Adaptive optimal control method for a gearbox

Abstract

The application provides an adaptive optimization control method for a gearbox, and relates to the technical field of gearbox control, and the method comprises the following steps: performing operation feature extraction on a gearbox operation data stream through an electronic control unit, performing driving prediction based on a vehicle operation state feature set and a steering wheel angle and a brake pedal position, and obtaining driving intention prediction information; matching and analyzing the driving intention prediction information and driving condition information as constraint parameters with a gearbox control strategy space; and performing control feedback evaluation on a target gearbox based on target gearbox control strategy parameters. The application can solve the technical problems that the existing gearbox control method has low accuracy and response timeliness in adjusting gearbox control parameters, often causes gear shifting delay and inaccuracy, and causes poor vehicle driving experience and limited vehicle performance, and can provide more comfortable and safe driving experience for drivers while optimizing vehicle driving performance.

Description

Technical Field

[0001] This application relates to the field of transmission control technology, and in particular to an adaptive optimization control method for transmissions. Background Technology

[0002] Intelligent transmission control is a key component of modern automotive technology. By integrating advanced electronic technology and complex control algorithms, intelligent transmission control systems can significantly improve transmission performance, achieving higher driving performance, fuel efficiency, and ride comfort, thereby better meeting the driving needs of users.

[0003] Currently, existing transmission control methods often suffer from shift delays and inaccurate shifts due to the low accuracy and responsiveness of transmission control parameter adjustments. This results in poor driving experience and limited vehicle performance. Summary of the Invention

[0004] The purpose of this application is to provide an adaptive optimization control method for transmissions to solve the technical problems of existing transmission control methods, which often result in shift delays and inaccurate shifts due to the low accuracy and responsiveness of transmission control parameter adjustments, leading to poor driving experience and limited vehicle performance.

[0005] In view of the above problems, this application provides an adaptive optimization control method for a transmission. The method includes: installing a monitoring and sensing module on a target transmission, the monitoring and sensing module including a speed sensor, a torque sensor, and an oil temperature sensor; acquiring transmission operation data stream through the monitoring and sensing module and transmitting the transmission operation data stream to an electronic control unit; extracting operation features from the transmission operation data stream through the electronic control unit to obtain a vehicle operation state feature set, and simultaneously obtaining the steering wheel angle and brake pedal position through the vehicle control system; performing driving prediction based on the vehicle operation state feature set and the steering wheel angle and brake pedal position to obtain driving intention prediction information; identifying and acquiring driving condition information, constructing a transmission control strategy space, and performing matching analysis between the driving intention prediction information and the driving condition information as constraint parameters and the transmission control strategy space to obtain target transmission control strategy parameters; evaluating control feedback on the target transmission based on the target transmission control strategy parameters to obtain control feedback effect data, and optimizing and recording the target transmission control strategy parameters based on the control feedback effect data.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] A monitoring and sensing module, including a speed sensor, torque sensor, and oil temperature sensor, is installed on the target transmission. This module collects transmission operation data streams and transmits them to the electronic control unit (ECU). The ECU extracts operational features from the transmission operation data streams to obtain a set of vehicle operation state features. Simultaneously, the vehicle control system obtains the steering wheel angle and brake pedal position. Based on the vehicle operation state feature set and the steering wheel angle and brake pedal position, driving intention prediction is performed to obtain driving intention prediction information. Driving condition information is identified and acquired to construct a transmission control strategy space. The driving intention prediction information and the driving condition information are used as constraint parameters and matched with the transmission control strategy space to obtain target transmission control strategy parameters. Based on the target transmission control strategy parameters, control feedback is evaluated on the target transmission to obtain control feedback effect data. The target transmission control strategy parameters are then optimized and recorded using this data. In other words, by installing a monitoring and sensing module on the target transmission to collect data on the transmission's speed, torque, and oil temperature, a transmission operation data stream is obtained. Then, based on this data stream, operational features are extracted to obtain a set of vehicle operating state features. Further, based on the vehicle's steering wheel angle and brake pedal position, and combined with this set of features, driving intention prediction is performed to obtain driving intention prediction information. On the other hand, driving condition information is acquired, and the driving intention prediction information and driving condition information are input into the transmission control strategy space for matching analysis to obtain transmission control strategy parameters. Finally, the target transmission is controlled according to these parameters, and the control effect is evaluated and feedback data is recorded to optimize subsequent transmission control strategy parameters. Through real-time monitoring and intelligent decision-making, the accuracy and timeliness of transmission control parameter adjustments can be improved, resulting in smoother and more stable gear shifts, thus providing a more comfortable and safer driving experience and optimizing vehicle driving performance.

