Motorcycle test data monitoring method and system

Abstract

The invention relates to the technical field of test data monitoring, in particular to a motorcycle test data monitoring method and system. The method comprises the steps of firstly obtaining test data, obtaining a first influence index through a first interaction model, obtaining a second influence index through a second interaction model, and obtaining a third influence index through a third interaction model; then obtaining a comprehensive state vector according to the real-time test data and the influence index, and generating a real-time adjustment suggestion; meanwhile, a curve performance index set and a dynamic safety threshold value are calculated, and the curve performance index set is monitored and early warning is carried out; and after a test period, performing test clustering according to the curve performance index set and the comprehensive state vector, and adjusting vehicle parameters according to a test clustering result. According to the invention, the test accuracy is improved by effectively monitoring the data.

Description

Technical Field

[0001] The invention relates to the technical field of test data monitoring, and in particular to a motorcycle test data monitoring method and system. Background Art

[0002] The feedback control method based on multi-modal sensor fusion realizes the synchronous acquisition and feature extraction of vehicle dynamic parameters, environmental physical quantities and control input signals. By constructing a dynamic coupling model of engine output torque-speed-temperature, the engine operating condition parameters are optimized in combination with the Kalman filter algorithm; in the braking system control, the PID feedforward compensation algorithm based on real-time detection of the road adhesion coefficient significantly improves the braking distance prediction accuracy. The fuzzy PID and neural network composite controller can dynamically adjust the inertia simulation parameters of the chassis dynamometer, and establish a vehicle response prediction model under extreme working conditions to achieve adaptive dynamic control of the test process.

[0003] However, existing technologies mainly focus on the data of the vehicle itself, ignoring the interaction between the operator, vehicle status and environmental conditions. Especially during the curve test, the operator's behavior, vehicle parameter design and environmental changes all affect the dynamic performance of the vehicle in the curve. The operator's control behavior will directly affect the performance of the vehicle in the curve, and driving stability is also related to environmental conditions. Therefore, it is necessary to effectively monitor and accurately analyze the interaction of these factors in real time to safely and accurately evaluate the performance of the vehicle.

[0004] Therefore, a motorcycle test data monitoring method and system are proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for monitoring motorcycle test data. First, the test data is acquired, and the first influencing index is obtained through the first interactive model, the second influencing index is obtained through the second interactive model, and the third influencing index is obtained through the third interactive model; then, a comprehensive state vector is obtained according to the real-time test data and the influencing index, and a real-time adjustment suggestion is generated; at the same time, a set of cornering performance indicators and a dynamic safety threshold are calculated, the set of cornering performance indicators is monitored and an early warning is issued; after a test cycle, test clustering is performed according to the set of cornering performance indicators and the comprehensive state vector, and vehicle parameters are adjusted according to the test clustering results. The present invention improves the accuracy of the test by effectively monitoring the data.

[0006] To achieve the above object, the present invention provides the following technical solutions: A motorcycle test data monitoring method, comprising: Acquiring real-time test data, including operator data, vehicle status data, and environmental status data; the operator data includes physical status data and operation control data; Process the operator data and the vehicle state data through a first interaction model to obtain a first impact index, process the vehicle state data and the environment state data through a second interaction model to obtain a second impact index, and process the operator data and the environment state data through a third interaction model to obtain a third impact index; Obtaining a comprehensive state vector according to the real-time test data, the first influencing indicator, the second influencing indicator, and the third influencing indicator, and generating a real-time adjustment suggestion according to the comprehensive state vector; Calculating a set of cornering performance indicators according to the real-time test data, and calculating a dynamic safety threshold, and monitoring the set of cornering performance indicators and issuing an early warning according to the dynamic safety threshold; After a test cycle, test clustering is performed based on the set of cornering performance indicators and the comprehensive state vector, and vehicle parameters are adjusted based on the test clustering results.

