Intelligent control platform for retractable tail structure

Through the intelligent control platform, a variety of information is collected and processed in real time, and an optimized control solution is generated, which solves the problems of untimely and inaccurate tail wing adjustment in the existing technology, improves the aerodynamic performance and driving stability of the vehicle, and adapts to complex driving environments. need.

CN118810649BActive Publication Date: 2024-12-06AISHIEN POWER TECHNOLOGY (JIANGSU) CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411297761.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-18
Publication Date
2024-12-06
Estimated Expiration
2044-09-18

AI Technical Summary

Technical Problem

Due to the limitations of preset strategies and data transmission lag, the existing telescopic tail control system has untimely and inaccurate tail adjustments, which affects the vehicle's aerodynamic performance and driving stability, and cannot meet the response speed in complex driving environments. and accuracy requirements.

Method used

Provide an intelligent control platform, including monitoring end, control end and service center, to predict driving stability and drag coefficient by collecting and processing airflow velocity, angle, motion speed, and tail structure information in real time, and generate optimization control solutions to achieve real-time optimization of tail velocity Structural control.

Benefits of technology

Real-time optimization and control of telescopic tail wing structure is achieved, which improves the vehicle's aerodynamic performance and driving stability, meets the response speed and accuracy requirements of complex driving environments, and reduces driving risks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118810649B_ABST
    Figure CN118810649B_ABST
Patent Text Reader

Abstract

The present application provides an intelligent control platform for a retractable tail structure, which relates to the field of intelligent control technology, including: a monitoring end collects airflow velocity information and airflow angle information; a control end uploads motion velocity information, tail structure telescopic length information, tail structure azimuth information and tail structure pitch angle information; a service center, including: a stability prediction unit predicts a driving stability coefficient; a drag prediction unit predicts a driving drag coefficient; a control optimization unit optimizes the motion velocity information, tail structure telescopic length information, tail structure azimuth information and tail structure pitch angle information to generate a retractable tail structure control scheme; a data interaction unit controls the retractable tail structure. The present application can solve the technical problems of untimely and inaccurate tail adjustment in the prior art, achieve the technical goal of real-time optimization and control of the retractable tail structure, and achieve the technical effect of improving the aerodynamic performance and driving stability of the vehicle.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of intelligent control technology, and in particular to an intelligent control platform for a retractable tail wing structure. Background Art

[0002] In the optimization of modern automobile aerodynamics, the application of retractable rear wing structures has become increasingly common. The rear wing structure reduces drag and increases downforce by adjusting the air flow at the rear of the vehicle, thereby improving the stability and handling of the vehicle. However, the existing retractable rear wing control system still has some shortcomings when dealing with complex and changeable driving conditions, and it is in urgent need of improvement.

[0003] At present, the existing technology mainly relies on preset tail control strategies, which are usually based on fixed driving conditions or simple sensor feedback. However, the airflow speed and angle in the actual driving environment vary greatly, and the vehicle's motion state is also constantly changing. The preset strategy is difficult to cope with these dynamic changes, resulting in delayed or inaccurate tail adjustment. In addition, the existing system lacks comprehensive consideration of driving stability and resistance, and often only focuses on optimization in one aspect, and cannot achieve overall performance improvement. For complex driving environments, such as high-speed driving, sharp turns, or sudden strong winds, the response speed and adjustment accuracy of the existing control system cannot meet the requirements, resulting in reduced vehicle stability and increased driving risks. In addition, the existing technology also has defects in data processing and transmission. Due to the untimely and inaccurate data transmission, the tail control system cannot adjust the tail structure in real time, resulting in a deviation between the actual control effect and the expected effect. This situation is particularly obvious when driving at high speeds, the airflow changes quickly, and the tail adjustment requires a higher response speed and accuracy. However, due to the lag in data interaction, the existing system often cannot meet this requirement.

[0004] In summary, the prior art has technical problems in that the rear wing adjustment is not timely and accurate due to the limitations of the preset control strategy and the lag in data transmission, which further affects the aerodynamic performance and driving stability of the vehicle. Summary of the invention

[0005] The purpose of this application is to provide an intelligent control platform for a retractable tail wing structure, so as to solve the technical problem in the prior art that the tail wing adjustment is not timely and accurate due to the limitations of the preset control strategy and the lag in data transmission, which further affects the vehicle's aerodynamic performance and driving stability.

[0006] In view of the above problems, the present application provides an intelligent control platform for a retractable tail wing structure.