[0008] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0010] Figure 1 This is a flowchart illustrating the adaptive optimization control method for a transmission used in this application.

[0011] Figure 2 This is a schematic diagram of the process for obtaining driving intention prediction information in the adaptive optimization control method for transmissions used in this application. Detailed Implementation

[0012] This application provides an adaptive optimization control method for transmissions, solving the technical problem that existing transmission control methods often suffer from shift delays and inaccurate shifts due to low accuracy and responsiveness in adjusting transmission control parameters, resulting in a poor driving experience and limited vehicle performance. Through real-time monitoring and intelligent decision-making, the accuracy and responsiveness of transmission control parameter adjustments can be improved, leading to smoother and more stable transmission shifts. This provides drivers with a more comfortable and safer driving experience while optimizing vehicle driving performance.

[0013] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0014] Please see the appendix Figure 1 This application provides an adaptive optimization control method for a transmission, the method specifically including the following steps:

[0015] Step 1: Install a monitoring and sensing module on the target transmission. The monitoring and sensing module includes a speed sensor, a torque sensor, and an oil temperature sensor. The monitoring and sensing module collects transmission operation data streams and transmits the transmission operation data streams to the electronic control unit.

[0016] Specifically, firstly, a monitoring and sensing module is installed on the target transmission. This module includes a speed sensor, a torque sensor, and an oil temperature sensor. The speed sensor measures the rotational speeds of the transmission's input and output shafts, crucial for determining shift points and monitoring transmission response. The torque sensor measures the torque transmitted to the transmission, helping to assess engine load and transmission efficiency. The oil temperature sensor monitors the temperature of the transmission fluid, as excessively high or low temperatures can affect transmission performance and lifespan. Next, at preset time points, the monitoring and sensing module acquires transmission operation data streams. These preset time points can be set according to actual conditions, for example, an interval of 1 second between adjacent time points. The transmission operation data stream includes speed, torque, and oil temperature data. This data stream is then transmitted to the electronic control unit (ECU), which acts as the vehicle's brain, processing this data and making corresponding control decisions.

[0017] Step 2: The electronic control unit extracts the operating features of the transmission operating data stream to obtain a set of vehicle operating status features. At the same time, the vehicle control system obtains the steering wheel angle and brake pedal position. Based on the set of vehicle operating status features and the steering wheel angle and brake pedal position, driving prediction is performed to obtain driving intention prediction information.

[0018] Specifically, the electronic control unit (ECU) extracts operational features from the transmission's operational data stream. Before feature extraction, the ECU preprocesses the collected data, including noise removal, outlier correction, filtering, and normalization, to ensure data accuracy and consistency. Then, feature extraction algorithms are used to extract the most useful information describing the vehicle's operating state from the raw data. These algorithms include statistical methods, time-frequency analysis, and machine learning techniques. For example, speed data features include average speed, speed change rate, and speed fluctuation; torque data features include average torque, peak torque, and torque fluctuation; and oil temperature data features include oil temperature trend, oil temperature stability, and peak oil temperature. This process yields a set of vehicle operating state features.

[0019] On the other hand, the steering wheel angle and brake pedal position are obtained through the vehicle control system. The steering wheel angle sensor accurately measures the steering wheel's rotation angle, which is crucial for vehicle steering control. By analyzing the steering wheel angle data, the vehicle's steering intention can be predicted, and the vehicle's stability control strategy can be adjusted accordingly. The brake pedal position determines the brake pedal travel, thus indicating the driver's intention to decelerate or stop. By analyzing the brake pedal position data, the vehicle's deceleration or stopping needs can be predicted, and the vehicle's braking system control strategy can be adjusted accordingly. Then, based on the vehicle's operating state feature set and the steering wheel angle and brake pedal position, driving prediction is performed. Driving prediction refers to predicting the driver's intention based on real-time vehicle operating data and the driver's input, obtaining driving intention prediction information. This driving intention prediction information includes acceleration, deceleration, turning, or stopping, etc. Machine learning algorithms or other pattern recognition techniques can be used to analyze the data and predict the driver's future driving intentions, such as using a support vector machine to build a prediction model.

