the corresponding real-time vehicle data. From these real-time data, the data processing module extracts data features including timestamp, vehicle speed, engine speed, accelerator pedal position, and vehicle load.

[0046] The extracted data features will be input into the preset model knowledge base for matching. The preset model knowledge base includes a variety of models, such as neural networks, decision trees, and support vector machines. Each model is suitable for different data features and shift control scenarios. Through the matching process, the data processing module selects a model that best suits the current data features and shift control requirements.

[0047] When a suitable model is selected, the data processing module will use the real-time vehicle data corresponding to the data to be corrected as the input part of the training data set to train the model. The purpose of training is to enable the model to learn the mapping relationship between the vehicle shift parameters and real-time data, thereby improving the accuracy of shift control. At the same time, the data processing module will also use the preset shift parameters corresponding to the data to be corrected as the output part of the verification data set, i.e., the target value, to evaluate the prediction performance of the model.

[0048] After training and verification, the data processing module will output a gear shift simulation model for the data to be corrected. The gear shift simulation model can more accurately predict the optimal gear shift timing and gear selection under similar driving conditions.

[0049] The data processing module can significantly improve the accuracy and stability of gear shift control through in-depth analysis and model optimization of real-time data, thereby enhancing the driving experience and vehicle performance. In addition, the gear shift simulation model can also provide strong data support for the continuous optimization and improvement of the system.

[0050] The optimization module is used to substitute the real-time vehicle data corresponding to the data to be corrected into the shift parameter simulation model of the data to be corrected to obtain the shift parameter simulation parameters corresponding to the data to be corrected, use the shift parameter simulation parameters corresponding to the corrected data as the shift parameters to be used, substitute the shift parameters to be used into a preset vehicle operation simulation model to obtain the vehicle operation data simulated by the shift parameters to be used, send the shift parameters to be used to the shift device, receive the data fed back by the shift device, compare the data fed back by the shift device with the vehicle operation data simulated by the shift parameters to be used, if the vehicle operation data error data is higher than the preset vehicle operation error range, use the genetic algorithm to optimize the shift simulation model of the data to be corrected to obtain the optimized shift simulation model of the data to be corrected, use the shift simulation model of the data to be corrected to output the optimized shift parameter simulation parameters corresponding to the data to be corrected, and use the optimized shift parameter simulation parameters corresponding to the data to be corrected as the shift execution parameters.

[0051] The optimization module is responsible for continuously optimizing the shift simulation model of the data to be corrected in the vehicle shift optimization adjustment system based on fuzzy control.

[0052] The optimization module first obtains the real-time vehicle data corresponding to the data to be corrected, substitutes the real-time data into the previously generated gear shift parameter simulation model of the data to be corrected, and calculates the gear shift parameter simulation parameters corresponding to the data to be corrected.

[0053] The calculated shift parameter simulation parameters are used as the shift parameters to be used. These shift parameters to be used are substituted into a preset vehicle operation simulation model to simulate the operation of the vehicle under these shift parameters, and obtain the vehicle operation data simulated by the shift parameters to be used.

[0054] The gear shift parameters to be used are sent to the gear shift device for actual gear shifting operation, and actual vehicle operation data fed back by the gear shift device are received. The actual vehicle operation data fed back by the gear shift device are compared with the vehicle operation data simulated by the gear shift parameters to be used.

[0055] Calculate the error data between the two and evaluate whether the error is higher than the preset vehicle operation error range.

[0056] If the error is higher than the preset range, it means that the current shift simulation model is insufficient and needs to be optimized. The genetic algorithm is used to optimize the shift simulation model of the data to be corrected. The genetic algorithm is a heuristic search algorithm that simulates natural selection and genetic mechanisms to find the optimal solution. During the optimization process, the model parameters and structure are continuously adjusted to reduce the error between the simulation parameters and the actual operating data.

[0057] After optimization, an optimized gear shift simulation model of the data to be corrected is obtained. The optimized model is used to re-output the gear shift parameter simulation parameters corresponding to the data to be corrected. The optimized gear shift parameter simulation parameters are used as the final gear shift execution parameters for actual gear shift control.