[0007] The present application provides an intelligent control platform for a retractable tail wing structure, which includes: a monitoring end, the monitoring end is used to collect airflow speed information and airflow angle information in a pre-driving area; a control end, the control end is used to upload movement speed information, tail wing structure telescopic length information, tail wing structure azimuth information and tail wing structure pitch angle information; a service center, including: a stability prediction unit, used to process the airflow speed information, the airflow angle information, the movement speed information, the tail wing structure telescopic length information, the tail wing structure azimuth information and the tail wing structure pitch angle information, and predict the driving stability coefficient; a resistance prediction unit, Used to process the airflow velocity information, the airflow angle information, the movement speed information, the tail wing structure telescopic length information, the tail wing structure azimuth information and the tail wing structure pitch angle information, and predict the driving resistance coefficient; a control optimization unit, used to optimize the movement speed information, the tail wing structure telescopic length information, the tail wing structure azimuth information and the tail wing structure pitch angle information according to the driving stability coefficient and the driving resistance coefficient, and generate a telescopic tail wing structure control plan; a data interaction unit, used to send the retractable tail wing structure control plan to the control end to control the telescopic tail wing structure.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The monitoring end is used to collect airflow speed information and airflow angle information in the pre-driving area; the control end is used to upload movement speed information, tail wing structure telescopic length information, tail wing structure azimuth information and tail wing structure pitch angle information; the service center includes: a stability prediction unit, which is used to process the airflow speed information, the airflow angle information, the movement speed information, the tail wing structure telescopic length information, the tail wing structure azimuth information and the tail wing structure pitch angle information to predict the driving stability coefficient; a resistance prediction unit, which is used to process the airflow speed information, the airflow angle information, the movement speed information, the tail wing structure telescopic length information, the tail wing structure azimuth information and the tail wing structure pitch angle information to predict the driving stability coefficient; The telescopic length information, the azimuth angle information of the tail wing structure and the pitch angle information of the tail wing structure are used to predict the driving resistance coefficient; a control optimization unit is used to optimize the movement speed information, the telescopic length information of the tail wing structure, the azimuth angle information of the tail wing structure and the pitch angle information of the tail wing structure according to the driving stability coefficient and the driving resistance coefficient, and generate a telescopic tail wing structure control plan; a data interaction unit is used to send the retractable tail wing structure control plan to the control end to control the telescopic tail wing structure, thereby realizing the technical goal of real-time optimization and control of the telescopic tail wing structure, and achieving the technical effect of improving the aerodynamic performance and driving stability of the vehicle.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 This is a schematic diagram of the structure of the intelligent control platform for the retractable tail structure in this application;

[0013] Figure 2 This is a schematic diagram of the process of executing the stability prediction unit in the intelligent control platform for the retractable tail structure of the present application.

[0014] Description of reference numerals:

[0015] Monitoring terminal 10 , control terminal 20 , service center 30 , stability prediction unit 31 , resistance prediction unit 32 , control optimization unit 33 , data interaction unit 34 . DETAILED DESCRIPTION

[0016] This application provides an intelligent control platform for a retractable tail wing structure, which solves the technical problem in the prior art that the tail wing adjustment is not timely and accurate due to the limitations of the preset control strategy and the lag of data transmission, which further affects the aerodynamic performance and driving stability of the vehicle. The technical goal of real-time optimization and control of the retractable tail wing structure is achieved, and the technical effect of improving the aerodynamic performance and driving stability of the vehicle is achieved.

[0017] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0018] For examples, please see the attached Figure 1 The present application provides an intelligent control platform for a retractable tail structure, which specifically includes:

[0019] The monitoring terminal 10 is used to collect airflow velocity information and airflow angle information in the pre-driving area.

[0020] Specifically, the main function of the monitoring terminal 10 is to collect airflow velocity information and airflow angle information in the pre-driving area. The monitoring terminal 10 monitors and records the airflow changes in front of the vehicle in real time through sensors and data acquisition systems. The airflow changes are used to adjust and control the tail wing structure, because the speed and angle of the airflow will directly affect the stability and handling performance of the vehicle. Through continuous monitoring, it is ensured that the tail wing structure can adapt to the airflow changes in different driving environments, thereby improving the driving safety and stability of the vehicle.

[0021] The control terminal 20 is used to upload movement speed information, tail structure extension length information, tail structure azimuth angle information and tail structure pitch angle information.

[0022] Specifically, the control terminal 20 is responsible for processing and uploading multiple key information, including the vehicle's motion speed information, the telescopic length information of the tail structure, the azimuth information of the tail structure, and the pitch angle information of the tail structure. The motion speed information refers to the driving speed data of the vehicle at a certain point in time. Through the speed sensor on the vehicle, the vehicle's driving speed changes can be reflected in real time. The motion speed information is crucial to the control of the tail structure, because the adjustment of the tail needs to be dynamically adjusted according to the speed of the vehicle to ensure the optimization of aerodynamic performance. The telescopic length information of the tail structure refers to the extension or contraction length of the tail under different states. Through the position sensor installed on the tail structure, the specific telescopic state of the tail during operation can be reflected. The precise measurement and control of the telescopic length information of the tail structure helps to adjust the aerodynamic effect of the tail under different speed and airflow conditions, thereby improving the stability and handling of the vehicle. The azimuth information of the tail structure refers to the rotation angle of the tail relative to the longitudinal axis of the vehicle. Through the azimuth sensor to measure, the angle change of the tail under different operating states can be accurately reflected. By controlling the azimuth angle of the rear wing, the aerodynamic characteristics of the rear wing are optimized, thereby maintaining the stability and efficiency of the vehicle under different driving conditions. The pitch angle information of the rear wing structure refers to the inclination angle of the rear wing relative to the horizontal plane. It is obtained through the pitch angle sensor and can accurately reflect the inclination angle of the rear wing under different operating conditions. The pitch angle adjustment of the rear wing has a direct impact on the aerodynamic effect of the vehicle in the up and down directions. Accurate pitch angle control can improve the vehicle's handling performance and driving safety.