[0020] Step 3: Identify and acquire driving condition information, construct a transmission control strategy space, and perform matching analysis between the driving intention prediction information and the driving condition information as constraint parameters and the transmission control strategy space to obtain the target transmission control strategy parameters.

[0021] Specifically, the system identifies and categorizes current driving conditions, such as road type (highway, city road, mountain road, etc.), traffic conditions (congestion, smooth traffic, etc.), and weather conditions (sunny, rainy, snowy, etc.), to obtain driving condition information. For example, current driving conditions can be obtained through navigation software. A transmission control strategy space is constructed, which consists of adjustment thresholds for multiple transmission control parameters, including shift parameters, throttle response parameters, and clutch control parameters, obtained through attribute analysis of the target transmission.

[0022] Then, the predicted driving intention information and the driving condition information are used as constraint parameters to perform a matching analysis with the transmission control strategy space. This matching analysis includes optimization algorithms and machine learning models to find the optimal transmission control parameter settings. Based on the matching analysis results, target transmission control strategy parameters are determined, which are the most suitable transmission control parameters under the current driving conditions. In this way, the vehicle control system can dynamically adjust the transmission control strategy according to real-time changes in driving conditions and the driver's predicted intentions, providing a safer, more comfortable, and more efficient driving experience.

[0023] Step 4: Based on the target transmission control strategy parameters, perform control feedback evaluation on the target transmission to obtain control feedback effect data, and optimize and record the target transmission control strategy parameters using the control feedback effect data.

[0024] Specifically, based on the electronic control unit, control commands are sent to the target transmission according to the target transmission control strategy parameters, including shift timing, shift speed, and throttle response. Simultaneously, control results are collected to obtain a control result dataset. For example, sensors continuously monitor the transmission's operating status, including speed, torque, and oil temperature, while also monitoring the vehicle's operating status, such as speed, acceleration, and steering wheel angle. Then, a preset evaluation algorithm or model is used to evaluate the control results based on the control result dataset. Evaluation indicators include the smoothness of control performance, response speed, and fuel efficiency, yielding control feedback effect data. The target transmission control strategy parameters are then optimized based on the control feedback effect data. For example, if the control feedback effect of a certain indicator does not meet expectations, parameter optimization analysis is performed on that indicator to obtain optimized control strategy parameters for adaptive control of the target transmission. During the parameter optimization analysis, all data related to transmission control stability and reliability should be recorded to provide crucial information for subsequent fault diagnosis, performance optimization, and maintenance plan development. These data records are essential for ensuring long-term stable transmission operation and improving overall vehicle performance. Real-time monitoring and intelligent decision-making can improve the accuracy and timeliness of gearbox control parameter adjustments, making gearbox shifts smoother and more stable, thereby providing drivers with a more comfortable and safer driving experience, and optimizing vehicle driving performance.

[0025] The above method can solve the technical problem of existing transmission control methods, which often suffer from shift delays and inaccurate shifts due to the low accuracy and responsiveness of transmission control parameter adjustments, resulting in poor driving experience and limited vehicle performance. First, a monitoring and sensing module is installed on the target transmission. This module includes a speed sensor, a torque sensor, and an oil temperature sensor. The module collects transmission operation data streams and transmits them to the electronic control unit (ECU). Then, the ECU extracts operational features from the transmission data streams to obtain a set of vehicle operating state features. Simultaneously, the vehicle control system obtains the steering wheel angle and brake pedal position. Based on the vehicle operating state feature set and the steering wheel angle and brake pedal position, driving intention prediction is performed to obtain driving intention prediction information. Next, driving condition information is identified and acquired to construct a transmission control strategy space. The driving intention prediction information and the driving condition information are used as constraint parameters and matched with the transmission control strategy space to obtain target transmission control strategy parameters. Finally, based on the target transmission control strategy parameters, control feedback is evaluated on the target transmission to obtain control feedback effect data. This data is then used to optimize and record the target transmission control strategy parameters. By installing a monitoring and sensing module on the target transmission to collect data on transmission speed, torque, and oil temperature, a transmission operation data stream is obtained. Then, based on this data stream, operational features are extracted to obtain a set of vehicle operating state features. Further, based on the vehicle's steering wheel angle and brake pedal position, and combined with this set of features, driving intention prediction is performed to obtain driving intention prediction information. Simultaneously, driving condition information is acquired, and the driving intention prediction information and driving condition information are input into the transmission control strategy space for matching analysis to obtain transmission control strategy parameters. Finally, the target transmission is controlled according to these parameters, and the control effect is evaluated and feedback data is recorded to optimize subsequent transmission control strategy parameters. Through real-time monitoring and intelligent decision-making, the accuracy and timeliness of transmission control parameter adjustments can be improved, resulting in smoother and more stable gear shifts, thus providing a more comfortable and safer driving experience and optimizing vehicle driving performance.