[0007] Furthermore, the first interaction model adopts a multi-layer perceptron structure, the input layer receives the operator data and the vehicle status data, the hidden layer constructs a feature map through a nonlinear activation function, and the output layer generates the first impact index through an activation function; The second interaction model uses a convolutional neural network and a long short-term memory network, wherein the input layer receives the vehicle state data and the environment state data, the convolution layer extracts spatial features, the LSTM layer captures time series features, the fully connected layer integrates the spatial features and the time series features, and the output layer generates the second impact indicator through an activation function; The third interaction model adopts a GRU network based on an attention mechanism, wherein the input layer receives the operator data and the environmental status data, the attention layer calculates the dynamic impact weight of environmental factors on the operator, and the GRU layer outputs the third impact indicator according to the dynamic impact weight.

[0008] Furthermore, the operator, vehicle and environment are defined as graph nodes, the corresponding real-time test data are used as feature vectors of the graph nodes, the first influencing indicator, the second influencing indicator and the third influencing indicator are used as edge weights, and a completely undirected graph is constructed; a graph attention network is adopted, and the node feature vectors are aggregated through a multi-head attention mechanism to obtain aggregated features, and the aggregated features are processed by global pooling to generate the comprehensive state vector.

[0009] Furthermore, an operator adjustment model is constructed based on the decision tree, and the comprehensive state vector is input into the operator adjustment model to identify the operator adjustment requirements; the operator adjustment requirements include steering control adjustment, speed control adjustment, posture adjustment, and no adjustment required; according to the operator adjustment requirements, the real-time adjustment suggestions are generated through the knowledge graph; the urgency is calculated based on the comprehensive state vector change rate , select the reminder method of the real-time adjustment suggestion according to the urgency; when When When When the time comes, use visual reminders; and They are the first emergency threshold and the second emergency threshold respectively.

[0010] Furthermore, the dynamic safety threshold calculation formula of the cornering performance index is: ; in, is the dynamic safety threshold, and are the basic safety threshold and standard deviation of the cornering performance index obtained based on historical test data, and are the current integrated state vector and the previous integrated state vector respectively, is the safety factor, is the weight coefficient of the comprehensive state vector, is the Euclidean norm.

[0011] Furthermore, a test cycle is defined, each test cycle includes K rounds of testing, and a set of cornering performance indicators and a comprehensive state vector sequence are obtained at the end of each round of testing; Constructing a space-time tensor according to a set of curve performance indicators and a comprehensive state vector sequence of a test cycle, and extracting correlation features by processing the space-time tensor through a three-dimensional convolution kernel; According to the correlation features, spectral clustering is used to divide the K rounds of tests into C test abnormality modes; the corresponding vehicle parameters under each test abnormality mode are analyzed by regression models to guide vehicle parameter adjustment.

[0012] A motorcycle test data monitoring system, comprising: A test data acquisition module, which acquires real-time test data, including operator data, vehicle status data and environmental status data; the operator data includes physical status data and operation control data; a data interaction analysis module, processing the operator data and the vehicle state data through a first interaction model to obtain a first impact index, processing the vehicle state data and the environment state data through a second interaction model to obtain a second impact index, and processing the operator data and the environment state data through a third interaction model to obtain a third impact index; A real-time adjustment suggestion module, which obtains a comprehensive state vector according to the real-time test data, the first influencing indicator, the second influencing indicator and the third influencing indicator, and generates a real-time adjustment suggestion according to the comprehensive state vector; A curve test analysis module, which calculates a curve performance index set according to the real-time test data, and calculates a dynamic safety threshold, and monitors the curve performance index set and issues an early warning according to the dynamic safety threshold; The vehicle parameter recommendation module, after a test cycle, performs test clustering based on the set of cornering performance indicators and the comprehensive state vector, and adjusts the vehicle parameters based on the test clustering results.

