Semantic analysis-based inspection and detection service method

Abstract

The invention relates to the technical field of inspection and detection, in particular to an inspection and detection service method based on semantic analysis. The method comprises the following steps that vehicle log data and configuration parameters are obtained, the semantic analysis technology is combined, the vehicle driving condition is analyzed, and a corresponding simulation model is constructed; comprising the following steps of: counting and estimating the running mileage of the vehicle and the abrasion and fracture probability of a brake disc, and analyzing the tire condition of the vehicle and brake performance attenuation; by evaluating the sideslip probability and stability of the vehicle, vehicle configuration optimization is implemented, and the safety performance of the vehicle under various driving conditions is ensured; the method covers aerodynamic characteristic analysis and vehicle body structure evaluation so as to realize more comprehensive performance detection. According to the method, the test and detection service method based on semantic analysis is optimized, so that the test and detection service is more efficient and accurate.

Description

Technical Field

[0001] The present invention relates to the field of inspection and testing technology, and in particular to an inspection and testing service method based on semantic analysis. Background Art

[0002] Existing detection methods mainly rely on industry specifications, but in actual operation, there are problems such as uneven detection technology levels and aging equipment. These factors lead to missed detection of safety hazards, thus affecting driving safety. Therefore, the development of more scientific and systematic inspection and testing service methods can effectively improve the safety and reliability of vehicles and ensure traffic safety. The rapid development of modern vehicle technology also requires continuous updating of detection methods to adapt to the safety performance requirements of new vehicles. The emergence of electric vehicles and intelligent driving systems has brought challenges to traditional detection methods. Therefore, research on inspection and testing methods based on advanced technologies, such as data analysis and artificial intelligence, will help improve detection efficiency and accuracy. However, traditional vehicle inspection and testing service methods have problems with inaccurate prediction of vehicle safety performance attenuation and inaccurate vehicle performance inspection and testing. Summary of the invention

[0003] Based on this, it is necessary to provide an inspection and testing service method based on semantic analysis to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a semantic analysis-based inspection and testing service method includes the following steps:

[0005] Step S1: Acquire vehicle log data and vehicle configuration parameter data; perform vehicle driving condition analysis on the vehicle log data based on semantic analysis to obtain vehicle driving condition data; construct a vehicle simulation model based on the vehicle driving condition data and vehicle configuration parameter data to obtain a vehicle simulation model;

[0006] Step S2: performing vehicle mileage statistics according to the vehicle driving condition data to obtain vehicle mileage data; performing vehicle brake disc wear estimation on the vehicle simulation model according to the vehicle driving distance data to obtain vehicle brake disc wear data; performing brake disc rupture probability calculation according to the vehicle brake disc wear data to obtain brake disc rupture probability data;

[0007] Step S3: analyzing the vehicle tire condition according to the vehicle driving condition data to obtain the vehicle tire condition data; performing a brake performance attenuation test on the vehicle simulation model according to the vehicle tire condition data, the brake disc rupture probability data, and the brake disc wear data to obtain the vehicle brake performance attenuation data;

[0008] Step S4: Estimating the sideslip probability based on the vehicle brake performance attenuation data and the vehicle tire condition data to obtain vehicle sideslip probability data; optimizing the vehicle configuration of the vehicle simulation model based on the vehicle sideslip probability data and the vehicle brake performance attenuation data to obtain vehicle configuration optimization data.