[0023] Service Center 30, including:

[0024] The stability prediction unit 31 is used to process the airflow velocity information, the airflow angle information, the movement speed information, the tail wing structure extension length information, the tail wing structure azimuth angle information and the tail wing structure pitch angle information to predict the driving stability coefficient.

[0025] Specifically, the stability prediction unit 31 is used to process a variety of information, including airflow velocity information, airflow angle information, motion speed information, tail wing structure telescopic length information, tail wing structure azimuth information and tail wing structure pitch angle information, and then predict the driving stability coefficient of the vehicle. The airflow velocity information and airflow angle information provide data on the dynamic changes of the external environment, which are used to predict the behavior of the vehicle under different wind speeds and wind directions. The motion speed information reflects the current driving state of the vehicle, and the specific adjustment state of the tail wing and the position of the tail wing in space are obtained through various information of the tail wing structure.

[0026] By processing real-time data and comparing historical data, a driving stability coefficient is generated that reflects the current driving environment and vehicle status, helping the vehicle control system to make more precise adjustments, improving the stability and safety of the vehicle under various driving conditions, predicting stability problems that the vehicle may encounter in advance, and making corresponding adjustments before problems occur to ensure that the vehicle is always in the best condition.

[0027] The resistance prediction unit 32 is used to process the airflow velocity information, the airflow angle information, the movement speed information, the tail wing structure extension length information, the tail wing structure azimuth angle information and the tail wing structure pitch angle information to predict the driving resistance coefficient.

[0028] Specifically, the resistance prediction unit 32 is used to process a variety of key information to predict the driving resistance coefficient, including airflow velocity information, airflow angle information, motion speed information, tail wing structure telescopic length information, tail wing structure azimuth information and tail wing structure pitch angle information. First, the airflow velocity information and airflow angle information provide detailed data about the aerodynamic environment around the vehicle, and then obtain the resistance exerted by the air on the vehicle, because the speed and angle of the airflow directly affect the flow mode of the air and the magnitude of the resistance generated. By monitoring the airflow information in real time, the aerodynamic effect can be predicted more accurately. The motion speed information reflects the current driving speed of the vehicle. The faster the vehicle travels, the greater the air resistance it suffers. Therefore, accurate motion speed information is an important basic data for predicting the driving resistance coefficient. The telescopic length information of the tail wing structure, the azimuth information of the tail wing structure and the pitch angle information of the tail wing structure describe the specific state of the tail wing structure, and determine the specific shape and position of the tail wing under different driving conditions. The adjustment of the tail wing structure can significantly affect the aerodynamic characteristics, thereby affecting the overall drag coefficient of the vehicle. By processing and analyzing multiple information, the optimal configuration of the tail wing structure under specific conditions is determined to minimize air resistance.

[0029] The control optimization unit 33 is used to optimize the movement speed information, the telescopic length information of the tail structure, the azimuth angle information of the tail structure and the pitch angle information of the tail structure according to the driving stability coefficient and the driving resistance coefficient, and generate a telescopic tail structure control scheme.

[0030] Specifically, the control optimization unit 33 is responsible for optimizing various parameter information according to the driving stability coefficient and the driving resistance coefficient, including movement speed information, tail wing structure telescopic length information, tail wing structure azimuth angle information and tail wing structure pitch angle information, and then generating an optimized telescopic tail wing structure control scheme.

[0031] During the optimization process, the driving stability coefficient is evaluated by the control optimization unit 33. A high stability coefficient means that the vehicle can maintain good balance and control during driving, reducing vibration and instability. On the other hand, the driving resistance coefficient reflects the air resistance encountered by the vehicle during driving. By reducing the driving resistance coefficient, the fuel efficiency and overall performance of the vehicle can be improved.

[0032] The control optimization unit conducts an in-depth analysis of the driving stability coefficient and driving resistance coefficient to determine the specific parameters that need to be adjusted. The motion speed information is used to determine the current driving speed of the vehicle and is adjusted as needed to optimize the aerodynamic performance. The telescopic length, azimuth and pitch angle information of the tail wing structure determine the specific configuration of the tail wing under different driving conditions. Through the precise control of multiple parameters, the telescopic tail wing structure control scheme is generated to optimize the vehicle's driving performance.

[0033] The data exchange unit 34 is used to send the retractable tail structure control solution to the control end to control the retractable tail structure.

[0034] Specifically, the control scheme of the retractable tail wing structure generated by the control optimization unit is sent to the control end through the data interaction unit 34, thereby ensuring that the control scheme can be transmitted and executed in a timely and accurate manner, thereby achieving real-time control of the tail wing structure. The tail wing structure is dynamically adjusted according to actual driving conditions to ensure that the vehicle is always in the best aerodynamic state. The control scheme of the retractable tail wing structure is sent to the control end through the data interaction unit 34, thereby ensuring the accuracy and timeliness of data transmission, and avoiding delays or errors in data transmission that affect the execution effect of the control scheme.

[0035] The intelligent control platform for the retractable rear wing structure achieves the technical goal of optimizing and controlling the retractable rear wing structure in real time, and achieves the technical effect of improving the aerodynamic performance and driving stability of the vehicle.

