Limit scooter structure design management method and system and limit scooter

Abstract

The invention relates to the technical field of data processing, and discloses a limit scooter structure design management method and system and a limit scooter. The method comprises the following steps: performing intelligent acquisition and preprocessing on multi-source heterogeneous data to obtain a multi-dimensional comprehensive data set; performing multi-level index construction and nonlinear calculation on the multi-dimensional comprehensive data set to obtain a limit scooter structure design quantitative index system; performing spatio-temporal multi-scale feature analysis on the limit scooter structure design quantitative index system to obtain a spatio-temporal distribution feature map; performing high-order correlation analysis on the spatial-temporal distribution characteristic spectrum to obtain a multi-dimensional correlation intensity distribution matrix among frame geometric parameters, wheel set configuration and a damping system, performing key factor identification and sensitivity analysis to obtain an influence factor importance ranking table, and performing parameterized structure design scheme optimization; and obtaining a multi-target structure design scheme combination and a performance evaluation index set. According to the invention, the efficiency and accuracy of limit scooter structure design management are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to an extreme scooter structural design management method and system, and an extreme scooter. Background Art

[0002] As a new type of extreme sports equipment, extreme scooters have become very popular among young people in recent years. The traditional extreme scooter structural design mainly relies on the designer's experience and simple mechanical analysis, and usually uses finite element analysis and static load testing to evaluate the frame strength and stiffness. In terms of wheel design, parameters such as wheel diameter, wheel width and hardness are mainly considered, while the shock absorption system mainly focuses on the selection of spring stiffness and damping coefficient. These methods can meet basic performance requirements to a certain extent, but it is difficult to cope with complex and changeable extreme sports scenes.

[0003] However, with the continuous development of extreme sports, traditional design methods can no longer meet the needs of high performance and personalization. First, the existing design process lacks the comprehensive use of multi-source heterogeneous data, and it is difficult to fully consider the complex relationship between the frame stress distribution, the dynamic response of the wheel group and the performance of the shock absorption system. Secondly, the existing performance evaluation index system is relatively simple and it is difficult to accurately reflect the dynamic performance of the scooter under different road conditions. Furthermore, when performing structural optimization, traditional methods often only consider a single goal or a limited number of goals, making it difficult to achieve global optimization of multiple goals. Finally, the existing design process lacks systematicity and intelligence, making it difficult to efficiently optimize parameters and iterate solutions. Summary of the invention

[0004] The present application provides an extreme scooter structural design management method, system and extreme scooter, which are used to improve the efficiency and accuracy of extreme scooter structural design management.

[0005] In a first aspect, the present application provides a method for structural design management of an extreme scooter, the method comprising: intelligently collecting and preprocessing multi-source heterogeneous data to obtain a multidimensional comprehensive data set including frame stress distribution data, wheel group dynamic response data and shock absorption system performance; performing multi-level index construction and nonlinear calculation on the multidimensional comprehensive data set to obtain a quantitative index system for structural design of an extreme scooter including a body stiffness index, a steering sensitivity coefficient and a vibration attenuation rate; performing spatiotemporal multi-scale feature analysis on the quantitative index system for structural design of an extreme scooter to obtain a spatiotemporal distribution feature map reflecting the dynamic response of the body structure under different road conditions; performing high-order correlation analysis on the spatiotemporal distribution feature map to obtain a multidimensional correlation intensity distribution matrix between frame geometric parameters, wheel group configuration and shock absorption system; performing key factor identification and sensitivity analysis on the multidimensional correlation intensity distribution matrix to obtain an importance ranking table of influencing factors including frame material elastic modulus, wheel group angular momentum and shock absorber damping coefficient; performing parametric structural design scheme optimization according to the importance ranking table of influencing factors to obtain a multi-objective structural design scheme combination and a performance evaluation index set.

[0006] In a second aspect, the present application provides an extreme scooter structure design management system, the extreme scooter structure design management system comprising: A processing module is used to intelligently collect and preprocess multi-source heterogeneous data to obtain a multi-dimensional comprehensive data set including frame stress distribution data, wheel set dynamic response data and shock absorption system performance; A calculation module, used for performing multi-level index construction and nonlinear calculation on the multi-dimensional comprehensive data set to obtain a quantitative index system for the extreme scooter structure design including a body stiffness index, a steering sensitivity coefficient and a vibration attenuation rate; A quantification module, used to perform spatiotemporal multi-scale feature analysis on the extreme scooter structural design quantitative index system, and obtain a spatiotemporal distribution feature map reflecting the dynamic response of the vehicle body structure under different road conditions; An analysis module, used for performing a high-order correlation analysis on the spatiotemporal distribution characteristic map to obtain a multi-dimensional correlation intensity distribution matrix between the frame geometric parameters, the wheel set configuration and the shock absorption system; An identification module is used to perform key factor identification and sensitivity analysis on the multi-dimensional correlation intensity distribution matrix to obtain an importance ranking table of influencing factors including the elastic modulus of the frame material, the angular momentum of the wheelset and the damping coefficient of the shock absorber; The optimization module is used to optimize the parameterized structural design scheme according to the importance ranking table of the influencing factors to obtain a combination of multi-objective structural design schemes and a set of performance evaluation indicators.

[0007] The third aspect of the present application provides an extreme scooter, which includes: a frame having a structure optimized by a vehicle body stiffness index; a wheel set connected to the frame, wherein the configuration parameters of the wheel set are optimized based on a steering sensitivity coefficient; a shock absorption system installed on the frame, wherein the shock absorber damping coefficient of the shock absorption system is optimized through vibration attenuation rate analysis; a control system arranged on the frame, for real-time monitoring and adjusting the dynamic response of the vehicle body structure; a sensor network connected to the control system, for collecting frame stress distribution, wheel set dynamic response and shock absorption system performance data; and a human-computer interaction interface installed on the frame, for displaying vehicle performance parameters and receiving user input.

[0008] In the technical solution provided by this application, a multi-dimensional comprehensive data set including frame stress distribution, wheel group dynamic response and shock absorption system performance is obtained by intelligently collecting and preprocessing multi-source heterogeneous data, realizing the comprehensive collection and integration of scooter structure-related data, and providing a rich data basis for subsequent analysis. Multi-level index construction and nonlinear calculation of the multi-dimensional comprehensive data set are carried out to obtain a quantitative index system for the structural design of extreme scooters including body stiffness index, steering sensitivity coefficient and vibration attenuation rate, and a comprehensive and scientific performance evaluation system is established, which can more accurately reflect the structural characteristics and dynamic performance of scooters. By performing spatiotemporal multi-scale feature analysis on the quantitative index system for the structural design of extreme scooters, a spatiotemporal distribution feature map reflecting the dynamic response of the body structure under different road conditions is obtained. This process deeply reveals the performance of scooters in various use environments and provides an important basis for structural optimization. A high-order correlation analysis is performed on the spatiotemporal distribution feature map to obtain a multi-dimensional correlation intensity distribution matrix between frame geometric parameters, wheel group configuration and shock absorption system. This step reveals the complex interaction relationship between various structural parameters, which helps to fully understand the overall performance of the system. By identifying key factors and performing sensitivity analysis on the multidimensional correlation intensity distribution matrix, we obtain the importance ranking table of influencing factors including the elastic modulus of the frame material, the angular momentum of the wheelset, and the damping coefficient of the shock absorber. This process clarifies the contribution of each design parameter to the overall performance and provides a clear direction for the optimization design. Finally, the parametric structural design scheme is optimized according to the importance ranking table of influencing factors to obtain a combination of multi-objective structural design schemes and a set of performance evaluation indicators. This step achieves a comprehensive optimization of the scooter structure and can find the best balance between multiple performance objectives. In general, this method achieves a comprehensive optimization of the extreme scooter structure through a systematic and intelligent data processing and analysis process, significantly improving the comprehensive performance of the scooter, including but not limited to improving the body stiffness, improving steering sensitivity, and enhancing the shock absorption effect. At the same time, this method also greatly improves the design efficiency, shortens the product development cycle, and reduces the design cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0010] Figure 1 A schematic diagram of an embodiment of the extreme scooter structure design management method in the embodiment of the present application;