[0013] Compared with the prior art, the present invention has the following beneficial effects: 1. The dynamic interaction between operator-vehicle, vehicle-environment, and operator-environment is processed separately through three interaction models, and then the three are jointly analyzed as a whole. The first interaction model captures the nonlinear relationship between the operator and the vehicle; the second interaction model extracts the spatial-temporal association between the vehicle and the environment; the third interaction model dynamically quantifies the weight of the environment's impact on the operator, avoiding the limitations of a single model. The comprehensive state vector is further obtained based on real-time test data and impact indicators, providing a multi-dimensional basis for subsequent decision-making. The interactive analysis of data from three sources comprehensively improves the characterization ability of test data, realizes comprehensive monitoring of the interaction effects between people, vehicles, and the environment during the test, and provides more accurate input for real-time adjustment suggestions and safety monitoring.

[0014] 2. At the real-time level, the operator adjustment model based on decision trees and knowledge graphs is combined with the short-term rate of change of the comprehensive state vector to calculate the degree of urgency and dynamically generate multimodal reminders to ensure that operators respond to risks in a timely manner. At the periodic level, the spatiotemporal correlation features of multiple rounds of tests are extracted through spatiotemporal tensors, and three-dimensional convolution and spectral clustering are used to identify test abnormal patterns, associate vehicle parameter defects and generate adjustment suggestions. Real-time intervention solves sudden risks, and periodic optimization helps to correct vehicle design shortcomings. The collaboration between the two not only ensures test safety, but also improves test effectiveness, achieving the dual goals of dynamic risk response and continuous vehicle optimization.

[0015] 3. Define the operator, vehicle, and environment as graph nodes, use real-time data as node features, and three influencing indicators as edge weights to construct a completely undirected graph. Aggregate node features through the multi-head attention mechanism of the graph attention network, and then generate a comprehensive state vector through global pooling, which can capture implicit associations while retaining local interaction details and global state features. This makes the comprehensive state vector have both high-dimensional representation capabilities and robustness, providing a unified high-quality input for real-time decision-making and cycle optimization. The application of the graph attention network realizes the efficient fusion of multi-source data, providing a more comprehensive state representation for real-time adjustment suggestions and long-term parameter optimization during the test process. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic flow chart of a motorcycle test data monitoring method of the present invention; Figure 2 A schematic diagram of the structure of a motorcycle test data monitoring system of the present invention; Figure 3 The figure is a schematic diagram of the data flow of the comprehensive state vector acquisition of the present invention. DETAILED DESCRIPTION

[0017] 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 are within the scope of protection of the present invention.

[0018] See also Figures 1 to 3 The present invention provides a motorcycle test data monitoring method and system, and the technical solution is as follows: Embodiment 1:

[0019] In order to evaluate and optimize the performance of motorcycles when driving on curves, Figure 1 As shown, a motorcycle test data monitoring method is applied, comprising: Acquiring real-time test data, including operator data, vehicle status data, and environmental status data; the operator data includes physical status data and operation control data; Process the operator data and the vehicle state data through a first interaction model to obtain a first impact index, process the vehicle state data and the environment state data through a second interaction model to obtain a second impact index, and process the operator data and the environment state data through a third interaction model to obtain a third impact index; Obtaining a comprehensive state vector according to the real-time test data, the first influencing indicator, the second influencing indicator, and the third influencing indicator, and generating a real-time adjustment suggestion according to the comprehensive state vector; Calculating a set of cornering performance indicators according to the real-time test data, and calculating a dynamic safety threshold, and monitoring the set of cornering performance indicators and issuing an early warning according to the dynamic safety threshold; After a test cycle, test clustering is performed based on the set of curve performance indicators and the comprehensive state vector, and vehicle parameters are adjusted based on the test clustering results. Table 1 shows the collection method of some original test data. The original test data is synchronized with multi-frequency data through timestamp alignment and interpolation algorithms. For high-frequency data, a sliding window is used to downsample to the lowest common frequency to ensure timing consistency; for low-frequency data, linear interpolation is used to fill in the intermediate time points. After the data stream is denoised and standardized, a real-time test data sequence is generated.

[0020] Table 1 Original test data collection

[0021] The interactive effects between the operator, vehicle, and environmental data are accurately quantified through three interactive models, and the comprehensive state vector is generated in combination with the graph attention network, thus achieving comprehensive monitoring of the test process. Adjustment suggestions are generated in real time based on the comprehensive state vector, and different reminder methods are selected according to the degree of urgency to ensure test safety. At the same time, a dynamic safety threshold mechanism is introduced to enable safety monitoring to adapt to complex and changing test environments and identify potential risks in advance. In addition, through cluster analysis of the test cycle, the system can discover regular problems in the test and provide a scientific basis for vehicle parameter optimization.