[0009] The present invention can establish a comprehensive vehicle status file by acquiring vehicle log data and configuration parameter data, providing a basis for subsequent analysis. This step ensures the accuracy and integrity of the data, especially in the analysis of vehicle driving conditions, it can effectively identify driving behavior and environmental influencing factors, thereby providing a reliable basis for the subsequent construction of simulation models. Through semantic analysis, valuable information can be extracted to understand the performance of the vehicle under different conditions, which is helpful to evaluate its safety and performance. In mileage statistics, accurate data can reveal the frequency of vehicle use and its degree of wear, which is crucial for the estimation of brake disc wear. Accurately grasping the driving distance helps to predict the use of the brake system and identify potential risks in advance. Combined with the wear data of the brake disc, the probability of rupture is calculated, which can quantify the safety hazards of the brake system, provide data support for timely maintenance and replacement, reduce the risk of accidents, and improve the safety of the vehicle. The subsequent tire condition analysis provides important information for the overall evaluation of braking performance. The synergy between tires and the brake system directly affects the handling and safety of the vehicle. Through comprehensive analysis of tire conditions and brake performance, key factors affecting the braking effect can be identified, so as to take targeted optimization measures to ensure the stability and safety of the vehicle under various conditions. Further prediction of the probability of sideslip provides an important basis for understanding the performance of the vehicle under extreme conditions. By analyzing the risk of sideslip, drivers can take preventive measures to reduce the possibility of loss of control. Configuration optimization combined with brake performance attenuation data can improve the handling and stability of the vehicle, laying the foundation for a safer driving environment. The integrated analysis of this series of steps makes the evaluation and optimization of vehicle safety performance more scientific. Therefore, the present invention is an optimization of the traditional inspection and testing service method based on semantic analysis, which solves the problems of inaccurate prediction of vehicle safety performance attenuation and inaccurate vehicle performance inspection and testing in the traditional inspection and testing service method based on semantic analysis, and improves the accuracy of vehicle safety performance attenuation prediction and vehicle performance inspection and testing.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Acquire vehicle log data and vehicle configuration parameter data;

[0012] Step S12: analyzing the vehicle driving condition of the vehicle log data based on semantic analysis to obtain vehicle driving condition data;

[0013] Step S13: performing aerodynamic characteristic analysis according to the vehicle configuration parameter data to obtain vehicle aerodynamic characteristic data;

[0014] Step S14: constructing a vehicle simulation model according to the vehicle driving condition data, the vehicle aerodynamic characteristic data and the vehicle parameters to obtain a vehicle simulation model.

[0015] The acquisition of vehicle log data and configuration parameters by the present invention is the basis of the entire analysis process, and can provide accurate and comprehensive information for subsequent evaluations. The integration of these data makes the subsequent analysis no longer rely on subjective judgment, but is supported by objective data, thereby improving the scientificity and credibility of the analysis. The driving condition evaluation of vehicle log data based on semantic analysis makes the understanding of the vehicle's operating status more in-depth. By mining and analyzing the data generated during driving, the abnormal behavior and potential risks of the vehicle can be accurately identified. This method helps to find problems in time, take preventive measures, and reduce the possibility of accidents. Aerodynamic characteristic analysis further supplements the evaluation of vehicle performance. By analyzing the shape, material and configuration of the vehicle, the air resistance and stability of the vehicle during driving can be evaluated. This not only helps to improve the vehicle's handling performance, but also combines the driving condition data, aerodynamic characteristic data and vehicle parameters to build a simulation model that can accurately simulate the behavior of the vehicle in different driving environments. This model provides engineers with a powerful tool to facilitate optimization in the design stage to ensure that the vehicle has excellent safety and performance in actual use. The comprehensive application of this series of steps will help promote the advancement of vehicle safety technology and the construction of intelligent transportation systems. Driving condition assessment based on semantic analysis helps to timely identify abnormalities in vehicle operation and reduce accident risks. At the same time, aerodynamic characteristic analysis can optimize vehicle design and improve fuel efficiency and driving stability.

[0016] Preferably, step S13 comprises the following steps:

[0017] Step S131: extracting the vehicle body structure according to the vehicle parameter data to obtain vehicle body structure data;

[0018] Step S132: performing a vehicle front face shape analysis and a vehicle body shape analysis according to the vehicle body structure data to obtain vehicle front face shape data and vehicle body shape data;

[0019] Step S133: simulating the flow distribution of the vehicle's running airflow according to the vehicle's front face shape data and the vehicle's body shape data to obtain the flow distribution data of the vehicle's running airflow;

[0020] Step S134: Calculating the vehicle lift coefficient using the vehicle running airflow fluid distribution data to obtain vehicle lift coefficient data;

[0021] Step S135: Perform an aerodynamic characteristic analysis based on the vehicle lift coefficient data and the vehicle running airflow fluid distribution data to obtain the vehicle aerodynamic characteristic data.