[0011] Figure 2 This is a schematic diagram of an embodiment of the extreme scooter structure design management system in the embodiment of the present application. DETAILED DESCRIPTION

[0012] The embodiments of the present application provide an extreme scooter structural design management method, system and extreme scooter. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0013] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 , an embodiment of the extreme scooter structure design management method in the embodiment of the present application includes: Step S101, intelligently collect and preprocess multi-source heterogeneous data to obtain a multi-dimensional comprehensive data set including frame stress distribution data, wheel set dynamic response data and shock absorption system performance; Step S102, constructing a multi-level index and performing nonlinear calculation on the multi-dimensional comprehensive data set to obtain a quantitative index system for the structural design of an extreme scooter including a body stiffness index, a steering sensitivity coefficient, and a vibration attenuation rate; Step S103, performing a spatiotemporal multi-scale characteristic analysis on the extreme scooter structural design quantitative index system to obtain a spatiotemporal distribution characteristic map reflecting the dynamic response of the vehicle body structure under different road conditions; Step S104, performing high-order correlation analysis on the spatiotemporal distribution characteristic map to obtain a multi-dimensional correlation intensity distribution matrix between the frame geometric parameters, the wheel set configuration and the shock absorption system; Step S105, performing key factor identification and sensitivity analysis on the multi-dimensional correlation intensity distribution matrix, and obtaining an importance ranking table of influencing factors including the elastic modulus of the frame material, the angular momentum of the wheelset, and the damping coefficient of the shock absorber; Step S106: Optimize the parametric structural design scheme according to the importance ranking table of influencing factors to obtain a multi-objective structural design scheme combination and a performance evaluation index set.

[0014] It is understandable that the execution subject of the present application can be the extreme scooter structure design management system, or a terminal or a server, which is not limited here. The present application embodiment is described by taking the server as the execution subject as an example.

[0015] Specifically, multi-source heterogeneous data are intelligently collected and preprocessed to obtain a multi-dimensional comprehensive data set including frame stress distribution data, wheel group dynamic response data and shock absorption system performance. In this step, the stress data of each key point of the frame are collected by using a distributed sensor network, the dynamic response data of the wheel group is collected by using an accelerometer and a gyroscope, and the performance data of the shock absorption system is collected by using a displacement sensor and a force sensor. The collected raw data are processed by outlier detection, denoising and standardization to form cleaned multi-source heterogeneous data. Subsequently, these data are subjected to feature extraction and dimensionality reduction processing, the data dimension is compressed using the principal component analysis algorithm, and finally high-dimensional feature extraction is performed through the tensor decomposition algorithm to obtain a multi-dimensional comprehensive data set. Multi-level index construction and nonlinear calculation are performed on the multi-dimensional comprehensive data set to obtain a quantitative index system for the structural design of the extreme scooter including the body stiffness index, steering sensitivity coefficient and vibration attenuation rate. In this step, the index hierarchy is first constructed, and then nonlinear mapping and fuzzy comprehensive evaluation are performed. For the body stiffness index, the deformation of the frame under different loads is calculated by finite element analysis, and the stiffness index is calculated in combination with material properties. The steering sensitivity coefficient is obtained by establishing a steering dynamics model and analyzing the influence of wheel geometry parameters and mass distribution on steering performance. The vibration attenuation rate is obtained by spectrum analysis of the shock absorption system and attenuation curve fitting.

[0016] Subsequently, the time-space multi-scale feature analysis of the extreme scooter structural design quantitative index system was carried out to obtain the time-space distribution feature map reflecting the dynamic response of the vehicle body structure under different road conditions. In this step, the index system was first decomposed into time series and analyzed in space distribution, and then the time-space multi-scale features were obtained through wavelet analysis and multi-scale spatial autocorrelation analysis. The time and space features were combined by tensor fusion technology, and the dimension was reduced by principal component analysis to obtain the time-space feature matrix. Then, the road condition recognition model was established using cluster analysis and support vector machine, and the dynamic response data under different road conditions were classified and time-space interpolated. Finally, the time-space distribution feature map was visualized by contour drawing algorithm. The time-space distribution feature map was analyzed by high-order correlation analysis to obtain the multi-dimensional correlation intensity distribution matrix between the frame geometric parameters, wheel configuration and shock absorption system. In this step, the feature map was first reduced in dimension, and then the preliminary correlation matrix was obtained by Pearson correlation analysis and partial correlation analysis. Then, nonlinear correlation analysis and mutual information algorithm were performed to quantify and obtain a high-order correlation index set. The correlation is structured through cluster analysis and hierarchical clustering algorithm, and finally the connectivity is analyzed through graph theory algorithm to obtain a multidimensional correlation intensity distribution matrix.

[0017] Then, the key factors are identified and sensitivity analyzed on the multidimensional correlation intensity distribution matrix, and the importance ranking table of influencing factors including the elastic modulus of the frame material, the angular momentum of the wheelset and the damping coefficient of the shock absorber is obtained. First, eigenvalue decomposition and principal component analysis are performed to obtain the preliminary importance ranking of factors. Then, the influence of each factor is quantified by variance analysis and global sensitivity analysis methods. After threshold screening and local sensitivity analysis, the key factor set is obtained. Finally, the fuzzy comprehensive evaluation and multi-criteria decision-making methods are used to obtain the balanced importance index, which is normalized and sorted to form the final importance ranking table of influencing factors. According to the importance ranking table of influencing factors, the parametric structural design scheme is optimized to obtain the combination of multi-objective structural design schemes and the performance evaluation index set. In this step, parameter sensitivity analysis and orthogonal experimental design are first performed to obtain the parameter optimization scheme. Then, a multi-objective function is constructed and solved using a genetic algorithm to obtain a candidate solution set. The weighted non-inferior solution set is obtained by Pareto frontier analysis and hierarchical analysis. Cluster analysis and fuzzy comprehensive evaluation are performed on the scheme to obtain the evaluation score matrix. Finally, the optimal scheme combination and performance index set are obtained by multi-criteria decision analysis and performance simulation.

[0018] For example, in the design process of a certain extreme scooter, the stress data of 20 key points of the frame are first collected through strain gauges, the dynamic response data of the wheels are collected by acceleration sensors and gyroscopes, and the performance data of the shock absorption system are collected by displacement sensors and force sensors. After data cleaning and feature extraction, a multidimensional comprehensive data set containing 100 features is obtained. Through multi-level index construction, the body stiffness index is calculated to be 85MPa / mm, the steering sensitivity coefficient is 0.8rad / s / °, and the vibration attenuation rate is 0.15s^-1. The spatiotemporal multi-scale feature analysis reveals the dynamic response characteristics of the body structure under five typical road conditions. The high-order correlation analysis shows that there is a complex nonlinear relationship between the frame geometric parameters, wheel configuration and shock absorption system, and the maximum eigenvalue of the correlation coefficient matrix is ​​0.92. The sensitivity analysis results show that the importance weights of the influencing factors of the frame material elastic modulus, wheel angular momentum and shock absorber damping coefficient are 0.4, 0.35 and 0.25 respectively. The final optimized structural design scheme increased the body stiffness by 15%, improved the steering sensitivity by 10%, and enhanced the shock absorption effect by 20% while maintaining the original weight.