[0022] Furthermore, the first interaction model adopts a multi-layer perceptron structure, the input layer receives the operator data and the vehicle status data, the hidden layer constructs a feature map through a nonlinear activation function, and the output layer generates the first impact index through an activation function; The second interaction model uses a convolutional neural network and a long short-term memory network, wherein the input layer receives the vehicle state data and the environment state data, the convolution layer extracts spatial features, the LSTM layer captures time series features, the fully connected layer integrates the spatial features and the time series features, and the output layer generates the second impact indicator through an activation function; The third interaction model adopts a GRU network based on an attention mechanism, wherein the input layer receives the operator data and the environmental status data, the attention layer calculates the dynamic impact weight of environmental factors on the operator, and the GRU layer outputs the third impact indicator according to the dynamic impact weight.

[0023] Through multi-layer perceptrons, convolutional neural networks combined with long short-term memory networks and GRU networks based on attention mechanisms, the interactive relationships of different dimensions are processed separately, which can accurately capture the complex nonlinear relationships between different types of data, ensure the targeted capture of key influencing factors, and fully understand the interactive effects among the operator, vehicle and environment, thereby improving the accuracy and reliability of the interactive impact indicators.

[0024] Furthermore, the operator, vehicle and environment are defined as graph nodes, the corresponding real-time test data are used as feature vectors of the graph nodes, the first influencing indicator, the second influencing indicator and the third influencing indicator are used as edge weights, and a completely undirected graph is constructed; a graph attention network is adopted, and the node feature vectors are aggregated through a multi-head attention mechanism to obtain aggregated features, and the aggregated features are processed by global pooling to generate the comprehensive state vector.

[0025] The graph structure and graph attention network are introduced to process the comprehensive state. The operator, vehicle and environment are defined as graph nodes, and the three influencing indicators are used as edge weights to construct a completely undirected graph. The node feature vectors are aggregated through a multi-head attention mechanism and globally pooled to generate a comprehensive state vector. The graph-based representation method can capture the complex relationship between various elements in the motorcycle test process, provide a more comprehensive and accurate state representation, and provide a solid foundation for the subsequent generation of adjustment suggestions.

[0026] Furthermore, an operator adjustment model is constructed based on the decision tree, and the comprehensive state vector is input into the operator adjustment model to identify the operator adjustment requirements; the operator adjustment requirements include steering control adjustment, speed control adjustment, posture adjustment, and no adjustment required; according to the operator adjustment requirements, the real-time adjustment suggestions are generated through the knowledge graph; the urgency is calculated based on the comprehensive state vector change rate , select the reminder method of the real-time adjustment suggestion according to the urgency; when When When When the time comes, use visual reminders; and They are the first emergency threshold and the second emergency threshold respectively.

[0027] Table 2 shows example data of real-time adjustment recommendations. The operator adjustment model is constructed using the random forest algorithm, and the training data comes from historical test data and best practice experience annotated by professional drivers.

[0028] Table 2 Real-time adjustment suggestion example data

[0029] The generation of adjustment suggestions based on decision trees and knowledge graphs improves safety during the testing process. Combined with urgency graded reminders, it can provide feedback of appropriate intensity, avoiding excessive intervention in low-risk situations and reminding operators in a timely and effective manner in high-risk situations, ensuring that operators receive the most appropriate feedback at different risk levels and reducing misjudgments and response delays.

[0030] Furthermore, the dynamic safety threshold calculation formula of the cornering performance index is: ; in, is the dynamic safety threshold, and are the basic safety threshold and standard deviation of the cornering performance index obtained based on historical test data, and are the current integrated state vector and the previous integrated state vector respectively, is the safety factor, is the weight coefficient of the comprehensive state vector, is the Euclidean norm.

