AMT gear shifting strategy selection method, system and equipment based on working condition prediction and medium
Through the method of matching working condition prediction and shift strategy, the problem of traditional AMT gearbox lacking prediction capabilities in shift strategy is solved, more flexible shift control is achieved, and driving experience and vehicle performance are improved.
Patent Information
- Application Number
- CN202411064164.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-08-05
AI Technical Summary
Traditional AMT gearboxes lack working conditions prediction capabilities, resulting in insufficient flexibility in gear shifting time, affecting driving experience and vehicle performance, and the clutch control accuracy and engine torque management during gear shifting are inconsistent, affecting gear shift smoothness and fuel economy.
Using the AMT shift strategy selection method based on working condition prediction, by determining the characteristic parameters of CAN signal, building a sample signal matrix, performing data standardization and principal component analysis, realizing dimensionality reduction and clustering, predicting driving conditions, and matching the corresponding shift strategy Take control.
Shorten shifting time, reduce vehicle impact, improve shift smoothness and acceleration performance, improve fuel economy, and enhance vehicle control flexibility and comfort.
Smart Images

Figure CN119042313A_ABST
Abstract
Description
Background Art
[0002] AMT transmission is an automated manual transmission. Compared with traditional automatic transmission, AMT transmission has lower cost, can provide higher driving experience and comfort, and has lower maintenance cost. AMT transmission is the foundation of automatic transmission vehicle development, especially AMT transmission with automatic electronic control unit, which is more competitive in manufacturing process and cost. In addition, AMT transmission can control shifting time and shifting speed more accurately, so AMT transmission has higher fuel economy than traditional automatic transmission without sacrificing power performance.
[0003] As an upgrade of the traditional manual transmission, the AMT transmission realizes the automatic separation and engagement of the clutch and the automatic switching of gears through the electronic control system, which simplifies the driver's operation to a certain extent and improves the convenience of driving. But first of all, the traditional AMT shifting strategy is mostly based on the current vehicle status for decision-making, lacking the ability to predict future changes in working conditions, resulting in inflexible shifting time and affecting the driving experience. Secondly, during the shifting process using the traditional shifting strategy, the incoordination between the clutch control accuracy and the engine torque management will affect the smoothness of the shifting. If the control is improper, it will cause a large shifting shock, affecting the comfort of passengers and even causing unnecessary wear on vehicle parts. Finally, for complex and changeable working conditions, the traditional shifting strategy often fails to respond quickly to environmental changes, and the shifting time is too long, affecting the vehicle's acceleration performance and fuel economy.
[0004] This is a shortcoming of the prior art. Therefore, in view of the above-mentioned defects in the prior art, it is very necessary to provide an AMT shift strategy selection method, system, equipment and medium based on working condition prediction. Summary of the invention
[0005] In view of the defects of the above-mentioned traditional AMT shift strategy in the prior art that lacks the ability to predict operating conditions, resulting in inflexible shift time, affecting driving experience, affecting shift smoothness, affecting passenger comfort, and long shift time affecting vehicle acceleration performance and fuel economy, the present invention provides an AMT shift strategy selection method, system, device and medium based on operating condition prediction to solve the above-mentioned technical problems.
[0006] In a first aspect, the present invention provides an AMT shift strategy selection method based on working condition prediction, comprising the following steps: S1. Determine the characteristic parameters of the CAN signal and collect the corresponding vehicle driving data to construct a sample signal matrix; S2. Perform data standardization on the sample signal matrix to obtain a standardized sample signal matrix; S3. Use the principal component analysis method to analyze the standardized sample signal matrix to achieve dimensionality reduction of the CAN signal characteristic parameters, and obtain a reduced-dimensional sample signal matrix based on the CAN signal characteristic parameters after dimensionality reduction; S4. Perform cluster analysis on the reduced-dimensional sample signal matrix, output the driving condition classification results, and set the AMT shift strategy for each driving condition classification result; S5. Obtain the real-time vehicle driving data corresponding to the CAN signal characteristic parameters after dimension reduction of the actual working condition, update the working condition classification result, predict the working condition, match the predicted working condition with the driving condition classification result, and select the corresponding AMT shift strategy for shift control. Furthermore, the specific steps of step S1 are as follows: S11. Determine the characteristic parameters of the CAN signal of the original dimension p; S12. Collecting vehicle driving data corresponding to the original dimension CAN signal characteristic parameters of a set number n; S13. Construct a sample signal matrix of p╳n based on the collected vehicle driving data, where the elements of the sample signal matrix are x ij , 1≤i≤p, 1≤j≤n.