[0022] The present invention can lay the foundation for the aerodynamic performance analysis of the vehicle by extracting the vehicle body structure according to the vehicle parameter data. This step ensures a comprehensive understanding of the vehicle shape and structure, identifies the key design factors that affect the airflow, and thus provides the necessary geometric data for the subsequent aerodynamic analysis. This precise structural extraction not only helps to improve the design efficiency of the vehicle, but also identifies potential air resistance problems at an early stage. The front face shape and body shape analysis based on the body structure data can reveal the impact of different designs on the airflow. The front face shape is crucial in aerodynamics and directly affects the frontal area and air flow pattern of the vehicle. By deeply analyzing these shape features, the vehicle shape can be optimized, air resistance can be reduced, and fuel efficiency and driving stability can be improved. At the same time, the analysis of the body shape also provides a basis for identifying design defects that cause airflow separation, thereby improving the overall aerodynamic performance. The subsequent fluid distribution simulation can simulate the airflow characteristics of the vehicle when it is driving, providing empirical support for the aerodynamic design of the vehicle. Through the accurate simulation of the airflow fluid distribution, the aerodynamic characteristics of the vehicle during driving can be evaluated, and the force and distribution of the airflow on the body can be identified. The lift coefficient calculation based on the airflow and fluid distribution data can quantify the lift of the vehicle during driving. This indicator is crucial to the stability and handling of the vehicle, especially when driving at high speeds, where lift control can effectively prevent the risk of loss of control or rollover. By calculating the lift coefficient and performing aerodynamic characteristic analysis based on the lift coefficient data and airflow and fluid distribution data, the aerodynamic performance of the vehicle can be fully evaluated. Through this analysis, the key aerodynamic parameters that affect the vehicle's handling and stability can be identified, thus providing important directions for subsequent optimization designs.

[0023] Preferably, step S14 comprises the following steps:

[0024] Step S141: Calculating the average vehicle load and the average vehicle speed according to the vehicle driving condition data to obtain the average vehicle load data and the average vehicle speed data;

[0025] Step S142: extracting the vehicle tire size according to the vehicle configuration parameter data to obtain the vehicle tire size data;

[0026] Step S143: performing a vehicle side wind sensitivity analysis based on the vehicle tire size data, the vehicle average load data and the vehicle aerodynamic characteristic data to obtain vehicle driving side wind sensitivity data;

[0027] Step S144: performing vehicle driving stability analysis according to the vehicle driving side wind sensitivity data and the vehicle driving average speed data to obtain vehicle driving stability data;

[0028] Step S145: constructing a vehicle simulation model according to the vehicle driving stability data, the vehicle configuration parameter data and the vehicle aerodynamic characteristic data to obtain a vehicle simulation model.

[0029] The present invention calculates the average load and the average speed of the vehicle through the vehicle driving condition data, which can provide important reference information for analyzing the dynamic performance of the vehicle. These data not only help to identify the performance of the vehicle under different loads and speeds, but also lay the foundation for optimizing vehicle design and improving driving safety. Obtaining tire size data is an important link for further analysis, because tires are the key factors affecting the vehicle's grip and handling stability, and accurate tire size information can ensure a comprehensive evaluation of vehicle performance. Combining tire size, average load and aerodynamic characteristics to conduct crosswind sensitivity analysis helps to understand the performance of the vehicle under crosswind conditions and identify potential safety hazards. This analysis can provide suggestions for vehicle design and help engineers take measures in the design stage to enhance the vehicle's ability to resist crosswinds and reduce driving risks. Stability analysis based on crosswind sensitivity data and average driving speed can evaluate the stability of the vehicle under various driving conditions, ensure controllability under different speeds and external environments, and thus improve driving experience and safety. Finally, the vehicle simulation model constructed using driving stability data, configuration parameters and aerodynamic characteristics not only provides an in-depth understanding of the vehicle's dynamic performance, but also can perform simulation tests of multiple scenarios in the design stage to optimize the vehicle structure and configuration.

[0030] Preferably, step S2 comprises the following steps:

[0031] Step S21: Counting the vehicle mileage according to the vehicle driving condition data to obtain the vehicle mileage data;

[0032] Step S22: performing driving habit analysis on the vehicle driving condition data based on semantic analysis to obtain vehicle driving habit data;

[0033] Step S23: Predicting the wear of the vehicle brake disc by using the vehicle simulation model according to the vehicle travel distance data and the vehicle driving habit data, and obtaining the wear data of the vehicle brake disc;

[0034] Step S24: Calculate the probability of brake disc rupture according to the vehicle brake disc wear data to obtain brake disc rupture probability data.