[0058] The optimization module can continuously improve and optimize the shift simulation model to enhance the accuracy of shift control. Through optimization techniques such as genetic algorithms, the optimization module can automatically adjust the model parameters to better adapt to different driving scenarios and vehicle conditions.

[0059] Specifically, in the vehicle shift optimization adjustment system based on fuzzy control of the present invention, the data acquisition module is also used for: According to time, the vehicle real-time data is divided into the same time period as the vehicle shift simulation grouping to form vehicle real-time grouping data. Each real-time data point can correspond to a simulation grouping to determine the time period to which each real-time data point belongs; For each vehicle real-time grouped data, the gear shift parameters are extracted, and the gear shift parameters include engine speed, vehicle speed and accelerator pedal position; The real-time vehicle data is compared with the preset shift parameters in the vehicle shift simulation grouping within the corresponding time period. For each compared parameter, the difference between the real-time parameter and the preset parameter is calculated, and the difference is the real-time vehicle shift parameter error data.

[0060] In the vehicle shift optimization adjustment system based on fuzzy control, the function of the data acquisition module is further refined and enhanced to obtain and analyze real-time vehicle data, thereby providing strong support for shift optimization.

[0061] The data acquisition module first divides the continuous vehicle real-time data into the same time period as the vehicle shift simulation grouping according to time, so that each real-time data point can correspond to a specific simulation grouping, which is convenient for subsequent analysis and comparison.

[0062] Through this division, vehicle real-time group data is formed, and each group contains all real-time data points within a specific time period.

[0063] For each vehicle real-time grouping data, the data acquisition module will further extract key shift parameters. These parameters usually include engine speed, vehicle speed and accelerator pedal position, which are important bases for judging the timing of shifting and selecting the appropriate gear. The extracted shift parameters will be used for subsequent model substitution and error calculation.

[0064] The data acquisition module compares the extracted real-time vehicle shift parameters with the preset shift parameters in the vehicle shift simulation grouping within the corresponding time period. This includes comparing the real-time engine speed with the preset engine speed, the real-time vehicle speed with the preset vehicle speed, and the real-time accelerator pedal position with the preset accelerator pedal position. For each compared parameter, the data acquisition module calculates the difference between the real-time parameter and the preset parameter. This difference is the real-time vehicle shift parameter error data, which reflects the degree of difference between the actual shift state and the simulated state.

[0065] The enhanced function of the data acquisition module in the present invention is of great significance to the entire shift optimization adjustment system. Through precise time period division and shift parameter extraction, the data acquisition module can ensure that each real-time data point can be accurately located and classified, thereby providing a reliable basis for subsequent model substitution and error calculation. At the same time, by calculating the difference between the real-time parameters and the preset parameters, the data acquisition module can promptly detect the deviation in the shift process and provide clear guidance for subsequent correction and optimization.

[0066] Specifically, in the vehicle shift optimization adjustment system based on fuzzy control of the present invention, the shift data detection module is also used for: Obtaining a preset vehicle shift error range value from a system configuration or a database to determine whether a real-time shift parameter deviates from an acceptable range; The real-time vehicle shift parameter error data includes the error between the real-time value and the preset value of the engine speed data, the vehicle speed data, and the accelerator pedal position data; For each real-time error data point, compare each real-time error data point with a preset vehicle shift error range value to check whether the absolute value of the error is less than or equal to the upper limit of the preset range; If the value of each real-time error data point exceeds the preset vehicle shift error range value, that is, the absolute value of the error is greater than the upper limit of the preset range, each real-time error data point is marked as data to be corrected; If the error is within the preset range, the data point is usable; A data set to be corrected is formed for the data points marked as to be corrected, and the data set to be corrected is used to correct the shift parameters that deviate from the preset range.

[0067] In the vehicle gear shift optimization adjustment system based on fuzzy control, it is responsible for monitoring the difference between the real-time gear shift parameters and the preset values, and identifying the data points that need to be corrected.