[0036] Further, if Figure 2 As shown, this application also includes:

[0037] The jitter frequency prediction node is used to process the airflow velocity information, the airflow angle information, the movement speed information, the telescopic length information of the tail wing structure, the azimuth information of the tail wing structure and the pitch angle information of the tail wing structure to predict the driving jitter frequency; the jitter amplitude prediction node is used to process the airflow velocity information, the airflow angle information, the movement speed information, the telescopic length information of the tail wing structure, the azimuth information of the tail wing structure and the pitch angle information of the tail wing structure to predict the driving jitter amplitude; the stability prediction node is used to process the driving jitter frequency and the driving jitter amplitude to generate the driving stability coefficient.

[0038] Specifically, the service center 30 includes a stability prediction unit 31, which is composed of multiple key nodes, which process and predict different types of information respectively. One node of the stability prediction unit 31 is a jitter frequency prediction node, which processes airflow velocity information, airflow angle information, motion velocity information, tail wing structure telescopic length information, tail wing structure azimuth information and tail wing structure pitch angle information. Through comprehensive analysis of multiple data, the jitter frequency prediction node can predict the jitter frequency of the vehicle during driving, and then understand the dynamic response of the vehicle under different conditions, which can help make corresponding adjustments in advance to improve the driving stability of the vehicle.

[0039] Then, another node is the jitter amplitude prediction node, which processes the same set of information, namely airflow velocity information, airflow angle information, motion speed information, tail wing structure telescopic length information, tail wing structure azimuth information and tail wing structure pitch angle information. The jitter amplitude prediction node can predict the possible jitter amplitude of the vehicle during driving through in-depth analysis of multiple data. Predicting the jitter amplitude helps to understand the vehicle's ability to cope with different airflow conditions and speed states, so that measures can be taken to reduce the jitter amplitude and improve the vehicle's ride comfort and safety.

[0040] Next, the last node is the stability prediction node, which processes the data generated by the other two nodes, namely the driving jitter frequency and driving jitter amplitude. Through comprehensive analysis, the stability prediction node can generate a driving stability coefficient to measure the overall stability of the vehicle under the current driving conditions. After the driving stability coefficient is generated, corresponding adjustments and optimizations are made based on the driving stability coefficient to ensure that the vehicle can maintain optimal stability under various driving conditions.

[0041] The stability prediction unit 31 in the service center 30 processes and predicts key driving data based on the coordinated work of the jitter frequency prediction node, the jitter amplitude prediction node and the stability prediction node, thereby generating a driving stability coefficient to help the vehicle maintain optimal stability and safety under various driving conditions.

[0042] Furthermore, the present application also includes:

[0043] The stability prediction node construction step includes: constructing a stability prediction function: , wherein S represents the driving stability coefficient, p and q are adjustment indexes, indicating the nonlinear degree of the influence of the jitter amplitude and frequency on the stability, A represents the jitter amplitude, Z represents the jitter frequency, k represents the first adjustment factor, and c is the second adjustment factor; configure a first stability prediction loss function, wherein the first stability prediction loss function is used to calculate the mean of the driving stability coefficient prediction deviation for each N training times; configure a second stability prediction loss function, wherein the second stability prediction loss function is used to calculate the proportion of the driving stability coefficient prediction deviation for each N training times that is less than or equal to the stability coefficient prediction deviation threshold; according to the main model of the retractable tail structure deployment, collect the driving jitter frequency record data set, the driving jitter amplitude record data set and the driving stability coefficient identification data set, and configure the stability prediction function; when the first stability prediction loss function is less than or equal to the stability coefficient prediction deviation threshold, and the second stability prediction loss function is less than or equal to the abnormal proportion threshold, generate the stability prediction node.

[0044] Specifically, the construction step of the stability prediction node includes constructing a stability prediction function for characterizing the driving stability coefficient of the vehicle. When the value of the shaking amplitude A or the shaking frequency Z is smaller and other parameters remain unchanged, the driving stability is higher when the value of the driving stability coefficient S is larger, and vice versa.

[0045] Then, in the process of constructing the stability prediction node, the first stability prediction loss function is configured. The first stability prediction loss function is used to calculate the deviation mean of the driving stability coefficient prediction after each N trainings, and then evaluate the accuracy and reliability of the prediction model, so as to make corresponding adjustments and optimizations to ensure the accuracy of the prediction results.

[0046] Next, configure the second stability prediction loss function to construct the stability prediction node. The second stability prediction loss function is used to calculate the proportion of driving stability coefficient prediction deviations less than or equal to the stability coefficient prediction deviation threshold after each N trainings, which reflects the stability and consistency of the model prediction results and helps evaluate the performance of the model in practical applications.

[0047] Next, before configuring the stability prediction function, it is necessary to collect relevant data sets according to the specific deployment model of the retractable tail structure, including the driving vibration frequency record data set, the driving vibration amplitude record data set and the driving stability coefficient identification data set. By analyzing the collected data sets, the stability prediction function can be reasonably configured, that is, the collected data sets are input into the stability prediction function, which can more accurately reflect the driving stability of the vehicle under different conditions.

[0048] Then, when the value of the first stability prediction loss function is less than or equal to the set stability coefficient prediction deviation threshold, and the value of the second stability prediction loss function is less than or equal to the set abnormal proportion threshold, it means that the prediction accuracy and stability of the model have met the requirements. Then, a stability prediction node is generated, so that the stability prediction node can play a role in practical applications.