[0019] In the embodiment of the present application, a multidimensional comprehensive data set including frame stress distribution, wheel group dynamic response and shock absorption system performance is obtained by intelligently collecting and preprocessing multi-source heterogeneous data, realizing comprehensive collection and integration of scooter structure-related data, and providing a rich data basis for subsequent analysis. Multi-level index construction and nonlinear calculation are performed on the multidimensional comprehensive data set to obtain a quantitative index system for the structural design of an extreme scooter including body stiffness index, steering sensitivity coefficient and vibration attenuation rate, and establish a comprehensive and scientific performance evaluation system that can more accurately reflect the structural characteristics and dynamic performance of the scooter. By performing spatiotemporal multi-scale feature analysis on the quantitative index system for the structural design of an extreme scooter, a spatiotemporal distribution feature map reflecting the dynamic response of the body structure under different road conditions is obtained. This process deeply reveals the performance of the scooter under various usage environments and provides an important basis for structural optimization. A high-order correlation analysis is performed on the spatiotemporal distribution feature map to obtain a multidimensional correlation intensity distribution matrix between frame geometric parameters, wheel group configuration and shock absorption system. This step reveals the complex interaction relationship between various structural parameters, which helps to fully understand the overall performance of the system. By identifying key factors and performing sensitivity analysis on the multidimensional correlation intensity distribution matrix, we obtain the importance ranking table of influencing factors including the elastic modulus of the frame material, the angular momentum of the wheelset, and the damping coefficient of the shock absorber. This process clarifies the contribution of each design parameter to the overall performance and provides a clear direction for the optimization design. Finally, the parametric structural design scheme is optimized according to the importance ranking table of influencing factors to obtain a combination of multi-objective structural design schemes and a set of performance evaluation indicators. This step achieves a comprehensive optimization of the scooter structure and can find the best balance between multiple performance objectives. In general, this method achieves a comprehensive optimization of the extreme scooter structure through a systematic and intelligent data processing and analysis process, significantly improving the comprehensive performance of the scooter, including but not limited to improving the body stiffness, improving steering sensitivity, and enhancing the shock absorption effect. At the same time, this method also greatly improves the design efficiency, shortens the product development cycle, and reduces the design cost.

[0020] In a specific embodiment, the process of executing step S101 may specifically include the following steps: (1) Collect multi-source heterogeneous data to obtain the original data set, and perform outlier detection and denoising on the original data set to obtain cleaned multi-source heterogeneous data; (2) Extract features from the cleaned multi-source heterogeneous data to obtain a preliminary feature set, and perform dimensionality reduction on the preliminary feature set using the principal component analysis algorithm to obtain a compressed feature representation; (3) Perform spatial interpolation analysis on the frame stress distribution data to obtain a continuous stress field, and refine the continuous stress field using the finite element method to obtain the frame stress distribution data; (4) Perform time-frequency domain analysis on the dynamic response data of the wheelset to obtain the response characteristic spectrum, and perform multi-scale decomposition of the response characteristic spectrum through wavelet transform to obtain the dynamic response data of the wheelset; (5) Conduct multi-condition tests on the performance of the shock absorption system to obtain the original shock absorption performance, and smooth the original shock absorption performance through the Kalman filter algorithm to obtain the shock absorption system performance; (6) The compressed feature representation, frame stress distribution data, wheel dynamic response data, and shock absorption system performance are fused to obtain a preliminary fused data set. High-dimensional features are extracted from the preliminary fused data set using a tensor decomposition algorithm to obtain a multidimensional comprehensive data set.

[0021] Specifically, multi-source heterogeneous data are collected to obtain the original data set. These data include information such as frame stress distribution, wheel group dynamic response and shock absorption system performance, which are collected through a distributed sensor network. For example, strain gauges are used to collect stress data of key points of the frame, acceleration sensors and gyroscopes are used to collect dynamic response data of the wheel group, and displacement sensors and force sensors are used to collect performance data of the shock absorption system. Outlier detection is performed on the original data set, outliers are identified using the 3σ criterion, and median filtering is used for denoising to obtain cleaned multi-source heterogeneous data. Feature extraction is performed on the cleaned multi-source heterogeneous data to obtain a preliminary feature set. The feature extraction process includes the calculation of time domain features (such as mean, variance, peak) and frequency domain features (such as power spectrum density, main frequency). Then, the preliminary feature set is reduced in dimension by the principal component analysis (PCA) algorithm. The PCA algorithm calculates eigenvectors and eigenvalues, selects the eigenvectors corresponding to the largest k eigenvalues ​​as the principal components, and thus obtains the compressed feature representation. For the frame stress distribution data, spatial interpolation analysis is performed to obtain a continuous stress field. Here, the Kriging interpolation method is used, which takes into account the spatial correlation between data points and can more accurately estimate the value of unknown points. Then, the continuous stress field is refined by the finite element method. The finite element method discretizes the frame structure into small units, and by solving the stress state of each unit, more detailed frame stress distribution data is obtained.

[0022] The dynamic response data of the wheel set is analyzed in the time and frequency domain to obtain the response characteristic spectrum. The time domain analysis includes calculating statistics such as mean, standard deviation, and peak value, while the frequency domain analysis uses fast Fourier transform (FFT) to convert the time domain signal into the frequency domain. Subsequently, the response characteristic spectrum is decomposed in multiple scales by wavelet transform. Wavelet transform can simultaneously locate the time and frequency characteristics of the signal on the time-frequency plane, which is suitable for analyzing non-stationary signals. Here, Morlet wavelet is selected to perform multi-scale decomposition of the response characteristic spectrum to obtain the time-frequency characteristics of the dynamic response data of the wheel set. The performance of the shock absorption system is tested under multiple working conditions to obtain the original shock absorption performance data. The test conditions include different road types, different speeds, and different load conditions. The original shock absorption performance data is smoothed by the Kalman filter algorithm. Kalman filtering is a recursive algorithm that can estimate the state of a dynamic system in a noisy environment. It continuously optimizes the state estimation through two steps of prediction and update to obtain the smoothed shock absorption system performance data.

[0023] Finally, the compressed feature representation, frame stress distribution data, wheel group dynamic response data and shock absorption system performance are fused to obtain a preliminary fused data set. The data fusion adopts the Dempster-Shafer evidence theory, which can process data from different sources and different precisions and reasonably allocate confidence. Then, the tensor decomposition algorithm is used to extract high-dimensional features from the preliminary fused data set. Decomposition is used here to decompose the high-dimensional data tensor into the product of the core tensor and the factor matrix to obtain a multidimensional comprehensive data set. For example, in the design process of a certain extreme scooter, the stress data of the frame is first collected by 20 strain gauges, the dynamic response data of the wheel group is collected by 4 triaxial accelerometers and 2 gyroscopes, and the performance data of the shock absorption system is collected by 4 displacement sensors and 2 force sensors. The original data set contains about 1 million data points. After outlier detection and denoising, 950,000 valid data points are retained. 500 initial features are obtained by feature extraction, and 50 principal components are retained after dimensionality reduction by the PCA algorithm, explaining 95% of the variance. The frame stress distribution data was obtained by Kriging interpolation method to obtain 1000x1000 grid data, and the finite element analysis was further refined into 10000x10000 high-precision stress distribution. After FFT and wavelet transformation, the dynamic response data of the wheel set obtained a 100x100 time-frequency feature matrix. The shock absorption system performance data was tested under 10 different working conditions, and 1000 data points were collected for each working condition. After Kalman filtering and smoothing, a continuous performance curve was obtained. Finally, through data fusion and tensor decomposition, a 50x100x100x10 four-dimensional tensor was obtained. As a multi-dimensional comprehensive data set, it provides comprehensive and accurate data support for subsequent structural design optimization.

[0024] In a specific embodiment, the process of executing step S102 may specifically include the following steps: (1) Perform hierarchical analysis on the multidimensional comprehensive data set to obtain the indicator hierarchy, and assign weights to the indicator hierarchy to obtain a preliminary indicator system; (2) Perform nonlinear mapping on the preliminary indicator system to obtain a nonlinear indicator set, and fuse the nonlinear indicator set through a fuzzy comprehensive evaluation method to obtain a fused indicator system; (3) Perform stress-strain analysis on the body stiffness-related data in the fusion index system to obtain the body stiffness distribution, and quantify the body stiffness distribution through finite element calculation to obtain the body stiffness index; (4) Perform dynamic modeling on the steering system related data in the fusion index system to obtain the steering dynamics model, and extract parameters of the steering dynamics model through sensitivity analysis to obtain the steering sensitivity coefficient; (5) Perform spectrum analysis on the vibration-related data in the fusion index system to obtain the vibration spectrum, and extract features from the vibration spectrum through attenuation curve fitting to obtain the vibration attenuation rate; (6) A comprehensive evaluation is conducted on the body stiffness index, steering sensitivity coefficient, and vibration attenuation rate to obtain a comprehensive performance index. The comprehensive performance index is weighed through a multi-objective optimization algorithm to obtain a quantitative index system for the extreme scooter structural design.