[0068] The shift data detection module first obtains the preset vehicle shift error range value from the system configuration or database. These preset values ​​are determined based on multiple factors such as vehicle performance, driving habits, road conditions, etc., and are used to define the acceptable deviation range of shift parameters. The shift data detection module receives the vehicle shift parameters provided by the data acquisition module in real time, including engine speed, vehicle speed, accelerator pedal position, etc.

[0069] For each parameter, the shift data detection module calculates the error between its real-time value and the preset value to form real-time vehicle shift parameter error data. For each real-time error data point, the shift data detection module compares it with the preset vehicle shift error range value. Check whether the absolute value of the error is less than or equal to the upper limit of the preset range to determine whether the data point is within the acceptable range.

[0070] If the value of a real-time error data point exceeds the preset vehicle shift error range (i.e., the absolute value of the error is greater than the upper limit of the preset range), the data point is marked as data to be corrected. On the contrary, if the error is within the preset range, the data point is considered usable and does not need to be corrected.

[0071] The gear shift data detection module collects all the data points marked as to-be-corrected to form a data set to be corrected.

[0072] The data set contains all the shift parameter information that deviates from the preset range, and is an important basis for subsequent model correction and optimization.

[0073] The shift data detection module can detect abnormal deviations in the shift process in a timely manner and provide clear goals for system correction and optimization. By accurately calculating the real-time error and comparing it with the preset range, the shift data detection module can ensure the accuracy of the shift control. At the same time, the data set to be corrected provides data support for subsequent model training and parameter adjustment, which helps to continuously improve the performance of the shift optimization adjustment system.

[0074] Specifically, in the vehicle shift optimization adjustment system based on fuzzy control of the present invention, the data processing module is also used for: Extracting data features from the data to be corrected, wherein the data features extracted from the data to be corrected include a timestamp, a vehicle speed, an engine speed, an accelerator pedal position, and a vehicle load; The extracted data features are input into a preset model knowledge base, which includes a neural network, a decision tree, and a support vector machine. Each model in the preset model knowledge base is suitable for different data features and shift control scenarios; Using the real-time vehicle data corresponding to the data to be corrected as the input part of the training data set, and using the training data model for training, so that the model can learn the mapping relationship between the vehicle shift parameters and the real-time data; The preset shift parameters corresponding to the data to be corrected are used as the output part of the verification data set, i.e., the target value. The trained model is applied to the input part of the verification data set, i.e., the real-time vehicle data corresponding to the data to be corrected, and the prediction result is output.

[0075] In the vehicle shift optimization adjustment system based on fuzzy control, the data processing module is responsible for in-depth analysis and processing of the data to be corrected to extract valuable information and use this information to train and optimize the shift control model.

[0076] The data processing module first extracts key data features from the data to be corrected, including timestamps (used to determine the time sequence and relevance of the data), vehicle speed, engine speed, accelerator pedal position, and vehicle load (such as the number of passengers, cargo weight, etc., reflecting the current load status of the vehicle). The extracted data features are input into the preset model knowledge base. This knowledge base contains a variety of machine learning models, such as neural networks, decision trees, and support vector machines.

[0077] Each model has its own applicable data characteristics and shift control scenarios. For example, neural networks may be better at handling complex nonlinear relationships, while decision trees are suitable for handling problems with clear branching logic. The data processing module will select the appropriate model for subsequent training and verification based on the characteristics of the data to be corrected and the specific needs of the shift control.

[0078] The real-time vehicle data corresponding to the data to be corrected is used as the input of the training data set. These data contain the actual performance of the vehicle under various driving conditions and are an important resource for model learning. By training the data model, the model can learn the mapping relationship between the vehicle shift parameters (such as shift timing, shift sequence, etc.) and real-time data (such as vehicle speed, engine speed, etc.). During the training process, the data processing module will use various optimization algorithms (such as gradient descent, random forest, etc.) to adjust the parameters of the model to improve the prediction accuracy and generalization ability of the model.

[0079] Use the preset shift parameters corresponding to the data to be corrected as the output part of the validation data set (i.e., the target value). These preset shift parameters are determined based on experience or expert knowledge and are used to evaluate the accuracy of the model's prediction results. Apply the trained model to the input part of the validation data set (i.e., the real-time vehicle data corresponding to the data to be corrected) and output the prediction results.