[0007] Furthermore, the specific steps of step S2 are as follows: S21. Find the minimum element min(x i ), calculate the difference between each element xi in the row vector and the minimum element min(x i ) as the row deviation; S22. From the column vector x of the sample signal matrix j Find the maximum element max(x i ) and the minimum element min(x i ), calculate the deviation between the two as the column deviation; S23. Calculate the ratio of row deviation to column deviation for each element in the sample signal matrix to obtain the normalized element y: ; S24. Use the matrix formed by the normalized elements y as the standardized sample signal matrix.
[0008] Furthermore, the specific steps of step S3 are as follows: S31. Calculate the covariance matrix for the standardized sample signal matrix ,in ; S32. Calculate the covariance matrix The eigenvalue of and the corresponding orthogonal eigenvectors ; S33. According to the eigenvalue Size selection covariance matrix Before The characteristic value of As before The variance corresponding to the principal components; S34. Settings The corresponding unit eigenvector Main component The coefficient of the original variable X is principal components for: ; S35. Calculate the principal component by the following formula The variance contribution rate , characterize the signal quantity of each CAN signal characteristic parameter: ; S36. Calculate the cumulative variance contribution rate using the following formula: ; S37. Determine whether the cumulative contribution rate is greater than the set threshold; If yes, go to step S38; If not, adjust the value of m and return to step S33; S38. Determine the m value by the cumulative variance contribution rate, and the main component selected is , realize the dimension reduction of CAN signal characteristic parameters, and obtain the reduced dimension sample signal matrix Z based on the reduced dimension CAN signal characteristic parameters.
[0009] Furthermore, the specific steps of step S4 are as follows: S41. Taking the row vector in the reduced-dimensional sample signal matrix Z as the working condition signal; S42. Select any working condition signal and calculate the cumulative distance between the selected working condition signal and all working condition signals in the reduced dimension sample signal; S43. Calculate the cumulative number, average value, variance and eccentricity of the working condition signal; S44. Select the K-Means clustering method, use the number, mean, variance and eccentricity of the working condition signals as input to perform a preliminary clustering analysis and obtain micro-clusters; S45. Identify and merge similar operating signals to form macro clusters by creating an adjacency matrix and determining the conditions for intersection of micro clusters, and then process each micro cluster in the macro cluster; S46. Analyze each driving condition category and its CAN signal characteristic parameters to extract the characteristics of each driving condition category; S47. Set the corresponding AMT shift strategy based on the characteristics of each driving condition category.
[0010] Furthermore, the specific steps of step S45 are as follows: S451. Create an adjacency matrix for each micro-cluster, wherein the dimension of the adjacency matrix is the same as the number of micro-clusters; S452. Determine whether two microclusters intersect based on the elements in the adjacency matrix; If so, it is determined that the two microclusters intersect, and the process goes to step S453; If not, it is determined that the two microclusters do not intersect, and the process goes to step S454; S453. setting two intersecting microclusters having similar operating condition signals as similar microclusters; S454. Merge similar microclusters to obtain macroclusters; S455. Divide each macro cluster into unified areas, calculate the cluster density of each area, and set the area with cluster density below the threshold as a low-density area, and set the area with cluster density above the threshold as a high-density area; S456. discarding the microclusters located in the low-density area and activating the microclusters in the high-density area; S457. Calculate the weight of each activated micro-cluster in each macro-cluster, and perform weighted normalization processing on each micro-cluster.