[0026] Further details are attached. Figure 2 As shown, step two of this application includes:

[0027] A driving intent label library is constructed based on vehicle driving application scenarios; a vehicle driving database is collected and acquired, and the vehicle driving database is labeled according to the driving intent label library to obtain a vehicle driving intent label database; a support vector machine is used to train the vehicle driving intent label database for intent classification to obtain a driving intent classification predictor; the driving intent classification predictor is evaluated and optimized in multiple dimensions to generate a driving intent classification optimized predictor, and driving prediction is performed based on the driving intent classification optimized predictor on the vehicle operating state feature set and the steering wheel angle and brake pedal position to obtain the driving intent prediction information.

[0028] Specifically, firstly, the vehicle driving application scenarios are analyzed, such as different driving scenarios and purposes, including city driving, highway driving, mountain driving, and emergency avoidance. Then, the different driving intentions that the driver may take in these scenarios are identified and divided into several main categories, such as acceleration, deceleration, turning, and maintaining a straight course. Next, for each category, the intentions are further subdivided. For example, acceleration can be divided into slow acceleration, smooth acceleration, and rapid acceleration. Different levels are defined for each intention category to reflect the intensity and urgency of the driver's intention. For example, deceleration can be divided into slight deceleration, moderate deceleration, and emergency braking. Furthermore, a driving intention tag library is constructed based on multiple driving intentions and corresponding levels. The driving intention tag library contains all the predefined driving intention tags, and each tag has its corresponding category and level. At the same time, driving scenarios and driver operations can be mapped to the corresponding tags. For example, on a highway, a driver may perform smooth acceleration, which can be mapped to the smooth acceleration category in the tag library.

[0029] A vehicle driving database is collected. For example, using the target vehicle as a constraint, historical vehicle driving data is retrieved to construct the database. This data includes vehicle speed, engine speed, steering wheel angle, brake pedal position, and accelerator pedal position. Then, the vehicle driving database is tagged according to the driving intent tag library. This involves labeling the vehicle driving data and establishing a mapping between the data and the tags, thus constructing a vehicle driving intent tag database.

[0030] Support Vector Machines (SVMs) are a widely used supervised learning algorithm for classification and regression analysis. They are highly effective in solving both linearly and non-linearly separable problems. The core idea is to find an optimal decision boundary that separates different classes of data as much as possible while maximizing the distance from the boundary to the data points on either side. Using the vehicle driving intention label database as training data, the SVM is trained under supervised supervision. The input data for the SVM consists of vehicle driving data, including vehicle operating state features, steering wheel angle, and brake pedal position. The output data is the driving intention, resulting in a driving intention classification predictor that meets the expected convergence constraint, which is the expected output accuracy metric and can be set according to actual needs.

[0031] Next, the driving intention classification predictor undergoes multi-dimensional evaluation and optimization to improve the model's performance and accuracy. This multi-dimensional evaluation includes accuracy, precision, recall, and generalization ability. Based on the evaluation results, the driving intention classification predictor is further optimized to obtain an optimized driving intention classification predictor. This optimized predictor is then used to perform driving intention prediction based on the vehicle's operating state feature set, the steering wheel angle, and the brake pedal position, outputting the predicted driving intention information.

[0032] By constructing a driving intention classification predictor based on support vector machines and optimizing the predictor according to multidimensional evaluation results, the performance and accuracy of the predictor can be improved, thereby improving the accuracy, reliability and efficiency of obtaining driving intention prediction information.