[0080] The data processing module calculates the error between the predicted result and the preset shift parameters to evaluate the performance of the model. If the error is within an acceptable range, it means that the model has good prediction ability; otherwise, the model needs to be further adjusted and optimized.

[0081] In the vehicle shift optimization adjustment system based on fuzzy control, the data processing module can establish a mapping relationship between vehicle shift parameters and real-time data by extracting data features, selecting appropriate models, and performing model training and verification, thereby providing accurate prediction and decision support for shift control.

[0082] In a second aspect, a vehicle shift optimization adjustment method based on fuzzy control is applied to the vehicle shift optimization adjustment system based on fuzzy control, comprising: Step S101, obtaining vehicle historical data, the vehicle historical data including historical vehicle operation data, historical vehicle shifting data, historical driver operation intention data, historical vehicle operation environment data and historical vehicle load data, using the historical vehicle shifting data, historical driver operation intention data, historical vehicle operation environment data and historical vehicle load data as training data to train a random forest model, using the historical vehicle operation data as verification data to obtain a vehicle shifting simulation model; Step S102, collecting vehicle real-time data, substituting the vehicle real-time data into a vehicle shift simulation model, outputting a vehicle shift simulation result, grouping the vehicle shift simulation result according to time periods to obtain vehicle shift simulation group data, substituting the vehicle shift simulation group data into a preset vehicle shift parameter knowledge base in sequence for matching to obtain preset shift parameters corresponding to each vehicle shift simulation group, aligning the vehicle real-time data with the vehicle shift simulation group in units of time to obtain vehicle real-time group data, comparing the vehicle real-time group data with the preset shift parameters corresponding to each vehicle shift simulation group to obtain real-time vehicle shift parameter error data; Step S103, receiving a preset vehicle gear shift error range value, comparing the real-time vehicle gear shift parameter error data with the preset vehicle gear shift error range value, and if the real-time vehicle gear shift parameter error data exceeds the preset vehicle gear shift error range value, marking the real-time vehicle gear shift parameter error data exceeding the preset vehicle gear shift error range value as data to be corrected; Step S104, aligning the preset shift parameters corresponding to each vehicle shift simulation group with the data to be corrected based on time to obtain the preset shift parameters corresponding to the data to be corrected, retrieving the vehicle real-time data corresponding to the data to be corrected, extracting data features of the vehicle real-time data corresponding to the data to be corrected to obtain data features of the data to be corrected, matching the data features of the data to be corrected in a preset model knowledge base to obtain a model corresponding to the data features of the corrected data, using the vehicle real-time data corresponding to the data to be corrected to train the model, using the preset shift parameters corresponding to the data to be corrected as verification data, and obtaining a shift simulation model of the data to be corrected; Step S105, substitute the real-time vehicle data corresponding to the data to be corrected into the shift parameter simulation model of the data to be corrected to obtain the shift parameter simulation parameters corresponding to the data to be corrected, use the shift parameter simulation parameters corresponding to the corrected data as the shift parameters to be used, substitute the shift parameters to be used into the preset vehicle operation simulation model to obtain the vehicle operation data simulated by the shift parameters to be used, send the shift parameters to be used to the shift device, receive the data fed back by the shift device, compare the data fed back by the shift device with the vehicle operation data simulated by the shift parameters to be used, if the error data of the vehicle operation data is higher than the preset vehicle operation error range, use the genetic algorithm to optimize the shift simulation model of the data to be corrected to obtain the optimized shift simulation model of the data to be corrected, use the shift simulation model of the data to be corrected to output the optimized shift parameter simulation parameters corresponding to the data to be corrected, and use the optimized shift parameter simulation parameters corresponding to the data to be corrected as the shift execution parameters.