[0011] Furthermore, the specific steps of step S5 are as follows: S51. Obtaining real-time vehicle driving data corresponding to the p-dimensional CAN signal characteristic parameters of the actual working condition; S52. Construct a sample signal matrix according to step S1, standardize the sample signal matrix according to step S2, perform dimensionality reduction according to step S3, and perform clustering according to step S4, and then use the clustering results to update the driving condition category; S53. Compare the reduced-dimensional CAN signal characteristic parameters of the real-time working condition with each driving condition category to achieve working condition prediction; S54. Match the predicted working condition with the driving condition classification result, select the AMT shift strategy corresponding to the matched driving condition category for output, and perform shift control.
[0012] In a second aspect, the present invention provides an AMT shift strategy selection system based on working condition prediction, comprising: A sample signal matrix building module is used to determine the characteristic parameters of the CAN signal and collect the corresponding vehicle driving data to build a sample signal matrix; A matrix standardization module is used to perform data standardization on the sample signal matrix to obtain a standardized sample signal matrix; The matrix dimension reduction module is used to analyze the standardized sample signal matrix using the principal component analysis method to achieve dimension reduction of the CAN signal characteristic parameters, and obtain a dimension reduction sample signal matrix based on the CAN signal characteristic parameters after dimension reduction; The driving condition clustering module is used to perform cluster analysis on the reduced-dimensional sample signal matrix, output the driving condition classification results, and set the AMT shift strategy for each driving condition classification result; The shift strategy selection module is used to obtain the real-time vehicle driving data corresponding to the CAN signal characteristic parameters after dimension reduction of the actual working condition, update the working condition classification result, predict the working condition, match the predicted working condition with the driving condition classification result, and select the corresponding AMT shift strategy for shift control.
[0013] In a third aspect, the present invention provides a device, comprising a processor and a memory; The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the device executes the method described in the first aspect above.
[0014] In a fourth aspect, the present invention provides a storage medium, The storage medium stores instructions, which, when executed on a computer, enable the computer to execute the method described in the first aspect.
[0015] The beneficial effects of the present invention are: The AMT shift strategy selection method, system, device and medium based on working condition prediction provided by the present invention are based on the main influencing factors in the working condition identification process, and use these factors as input data of the prediction model, analyze the changing trend of the working condition data required for working condition prediction, strengthen the model's control over the vehicle, shorten the shift time, and reduce the vehicle's impact degree to ensure the vehicle's smoothness, thereby adjusting the selection of the vehicle's shift strategy and improving the shift performance.
[0016] In addition, the invention has a reliable design principle, a simple structure and a very broad application prospect.
[0017] It can be seen that compared with the prior art, the present invention has outstanding substantive features and significant progress, and the beneficial effects of its implementation are also obvious. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0019] Figure 1It is a flow chart of the AMT shift strategy selection method based on working condition prediction of the present invention.
[0020] Figure 2 It is a schematic diagram of the AMT shift strategy selection system based on working condition prediction of the present invention. DETAILED DESCRIPTION
[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0022] The AMT shift strategy selection method based on working condition prediction can be applied to one or more devices, wherein the device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.
[0023] The device can be any electronic product that can interact with the user, such as a personal computer, tablet computer, smart phone, personal digital assistant (PDA), interactive network television (IPTV), etc. The network where the device is located includes but is not limited to the Internet, wide area network, metropolitan area network, local area network, virtual private network (VPN), etc.
[0024] See also Figure 1 The figure shows a method for selecting an AMT shift strategy based on working condition prediction in a specific implementation, which includes the following steps: S1. Determine the characteristic parameters of the CAN signal and collect the corresponding vehicle driving data to construct a sample signal matrix; S2. Perform data standardization on the sample signal matrix to obtain a standardized sample signal matrix; S3. Use the principal component analysis method to analyze the standardized sample signal matrix to achieve dimensionality reduction of the CAN signal characteristic parameters, and obtain a reduced-dimensional sample signal matrix based on the CAN signal characteristic parameters after dimensionality reduction; S4. Perform cluster analysis on the reduced-dimensional sample signal matrix, output the driving condition classification results, and set the AMT shift strategy for each driving condition classification result; S5. Obtain the real-time vehicle driving data corresponding to the CAN signal characteristic parameters after dimension reduction of the actual working condition, update the working condition classification result, predict the working condition, match the predicted working condition with the driving condition classification result, and select the corresponding AMT shift strategy for shift control.