[0035] The present invention can obtain important data on the actual use of the vehicle by counting the vehicle mileage, which provides a basis for subsequent maintenance and safety assessment. Accurate records of mileage can help identify performance changes of the vehicle at different stages and ensure timely maintenance and repair. In addition, the driving habit analysis of the vehicle driving condition based on semantic analysis can deeply understand the driver's behavior pattern, such as sudden braking or sudden acceleration, etc., which is crucial for evaluating the impact of driving habits on vehicle performance. The wear estimation of the brake disc combined with the driving distance and driving habit data can identify potential safety hazards in advance. This process ensures the foresight of maintenance work, so that necessary measures can be taken before problems occur in the brake system to avoid accidents caused by brake failure. Finally, the probability of rupture is calculated based on the wear data of the brake disc, which can provide a quantitative indicator for the reliability of the brake system. This calculation provides important safety warnings for car owners and maintenance personnel, so that necessary replacement or repair can be carried out before the problem becomes serious. The comprehensive application of this series of steps not only enhances the understanding of the performance of the vehicle brake system, but also improves driving safety.

[0036] Preferably, step S23 includes the following steps:

[0037] Step S231: obtaining brake disc material data and brake caliper material data;

[0038] Step S232: Calculating the brake friction coefficient according to the brake disc material data and the brake caliper material data to obtain the vehicle brake friction coefficient data;

[0039] Step S233: Counting excessive sudden braking according to the vehicle driving habit data to obtain vehicle excessive sudden braking data;

[0040] Step S234: Calculating the friction heat according to the vehicle over-sudden braking data and the vehicle brake friction coefficient data to obtain the vehicle brake friction heat data;

[0041] Step S235: The vehicle brake disc wear is estimated on the vehicle simulation model according to the vehicle travel distance data and the vehicle brake friction heat data to obtain the vehicle brake disc wear data.

[0042] By obtaining the material data of the brake disc and the brake caliper, the present invention can deeply understand the composition of the brake system and provide a key basis for subsequent performance analysis. These material properties have a direct impact on the wear resistance, thermal stability and overall safety of the brake system. Based on these data, the calculation of the brake friction coefficient can quantify the braking effect and provide data support for the evaluation of brake performance under different driving conditions. Accurate friction coefficient data helps to ensure that the brake system can work effectively under various conditions and improve the overall safety of the vehicle. By counting the excessive braking behavior in driving habits, potential driving risks can be identified. This analysis not only helps to improve the driver's safety awareness, but also provides guidance for subsequent vehicle maintenance and reduces the wear of the brake system due to improper use. At the same time, by combining the excessive braking data with the friction coefficient, the friction heat is calculated, and the heat borne by the brake system in actual use can be evaluated. This evaluation is crucial to identifying the performance of the brake system under high load conditions, and can provide early warning of performance degradation or failure. Finally, the driving distance data is combined with the brake friction heat for the estimation of brake disc wear, which not only improves the foresight of the brake system maintenance, but also ensures the reliability of the brake performance. The combined use of this series of steps enhances the overall understanding of brake system performance.

[0043] Preferably, step S24 includes the following steps:

[0044] Step S241: calculating the wear thickness of the brake disc according to the wear data of the vehicle brake disc to obtain the wear thickness data of the brake disc;

[0045] Step S242: performing brake disc deformation analysis according to the vehicle brake disc wear thickness data to obtain brake disc deformation data;

[0046] Step S243: performing brake disc degradation analysis according to the brake disc deformation data and the vehicle brake disc wear thickness data to obtain vehicle brake disc degradation data;

[0047] Step S244: Calculate the probability of brake disc rupture according to the vehicle brake disc degradation data and the brake disc deformation data to obtain brake disc rupture probability data.