[0033] Furthermore, this application also includes the following steps:

[0034] The driving intention classification predictor is evaluated using a data validation set to determine its multidimensional performance evaluation parameters. A predictor optimization parameter space is constructed, comprising predictor performance evaluation parameters, model optimization parameters, and corresponding model optimization effect data. Based on the multidimensional performance evaluation parameters and the predictor optimization parameter space, parameter matching and filtering are performed to obtain a set of predictor optimization parameters. The model optimization effect data is then compared and optimized within the predictor optimization parameter set to determine the model optimization parameters. Based on these model optimization parameters, the driving intention classification predictor is iteratively optimized to generate the optimized driving intention classification predictor.

[0035] Specifically, the method for generating a driving intent classification prediction optimizer is as follows: First, the driving intent classification prediction optimizer is evaluated using a data validation set to obtain multi-dimensional performance evaluation parameters, including accuracy, precision, recall, and generalization ability. Next, a prediction optimizer parameter space is constructed, comprising prediction performance evaluation parameters, model optimization parameters, and corresponding model optimization effect data. The prediction performance evaluation parameters are standard performance evaluation parameters, such as accuracy, precision, recall, and generalization ability metrics. The model optimization parameters include learning rate update step size, number of iterations, and regularization parameters. The model optimization effect data is used to evaluate the optimization effect of different parameter combinations.

[0036] Then, the predictor's multidimensional performance evaluation parameters are iterated and compared according to the predictor performance evaluation parameters in the predictor optimization parameter space. Parameters that do not meet the predictor performance evaluation parameters are set as predictor optimization parameters, resulting in a set of predictor optimization parameters. For example, if the accuracy is less than the accuracy index, then the accuracy is the predictor optimization parameter. Further, the model optimization effect data is compared and optimized within the set of predictor optimization parameters, and the model optimization parameter with the best optimization effect is selected. Then, the driving intention classification predictor is iteratively optimized according to the model optimization parameters, such as increasing the number of iterations, adjusting the learning rate update step size, etc., until the driving intention classification optimized predictor that meets the expected index is obtained.

[0037] Furthermore, step three of this application includes:

[0038] An attribute classifier is constructed to divide and cluster the transmission control strategy space, obtaining a transmission attribute feature strategy space. The driving intention prediction information and driving condition information are used as constraint parameters, and these constraint parameters are labeled based on the attribute classifier to obtain driving calibration feature parameters. A mapping and matching process is performed between the driving calibration feature parameters and the transmission attribute feature strategy space to obtain a transmission calibration strategy library. A transmission control cost function is constructed, and the transmission calibration strategy library is evaluated and optimized based on the transmission control cost function to obtain the target transmission control strategy parameters.

[0039] Specifically, an attribute classifier is constructed based on the decision tree principle to better understand the diversity of transmission control strategies and divide them into strategy groups with similar attribute features. Then, the attribute classifier is used to partition and cluster the transmission control strategy space, further refining and optimizing the strategy space to better align with actual driving needs, thus obtaining a transmission attribute feature strategy space. Furthermore, the driving intention prediction information and the driving condition information are used as constraint parameters. The attribute classifier labels the driving intention prediction information and the driving condition information, where labeling refers to identifying the constraint parameters as feature parameters, resulting in driving calibration feature parameters, which are the feature parameters classified by the attribute classifier.

[0040] Next, the driving calibration feature parameters and the transmission attribute feature strategy space are mapped and matched, that is, the driving calibration feature parameters are identified to the transmission attribute feature strategies in the transmission attribute feature strategy space to construct a transmission calibration strategy library. On the other hand, a transmission control cost function is constructed, which is used to evaluate the transmission control effect. The better the control effect, the smaller the cost function evaluation result. Then, the transmission calibration strategy library is evaluated according to the transmission control cost function to determine multiple cost function evaluation results. Further, the transmission calibration strategy corresponding to the smallest cost function evaluation result among the multiple cost function evaluation results is selected as the target transmission control strategy parameter to obtain the target transmission control strategy parameter.

[0041] Furthermore, this application also includes the following steps:

[0042] The transmission attribute factor information is obtained, including driving intention information and driving condition information; the attribute content nodes of the transmission attribute factor information are extracted sequentially to obtain a set of transmission attribute content nodes; feature parameters are assigned to each content node in the set of transmission attribute content nodes to obtain a set of attribute content node feature parameters; the attribute classifier is constructed based on the set of transmission attribute content nodes and the set of attribute content node feature parameters.