[0025] In this embodiment, the specific steps of step S1 are as follows: S11. Determine the characteristic parameters of the CAN signal of the original dimension p; for example, select the commonly used characteristic parameters of the CAN signal: maximum speed , Maximum acceleration , Maximum deceleration , average speed , average acceleration , average deceleration , high-speed driving time ratio , medium speed driving time ratio , low speed driving time ratio , Idle time ratio , standard deviation of speed , standard deviation of acceleration ; S12. Collecting vehicle driving data corresponding to the original dimension CAN signal characteristic parameters of a set number n; S13. Construct a sample signal matrix of p╳n based on the collected vehicle driving data, where the elements of the sample signal matrix are x ij , 1≤i≤p, 1≤j≤n; For example, the constructed sample signal matrix Z is as follows:
[0026] The specific steps of step S2 are as follows: S21. Find the minimum element min(x i ), calculate the difference between each element xi in the row vector and the minimum element min(x i ) as the row deviation; S22. From the column vector x of the sample signal matrix j Find the maximum element max(x i ) and the minimum element min(x i ), calculate the deviation between the two as the column deviation; S23. Calculate the ratio of row deviation to column deviation for each element in the sample signal matrix to obtain the normalized element y: ; S24. The matrix formed by the normalized elements y is used as the standardized sample signal matrix; It should be noted that to perform data standardization on the sample signal matrix, that is, to find the mean, first calculate the maximum and minimum values in each operating signal data instance, and calculate the range; then, subtract the minimum value from each observation value, and then divide it by the range to complete the standardization; It should be noted that many related indicators, such as Indicators Regroup into fewer uncorrelated composite indicators , to replace the original indicators; these comprehensive indicators can not only reflect the original variables to the greatest extent The information represented can also ensure that the new indicators are independent of each other; The specific steps of step S3 are as follows: S31. Calculate the covariance matrix for the standardized sample signal matrix ,in ; S32. Calculate the covariance matrix The eigenvalue of and the corresponding orthogonal eigenvectors ; S33. According to the eigenvalue Size selection covariance matrix Before The characteristic value of As before The variance corresponding to the principal components; S34. Settings The corresponding unit eigenvector Main component The coefficient of the original variable X is principal components for: ; S35. Calculate the principal component by the following formula The variance contribution rate , characterize the signal quantity of each CAN signal characteristic parameter: ; S36. Calculate the cumulative variance contribution rate using the following formula: ; S37. Determine whether the cumulative contribution rate is greater than the set threshold; If yes, go to step S38; If not, adjust the value of m and return to step S33; S38. Determine the m value by the cumulative variance contribution rate, and the main component selected is , realize the dimension reduction of CAN signal characteristic parameters, and obtain the dimension reduction sample signal matrix Z based on the dimension reduction CAN signal characteristic parameters; For example, after principal component analysis, the original CAN signal matrix changes to: , the signals obtained are maximum speed, maximum acceleration, maximum deceleration, average speed, average acceleration, average deceleration, high-speed driving time ratio, low-speed driving time ratio, and idling time ratio; The specific steps of step S4 are as follows: S41. Taking the row vector in the reduced-dimensional sample signal matrix Z as the working condition signal; S42. Select any working condition signal and calculate the cumulative distance between the selected working condition signal and all working condition signals in the reduced dimension sample signal; S43. Calculate the cumulative number, average value, variance and eccentricity of the working condition signal; The accumulated number of working condition signals is: ; The average value of the signal quantity at the current moment is: ; The variance of the signal at the current moment is: ; The eccentricity of the signal at the current moment becomes: ; S44. Select the K-Means clustering method, use the number, mean, variance and eccentricity of the working condition signals as input to perform a preliminary clustering analysis and obtain micro-clusters; S45. Identify and merge similar operating signals to form macro clusters by creating an adjacency matrix and determining the conditions for the intersection of micro clusters, and then process each micro cluster in the macro cluster; the specific steps of step S45 are as follows: S451. Create an adjacency matrix for each micro-cluster, wherein the dimension of the adjacency matrix