[0031] Furthermore, the curve performance index includes a curve deceleration control index , Curve stability index , Curve acceleration stability index and grip utilization index ; The calculation formula is: ; ; ; ; in, , and They are actual deceleration, ideal deceleration and maximum safe deceleration, is the minimum function; and are the standard deviation of the inclination angle in the curve and the maximum safe inclination angle; and are the acceleration standard deviation and the maximum safe acceleration respectively; , , and They are longitudinal acceleration, lateral acceleration, road friction coefficient and gravity acceleration.

[0032] In this embodiment, a comprehensive state vector is obtained by setting a time window. Every other time window, the first influencing index, the second influencing index and the third influencing index are obtained according to the real-time test data in the accumulated time window. The comprehensive state vector is obtained through the graph attention network in combination with the current real-time test data. The cornering deceleration control index, the cornering stability index and the cornering acceleration smoothness index in the cornering performance index are the performance indicators corresponding to the cornering entrance stage, the cornering stage and the cornering exit stage respectively. The cornering test site is divided into the cornering entrance area, the cornering area and the cornering exit area. The corresponding performance indicators are calculated by combining the area where the motorcycle is sensed by the sensor, and the grip utilization index needs to be calculated in all areas. Therefore, when monitoring the cornering performance index, the dynamic safety threshold corresponding to each performance indicator is used to monitor the performance index and the grip utilization index of the corresponding area.

[0033] The basic security threshold is combined with the change of the comprehensive state vector to achieve adaptive adjustment of the threshold. The dynamic threshold mechanism takes into account the statistical characteristics of historical data and the real-time changes of the current test environment, making security monitoring more flexible and accurate, solving the lag problem of fixed thresholds in complex scenarios, and improving the effectiveness of security monitoring.

[0034] Furthermore, a test cycle is defined, each test cycle includes K rounds of testing, and a set of cornering performance indicators and a comprehensive state vector sequence are obtained at the end of each round of testing; Constructing a space-time tensor according to a set of curve performance indicators and a comprehensive state vector sequence of a test cycle, and extracting correlation features by processing the space-time tensor through a three-dimensional convolution kernel; According to the correlation features, spectral clustering is used to divide the K rounds of tests into C test abnormality modes; the corresponding vehicle parameters under each test abnormality mode are analyzed by regression models to guide vehicle parameter adjustment.

[0035] Specifically, each test cycle includes 10 rounds of tests. After each round of tests, the set of cornering performance indicators and the comprehensive state vector sequence are collected and fused through outer product operations to construct a spatiotemporal tensor. Table 3 shows the test clustering results obtained in multiple test cycles, which are used to guide vehicle parameter adjustment.

[0036] Table 3 Test clustering results

[0037] The cluster analysis method based on the test cycle provides a basis for adjusting vehicle parameters by constructing spatiotemporal tensors, extracting correlation features and identifying test abnormal patterns through spectral clustering. The periodic analysis method can discover potential regularities and systematic problems in the test process. Through comprehensive analysis of multiple rounds of test data, the system can identify key parameters that affect vehicle performance under specific conditions and provide a more targeted basis for adjusting vehicle parameters. Embodiment 2:

[0038] This embodiment provides a motorcycle test data monitoring system. Figure 2 , including a test data acquisition module, a data interaction analysis module, a real-time adjustment suggestion module and a vehicle parameter suggestion module, which are used to implement the following steps: Acquiring real-time test data, including operator data, vehicle status data, and environmental status data; the operator data includes physical status data and operation control data; like Figure 3 As shown, the operator data and the vehicle state data are processed by a first interaction model to obtain a first impact index, the vehicle state data and the environment state data are processed by a second interaction model to obtain a second impact index, and the operator data and the environment state data are processed by a third interaction model to obtain a third impact index; like Figure 3 As shown, a comprehensive state vector is obtained according to the real-time test data, the first influencing indicator, the second influencing indicator and the third influencing indicator, and a real-time adjustment suggestion is generated according to the comprehensive state vector; A curve test analysis module, which calculates a curve performance index set according to the real-time test data, and calculates a dynamic safety threshold, and monitors the curve performance index set and issues an early warning according to the dynamic safety threshold; After a test cycle, test clustering is performed based on the set of cornering performance indicators and the comprehensive state vector, and vehicle parameters are adjusted based on the test clustering results.