[0049] By constructing prediction functions, configuring loss functions, collecting data sets, and generating nodes, we ensure that the stability prediction node can accurately and stably predict the vehicle's driving stability.

[0050] Furthermore, the present application also includes:

[0051] The model of the main body deployed with the retractable tail wing structure is used as the category retrieval condition; the airflow velocity information and the airflow angle information are normalized to construct the driving scene feature coordinates, and the first fuzzy retrieval condition is constructed in combination with the scene deviation Euclidean distance threshold; the movement speed information, the tail wing structure retractable length information, the tail wing structure azimuth information and the tail wing structure pitch angle information are normalized to construct the driving control feature coordinates, and the second fuzzy retrieval condition is constructed in combination with the control deviation Euclidean distance threshold; a large sample analysis is performed based on the category retrieval condition, the first fuzzy retrieval condition and the second fuzzy retrieval condition to predict the driving resistance coefficient.

[0052] Specifically, the main model of the retractable tail structure deployment is used as the category retrieval condition, and then the relevant data is screened and classified, which ensures the targeted data analysis and can effectively handle the characteristics and behaviors of different models of tail structures.

[0053] Then, the airflow velocity information and airflow angle information are normalized, and the data is standardized to construct a unified driving scene feature coordinate. Through normalization, the scale differences between different data sources are eliminated, so that the airflow velocity and angle information can be compared and analyzed in the same coordinate system. On this basis, combined with the scene deviation Euclidean distance threshold, the first fuzzy retrieval condition is constructed, and then samples that meet the characteristics of specific airflow scenes are quickly retrieved from a large amount of data, thereby improving the efficiency and accuracy of the analysis.

[0054] Then, the motion speed information, tail wing structure extension length information, tail wing structure azimuth information and tail wing structure pitch angle information are normalized and integrated into a unified driving control feature coordinate after normalization, and then the changes of different control parameters are analyzed in a standardized coordinate system. Combined with the control deviation Euclidean distance threshold, the second fuzzy retrieval condition is constructed, which helps to quickly find samples that meet specific control characteristics in the data and support further analysis and prediction.

[0055] Then, according to the category search condition, the first fuzzy search condition and the second fuzzy search condition, a large sample analysis is performed using a large amount of historical data and currently collected data to predict the driving resistance coefficient. Large sample analysis can provide more representative and accurate prediction results, ensuring that the prediction of the driving resistance coefficient has high reliability and accuracy under different driving conditions.

[0056] Through data normalization processing, feature coordinate construction, fuzzy retrieval condition setting and large sample analysis, accurate prediction of driving resistance coefficient is achieved, and the performance and stability of the vehicle under different driving conditions are improved.

[0057] Furthermore, the present application also includes:

[0058] Collect a sample data set that meets the category retrieval condition, the first fuzzy retrieval condition, and the second fuzzy retrieval condition, wherein the sample data set includes a data collection source and driving resistance record data, and the data collection source and the driving resistance record data correspond one to one; perform historical shared data analysis on the data collection source to obtain the accuracy of the historical shared data; when the accuracy of the historical shared data is less than or equal to the data accuracy threshold, delete the driving resistance record data from the sample data set; when the data collection sources are all verified, obtain a credible driving resistance record data set; perform data fusion on the credible driving resistance record data set to generate the driving resistance coefficient.

[0059] Specifically, in the execution step of the resistance prediction unit, a sample data set that meets the category retrieval condition, the first fuzzy retrieval condition, and the second fuzzy retrieval condition is collected. The sample data set includes a data collection source and corresponding driving resistance record data. Each pair of data collection source and driving resistance record data is one-to-one corresponding, ensuring the integrity and relevance of the sample data, and providing a basis for subsequent analysis and prediction.

[0060] Then, by analyzing the accuracy of historical data, the reliability and value of the data collection source in the prediction process are evaluated to ensure the data quality in the sample data set. If it is found that the driving resistance record data corresponding to the data collection source, that is, the driving resistance record data corresponding to some historical shared data, is less than or equal to the set data accuracy threshold, the driving resistance record data corresponding to the historical contribution data will be deleted from the sample data set to exclude low-quality or unreliable data and ensure the accuracy and credibility of the prediction model.

[0061] Then, after all data collection sources have been verified and completed, a credible driving resistance record data set is obtained, that is, after screening and verification, a credible driving resistance record data set with high-quality and reliable data is obtained to ensure that the basic data for subsequent analysis is credible.

[0062] Next, data fusion is performed on the credible driving resistance record data set, and the driving resistance coefficient is generated by comprehensive analysis and processing of the data in the credible data set. Data fusion technology can combine information from multiple data sources to generate a comprehensive prediction result, improving the accuracy and reliability of the prediction. Through the fusion analysis of a large amount of high-quality data, the actual situation can be reflected more accurately, providing a reliable basis for the aerodynamic optimization of the vehicle.

[0063] Through data collection, historical data analysis, data verification and data fusion, an accurate driving resistance coefficient is generated to improve the performance and stability of the vehicle under different driving conditions.

[0064] Furthermore, the present application also includes:

[0065] Performing data fusion on the credible driving resistance record data set to generate the driving resistance coefficient includes: data fusion is mode analysis or central tendency analysis or box plot analysis.