is the same as the number of micro-clusters; S452. Determine whether two microclusters intersect based on the elements in the adjacency matrix; If so, it is determined that the two microclusters intersect, and the process goes to step S453; If not, it is determined that the two microclusters do not intersect, and the process goes to step S454; S453. setting two intersecting microclusters having similar operating condition signals as similar microclusters; S454. Merge similar microclusters to obtain macroclusters; S455. Divide each macro cluster into unified areas, calculate the cluster density of each area, and set the area with cluster density below the threshold as a low-density area, and set the area with cluster density above the threshold as a high-density area; S456. discarding the microclusters located in the low-density area and activating the microclusters in the high-density area; S457. Calculate the weight of each activated micro-cluster in each macro-cluster, and perform weighted normalization processing on each micro-cluster; S46. Analyze each driving condition category and its CAN signal characteristic parameters to extract the characteristics of each driving condition category; S47. Setting the corresponding AMT shift strategy based on the characteristics of each driving condition category; The specific steps of step S5 are as follows: S51. Obtaining real-time vehicle driving data corresponding to the p-dimensional CAN signal characteristic parameters of the actual working condition; S52. Construct a sample signal matrix according to step S1, standardize the sample signal matrix according to step S2, perform dimensionality reduction according to step S3, and perform clustering according to step S4, and then use the clustering results to update the driving condition category; S53. Compare the reduced-dimensional CAN signal characteristic parameters of the real-time working condition with each driving condition category to achieve working condition prediction; S54. Match the predicted working condition with the driving condition classification result, select the AMT shift strategy corresponding to the matched driving condition category for output, and perform shift control.
[0027] It should be understood that the order of execution of the steps in the above embodiment does not mean that the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0028] The following is an embodiment of the AMT shift strategy selection system based on operating condition prediction provided in the embodiments of the present disclosure. This system and the AMT shift strategy selection based on operating condition prediction in the above-mentioned embodiments belong to the same inventive concept. For details not fully described in the embodiment of the AMT shift strategy selection system based on operating condition prediction, please refer to the embodiment of the AMT shift strategy selection method based on operating condition prediction.
[0029] like Figure 2 As shown, the system includes: A sample signal matrix building module is used to determine the characteristic parameters of the CAN signal and collect the corresponding vehicle driving data to build a sample signal matrix; A matrix standardization module is used to perform data standardization on the sample signal matrix to obtain a standardized sample signal matrix; The matrix dimension reduction module is used to analyze the standardized sample signal matrix using the principal component analysis method to achieve dimension reduction of the CAN signal characteristic parameters, and obtain a dimension reduction sample signal matrix based on the CAN signal characteristic parameters after dimension reduction; The driving condition clustering module is used to perform cluster analysis on the reduced-dimensional sample signal matrix, output the driving condition classification results, and set the AMT shift strategy for each driving condition classification result; The shift strategy selection module is used to obtain the real-time vehicle driving data corresponding to the CAN signal characteristic parameters after dimension reduction of the actual working condition, update the working condition classification result, predict the working condition, match the predicted working condition with the driving condition classification result, and select the corresponding AMT shift strategy for shift control.
[0030] The AMT shift strategy selection method based on working condition prediction provided by the present invention is a combination of the modules and algorithm steps of each example described in the embodiments disclosed herein, and can be implemented by electronic hardware, computer software or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.
[0031] Those skilled in the art will appreciate that the various aspects of the AMT shift strategy selection method based on working condition prediction provided by the present invention can be implemented as a system, method or program product. Therefore, various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software, which can be collectively referred to as "circuit", "module" or "system" here.