[0083] Specifically, the vehicle shift optimization adjustment method based on fuzzy control according to the present invention, step S102 includes: According to time, the vehicle real-time data is divided into the same time period as the vehicle shift simulation grouping to form vehicle real-time grouping data. Each real-time data point can correspond to a simulation grouping to determine the time period to which each real-time data point belongs; For each vehicle real-time grouped data, the gear shift parameters are extracted, and the gear shift parameters include engine speed, vehicle speed and accelerator pedal position; The real-time vehicle data is compared with the preset shift parameters in the vehicle shift simulation grouping within the corresponding time period. For each compared parameter, the difference between the real-time parameter and the preset parameter is calculated, and the difference is the real-time vehicle shift parameter error data.

[0084] Specifically, the vehicle shift optimization adjustment method based on fuzzy control according to the present invention, step S103 includes: Obtaining a preset vehicle shift error range value from a system configuration or a database to determine whether a real-time shift parameter deviates from an acceptable range; The real-time vehicle shift parameter error data includes the error between the real-time value and the preset value of the engine speed data, the vehicle speed data, and the accelerator pedal position data; For each real-time error data point, compare each real-time error data point with a preset vehicle shift error range value to check whether the absolute value of the error is less than or equal to the upper limit of the preset range; If the value of each real-time error data point exceeds the preset vehicle shift error range value, that is, the absolute value of the error is greater than the upper limit of the preset range, each real-time error data point is marked as data to be corrected; If the error is within the preset range, the data point is usable; A data set to be corrected is formed for the data points marked as to be corrected, and the data set to be corrected is used to correct the shift parameters that deviate from the preset range.

[0085] Specifically, the vehicle shift optimization adjustment method based on fuzzy control of the present invention, step S104 includes: Extracting data features from the data to be corrected, wherein the data features extracted from the data to be corrected include a timestamp, a vehicle speed, an engine speed, an accelerator pedal position, and a vehicle load; The extracted data features are input into a preset model knowledge base, which includes a neural network, a decision tree, and a support vector machine. Each model in the preset model knowledge base is suitable for different data features and shift control scenarios; Using the real-time vehicle data corresponding to the data to be corrected as the input part of the training data set, and using the training data model for training, so that the model can learn the mapping relationship between the vehicle shift parameters and the real-time data; The preset shift parameters corresponding to the data to be corrected are used as the output part of the verification data set, i.e., the target value. The trained model is applied to the input part of the verification data set, i.e., the real-time vehicle data corresponding to the data to be corrected, and the prediction result is output.

[0086] The technical solution of the present invention effectively solves the problem that when the search range of fuzzy rules is too large, the input information needs to be matched with more rules, thereby increasing the workload of rule matching and causing the decision speed to decrease in real-time vehicle shift control through the innovative design of multiple modules and steps. The specific solution is as follows: First, a large amount of vehicle historical data is collected, including historical vehicle operation data, historical vehicle shifting data, historical driver operation intention data, historical vehicle operating environment data, and historical vehicle load data. The random forest model is trained using historical data to obtain a vehicle shifting simulation model. This model can predict the vehicle's shifting behavior to a certain extent, reducing the reliance on real-time fuzzy rule matching. The vehicle's operating status data, such as engine speed, vehicle speed, accelerator pedal position, etc., are collected in real time. The data is substituted into the vehicle shifting simulation model, the simulated shifting results are output, and the data is grouped according to time periods. The simulated grouped data is matched with the preset vehicle shifting parameter knowledge base to obtain the preset shifting parameters for each group. By comparing the difference between the real-time data and the simulated data, the real-time vehicle shifting parameter error data is calculated.

[0087] A vehicle shift error range value is preset to determine whether the real-time shift parameters deviate from the acceptable range. The real-time vehicle shift parameter error data is compared with the preset error range value, and the error data that exceeds the range is marked as the data to be corrected. For the data to be corrected, first extract its data features, such as timestamp, vehicle speed, engine speed, etc. Match the model that best suits the current data features in the preset model knowledge base (including neural networks, decision trees, support vector machines, etc.). Use the real-time data corresponding to the data to be corrected to train the selected model so that the model can learn the mapping relationship between the vehicle shift parameters and the real-time data. Use the preset shift parameters corresponding to the data to be corrected as verification data to evaluate the prediction performance of the model.