[0043] Specifically, the method for constructing the attribute classifier is as follows: First, obtain transmission attribute factor information, which includes driving intention information and driving condition information. Driving intention information includes acceleration, deceleration, turning, and maintaining straight driving, while driving condition information includes road type, traffic conditions, and weather conditions. Then, extract attribute content nodes sequentially from the transmission attribute factor information to obtain a set of transmission attribute content nodes. Each transmission attribute content node refers to the specific content information of each attribute factor. For example, driving conditions include road types such as highways, city roads, and mountain roads, and traffic conditions such as congestion and smooth traffic. Each attribute content is treated as a node.

[0044] Then, feature parameters are assigned to each content node in the gearbox attribute content node set. Feature parameter assignment refers to encoding each content node with different feature parameters. The parameter encoding format can be set by the user, for example, using letters and numbers to encode, thus obtaining the attribute content node feature parameter set. Next, based on the decision tree principle, the gearbox attribute content node is taken as a child node, and the corresponding attribute content node feature parameter is taken as the leaf node of the child node. Using the gearbox attribute content node set and the attribute content node feature parameter set as the construction data, the attribute classifier is generated.

[0045] Furthermore, this application also includes the following steps:

[0046] Define the transmission control objective, extract performance evaluation indicators for the transmission control objective, and obtain a set of transmission control performance evaluation indicators; assign weights to each evaluation indicator in the set of transmission control performance evaluation indicators to determine a set of performance evaluation indicator weight factors; based on the set of transmission control performance evaluation indicators and the set of performance evaluation indicator weight factors, perform data fitting on the transmission control strategy space to construct the transmission control cost function.

[0047] Specifically, firstly, the transmission control objectives are defined, that is, the performance and functional goals that the transmission control system needs to achieve are determined, such as shift smoothness, fuel efficiency, and driving experience. Then, effect evaluation indicators are extracted from these transmission control objectives. Based on the defined transmission control objectives, key indicators reflecting the control effect are extracted, including shift delay, shift shock, fuel consumption rate, and driving comfort, resulting in a set of transmission control effect evaluation indicators. Further, based on the coefficient of variation (COP) method, weights are assigned to each evaluation indicator in the set of transmission control effect evaluation indicators. The COP method is a commonly used weighting method that determines the importance of each indicator in the overall evaluation based on the degree of variation of its data. First, for each evaluation indicator in the set of transmission control effect evaluation indicators, its mean and standard deviation are calculated across all samples. Then, the COP is calculated, where the COP is the ratio of the standard deviation to the mean, used to measure the degree of variation of each evaluation indicator. Finally, based on the COP of each evaluation indicator, its weight in the overall evaluation is calculated, where a larger COP corresponds to a larger weight, thus determining the set of effect evaluation indicator weight factors. By using the coefficient of variation method for weight allocation, the evaluation of gearbox control performance can be made more reasonable and objective. This method can automatically adjust the weight of each evaluation index according to the characteristics of the data, thereby improving the accuracy and reliability of the evaluation results.

[0048] Finally, based on the set of evaluation indicators for transmission control effect and the set of weight factors for the evaluation indicators, data fitting is performed on the transmission control strategy space to generate a transmission control cost function. The evaluation result of the transmission control cost function is a weighted calculation result of the control effect evaluation indicators. The cost function evaluation result is inversely proportional to the control effect; that is, the better the control effect, the smaller the corresponding cost function evaluation result.

[0049] Furthermore, step four of this application includes:

[0050] Identify the effects to be optimized in the control feedback effect data, perform parameter optimization analysis on the effects to be optimized, and obtain the optimization direction of the control strategy parameters; dynamically optimize the control strategy parameters of the target transmission based on the optimization direction of the control strategy parameters, determine the optimized control strategy parameters of the transmission, and perform adaptive control of the target transmission based on the optimized control strategy parameters of the transmission.