[0025] Specifically, a hierarchical analysis is performed on the multidimensional comprehensive data set to obtain the indicator hierarchy. The analytic hierarchy process (AHP) is used to decompose complex problems into a target layer, a criterion layer, and an indicator layer. For extreme scooters, the target layer is the overall performance, the criterion layer includes safety, handling, and comfort, and the indicator layer includes specific indicators such as body stiffness, steering sensitivity, and vibration attenuation. Then, the indicator hierarchy is weighted, and a 9-point scale is used for pairwise comparison. The judgment matrix A is constructed, and the eigenvector W and the maximum eigenvalue λmax are calculated to obtain the weight of each indicator. The weight calculation formula is as follows:

[0026] Among them, A is the judgment matrix, W is the weight vector, is the maximum eigenvalue.

[0027] Next, the preliminary indicator system is nonlinearly mapped to obtain a nonlinear indicator set. Here, the sigmoid function is used for mapping, and the original indicator value Mapping to the interval [0,1]:

[0028] in, is the index value after mapping, α is the slope parameter, and β is the midpoint parameter. By adjusting α and β, the nonlinear degree of mapping can be controlled. Then, the fuzzy comprehensive evaluation method is used to fuse the nonlinear index set. First, the fuzzy relationship matrix R is established, and then the fuzzy comprehensive evaluation result B is calculated by combining the weight vector W:

[0029] in, Represents a fuzzy composite operation.

[0030] The stress-strain analysis of the body stiffness related data in the fusion index system is performed to obtain the body stiffness distribution. This step uses the finite element analysis method to discretize the body structure into a finite number of units, establish the stiffness matrix K and the load vector F, and solve the displacement vector :

[0031] By calculating the stress and strain of each unit, the overall stiffness distribution is obtained. Then, the body stiffness distribution is quantified through integral calculation to obtain the body stiffness index SI:

[0032] E(x) is the local stiffness at the spatial point x, and V is the volume of the entire vehicle body.

[0033] The steering system related data in the fusion index system are dynamically modeled to obtain the steering dynamics model. Here, a bicycle model is used to establish the balance equations of the center of mass lateral force, front and rear wheel lateral force, and yaw moment. By solving the state equation, the lateral velocity and yaw angular velocity of the vehicle are obtained. Then, the parameters of the steering dynamics model are extracted through sensitivity analysis to obtain the steering sensitivity coefficient SS:

[0034] Where ψ is the yaw angular velocity, δ is the front wheel steering angle.

[0035] Perform spectrum analysis on the vibration-related data in the fusion index system to obtain the vibration spectrum. This step uses fast Fourier transform (FFT) to convert the time domain signal into the frequency domain. Then, extract the features of the vibration spectrum through attenuation curve fitting to obtain the vibration attenuation rate DR. Use the exponential attenuation model:

[0036] in, is the amplitude at time t, is the initial amplitude, is the vibration attenuation rate.

[0037] Finally, the body stiffness index, steering sensitivity coefficient and vibration attenuation rate are comprehensively evaluated to obtain the comprehensive performance index CP:

[0038] in, , , is the weight of each index. The comprehensive performance index is weighed by a multi-objective optimization algorithm (such as NSGA-II) to obtain a quantitative index system for the extreme scooter structure design.

[0039] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0040] (1) Decompose the time series of the quantitative index system of extreme scooter structure design to obtain the time scale characteristics, and perform multi-resolution processing on the time scale characteristics through wavelet analysis to obtain the time multi-scale feature set; (2) The spatial distribution of the quantitative index system of extreme scooter structural design is analyzed to obtain spatial scale characteristics, and the spatial scale characteristics are processed through multi-scale spatial autocorrelation analysis to obtain a spatial multi-scale feature set; (3) Perform tensor fusion on the temporal multi-scale feature set and the spatial multi-scale feature set to obtain the spatiotemporal multi-scale feature tensor, and reduce the dimension of the spatiotemporal multi-scale feature tensor through principal component analysis to obtain the spatiotemporal feature matrix after dimensionality reduction; (4) Perform cluster analysis on the reduced-dimensional spatiotemporal feature matrix to obtain a road condition classification, and then use a support vector machine to model the road condition classification to obtain a road condition recognition model. (5) Collecting the dynamic response data of the vehicle structure under different road conditions to obtain the original dynamic response data, and classifying and processing the original dynamic response data through the road condition recognition model to obtain a classified dynamic response data set; (6) Perform spatiotemporal interpolation on the classified dynamic response data set to obtain a continuous spatiotemporal distribution function, which is then visualized using a contour drawing algorithm to obtain a spatiotemporal distribution feature map that reflects the dynamic response of the vehicle structure under different road conditions.

[0041] Specifically, the time series decomposition of the quantitative index system of the extreme scooter structure design is carried out to obtain the time scale characteristics. The empirical mode decomposition (EMD) method is used to decompose the original signal into a series of intrinsic mode functions (IMFs) and a residual term. The EMD method gradually extracts the high-frequency to low-frequency components in the signal through an iterative "screening" process to form IMFs of different time scales. Then, the time scale characteristics are processed by multi-resolution through wavelet analysis to obtain a time multi-scale feature set. Wavelet analysis uses discrete wavelet transform (DWT) to select appropriate wavelet basis functions (such as Daubechies wavelet) to decompose the signal at multiple scales. DWT decomposes the signal into approximate coefficients and detail coefficients, reflecting the characteristics of the signal at different scales and frequencies. The spatial distribution analysis of the quantitative index system of the extreme scooter structure design is carried out to obtain the spatial scale characteristics. This step uses spatial interpolation methods (such as Kriging interpolation) to expand the discrete measurement point data to continuous space. Then, the spatial scale characteristics are processed by multi-scale spatial autocorrelation analysis to obtain a spatial multi-scale feature set. Multiscale spatial autocorrelation analysis uses the Moran's I index to calculate autocorrelation at different spatial scales. The Moran's I index reflects the similarity between spatial units. The closer the value is to 1, the stronger the positive correlation is, the closer it is to -1, the stronger the negative correlation is, and the closer it is to 0, the random distribution is indicated.

[0042] Subsequently, the temporal multiscale feature set and the spatial multiscale feature set are tensor fused to obtain the spatiotemporal multiscale feature tensor. The tensor fusion adopts the Tucker decomposition method to represent the high-dimensional data as the product of the core tensor and the factor matrix. Tucker decomposition can effectively capture the relationship between multidimensional data and retain the structural information of the data. Then, the spatiotemporal multiscale feature tensor is reduced in dimension by principal component analysis (PCA) to obtain the spatiotemporal feature matrix after dimensionality reduction. PCA selects the main components by calculating the eigenvalues ​​and eigenvectors of the covariance matrix to achieve data dimensionality reduction while retaining the main variation information of the data. Cluster analysis is performed on the spatiotemporal feature matrix after dimensionality reduction to obtain the road condition type classification. Here, the K-means clustering algorithm is used to divide the data points into K clusters. The K-means algorithm achieves natural grouping of data by iteratively optimizing the cluster center position and minimizing the sum of squares within the cluster. Then, the road condition type classification is modeled by support vector machine (SVM) to obtain the road condition recognition model. SVM constructs the optimal separation hyperplane in high-dimensional feature space to achieve multi-category classification and has good generalization ability.

[0043] Subsequently, the dynamic response data of the vehicle structure under different road conditions are collected to obtain the original dynamic response data. The collection process uses accelerometers, strain gauges and other equipment to collect vibration, stress and other data at key locations of the vehicle body. The original dynamic response data is classified and processed by the road condition recognition model to obtain a classified dynamic response data set. This step uses the trained SVM model to assign the newly collected data to the corresponding road condition category, realizing the intelligent classification of real-time data. The classified dynamic response data set is interpolated in time and space to obtain a continuous space-time distribution function. The space-time interpolation uses the Kriging interpolation method, which takes into account the spatial and temporal correlation of the data and can estimate the data value at the unsampled position and time point. Then, the continuous space-time distribution function is visualized by the contour drawing algorithm to obtain the space-time distribution feature map reflecting the dynamic response of the vehicle structure under different road conditions. The contour drawing uses the Marching Squares algorithm to discretize the continuous function into a grid, and interpolate the contour lines in the grid unit to generate contour lines, which intuitively shows the spatial distribution characteristics of the data.