[0066] Specifically, the process of performing data fusion on the credible driving resistance record data set to generate the driving resistance coefficient includes multiple analysis methods to ensure the accuracy and reliability of the final result. The purpose of data fusion is to integrate the information from multiple data sources and obtain a comprehensive driving resistance coefficient through different statistical analysis methods.

[0067] One method is mode analysis. Mode analysis is to find the most frequently occurring value in a data set to represent the central trend of the overall data. In the driving resistance record data set, mode analysis can help identify the most common driving resistance value, which reflects the vehicle's resistance in most cases, and is used to identify common operating conditions and optimize the rear wing structure adjustment under common driving conditions.

[0068] Another method is central tendency analysis. Central tendency analysis includes statistics such as mean and median, which can be used to understand the central tendency and distribution of data. The mean can provide an overall average level, while the median can reduce the impact of outliers on the results. Through central tendency analysis, the overall characteristics of driving resistance data can be more comprehensively understood, thus providing a reliable reference for the determination of driving resistance coefficient.

[0069] Box plot analysis is a visual statistical method that can intuitively display the distribution characteristics, outliers, and quartiles of data. Box plot analysis can help identify the distribution of outliers in a data set, thereby filtering and processing data more effectively. Through box plot analysis, the distribution characteristics and variation range of data can be more clearly understood, providing a more detailed basis for the final determination of the driving resistance coefficient.

[0070] Through multiple data fusion methods such as mode analysis, central trend analysis and box plot analysis, a comprehensive analysis of the credible driving resistance record data set is carried out, and finally an accurate and reliable driving resistance coefficient is generated to improve the performance and stability of the vehicle under different driving conditions.

[0071] Furthermore, the present application also includes:

[0072] When the driving stability coefficient is less than or equal to the first convergence threshold, or / and the driving resistance coefficient is greater than or equal to the second convergence threshold: the interactive user end receives the expected driving speed range; the interactive control end receives the rated range of the telescopic length of the tail wing structure, the rated range of the azimuth angle of the tail wing structure and the rated range of the pitch angle of the tail wing structure; based on the rated range of the telescopic length of the tail wing structure, the rated range of the azimuth angle of the tail wing structure and the rated range of the pitch angle of the tail wing structure, uniformly distribute them within a preset step size to obtain a set of control schemes for the tail wing structure; traverse the set of control schemes for the tail wing structure with the minimum value of the expected driving speed range. , based on the stability prediction unit and the resistance prediction unit, analysis is performed to obtain a maximum value of a driving stability coefficient and a minimum value of a driving resistance coefficient; when the maximum value of the driving stability coefficient is less than or equal to a first convergence threshold, or / and the minimum value of the driving resistance coefficient is greater than or equal to a second convergence threshold, a suggestion for reducing the expected speed is generated, and the interactive user terminal updates the expected driving speed range; according to the expected driving speed update range, the movement speed information, the telescopic length information of the tail wing structure, the azimuth angle information of the tail wing structure and the pitch angle information of the tail wing structure are optimized to generate the telescopic tail wing structure control scheme.

[0073] Specifically, when the driving stability coefficient is less than or equal to the first convergence threshold or the driving resistance coefficient is greater than or equal to the second convergence threshold, or when the driving stability coefficient is less than or equal to the first convergence threshold and the driving resistance coefficient is greater than or equal to the second convergence threshold, data interaction is performed with the user end to receive an expected driving speed range, that is, the expected driving speed range is input by the user, reflecting the user's expectations and demands for the vehicle's driving speed.

[0074] Next, by exchanging data with the control end, the rated range information of the tail structure is received, including the rated range of the tail structure's telescopic length, the rated range of the tail structure's azimuth angle, and the rated range of the tail structure's pitch angle. By receiving multiple rated ranges, the operating range of the tail structure under different parameter settings is obtained, providing basic data for subsequent optimization.

[0075] Based on multiple rated intervals, a uniform distribution with a preset step size is used to generate a set of tail structure control solutions, which includes all possible combinations of tail structure under different parameter settings. The uniform distribution ensures that all possible tail parameter combinations are taken into account, thus providing comprehensive options for finding the best control solution.

[0076] Next, based on the minimum value of the expected driving speed range, the set of tail wing structure control schemes is accessed in sequence. Each tail wing structure control scheme is analyzed by the stability prediction unit 31 and the resistance prediction unit 32, and the driving stability coefficient and driving resistance coefficient under each tail wing structure control scheme are calculated. Finally, the combination of the maximum driving stability coefficient and the minimum driving resistance coefficient is selected as the optimal control scheme.

[0077] If in the optimal solution, when the maximum value of the driving stability coefficient is still less than or equal to the first convergence threshold or the minimum value of the driving resistance coefficient is still greater than or equal to the second convergence threshold, or when the maximum value of the driving stability coefficient is still less than or equal to the first convergence threshold and the minimum value of the driving resistance coefficient is still greater than or equal to the second convergence threshold, a suggestion to reduce the expected speed is generated, and the expected driving speed range is updated through the interactive user terminal, ensuring that the user can adjust the expected speed in time to achieve better driving effect.