[0039] Furthermore, the first interaction model adopts a multi-layer perceptron structure, the input layer receives the operator data and the vehicle status data, the hidden layer constructs a feature map through a nonlinear activation function, and the output layer generates the first impact index through an activation function; The second interaction model uses a convolutional neural network and a long short-term memory network, wherein the input layer receives the vehicle state data and the environment state data, the convolution layer extracts spatial features, the LSTM layer captures time series features, the fully connected layer integrates the spatial features and the time series features, and the output layer generates the second impact indicator through an activation function; The third interaction model adopts a GRU network based on an attention mechanism, wherein the input layer receives the operator data and the environmental status data, the attention layer calculates the dynamic impact weight of environmental factors on the operator, and the GRU layer outputs the third impact indicator according to the dynamic impact weight.

[0040] Furthermore, the operator, vehicle and environment are defined as graph nodes, the corresponding real-time test data are used as feature vectors of the graph nodes, the first influencing indicator, the second influencing indicator and the third influencing indicator are used as edge weights, and a completely undirected graph is constructed; a graph attention network is adopted, and the node feature vectors are aggregated through a multi-head attention mechanism to obtain aggregated features, and the aggregated features are processed by global pooling to generate the comprehensive state vector.

[0041] Furthermore, an operator adjustment model is constructed based on the decision tree, and the comprehensive state vector is input into the operator adjustment model to identify the operator adjustment requirements; the operator adjustment requirements include steering control adjustment, speed control adjustment, posture adjustment, and no adjustment required; according to the operator adjustment requirements, the real-time adjustment suggestions are generated through the knowledge graph; the urgency is calculated based on the comprehensive state vector change rate , select the reminder method of the real-time adjustment suggestion according to the urgency; when When When When the time comes, use visual reminders; and They are the first emergency threshold and the second emergency threshold respectively.

[0042] Furthermore, the dynamic safety threshold calculation formula of the cornering performance index is: ; in, is the dynamic safety threshold, and are the basic safety threshold and standard deviation of the cornering performance index obtained based on historical test data, and are the current integrated state vector and the previous integrated state vector respectively, is the safety factor, is the weight coefficient of the comprehensive state vector, is the Euclidean norm.

[0043] Furthermore, a test cycle is defined, each test cycle includes K rounds of testing, and a set of cornering performance indicators and a comprehensive state vector sequence are obtained at the end of each round of testing; Constructing a space-time tensor according to a set of curve performance indicators and a comprehensive state vector sequence of a test cycle, and extracting correlation features by processing the space-time tensor through a three-dimensional convolution kernel; According to the correlation features, spectral clustering is used to divide the K rounds of tests into C test abnormality modes; the corresponding vehicle parameters under each test abnormality mode are analyzed by regression models to guide vehicle parameter adjustment.

[0044] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A motorcycle test data monitoring method, characterized in that: include: Acquiring real-time test data, including operator data, vehicle status data, and environmental status data; the operator data includes physical status data and operation control data; Process the operator data and the vehicle state data through a first interaction model to obtain a first impact index, process the vehicle state data and the environment state data through a second interaction model to obtain a second impact index, and process the operator data and the environment state data through a third interaction model to obtain a third impact index; Obtaining a comprehensive state vector according to the real-time test data, the first influencing indicator, the second influencing indicator, and the third influencing indicator, and generating a real-time adjustment suggestion according to the comprehensive state vector; Calculating a set of cornering performance indicators according to the real-time test data, and calculating a dynamic safety threshold, and monitoring the set of cornering performance indicators and issuing an early warning according to the dynamic safety threshold; After a test cycle, test clustering is performed based on the set of cornering performance indicators and the comprehensive state vector, and vehicle parameters are adjusted based on the test clustering results.