[0044] For example, in the structural design process of a certain extreme scooter, the body stiffness index, steering sensitivity coefficient and vibration attenuation rate were first monitored continuously for 30 days with a sampling frequency of 100Hz. The time series was decomposed into 5 IMFs and 1 residual term by the EMD method, reflecting the time scale characteristics from high frequency to low frequency. The db4 wavelet was used for 5-layer decomposition to obtain wavelet coefficients reflecting different frequency characteristics. In terms of spatial scale, 100 key points of the vehicle body were measured and expanded to a 1000x1000 grid by Kriging interpolation. The Moran's I index at different scales (1cm, 5cm, 10cm, 50cm) was calculated, and 0.85, 0.72, 0.61, and 0.45 were obtained respectively, reflecting the change of spatial autocorrelation with scale. After tensor fusion, a 100x100x5 third-order tensor was obtained, and the first 20 principal components that explained 95% of the variance were retained after PCA dimensionality reduction. K-means clustering (K=5) divides the data into five typical road conditions, and the SVM model achieves a classification accuracy of 93% in cross-validation. The resulting spatiotemporal distribution feature map clearly shows how the stress distribution and vibration characteristics of various parts of the vehicle body change over time under different road conditions.

[0045] In a specific embodiment, the process of executing step S104 may specifically include the following steps: (1) Extract features from the spatiotemporal distribution feature map to obtain a high-dimensional feature vector, and reduce the dimension of the high-dimensional feature vector through principal component analysis to obtain a feature set after dimensionality reduction; (2) Perform Pearson correlation analysis on the feature set after dimensionality reduction to obtain a preliminary correlation matrix, and correct the preliminary correlation matrix through partial correlation analysis to obtain a corrected correlation matrix; (3) Perform nonlinear correlation analysis on the corrected correlation matrix to obtain nonlinear correlation indicators, and quantify the nonlinear correlation indicators through mutual information algorithm to obtain a set of high-order correlation indicators; (4) Perform cluster analysis on the high-order correlation index set to obtain correlation clusters, and then structure the correlation clusters through a hierarchical clustering algorithm to obtain a correlation hierarchy tree; (5) Pruning the correlation hierarchy tree to obtain an optimized correlation structure, and performing connectivity analysis on the optimized correlation structure using a graph theory algorithm to obtain a connection strength distribution; (6) The connection strength distribution is normalized to obtain the standardized strength distribution, and the standardized strength distribution is reconstructed through matrix transformation to obtain the multidimensional correlation strength distribution matrix among the frame geometric parameters, wheel configuration and shock absorption system.

[0046] Specifically, the spatiotemporal distribution feature map is extracted to obtain a high-dimensional feature vector. This step uses statistical moment and texture feature extraction methods, including calculating the mean, variance, skewness, kurtosis and other statistics of the map, and extracting gray-level co-occurrence matrix (GLCM) features. Then, the high-dimensional feature vector is reduced in dimension through principal component analysis (PCA) to obtain a feature set after dimensionality reduction. The core of PCA is to solve the eigenvalue equation:

[0047] Where C is the covariance matrix, λ is the eigenvalue, v is the eigenvector, and I is the unit matrix. Data dimensionality reduction is achieved by selecting the eigenvectors corresponding to the largest k eigenvalues. Next, Pearson correlation analysis is performed on the reduced feature set to obtain a preliminary correlation matrix. Then, the preliminary correlation matrix is ​​corrected by partial correlation analysis to obtain a corrected correlation matrix. Partial correlation analysis eliminates the influence of other variables and reflects the direct correlation between two variables.

[0048] Subsequently, the corrected correlation matrix is ​​subjected to nonlinear correlation analysis to obtain nonlinear correlation indicators. The nonlinear correlation indicators are quantified by the mutual information algorithm to obtain a set of high-order correlation indicators. The set of high-order correlation indicators is clustered to obtain correlation clusters. Here, the K-means clustering algorithm is used to divide the data points by minimizing the sum of squares within the cluster. Then, the correlation clusters are structured by the hierarchical clustering algorithm to obtain a correlation hierarchy tree. Hierarchical clustering gradually merges clusters by calculating the distance between clusters (such as Ward distance) to form a tree structure.

[0049] Prune the correlation hierarchy tree to obtain an optimized correlation structure. The pruning process removes redundant or insignificant branches based on the set threshold or inter-cluster distance. Then, the optimized correlation structure is analyzed for connectivity through a graph theory algorithm to obtain a connection strength distribution. The PageRank algorithm is used here to calculate the importance of a node, and the formula is:

[0050] in, For Node The PageRank value of , d is the damping coefficient, N is the total number of nodes, To point to The node set of for Finally, the connection strength distribution is normalized to obtain the standardized strength distribution. The standardized strength distribution is reconstructed through matrix transformation to obtain the multi-dimensional correlation strength distribution matrix between the frame geometric parameters, wheel configuration and shock absorption system.

[0051] In a specific embodiment, the process of executing step S105 may specifically include the following steps: (1) Perform eigenvalue decomposition on the multidimensional correlation intensity distribution matrix to obtain a set of eigenvectors, and then use principal component analysis to rank the importance of the eigenvectors to obtain a preliminary importance ranking of factors including the elastic modulus of the frame material, the angular momentum of the wheelset, and the damping coefficient of the shock absorber; (2) Perform variance analysis on the initial factor importance ranking to obtain the variance contribution rate of each factor, and quantify the variance contribution rate through the global sensitivity analysis method to obtain the global sensitivity index of the frame material elastic modulus, wheel angular momentum and shock absorber damping coefficient; (3) Threshold screening is performed on the global sensitivity index to obtain a set of key factors including the elastic modulus of the frame material, the angular momentum of the wheelset, and the damping coefficient of the shock absorber. The key factor set is then refined through a local sensitivity analysis method to obtain a local sensitivity index. (4) Perform fuzzy comprehensive evaluation on local sensitivity indicators to obtain the comprehensive importance scores of the frame material elastic modulus, wheelset angular momentum, and shock absorber damping coefficient. The comprehensive importance scores are weighed through a multi-criteria decision-making method to obtain a balanced importance index. (5) The importance indicators after balancing are normalized to obtain the standardized importance indicators of the frame material elastic modulus, the wheelset angular momentum, and the shock absorber damping coefficient. The standardized importance indicators are sorted by a sorting algorithm to obtain a ranking table of the importance of influencing factors.

[0052] Specifically, the multidimensional correlation intensity distribution matrix is ​​subjected to eigenvalue decomposition to obtain the eigenvector set. This step uses the singular value decomposition (SVD) method to decompose the matrix into the product of three matrices. The eigenvector set is ranked by importance through principal component analysis to obtain the preliminary factor importance ranking including the elastic modulus of the frame material, the angular momentum of the wheelset and the damping coefficient of the shock absorber. The principal component analysis is sorted based on the size of the eigenvalue. The larger the eigenvalue, the more important the corresponding principal component. The variance analysis is performed on the preliminary factor importance ranking to obtain the variance contribution rate of each factor. The variance analysis uses the F test to calculate the F value of each factor. The larger the F value, the more significant the influence of the factor. Then, the variance contribution rate is quantified by the global sensitivity analysis method to obtain the global sensitivity index of the elastic modulus of the frame material, the angular momentum of the wheelset and the damping coefficient of the shock absorber. Here, the Sobol' sensitivity analysis method is used to calculate the total effect index. The total effect index reflects the overall impact of the factor and its interaction with other factors on the output. The global sensitivity index is screened by threshold, and a set of key factors including the elastic modulus of the frame material, the angular momentum of the wheelset and the damping coefficient of the shock absorber are obtained. The selection of thresholds is based on the cumulative contribution rate, and factors with a cumulative contribution rate of 80% or 90% are usually selected. Then, the key factor set is refined by the local sensitivity analysis method to obtain the local sensitivity index. The local sensitivity analysis uses the partial derivative method to calculate the partial derivative of the output to each input factor, reflecting the degree of influence of a small change in the input on the output.