[0088] Substitute the real-time data corresponding to the data to be corrected into the trained model to obtain the optimized shift parameter simulation results. Substitute the simulation results as the shift parameters to be used into the preset vehicle operation simulation model to predict the vehicle's operating status. Send the shift parameters to be used to the shift device, and receive the actual operation data as feedback. Compare the predicted vehicle operation data with the actual operation data. If the error is large, use the genetic algorithm to optimize the model to obtain a more accurate shift simulation model.

[0089] Through the above steps, the present invention not only reduces the reliance on real-time fuzzy rule matching, but also continuously improves the prediction accuracy of the model through machine learning and optimization algorithms, thereby solving the problems of large workload of rule matching and low decision-making speed. The technical solution of the present invention has significant advantages in vehicle shift control with high real-time requirements.

Claims

1. A vehicle shift optimization adjustment system based on fuzzy control, characterized in that: include: A data acquisition module is used to acquire vehicle historical data, which includes historical vehicle operation data, historical vehicle shifting data, historical driver operation intention data, historical vehicle operation environment data, and historical vehicle load data. The historical vehicle shifting data, historical driver operation intention data, historical vehicle operation environment data, and historical vehicle load data are used as training data to train a random forest model, and the historical vehicle operation data is used as verification data to obtain a vehicle shifting simulation model. A data acquisition module is used to collect real-time vehicle data, substitute the real-time vehicle data into a vehicle shift simulation model, output a vehicle shift simulation result, group the vehicle shift simulation result according to time periods to obtain vehicle shift simulation group data, substitute the vehicle shift simulation group data into a preset vehicle shift parameter knowledge base in sequence for matching, obtain a preset shift parameter corresponding to each vehicle shift simulation group, align the real-time vehicle data with the vehicle shift simulation group in units of time to obtain the real-time vehicle group data, compare the real-time vehicle group data with the preset shift parameter corresponding to each vehicle shift simulation group, and obtain real-time vehicle shift parameter error data; A gear shift data detection module, used for receiving a preset vehicle gear shift error range value, comparing the real-time vehicle gear shift parameter error data with the preset vehicle gear shift error range value, and if the real-time vehicle gear shift parameter error data exceeds the preset vehicle gear shift error range value, marking the real-time vehicle gear shift parameter error data exceeding the preset vehicle gear shift error range value as data to be corrected; A data processing module is used to align the preset shift parameters corresponding to each vehicle shift simulation group with the data to be corrected based on time to obtain the preset shift parameters corresponding to the data to be corrected, retrieve the vehicle real-time data corresponding to the data to be corrected, extract data features of the vehicle real-time data corresponding to the data to be corrected, obtain data features of the data to be corrected, match the data features of the data to be corrected in a preset model knowledge base, obtain a model corresponding to the data features of the corrected data, use the vehicle real-time data corresponding to the data to be corrected to train the model, use the preset shift parameters corresponding to the data to be corrected as verification data, and obtain a shift simulation model of the data to be corrected; The optimization module is used to substitute the real-time vehicle data corresponding to the data to be corrected into the shift parameter simulation model of the data to be corrected to obtain the shift parameter simulation parameters corresponding to the data to be corrected, use the shift parameter simulation parameters corresponding to the corrected data as the shift parameters to be used, substitute the shift parameters to be used into a preset vehicle operation simulation model to obtain the vehicle operation data simulated by the shift parameters to be used, send the shift parameters to be used to the shift device, receive the data fed back by the shift device, compare the data fed back by the shift device with the vehicle operation data simulated by the shift parameters to be used, if the vehicle operation data error data is higher than the preset vehicle operation error range, use the genetic algorithm to optimize the shift simulation model of the data to be corrected to obtain the optimized shift simulation model of the data to be corrected, use the shift simulation model of the data to be corrected to output the optimized shift parameter simulation parameters corresponding to the data to be corrected, and use the optimized shift parameter simulation parameters corresponding to the data to be corrected as the shift execution parameters.