2. A motorcycle test data monitoring method according to claim 1, characterized in that: The first interaction model adopts a multi-layer perceptron structure, the input layer receives the operator data and the vehicle status data, the hidden layer constructs a feature map through a nonlinear activation function, and the output layer generates the first impact index through an activation function; The second interaction model uses a convolutional neural network and a long short-term memory network, wherein the input layer receives the vehicle state data and the environment state data, the convolution layer extracts spatial features, the LSTM layer captures time series features, the fully connected layer integrates the spatial features and the time series features, and the output layer generates the second impact indicator through an activation function; The third interaction model adopts a GRU network based on an attention mechanism, wherein the input layer receives the operator data and the environmental status data, the attention layer calculates the dynamic impact weight of environmental factors on the operator, and the GRU layer outputs the third impact indicator according to the dynamic impact weight.

3. A motorcycle test data monitoring method according to claim 1, characterized in that: The operator, vehicle and environment are defined as graph nodes, the corresponding real-time test data are used as the feature vectors of the graph nodes, the first influencing indicator, the second influencing indicator and the third influencing indicator are used as edge weights, and a completely undirected graph is constructed; a graph attention network is adopted, and the node feature vectors are aggregated through a multi-head attention mechanism to obtain aggregated features, and the aggregated features are processed by global pooling to generate the comprehensive state vector.

4. A motorcycle test data monitoring method according to claim 1, characterized in that: An operator adjustment model is constructed based on a decision tree, and the comprehensive state vector is input into the operator adjustment model to identify the operator adjustment requirements; the operator adjustment requirements include steering control adjustment, speed control adjustment, posture adjustment, and no adjustment required; and the real-time adjustment suggestions are generated through a knowledge graph according to the operator adjustment requirements; Calculate the urgency based on the comprehensive state vector change rate , select the reminder method of the real-time adjustment suggestion according to the urgency; when When When When the time comes, use visual reminders; and They are the first emergency threshold and the second emergency threshold respectively.

5. A motorcycle test data monitoring method according to claim 1, characterized in that: The calculation formula of the dynamic safety threshold of the cornering performance index is: ； in, is the dynamic safety threshold, and are the basic safety threshold and standard deviation of the cornering performance index obtained based on historical test data, and are the current integrated state vector and the previous integrated state vector respectively, is the safety factor, is the weight coefficient of the comprehensive state vector, is the Euclidean norm.

6. A motorcycle test data monitoring method according to claim 1, characterized in that: Define a test cycle. Each test cycle includes K rounds of testing. After each round of testing, a set of cornering performance indicators and a comprehensive state vector sequence are obtained. Constructing a space-time tensor according to a set of curve performance indicators and a comprehensive state vector sequence of a test cycle, and extracting correlation features by processing the space-time tensor through a three-dimensional convolution kernel; According to the correlation features, spectral clustering is used to divide the K rounds of tests into C test abnormality modes; the corresponding vehicle parameters under each test abnormality mode are analyzed by regression models to guide vehicle parameter adjustment.

7. A motorcycle test data monitoring system, characterized in that: include: A test data acquisition module, which acquires real-time test data, including operator data, vehicle status data and environmental status data; the operator data includes physical status data and operation control data; a data interaction analysis module, processing the operator data and the vehicle state data through a first interaction model to obtain a first impact index, processing the vehicle state data and the environment state data through a second interaction model to obtain a second impact index, and processing the operator data and the environment state data through a third interaction model to obtain a third impact index; A real-time adjustment suggestion module, which obtains a comprehensive state vector according to the real-time test data, the first influencing indicator, the second influencing indicator and the third influencing indicator, and generates a real-time adjustment suggestion according to the comprehensive state vector; A curve test analysis module, which calculates a curve performance index set according to the real-time test data, and calculates a dynamic safety threshold, and monitors the curve performance index set and issues an early warning according to the dynamic safety threshold; The vehicle parameter recommendation module, after a test cycle, performs test clustering based on the set of cornering performance indicators and the comprehensive state vector, and adjusts the vehicle parameters based on the test clustering results.

Images