[0053] Next, the local sensitivity index is subjected to fuzzy comprehensive evaluation to obtain the comprehensive importance scores of the elastic modulus of the frame material, the angular momentum of the wheelset and the damping coefficient of the shock absorber. The fuzzy comprehensive evaluation includes establishing a factor set, an evaluation set, determining the membership function and the weight vector, and finally performing a fuzzy synthesis operation. Then, the comprehensive importance score is weighed by a multi-criteria decision-making method to obtain the importance index after balance. Here, the analytic hierarchy process (AHP) is used to construct a judgment matrix, calculate the weight vector, and finally obtain the comprehensive weight of each factor. The balanced importance index is normalized to obtain the standardized importance index of the elastic modulus of the frame material, the angular momentum of the wheelset and the damping coefficient of the shock absorber. The normalization process uses the minimum-maximum normalization method to map the index value to the [0,1] interval. Then, the standardized importance index is sorted by a sorting algorithm to obtain an importance ranking table of influencing factors. The sorting algorithm can select efficient algorithms such as quick sort or heap sort.

[0054] For example, in the design process of a certain extreme scooter, 20 eigenvectors were first obtained through SVD decomposition, and principal component analysis showed that the first five principal components cumulatively explained 90% of the variance. The results of variance analysis showed that the F values ​​of the elastic modulus of the frame material, the angular momentum of the wheelset, and the damping coefficient of the shock absorber were 15.3, 12.7, and 10.2, respectively, which were significantly higher than other factors. The total effect index of these three factors obtained by Sobol's global sensitivity analysis was 0.45, 0.38, and 0.32, respectively. After threshold screening, these three factors were identified as key factors. Local sensitivity analysis showed that the elastic modulus of the frame material had the greatest impact on the overall performance near the working point, and every 1% change could lead to a 0.8% change in performance. The importance scores of the three factors obtained by fuzzy comprehensive evaluation were 0.85, 0.75, and 0.70, respectively. After AHP analysis, considering cost and feasibility, the importance indexes after balance were 0.82, 0.78, and 0.73, respectively. After normalization, the final standardized importance indexes are 0.95, 0.90 and 0.85. The ranking results show that the elastic modulus of the frame material, the angular momentum of the wheelset and the damping coefficient of the shock absorber are ranked first, second and third respectively.

[0055] In a specific embodiment, the process of executing step S106 may specifically include the following steps: (1) Perform parameter sensitivity analysis on the importance ranking table of influencing factors to obtain the parameter sensitivity matrix, and optimize the parameter sensitivity matrix through orthogonal experimental design to obtain the parameter optimization scheme; (2) Constructing a multi-objective function for the parameter optimization scheme to obtain an objective function set, and solving the objective function set through a genetic algorithm to obtain a candidate solution set; (3) Perform Pareto frontier analysis on the candidate solution set to obtain the non-inferior solution set, and assign weights to the non-inferior solution set through the analytic hierarchy process to obtain the weighted non-inferior solution set; (4) Perform cluster analysis on the weighted non-inferior solution set to obtain a solution cluster, and then evaluate the solution cluster using the fuzzy comprehensive evaluation method to obtain an evaluation score matrix; (5) Perform multi-criteria decision analysis on the evaluation score matrix to obtain the optimal solution combination, and verify the optimal solution combination through performance simulation to obtain a performance indicator set; (6) Comprehensively evaluate the performance indicator set to obtain a comprehensive performance score, and iteratively optimize the comprehensive performance score through a feedback optimization mechanism to obtain a multi-objective structural design scheme combination and a performance evaluation indicator set.

[0056] Specifically, the parameter sensitivity analysis is performed on the importance ranking table of influencing factors to obtain the parameter sensitivity matrix. The local sensitivity analysis method is used to calculate the partial derivative of each parameter with respect to the objective function, so as to determine the degree of influence of each parameter on the system performance. The parameter sensitivity matrix is ​​optimized by orthogonal experimental design to obtain the parameter optimization scheme. Orthogonal experimental design uses an orthogonal table to arrange experiments, which reduces the number of experiments while ensuring the representativeness and uniformity of the experiments, effectively improving the optimization efficiency. Multi-objective functions are constructed for the parameter optimization scheme to obtain the objective function set. Multi-objective functions usually include performance indicators (such as stiffness, stability) and cost indicators. These objective functions reflect multiple aspects that need to be balanced in the design of extreme scooters, such as performance, weight, cost, etc. The objective function set is solved by genetic algorithm to obtain the candidate solution set. Genetic algorithm simulates natural selection and genetic processes, and continuously optimizes the solution population through selection, crossover and mutation operations, which can effectively handle complex multi-objective optimization problems.

[0057] Subsequently, the candidate solution set is subjected to Pareto front analysis to obtain a non-inferior solution set. The Pareto front contains solutions that cannot be improved on any objective without compromising other objectives, and represents the optimal compromise solution for multi-objective optimization problems. The non-inferior solution set is weighted by the analytic hierarchy process to obtain a weighted non-inferior solution set. The analytic hierarchy process constructs a judgment matrix, and obtains the weight of each objective by solving the eigenvalue and eigenvector, which reflects the decision maker's preference for different objectives. The weighted non-inferior solution set is clustered to obtain a solution cluster. Here, the K-means clustering algorithm is used to cluster similar solutions together for subsequent evaluation and selection. Then, the solution cluster is evaluated by the fuzzy comprehensive evaluation method to obtain an evaluation score matrix. Fuzzy comprehensive evaluation is based on fuzzy set theory, takes into account the uncertainty and ambiguity of the evaluation, and can more objectively reflect the pros and cons of the solution.

[0058] Perform multi-criteria decision analysis on the evaluation score matrix to obtain the optimal solution combination. Multi-criteria decision can use the TOPSIS method to calculate the distance between each solution and the ideal solution and the negative ideal solution to obtain the relative proximity, so as to select the optimal solution. The optimal solution combination is verified by performance simulation to obtain a performance index set. Performance simulation can be performed using finite element analysis or multi-body dynamics simulation software to comprehensively evaluate the actual performance of the solution. Perform a comprehensive evaluation on the performance index set to obtain a comprehensive performance score. The comprehensive evaluation adopts the weighted summation method to weight each performance index according to its importance. The comprehensive performance score is iteratively optimized through the feedback optimization mechanism to obtain a multi-objective structural design solution combination and a performance evaluation index set. Feedback optimization adopts the gradient descent method to continuously adjust parameters to improve the comprehensive performance score and achieve continuous improvement of the solution.

[0059] For example, in the design process of a certain extreme scooter, the elastic modulus of the frame material, the angular momentum of the wheelset, and the damping coefficient of the shock absorber were first analyzed for parameter sensitivity, and the sensitivities were 0.45, 0.35, and 0.20, respectively. The orthogonal array design experiment determined the optimal parameter combination. The multi-objective function includes maximizing the stiffness index and minimizing the weight. 100 candidate solutions were obtained using the NSGA-II algorithm. Pareto front analysis screened out 20 non-inferior solutions, and the hierarchical analysis method gave the weights of stiffness and weight as 0.6 and 0.4 respectively. K-means clustering (K=5) divided the non-inferior solutions into 5 clusters, and fuzzy comprehensive evaluation was used to obtain the score of each cluster. The TOPSIS method selected the solution with the highest relative proximity, in which the elastic modulus of the frame material is 210GPa and the angular momentum of the wheelset is , the damping coefficient of the shock absorber is 1500N·s / m. Finite element simulation verifies the performance of the scheme under various working conditions. The final comprehensive performance score is 0.92, and after 5 rounds of iterative optimization, the score is improved to 0.95, forming a complete set of extreme scooter structural design scheme combination and performance evaluation index set.

[0060] The above describes the extreme scooter structure design management method in the embodiment of the present application. The following describes the extreme scooter structure design management system in the embodiment of the present application. Figure 2 In the embodiment of the present application, an embodiment of the extreme scooter structure design management system includes: Processing module 201, used for intelligently collecting and preprocessing multi-source heterogeneous data to obtain a multi-dimensional comprehensive data set including frame stress distribution data, wheel set dynamic response data and shock absorption system performance; A calculation module 202 is used to perform multi-level index construction and nonlinear calculation on the multi-dimensional comprehensive data set to obtain a quantitative index system for the extreme scooter structure design including a body stiffness index, a steering sensitivity coefficient, and a vibration attenuation rate; A quantification module 203 is used to perform a spatiotemporal multi-scale feature analysis on the extreme scooter structural design quantification index system to obtain a spatiotemporal distribution feature map reflecting the dynamic response of the vehicle body structure under different road conditions; An analysis module 204 is used to perform a high-order correlation analysis on the spatiotemporal distribution characteristic map to obtain a multi-dimensional correlation intensity distribution matrix between the frame geometric parameters, the wheel set configuration and the shock absorption system; An identification module 205 is used to perform key factor identification and sensitivity analysis on the multi-dimensional correlation intensity distribution matrix to obtain an importance ranking table of influencing factors including the elastic modulus of the frame material, the angular momentum of the wheelset and the damping coefficient of the shock absorber; The optimization module 206 is used to optimize the parameterized structural design scheme according to the importance ranking table of the influencing factors to obtain a combination of multi-objective structural design schemes and a set of performance evaluation indicators.