2. The vehicle shift optimization adjustment system based on fuzzy control as claimed in claim 1, characterized in that: The data acquisition module is also used for: According to time, the vehicle real-time data is divided into the same time period as the vehicle shift simulation grouping to form vehicle real-time grouping data. Each real-time data point can correspond to a simulation grouping to determine the time period to which each real-time data point belongs; For each vehicle real-time grouped data, the gear shift parameters are extracted, and the gear shift parameters include engine speed, vehicle speed and accelerator pedal position; The real-time vehicle data is compared with the preset shift parameters in the vehicle shift simulation grouping within the corresponding time period. For each compared parameter, the difference between the real-time parameter and the preset parameter is calculated, and the difference is the real-time vehicle shift parameter error data.

3. The vehicle shift optimization adjustment system based on fuzzy control as claimed in claim 1, characterized in that: The gear shift data detection module is further used for: Obtaining a preset vehicle shift error range value from a system configuration or a database to determine whether a real-time shift parameter deviates from an acceptable range; The real-time vehicle shift parameter error data includes the error between the real-time value and the preset value of the engine speed data, the vehicle speed data, and the accelerator pedal position data; For each real-time error data point, compare each real-time error data point with a preset vehicle shift error range value to check whether the absolute value of the error is less than or equal to the upper limit of the preset range; If the value of each real-time error data point exceeds the preset vehicle shift error range value, that is, the absolute value of the error is greater than the upper limit of the preset range, each real-time error data point is marked as data to be corrected; If the error is within the preset range, the data point is usable; A data set to be corrected is formed for the data points marked as to be corrected, and the data set to be corrected is used to correct the shift parameters that deviate from the preset range.

4. The vehicle shift optimization adjustment system based on fuzzy control as claimed in claim 1, characterized in that: The data processing module is further used for: Extracting data features from the data to be corrected, wherein the data features extracted from the data to be corrected include a timestamp, a vehicle speed, an engine speed, an accelerator pedal position, and a vehicle load; The extracted data features are input into a preset model knowledge base, which includes a neural network, a decision tree, and a support vector machine. Each model in the preset model knowledge base is suitable for different data features and shift control scenarios; Using the real-time vehicle data corresponding to the data to be corrected as the input part of the training data set, and using the training data model for training, so that the model can learn the mapping relationship between the vehicle shift parameters and the real-time data; The preset shift parameters corresponding to the data to be corrected are used as the output part of the verification data set, i.e., the target value. The trained model is applied to the input part of the verification data set, i.e., the real-time vehicle data corresponding to the data to be corrected, and the prediction result is output.

5. A vehicle shift optimization adjustment method based on fuzzy control, applied to the vehicle shift optimization adjustment system based on fuzzy control according to any one of claims 1 to 4, characterized in that: include: Step S101, obtaining vehicle historical data, the vehicle historical data including historical vehicle operation data, historical vehicle shifting data, historical driver operation intention data, historical vehicle operation environment data and historical vehicle load data, using the historical vehicle shifting data, historical driver operation intention data, historical vehicle operation environment data and historical vehicle load data as training data to train a random forest model, using the historical vehicle operation data as verification data to obtain a vehicle shifting simulation model; Step S102, collecting vehicle real-time data, substituting the vehicle real-time data into a vehicle shift simulation model, outputting a vehicle shift simulation result, grouping the vehicle shift simulation result according to time periods to obtain vehicle shift simulation group data, substituting the vehicle shift simulation group data into a preset vehicle shift parameter knowledge base in sequence for matching to obtain preset shift parameters corresponding to each vehicle shift simulation group, aligning the vehicle real-time data with the vehicle shift simulation group in units of time to obtain vehicle real-time group data, comparing the vehicle real-time group data with the preset shift parameters corresponding to each vehicle shift simulation group to obtain real-time vehicle shift parameter error data; Step S103, receiving a preset vehicle gear shift error range value, comparing the real-time vehicle gear shift parameter error data with the preset vehicle gear shift error range value, and if the real-time vehicle gear shift parameter error data exceeds the preset vehicle gear shift error range value, marking the real-time vehicle gear shift parameter error data exceeding the preset vehicle gear shift error range value as data to be corrected; Step S104, aligning the preset shift parameters corresponding to each vehicle shift simulation group with the data to be corrected based on time to obtain the preset shift parameters corresponding to the data to be corrected, retrieving the vehicle real-time data corresponding to the data to be corrected, extracting data features of the vehicle real-time data corresponding to the data to be corrected to obtain data features of the data to be corrected, matching the data features of the data to be corrected in a preset model knowledge base to obtain a model corresponding to the data features of the corrected data, using the vehicle real-time data corresponding to the data to be corrected to train the model, using the preset shift parameters corresponding to the data to be corrected as verification data, and obtaining a shift simulation model of the data to be corrected; Step S105, substitute the real-time vehicle data corresponding to the data to be corrected into the shift parameter simulation model of the data to be corrected to obtain the shift parameter simulation parameters corresponding to the data to be corrected, use the shift parameter simulation parameters corresponding to the corrected data as the shift parameters to be used, substitute the shift parameters to be used into the preset vehicle operation simulation model to obtain the vehicle operation data simulated by the shift parameters to be used, send the shift parameters to be used to the shift device, receive the data fed back by the shift device, compare the data fed back by the shift device with the vehicle operation data simulated by the shift parameters to be used, if the error data of the vehicle operation data is higher than the preset vehicle operation error range, use the genetic algorithm to optimize the shift simulation model of the data to be corrected to obtain the optimized shift simulation model of the data to be corrected, use the shift simulation model of the data to be corrected to output the optimized shift parameter simulation parameters corresponding to the data to be corrected, and use the optimized shift parameter simulation parameters corresponding to the data to be corrected as the shift execution parameters.