[0051] Specifically, the process involves identifying control indicators in the control feedback data that require optimization. These indicators do not meet the expected control requirements, such as control stability, control reliability, and shift smoothness. Next, parameter optimization analysis is performed based on these indicators. This involves analyzing control strategy parameters that may affect the control effect, such as shift timing, throttle response, and clutch control, to determine the optimization direction for these parameters. Optimization directions include adjusting parameter values, changing parameter ranges, and optimizing parameter combinations. Then, based on the optimization direction, the target transmission control strategy parameters are dynamically optimized to obtain optimized transmission control strategy parameters. Finally, adaptive control is applied to the target transmission using these optimized control strategy parameters. This means the control strategy automatically adjusts the transmission's control parameters, such as shift timing and shift speed, according to current driving conditions. This method improves transmission control performance, enhances the driving experience, and ensures vehicle stability and reliability under various driving conditions.

[0052] Furthermore, this application also includes the following steps:

[0053] Based on the optimization direction of the control strategy parameters, the control feedback effect data is subjected to regulation and correlation analysis to obtain the control strategy parameter optimization pace; the target transmission control strategy parameters are optimized and updated according to the control strategy parameter optimization pace to obtain a control variation update strategy parameter set; the control variation update strategy parameter set is evaluated and optimized based on the transmission control cost function to determine the optimal control strategy parameters for the transmission.

[0054] Specifically, the method for determining the optimal control strategy parameters for the transmission is as follows: First, based on the optimization direction of the control strategy parameters, a regulatory correlation analysis is performed on the control feedback effect data. This involves analyzing how changes in the control strategy parameters affect the control effect, and the impact of fluctuations in the control effect on the parameters. Next, the optimization pace of the control strategy parameters is determined based on the results of the regulatory correlation analysis. This optimization pace includes the frequency and magnitude of parameter updates. Then, the target transmission control strategy parameters are optimized and updated according to the optimization pace, resulting in an updated set of control variation update strategy parameters. Finally, the set of control variation update strategy parameters is evaluated and optimized based on the transmission control cost function. The control variation update strategy parameter with the smallest cost function evaluation result is selected as the optimal control strategy parameter for the transmission, thus obtaining the optimal control strategy parameters for the transmission.

[0055] In summary, the adaptive optimization control method for transmissions provided in this application has the following technical effects:

[0056] 1. By installing a monitoring and sensing module on the target transmission, data on transmission speed, torque, and oil temperature are collected to obtain a transmission operation data stream. Then, based on this data stream, operational features are extracted to obtain a set of vehicle operation state features. Further, based on the vehicle's steering wheel angle and brake pedal position, and combined with the vehicle operation state feature set, driving intention prediction is performed to obtain driving intention prediction information. Simultaneously, driving condition information is acquired, and the driving intention prediction information and driving condition information are input into the transmission control strategy space for matching analysis to obtain transmission control strategy parameters. Finally, the target transmission is controlled according to the transmission control strategy parameters, and the control effect is evaluated and feedback data is recorded to optimize subsequent transmission control strategy parameters. Through real-time monitoring and intelligent decision-making, the accuracy and timeliness of transmission control parameter adjustments can be improved, resulting in smoother and more stable transmission shifts, thus providing a more comfortable and safer driving experience for the driver, while also optimizing vehicle driving performance.

[0057] 2. By constructing a driving intention classification predictor based on support vector machines and optimizing the driving intention classification predictor according to the multidimensional evaluation results, the performance and accuracy of the predictor can be improved, thereby improving the accuracy, reliability and efficiency of obtaining driving intention prediction information.