[0061] Through the collaboration of the above components, and through intelligent collection and preprocessing of multi-source heterogeneous data, a multidimensional comprehensive data set including frame stress distribution, wheel group dynamic response and shock absorption system performance is obtained, which realizes the comprehensive collection and integration of scooter structure-related data, and provides a rich data basis for subsequent analysis. Multi-level index construction and nonlinear calculation of the multidimensional comprehensive data set are carried out to obtain a quantitative index system for the structural design of extreme scooters, including body stiffness index, steering sensitivity coefficient and vibration attenuation rate, which can more accurately reflect the structural characteristics and dynamic performance of scooters. Through the spatiotemporal multi-scale feature analysis of the quantitative index system for the structural design of extreme scooters, the spatiotemporal distribution feature map reflecting the dynamic response of the body structure under different road conditions is obtained. This process deeply reveals the performance of scooters in various usage environments and provides an important basis for structural optimization. The high-order correlation analysis of the spatiotemporal distribution feature map is carried out to obtain the multidimensional correlation intensity distribution matrix between the frame geometric parameters, wheel group configuration and shock absorption system, which reveals the complex interaction relationship between the structural parameters and helps to fully understand the overall performance of the system. By identifying key factors and performing sensitivity analysis on the multidimensional correlation intensity distribution matrix, we obtain the importance ranking table of influencing factors including the elastic modulus of the frame material, the angular momentum of the wheelset, and the damping coefficient of the shock absorber, clarifying the contribution of each design parameter to the overall performance, and providing a clear direction for the optimization design. Finally, the parametric structural design scheme is optimized according to the importance ranking table of influencing factors, and a combination of multi-objective structural design schemes and a set of performance evaluation indicators are obtained. This step achieves a comprehensive optimization of the scooter structure and can find the best balance between multiple performance objectives. In general, this method achieves a comprehensive optimization of the extreme scooter structure through a systematic and intelligent data processing and analysis process, and significantly improves the comprehensive performance of the scooter, including but not limited to improving the body stiffness, improving steering sensitivity, and enhancing shock absorption effect. At the same time, this method also greatly improves the design efficiency, shortens the product development cycle, and reduces the design cost.

[0062] Based on the same technical concept, an embodiment of the present application also provides an extreme scooter, characterized in that it includes: a frame, the frame has a structure optimized by the body stiffness index; a wheel set connected to the frame, the configuration parameters of the wheel set are optimized based on the steering sensitivity coefficient; a shock absorption system installed on the frame, the shock absorber damping coefficient of the shock absorption system is optimized through vibration attenuation rate analysis; a control system arranged on the frame, for real-time monitoring and adjusting the dynamic response of the body structure; a sensor network connected to the control system, for collecting frame stress distribution, wheel set dynamic response and shock absorption system performance data; a human-computer interaction interface installed on the frame, for displaying vehicle performance parameters and receiving user input.

[0063] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for designing and managing the structure of an extreme scooter, characterized in that: The extreme scooter structure design management method comprises: Intelligently collect and preprocess multi-source heterogeneous data to obtain a multi-dimensional comprehensive data set including frame stress distribution data, wheel set dynamic response data and shock absorption system performance; Performing multi-level index construction and nonlinear calculation on the multi-dimensional comprehensive data set to obtain a quantitative index system for the structural design of an extreme scooter including a body stiffness index, a steering sensitivity coefficient, and a vibration attenuation rate; Performing a spatiotemporal multi-scale characteristic analysis on the extreme scooter structural design quantitative index system to obtain a spatiotemporal distribution characteristic map reflecting the dynamic response of the vehicle body structure under different road conditions; Performing a high-order correlation analysis on the spatiotemporal distribution characteristic map to obtain a multi-dimensional correlation intensity distribution matrix among the frame geometric parameters, wheel set configuration and shock absorption system; Performing key factor identification and sensitivity analysis on the multi-dimensional correlation intensity distribution matrix to obtain an importance ranking table of influencing factors including the elastic modulus of the frame material, the angular momentum of the wheelset and the damping coefficient of the shock absorber; The parametric structural design scheme is optimized according to the importance ranking table of the influencing factors to obtain a multi-objective structural design scheme combination and a performance evaluation index set.

2. The extreme scooter structure design management method according to claim 1, characterized in that: The intelligent collection and preprocessing of multi-source heterogeneous data obtains a multi-dimensional comprehensive data set including frame stress distribution data, wheel set dynamic response data and shock absorption system performance, including: Collecting multi-source heterogeneous data to obtain an original data set, and performing outlier detection and denoising on the original data set to obtain cleaned multi-source heterogeneous data; Extracting features from the cleaned multi-source heterogeneous data to obtain a preliminary feature set, and performing dimensionality reduction processing on the preliminary feature set through a principal component analysis algorithm to obtain a compressed feature representation; Performing spatial interpolation analysis on the frame stress distribution data to obtain a continuous stress field, and refining the continuous stress field by a finite element method to obtain the frame stress distribution data; Performing time-frequency domain analysis on the dynamic response data of the wheelset to obtain a response characteristic spectrum, and performing multi-scale decomposition on the response characteristic spectrum through wavelet transform to obtain the dynamic response data of the wheelset; Performing multi-condition tests on the performance of the damping system to obtain original damping performance, and smoothing the original damping performance through a Kalman filter algorithm to obtain the performance of the damping system; The compressed feature representation, frame stress distribution data, wheel set dynamic response data and shock absorption system performance are fused to obtain a preliminary fused data set, and high-dimensional features are extracted from the preliminary fused data set through a tensor decomposition algorithm to obtain a multi-dimensional comprehensive data set.

3. The extreme scooter structure design management method according to claim 1, characterized in that: The multi-dimensional comprehensive data set is subjected to multi-level index construction and nonlinear calculation to obtain a quantitative index system for the structural design of an extreme scooter including a body stiffness index, a steering sensitivity coefficient and a vibration attenuation rate, including: Perform hierarchical analysis on the multidimensional comprehensive data set to obtain an indicator hierarchy, and assign weights to the indicator hierarchy to obtain a preliminary indicator system; Performing nonlinear mapping on the preliminary indicator system to obtain a nonlinear indicator set, and fusing the nonlinear indicator set through a fuzzy comprehensive evaluation method to obtain a fused indicator system; Performing stress-strain analysis on the vehicle body stiffness related data in the fusion index system to obtain the vehicle body stiffness distribution, and quantifying the vehicle body stiffness distribution through finite element calculation to obtain the vehicle body stiffness index; Performing dynamic modeling on steering system related data in the fusion index system to obtain a steering dynamics model, and extracting parameters of the steering dynamics model through sensitivity analysis to obtain a steering sensitivity coefficient; Performing spectrum analysis on the vibration-related data in the fusion index system to obtain a vibration spectrum, and extracting features of the vibration spectrum through attenuation curve fitting to obtain a vibration attenuation rate; The body stiffness index, steering sensitivity coefficient and vibration attenuation rate are comprehensively evaluated to obtain a comprehensive performance index, and the comprehensive performance index is weighed through a multi-objective optimization algorithm to obtain a quantitative index system for the extreme scooter structure design.