6. The vehicle shift optimization adjustment method based on fuzzy control as claimed in claim 5, characterized in that: The step S102 includes: According to time, the vehicle real-time data is divided into the same time period as the vehicle shift simulation grouping to form vehicle real-time grouping data. Each real-time data point can correspond to a simulation grouping to determine the time period to which each real-time data point belongs; For each vehicle real-time grouped data, the gear shift parameters are extracted, and the gear shift parameters include engine speed, vehicle speed and accelerator pedal position; The real-time vehicle data is compared with the preset shift parameters in the vehicle shift simulation grouping within the corresponding time period. For each compared parameter, the difference between the real-time parameter and the preset parameter is calculated, and the difference is the real-time vehicle shift parameter error data.

7. The vehicle shift optimization adjustment method based on fuzzy control as claimed in claim 5, characterized in that: The step S103 includes: Obtaining a preset vehicle shift error range value from a system configuration or a database to determine whether a real-time shift parameter deviates from an acceptable range; The real-time vehicle shift parameter error data includes the error between the real-time value and the preset value of the engine speed data, the vehicle speed data, and the accelerator pedal position data; For each real-time error data point, compare each real-time error data point with a preset vehicle shift error range value to check whether the absolute value of the error is less than or equal to the upper limit of the preset range; If the value of each real-time error data point exceeds the preset vehicle shift error range value, that is, the absolute value of the error is greater than the upper limit of the preset range, each real-time error data point is marked as data to be corrected; If the error is within the preset range, the data point is usable; A data set to be corrected is formed for the data points marked as to be corrected, and the data set to be corrected is used to correct the shift parameters that deviate from the preset range.

8. The vehicle shift optimization adjustment method based on fuzzy control as claimed in claim 5, characterized in that: The step S104 includes: Extracting data features from the data to be corrected, wherein the data features extracted from the data to be corrected include a timestamp, a vehicle speed, an engine speed, an accelerator pedal position, and a vehicle load; The extracted data features are input into a preset model knowledge base, which includes a neural network, a decision tree, and a support vector machine. Each model in the preset model knowledge base is suitable for different data features and shift control scenarios; Using the real-time vehicle data corresponding to the data to be corrected as the input part of the training data set, and using the training data model for training, so that the model can learn the mapping relationship between the vehicle shift parameters and the real-time data; The preset shift parameters corresponding to the data to be corrected are used as the output part of the verification data set, i.e., the target value. The trained model is applied to the input part of the verification data set, i.e., the real-time vehicle data corresponding to the data to be corrected, and the prediction result is output.

Images