[0078] Finally, according to the updated expected driving speed range, the movement speed information, the tail wing structure telescopic length information, the tail wing structure azimuth information and the tail wing structure pitch angle information are optimized. By adjusting the parameters, the final telescopic tail wing structure control scheme is generated to ensure driving stability and minimize driving resistance, while meeting the user's speed requirements and optimizing the overall performance of the vehicle.

[0079] Through user input and analysis, the vehicle's driving parameters are optimized, and ultimately a comprehensive retractable rear wing structure control solution is generated, which improves the vehicle's driving performance and stability under different conditions.

[0080] Furthermore, the present application also includes:

[0081] When the driving stability coefficient is greater than a first convergence threshold and the driving resistance coefficient is less than a second convergence threshold, the retractable tail wing structure control scheme is output.

[0082] Specifically, when the driving stability coefficient is greater than the first convergence threshold and the driving resistance coefficient is less than the second convergence threshold, the retractable tail wing structure control scheme is output, indicating that the current driving state has reached the preset optimization standard, that is, the vehicle has sufficient stability and maintains low air resistance during driving.

[0083] A driving stability coefficient greater than the first convergence threshold means that the vehicle's driving stability has reached or exceeded the system's requirements, reflecting the degree of stability that the vehicle can maintain under different driving conditions. A higher driving stability coefficient means that the vehicle can maintain good dynamic balance when dealing with airflow changes, speed changes, and rear wing adjustments, reducing vibration and shaking, and providing a more comfortable driving experience.

[0084] A driving drag coefficient less than the second convergence threshold indicates that the aerodynamic characteristics of the vehicle have been optimized and the drag has been effectively controlled. A lower driving drag coefficient means that the vehicle is subject to less air resistance during driving, which not only improves fuel efficiency but also improves the overall performance of the vehicle. The optimal configuration of the tail wing structure is achieved by precisely controlling parameters such as airflow speed, airflow angle, tail wing extension length, azimuth and pitch angle, thereby minimizing air resistance.

[0085] When the two conditions are met, the control scheme of the retractable rear wing structure is output, which includes all optimized parameter settings to ensure that the vehicle can maintain the best performance and stability during driving. The output scheme can not only be directly applied to the actual control of the vehicle, but also serve as a reference for subsequent optimization and adjustment.

[0086] When the driving stability coefficient and the driving resistance coefficient both meet the preset optimization standards, a fully optimized retractable rear wing structure control solution is output to ensure that the vehicle can maintain optimal stability and lowest resistance under various driving conditions, thereby improving driving efficiency and safety.

[0087] In summary, the intelligent control platform for a retractable tail wing structure provided by the present application has the following technical effects:

[0088] The monitoring end is used to collect airflow speed information and airflow angle information in the pre-driving area; the control end is used to upload movement speed information, tail wing structure telescopic length information, tail wing structure azimuth information and tail wing structure pitch angle information; the service center includes: a stability prediction unit, which is used to process the airflow speed information, the airflow angle information, the movement speed information, the tail wing structure telescopic length information, the tail wing structure azimuth information and the tail wing structure pitch angle information to predict the driving stability coefficient; a resistance prediction unit, which is used to process the airflow speed information, the airflow angle information, the movement speed information, the tail wing structure telescopic length information, the tail wing structure azimuth information and the tail wing structure pitch angle information to predict the driving stability coefficient; The telescopic length information, the azimuth angle information of the tail wing structure and the pitch angle information of the tail wing structure are used to predict the driving resistance coefficient; a control optimization unit is used to optimize the movement speed information, the telescopic length information of the tail wing structure, the azimuth angle information of the tail wing structure and the pitch angle information of the tail wing structure according to the driving stability coefficient and the driving resistance coefficient, and generate a telescopic tail wing structure control plan; a data interaction unit is used to send the retractable tail wing structure control plan to the control end to control the telescopic tail wing structure, thereby realizing the technical goal of real-time optimization and control of the telescopic tail wing structure, and achieving the technical effect of improving the aerodynamic performance and driving stability of the vehicle.

[0089] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be 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 the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0090] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. An intelligent control platform for a telescopic tail structure, characterized in that: include: A monitoring terminal, the monitoring terminal is used to collect airflow velocity information and airflow angle information in the pre-travel area; A control end, the control end is used to upload movement speed information, tail wing structure telescopic length information, tail wing structure azimuth information and tail wing structure pitch angle information, the movement speed information refers to the driving speed data of the vehicle at a certain point in time, which is collected by the speed sensor on the vehicle and can reflect the vehicle's driving speed changes in real time; Service centers, including: A stability prediction unit, used for processing the airflow velocity information, the airflow angle information, the movement speed information, the tail structure telescopic length information, the tail structure azimuth information and the tail structure pitch angle information, and predicting a driving stability coefficient; a resistance prediction unit, used for processing the airflow velocity information, the airflow angle information, the movement speed information, the tail wing structure telescopic length information, the tail wing structure azimuth information and the tail wing structure pitch angle information, and predicting the driving resistance coefficient; a control optimization unit, configured to optimize the movement speed information, the telescopic length information of the tail structure, the azimuth angle information of the tail structure, and the pitch angle information of the tail structure according to the driving stability coefficient and the driving resistance coefficient, and generate a control method for a telescopic tail structure; A data interaction unit is used to send the retractable tail structure control method to the control end to control the retractable tail structure.