4. The extreme scooter structure design management method according to claim 1, characterized in that: The time-space multi-scale characteristic analysis of the extreme scooter structural design quantitative index system is performed to obtain a time-space distribution characteristic map reflecting the dynamic response of the vehicle body structure under different road conditions, including: Decomposing the time series of the quantitative index system of the extreme scooter structure design to obtain time scale characteristics, and performing multi-resolution processing on the time scale characteristics through wavelet analysis to obtain a time multi-scale feature set; Performing spatial distribution analysis on the quantitative index system of the extreme scooter structural design to obtain spatial scale characteristics, and processing the spatial scale characteristics through multi-scale spatial autocorrelation analysis to obtain a spatial multi-scale feature set; Performing tensor fusion on the temporal multi-scale feature set and the spatial multi-scale feature set to obtain a spatiotemporal multi-scale feature tensor, and performing dimension reduction on the spatiotemporal multi-scale feature tensor through principal component analysis to obtain a spatiotemporal feature matrix after dimension reduction; Performing cluster analysis on the reduced-dimensional spatiotemporal feature matrix to obtain a road condition classification, and modeling the road condition classification using a support vector machine to obtain a road condition recognition model; Collecting dynamic response data of the vehicle body structure under different road conditions to obtain original dynamic response data, and classifying and processing the original dynamic response data through the road condition recognition model to obtain a classified dynamic response data set; The classified dynamic response data set is subjected to spatiotemporal interpolation to obtain a continuous spatiotemporal distribution function, and the continuous spatiotemporal distribution function is visualized through a contour drawing algorithm to obtain a spatiotemporal distribution characteristic map reflecting the dynamic response of the vehicle body structure under different road conditions.

5. The extreme scooter structure design management method according to claim 1, characterized in that: The high-order correlation analysis is performed on the spatiotemporal distribution characteristic map to obtain a multi-dimensional correlation intensity distribution matrix between the frame geometric parameters, the wheel set configuration and the shock absorption system, including: Extracting features from the spatiotemporal distribution feature map to obtain a high-dimensional feature vector, and reducing the dimension of the high-dimensional feature vector by principal component analysis to obtain a feature set after dimensionality reduction; Performing Pearson correlation analysis on the feature set after dimension reduction to obtain a preliminary correlation matrix, and correcting the preliminary correlation matrix through partial correlation analysis to obtain a corrected correlation matrix; Performing nonlinear correlation analysis on the corrected correlation matrix to obtain a nonlinear correlation index, and quantifying the nonlinear correlation index by a mutual information algorithm to obtain a high-order correlation index set; Performing cluster analysis on the high-order correlation index set to obtain correlation clusters, and performing structured processing on the correlation clusters through a hierarchical clustering algorithm to obtain a correlation hierarchy tree; Performing a pruning operation on the correlation hierarchy tree to obtain an optimized correlation structure, and performing a connectivity analysis on the optimized correlation structure using a graph theory algorithm to obtain a connection strength distribution; The connection strength distribution is normalized to obtain a standardized strength distribution, and the standardized strength distribution is reconstructed through matrix transformation to obtain a multi-dimensional correlation strength distribution matrix between frame geometric parameters, wheel set configuration and shock absorption system.

6. The extreme scooter structure design management method according to claim 1, characterized in that: The key factor identification and sensitivity analysis of the multi-dimensional correlation intensity distribution matrix is ​​performed to obtain an importance ranking table of influencing factors including the elastic modulus of the frame material, the angular momentum of the wheelset and the damping coefficient of the shock absorber, including: Performing eigenvalue decomposition on the multidimensional correlation intensity distribution matrix to obtain an eigenvector set, and ranking the eigenvector set by importance through principal component analysis to obtain a preliminary importance ranking of factors including the elastic modulus of the frame material, the angular momentum of the wheelset, and the damping coefficient of the shock absorber; Perform variance analysis on the importance ranking of the preliminary factors to obtain the variance contribution rate of each factor, and quantify the variance contribution rate through a global sensitivity analysis method to obtain global sensitivity indicators of the elastic modulus of the frame material, the angular momentum of the wheelset, and the damping coefficient of the shock absorber; Performing threshold screening on the global sensitivity index to obtain a set of key factors including the elastic modulus of the frame material, the angular momentum of the wheelset and the damping coefficient of the shock absorber, and performing a refined analysis on the set of key factors through a local sensitivity analysis method to obtain a local sensitivity index; Performing fuzzy comprehensive evaluation on the local sensitivity index to obtain comprehensive importance scores of the elastic modulus of the frame material, the angular momentum of the wheelset and the damping coefficient of the shock absorber, and weighing the comprehensive importance scores through a multi-criteria decision-making method to obtain a balanced importance index; The balanced importance indexes are normalized to obtain standardized importance indexes of the elastic modulus of the frame material, the angular momentum of the wheelset and the damping coefficient of the shock absorber, and the standardized importance indexes are sorted by a sorting algorithm to obtain an importance ranking table of influencing factors.

7. The extreme scooter structure design management method according to claim 1, characterized in that: The parametric structural design scheme optimization is performed according to the importance ranking table of the influencing factors to obtain a multi-objective structural design scheme combination and a performance evaluation index set, including: Perform parameter sensitivity analysis on the importance ranking table of influencing factors to obtain a parameter sensitivity matrix, and optimize the parameter sensitivity matrix through orthogonal experimental design to obtain a parameter optimization scheme; Constructing a multi-objective function for the parameter optimization scheme to obtain an objective function set, and solving the objective function set by a genetic algorithm to obtain a candidate solution set; Performing Pareto frontier analysis on the candidate solution set to obtain a non-inferior solution set, and assigning weights to the non-inferior solution set using a hierarchical analysis method to obtain a weighted non-inferior solution set; Performing cluster analysis on the weighted non-inferior solution set to obtain a solution cluster, and evaluating the solution cluster using a fuzzy comprehensive evaluation method to obtain an evaluation score matrix; Performing a multi-criteria decision analysis on the evaluation score matrix to obtain an optimal solution combination, and verifying the optimal solution combination through performance simulation to obtain a performance indicator set; The performance indicator set is comprehensively evaluated to obtain a comprehensive performance score, and the comprehensive performance score is iteratively optimized through a feedback optimization mechanism to obtain a multi-objective structural design scheme combination and a performance evaluation indicator set.

8. An extreme scooter structure design management system, used to implement the extreme scooter structure design management method as described in any one of claims 1 to 7, characterized in that: The extreme scooter structure design management system includes: A processing module is used to intelligently collect and preprocess multi-source heterogeneous data to obtain a multi-dimensional comprehensive data set including frame stress distribution data, wheel set dynamic response data and shock absorption system performance; A calculation module, used for performing multi-level index construction and nonlinear calculation on the multi-dimensional comprehensive data set to obtain a quantitative index system for the extreme scooter structure design including a body stiffness index, a steering sensitivity coefficient and a vibration attenuation rate; A quantification module, used to perform spatiotemporal multi-scale feature analysis on the extreme scooter structural design quantitative index system, and obtain a spatiotemporal distribution feature map reflecting the dynamic response of the vehicle body structure under different road conditions; An analysis module, used for performing a high-order correlation analysis on the spatiotemporal distribution characteristic map to obtain a multi-dimensional correlation intensity distribution matrix between the frame geometric parameters, the wheel set configuration and the shock absorption system; An identification module is used to perform key factor identification and sensitivity analysis on the multi-dimensional correlation intensity distribution matrix to obtain an importance ranking table of influencing factors including the elastic modulus of the frame material, the angular momentum of the wheelset and the damping coefficient of the shock absorber; The optimization module is used to optimize the parameterized structural design scheme according to the importance ranking table of the influencing factors to obtain a combination of multi-objective structural design schemes and a set of performance evaluation indicators.

9. An extreme scooter, characterized in that: include: A frame designed by the extreme scooter structural design management method according to any one of claims 1 to 7, wherein the frame has a structure optimized by a body stiffness index; A wheel set connected to the frame, wherein configuration parameters of the wheel set are optimized based on a steering sensitivity coefficient; A shock absorption system installed on the frame, wherein the damping coefficient of the shock absorber of the shock absorption system is optimized through vibration attenuation rate analysis; A control system arranged on the frame is used for real-time monitoring and adjusting the dynamic response of the vehicle body structure; a sensor network connected to the control system is used for collecting frame stress distribution, wheel group dynamic response and shock absorption system performance data; a human-computer interaction interface installed on the frame is used for displaying vehicle performance parameters and receiving user input.

Images