[0032] In the non-transitory computer-readable storage medium storing the method for selecting the AMT shift strategy based on the working condition prediction, it can be, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.
[0033] Although the present invention has been described in detail with reference to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention.
Claims
1. A method for selecting an AMT shift strategy based on working condition prediction, characterized in that: The steps include: S1. Determine the characteristic parameters of the CAN signal and collect the corresponding vehicle driving data to construct a sample signal matrix; S2. Perform data standardization on the sample signal matrix to obtain a standardized sample signal matrix; S3. Use the principal component analysis method to analyze the standardized sample signal matrix to achieve dimensionality reduction of the CAN signal characteristic parameters, and obtain a reduced-dimensional sample signal matrix based on the CAN signal characteristic parameters after dimensionality reduction; S4. Perform cluster analysis on the reduced-dimensional sample signal matrix, output the driving condition classification results, and set the AMT shift strategy for each driving condition classification result; S5. Obtain the real-time vehicle driving data corresponding to the CAN signal characteristic parameters after dimension reduction of the actual working condition, update the working condition classification result, predict the working condition, match the predicted working condition with the driving condition classification result, and select the corresponding AMT shift strategy for shift control.
2. The AMT shift strategy selection method based on working condition prediction according to claim 1, characterized in that: The specific steps of step S1 are as follows: S11. Determine the characteristic parameters of the CAN signal of the original dimension p; S12. Collecting vehicle driving data corresponding to the original dimension CAN signal characteristic parameters of a set number n; S13. Construct a sample signal matrix of p╳n based on the collected vehicle driving data, where the elements of the sample signal matrix are x ij , 1≤i≤p, 1≤j≤n.
3. The AMT shift strategy selection method based on working condition prediction according to claim 2, characterized in that: The specific steps of step S2 are as follows: S21. Find the minimum element min(x i ), calculate the difference between each element xi in the row vector and the minimum element min(x i ) as the row deviation; S22. From the column vector x of the sample signal matrix j Find the maximum element max(x i ) and the minimum element min(x i ), calculate the deviation between the two as the column deviation; S23. Calculate the ratio of row deviation to column deviation for each element in the sample signal matrix to obtain the normalized element y: ; S24. Use the matrix formed by the normalized elements y as the standardized sample signal matrix.
4. The AMT shift strategy selection method based on working condition prediction according to claim 3, characterized in that: The specific steps of step S3 are as follows: S31. Calculate the covariance matrix for the standardized sample signal matrix ,in ; S32. Calculate the covariance matrix The eigenvalue of and the corresponding orthogonal eigenvectors ; S33. According to the eigenvalue Size selection covariance matrix Before The characteristic value of As before The variance corresponding to the principal components; S34. Settings The corresponding unit eigenvector Main component The coefficient of the original variable X is principal components for: ; S35. Calculate the principal component by the following formula The variance contribution rate , characterize the signal quantity of each CAN signal characteristic parameter: ; S36. Calculate the cumulative variance contribution rate using the following formula: ; S37. Determine whether the cumulative contribution rate is greater than the set threshold; If yes, go to step S38; If not, adjust the value of m and return to step S33; S38. Determine the m value by the cumulative variance contribution rate, and the main component selected is , realize the dimension reduction of CAN signal characteristic parameters, and obtain the reduced dimension sample signal matrix Z based on the reduced dimension CAN signal characteristic parameters.
5. The AMT shift strategy selection method based on working condition prediction according to claim 4, characterized in that: The specific steps of step S4 are as follows: S41. Taking the row vector in the reduced-dimensional sample signal matrix Z as the working condition signal; S42. Select any working condition signal and calculate the cumulative distance between the selected working condition signal and all working condition signals in the reduced dimension sample signal; S43. Calculate the cumulative number, average value, variance and eccentricity of the working condition signal; S44. Select the K-Means clustering method, use the number, mean, variance and eccentricity of the working condition signals as input to perform a preliminary clustering analysis and obtain micro-clusters; S45. Identify and merge similar operating signals to form macro clusters by creating an adjacency matrix and determining the conditions for intersection of micro clusters, and then process each micro cluster in the macro cluster; S46. Analyze each driving condition category and its CAN signal characteristic parameters to extract the characteristics of each driving condition category; S47. Set the corresponding AMT shift strategy based on the characteristics of each driving condition category.