[0058] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0059] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. An adaptive optimization control method for a transmission, characterized in that, The method includes: A monitoring and sensing module is installed on the target transmission. The monitoring and sensing module includes a speed sensor, a torque sensor, and an oil temperature sensor. The transmission operation data stream is collected through the monitoring and sensing module and transmitted to the electronic control unit. The electronic control unit extracts the operating features of the transmission operating data stream to obtain a set of vehicle operating status features. At the same time, the vehicle control system obtains the steering wheel angle and brake pedal position. Based on the set of vehicle operating status features and the steering wheel angle and brake pedal position, driving prediction is performed to obtain driving intention prediction information. The driving condition information is identified and acquired, and a transmission control strategy space is constructed. The driving intention prediction information and the driving condition information are used as constraint parameters to match and analyze with the transmission control strategy space to obtain the target transmission control strategy parameters. Based on the target transmission control strategy parameters, the target transmission is evaluated for control feedback to obtain control feedback effect data, and the control strategy parameters of the target transmission are optimized and recorded using the control feedback effect data. The acquisition of driving intention prediction information includes: Build a driving intent tag library based on vehicle driving application scenarios; Collect and acquire a vehicle driving database, and tag the vehicle driving database according to the driving intention tag library to obtain a vehicle driving intention tag database; A driving intent classification predictor is obtained by training the vehicle driving intent label database using a support vector machine for intent classification. The driving intention classification predictor is evaluated and optimized in multiple dimensions to generate a driving intention classification optimized predictor. Based on the driving intention classification optimized predictor, driving prediction is performed on the vehicle operating state feature set, the steering wheel angle, and the brake pedal position to obtain the driving intention prediction information. The generated driving intention classification optimization predictor includes: The driving intention classification predictor is evaluated in multiple dimensions using a data validation set to determine the multidimensional performance evaluation parameters of the predictor. Construct a predictor optimization parameter space, which includes predictor performance evaluation parameters, model optimization parameters, and corresponding model optimization effect data; Based on the multidimensional performance evaluation parameters of the predictor and the optimization parameter space of the predictor, parameter matching and filtering are performed to obtain the set of optimization parameters for the predictor. The model optimization effect data is compared and optimized within the predictor optimization parameter set to determine the model optimization parameters. Based on the model optimization parameters, the driving intention classification predictor is iteratively optimized to generate the driving intention classification optimized predictor.

2. The adaptive optimization control method for a transmission as described in claim 1, characterized in that, The obtained target transmission control strategy parameters include: Construct an attribute classifier, and use the attribute classifier to divide and cluster the gearbox control strategy space to obtain the gearbox attribute feature strategy space; The driving intention prediction information and the driving condition information are used as constraint parameters. The constraint parameters are labeled based on the attribute classifier to obtain driving calibration feature parameters. Based on the driving calibration feature parameters and the transmission attribute feature strategy space, a mapping and matching is performed to obtain the transmission calibration strategy library; A transmission control cost function is constructed, and the transmission calibration strategy library is evaluated and optimized based on the transmission control cost function to obtain the target transmission control strategy parameters.

3. The adaptive optimization control method for a transmission as described in claim 2, characterized in that, The construction of the attribute classifier includes: Obtain transmission attribute factor information, which includes driving intention information and driving condition information; The attribute content nodes of the gearbox attribute factor information are extracted sequentially to obtain a set of gearbox attribute content nodes; Assign feature parameters to each content node in the gearbox attribute content node set to obtain the attribute content node feature parameter set; The attribute classifier is constructed based on the set of attribute content nodes of the gearbox and the set of feature parameters of the attribute content nodes.

4. The adaptive optimization control method for a transmission as described in claim 2, characterized in that, The construction of the transmission control cost function includes: Define the gearbox control objective, extract the effect evaluation index of the gearbox control objective, and obtain the gearbox control effect evaluation index set; Weights are assigned to each evaluation index in the gearbox control effect evaluation index set to determine the set of effect evaluation index weight factors. Based on the set of evaluation indicators for transmission control performance and the set of weight factors for the evaluation indicators, data fitting is performed on the transmission control strategy space to construct the transmission control cost function.

5. The adaptive optimization control method for a transmission as described in claim 2, characterized in that, The method includes: Identify the effects to be optimized in the control feedback effect data, perform parameter optimization analysis on the effects to be optimized, and obtain the direction of control strategy parameter optimization; The control strategy parameters of the target transmission are dynamically optimized based on the optimization direction of the control strategy parameters to determine the optimized control strategy parameters of the transmission, and the target transmission is adaptively controlled based on the optimized control strategy parameters of the transmission.

6. The adaptive optimization control method for a transmission as described in claim 5, characterized in that, The determination of the transmission optimization control strategy parameters includes: Based on the optimization direction of the control strategy parameters, the control feedback effect data is adjusted and correlated to obtain the control strategy parameter optimization pace. The control strategy parameters of the target gearbox are optimized and updated according to the optimization pace of the control strategy parameters to obtain a set of control mutation update strategy parameters. The control mutation update strategy parameter set is evaluated and optimized based on the transmission control cost function to determine the transmission optimized control strategy parameters.

Images