2. The platform according to claim 1, characterized in that The stability prediction unit comprises: A jitter frequency prediction node, used for processing the airflow velocity information, the airflow angle information, the movement speed information, the tail structure telescopic length information, the tail structure azimuth information and the tail structure pitch angle information, to predict the driving jitter frequency; A jitter amplitude prediction node, used for processing the airflow velocity information, the airflow angle information, the movement speed information, the tail wing structure telescopic length information, the tail wing structure azimuth information and the tail wing structure pitch angle information, to predict the driving jitter amplitude; The stability prediction node is used to process the driving vibration frequency and the driving vibration amplitude to generate the driving stability coefficient.

3. The platform according to claim 2, characterized in that The stability prediction node construction step comprises: Construct a stability prediction function: , Among them, S represents the driving stability coefficient, p and q are adjustment indexes, which represent the nonlinear degree of the influence of the vibration amplitude and frequency on the stability, A represents the vibration amplitude, Z represents the vibration frequency, k represents the first adjustment factor, and c is the second adjustment factor; Configure a first stability prediction loss function, wherein the first stability prediction loss function is used to calculate a mean value of a driving stability coefficient prediction deviation for each N training times; Configure a second stability prediction loss function, wherein the second stability prediction loss function is used to calculate the proportion of driving stability coefficient prediction deviations less than or equal to the stability coefficient prediction deviation threshold for each N training times; According to the main model of the retractable tail structure deployment, a driving jitter frequency record data set, a driving jitter amplitude record data set and a driving stability coefficient identification data set are collected to configure the stability prediction function; When the first stability prediction loss function is less than or equal to the stability coefficient prediction deviation threshold, and the second stability prediction loss function is less than or equal to the abnormality proportion threshold, the stability prediction node is generated.

4. The platform according to claim 1, characterized in that The resistance prediction unit performs the following steps: The main model of the telescopic tail structure deployment is used as the category search condition; Normalizing the airflow velocity information and the airflow angle information to construct the driving scene feature coordinates, and combining the scene deviation Euclidean distance threshold to construct a first fuzzy search condition; Normalizing the movement speed information, the telescopic length information of the tail structure, the azimuth angle information of the tail structure, and the pitch angle information of the tail structure to construct a driving control feature coordinate, and combining the control deviation Euclidean distance threshold to construct a second fuzzy search condition; A large sample analysis is performed based on the category retrieval condition, the first fuzzy retrieval condition, and the second fuzzy retrieval condition to predict the running resistance coefficient.

5. The platform according to claim 4, characterized in that Performing a large sample analysis according to the category search condition, the first fuzzy search condition, and the second fuzzy search condition to predict the driving resistance coefficient includes: Collecting a sample data set that satisfies the category search condition, the first fuzzy search condition, and the second fuzzy search condition, wherein the sample data set includes a data collection source and driving resistance record data, and the data collection source and the driving resistance record data correspond one to one; Performing historical shared data analysis on the data collection source to obtain the accuracy of the historical shared data; When the accuracy of the historical shared data is less than or equal to a data accuracy threshold, deleting the driving resistance record data from the sample data set; When the data collection sources are all verified, a reliable driving resistance record data set is obtained; Data fusion is performed on the credible driving resistance record data set to generate the driving resistance coefficient.

6. The platform according to claim 5, characterized in that Performing data fusion on the credible driving resistance record data set to generate the driving resistance coefficient includes: data fusion is mode analysis or central tendency analysis or box plot analysis.

7. The platform according to claim 1, characterized in that The control optimization unit performs the following steps: When the driving stability coefficient is less than or equal to the first convergence threshold, or / and the driving resistance coefficient is greater than or equal to the second convergence threshold: The interactive user terminal receives the expected driving speed range; The interactive control end receives the rated range of the extension and retraction length of the tail structure, the rated range of the azimuth angle of the tail structure, and the rated range of the pitch angle of the tail structure; Based on the rated range of the telescopic length of the tail structure, the rated range of the azimuth angle of the tail structure and the rated range of the pitch angle of the tail structure, uniformly distributed within a preset step length, a set of tail structure control methods is obtained; The set of tail structure control methods is traversed based on the minimum value of the expected driving speed range, and the maximum value of the driving stability coefficient and the minimum value of the driving resistance coefficient are obtained by performing analysis based on the stability prediction unit and the resistance prediction unit; When the maximum value of the driving stability coefficient is less than or equal to the first convergence threshold, or / and the minimum value of the driving resistance coefficient is greater than or equal to the second convergence threshold, a suggestion for lowering the expected speed is generated, and the interactive user terminal updates the expected driving speed range; According to the expected driving speed update interval, the movement speed information, the telescopic length information of the tail structure, the azimuth angle information of the tail structure and the pitch angle information of the tail structure are optimized to generate the telescopic tail structure control method.

8. The platform according to claim 7, characterized in that When the driving stability coefficient is greater than a first convergence threshold and the driving resistance coefficient is less than a second convergence threshold, the retractable tail wing structure control method is output.

Citation Information

Patent Citations

  • Multi-degree-of-freedom automobile active aerodynamic suite

    CN111634337A

  • Intelligent attack angle self-adaptive two-stage telescopic empennage device

    CN113682387A