6. The AMT shift strategy selection method based on working condition prediction according to claim 5, characterized in that: The specific steps of step S45 are as follows: S451. Create an adjacency matrix for each micro-cluster, wherein the dimension of the adjacency matrix is the same as the number of micro-clusters; S452. Determine whether two microclusters intersect based on the elements in the adjacency matrix; If so, it is determined that the two microclusters intersect, and the process goes to step S453; If not, it is determined that the two microclusters do not intersect, and the process goes to step S454; S453. setting two intersecting microclusters having similar operating condition signals as similar microclusters; S454. Merge similar microclusters to obtain macroclusters; S455. Divide each macro cluster into unified areas, calculate the cluster density of each area, and set the area with cluster density below the threshold as a low-density area, and set the area with cluster density above the threshold as a high-density area; S456. discarding the microclusters located in the low-density area and activating the microclusters in the high-density area; S457. Calculate the weight of each activated micro-cluster in each macro-cluster, and perform weighted normalization processing on each micro-cluster.
7. The AMT shift strategy selection method based on working condition prediction according to claim 5, characterized in that: The specific steps of step S5 are as follows: S51. Obtaining real-time vehicle driving data corresponding to the p-dimensional CAN signal characteristic parameters of the actual working condition; S52. Construct a sample signal matrix according to step S1, standardize the sample signal matrix according to step S2, perform dimensionality reduction according to step S3, and perform clustering according to step S4, and then use the clustering results to update the driving condition category; S53. Compare the reduced-dimensional CAN signal characteristic parameters of the real-time working condition with each driving condition category to achieve working condition prediction; S54. Match the predicted working condition with the driving condition classification result, select the AMT shift strategy corresponding to the matched driving condition category for output, and perform shift control.
8. An AMT shift strategy selection system based on working condition prediction, characterized in that: include: A sample signal matrix building module is used to determine the characteristic parameters of the CAN signal and collect the corresponding vehicle driving data to build a sample signal matrix; A matrix standardization module is used to perform data standardization on the sample signal matrix to obtain a standardized sample signal matrix; The matrix dimension reduction module is used to analyze the standardized sample signal matrix using the principal component analysis method to achieve dimension reduction of the CAN signal characteristic parameters, and obtain a dimension reduction sample signal matrix based on the CAN signal characteristic parameters after dimension reduction; The driving condition clustering module is used to perform cluster analysis on the reduced-dimensional sample signal matrix, output the driving condition classification results, and set the AMT shift strategy for each driving condition classification result; The shift strategy selection module is used to obtain the real-time vehicle driving data corresponding to the CAN signal characteristic parameters after dimension reduction of the actual working condition, update the working condition classification result, predict the working condition, match the predicted working condition with the driving condition classification result, and select the corresponding AMT shift strategy for shift control.
9. A device, characterized in that: including a processor and a memory; The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the device executes the method described in any one of claims 1 to 7.
10. A storage medium, characterized in that: The storage medium stores instructions, which, when executed on a computer, enable the computer to execute the method described in any one of claims 1 to 7.
Citation Information
Patent Citations
Prediction model establishing method for driving cycle of plug-in hybrid electric vehicle and vehicle energy management method
CN107909179A
Urban ramp driving condition construction method and application
CN111008505A
Self-adaptive adjustment method and system for auxiliary driving system based on driving conditions
CN111216736A
Method for identifying vehicle driving condition based on long short-term memory neural network
CN113485102A
Self-adaptive energy management method for hybrid electric vehicle based on driving condition recognition
CN113859219A
Cited By
Commercial vehicle distributed gear shifting control method and system based on AI
CN122523437A