[0048] The present invention calculates the wear thickness of the disc through the wear data of the vehicle brake disc, and can provide a detailed evaluation of the current state of the brake disc. This process is the key to ensuring the normal operation of the brake system, and timely understanding of the wear degree of the disc can provide an accurate basis for maintenance. Excessively worn brake discs lead to reduced braking performance and even affect driving safety, so regular thickness calculation is a necessary means to ensure vehicle safety. Next, the brake disc deformation analysis based on the wear thickness data helps to identify whether the disc is deformed during use. This analysis can not only reveal the physical state of the brake disc, but also reflect the thermal load and pressure effects of the brake system at work. Deformation leads to uneven braking effect and increases the risk of brake failure. Therefore, timely identification and analysis of this problem is crucial to ensure braking performance and extend the service life of the brake system. Further, the brake disc degradation analysis based on deformation data and wear thickness can comprehensively evaluate the overall health of the disc. This analysis provides a deeper perspective to judge the performance degradation of the brake disc in long-term use, ensuring that necessary replacement or maintenance is performed before the performance drops to a critical level, thereby avoiding potential safety hazards. The calculation of the probability of rupture combined with the deterioration and deformation data of the brake disc can provide a quantitative basis for the safety of the brake system. This calculation not only helps to understand the safety risks of the brake disc under different working conditions, but also provides strong data support for the maintenance and repair of the vehicle, ensuring that the driver can drive under safe conditions. Overall, the coordination of these steps makes the performance evaluation of the vehicle brake system more scientific and comprehensive, providing an important guarantee for improving driving safety.

[0049] Preferably, step S3 comprises the following steps:

[0050] Step S31: analyzing the vehicle tire condition according to the vehicle driving condition data and the vehicle mileage data to obtain the vehicle tire condition data;

[0051] Step S32: estimating the vehicle tire degradation trend according to the vehicle tire condition data to obtain the vehicle tire degradation trend data;

[0052] Step S33: performing disc performance attenuation detection according to the brake disc rupture probability data and the vehicle brake disc wear data to obtain vehicle disc performance attenuation data;

[0053] Step S34: performing a brake performance attenuation test on the vehicle simulation model according to the vehicle tire degradation data and the vehicle disc performance attenuation data to obtain the vehicle brake performance attenuation data.

[0054] The present invention can obtain specific status information of vehicle tires by analyzing vehicle driving conditions and mileage data. This analysis is the basis for ensuring vehicle safety and performance, because tires are key components that directly affect handling and braking performance. Timely evaluation of tire conditions can help identify potential wear, damage or insufficient pressure problems, thereby improving driving safety and handling stability and avoiding accident risks caused by tire problems. Next, the deterioration trend estimation based on tire condition data can predict the performance changes of tires in the future. This prediction can provide forward-looking guidance for vehicle maintenance, allowing car owners to arrange replacement or repair in advance and reduce driving risks caused by tire deterioration. At the same time, understanding the tire deterioration trend can also help optimize tire usage strategies, improve fuel efficiency and extend the service life of tires. In terms of the brake system, the disc performance attenuation detection based on the probability of rupture and wear data can systematically evaluate the performance changes of the brake disc during use. This detection can identify performance degradation in a timely manner and ensure the reliability and effectiveness of the brake system at critical moments. By performing this detection regularly, the risk of brake failure can be reduced and the safety of the vehicle during driving can be ensured. Finally, by combining tire degradation data with disc performance attenuation data and conducting brake performance attenuation tests on the vehicle simulation model, the overall braking performance of the vehicle can be comprehensively evaluated. This comprehensive analysis provides an important guarantee for vehicle safety, enabling real-time monitoring and evaluation of the effectiveness of the braking system during driving, ensuring that timely measures are taken when potential problems arise. The effective implementation of this series of steps not only improves the safety performance of the vehicle, but also provides a solid foundation for the further development of intelligent transportation systems.

[0055] Preferably, step S32 includes the following steps:

[0056] Step S321: performing tire heterogeneous wear analysis and tire pressure extraction according to the vehicle tire condition data to obtain tire heterogeneous wear data and vehicle tire pressure data;

[0057] Step S322: performing tread depth detection according to the tire heterogeneous wear data to obtain vehicle tire tread depth data;

[0058] Step S323: calculating the vehicle tire grip attenuation on the vehicle simulation model according to the vehicle tire tread depth data and the tire heterogeneous wear data to obtain the vehicle tire grip attenuation data;

[0059] Step S324: performing tire deformation analysis according to the tire pressure data of the vehicle tire to obtain the tire deformation data of the vehicle;

[0060] Step S325: performing tire unevenness inspection according to the vehicle tire deformation data and the vehicle tire pressure data to obtain vehicle tire unevenness data;

[0061] Step S326: The vehicle tire degradation trend is estimated based on the vehicle tire deformation data, the vehicle tire unevenness data and the vehicle tire grip attenuation data to obtain the vehicle tire degradation trend data.

[0062] The tire heterogeneous wear analysis and tire pressure extraction performed by the present invention through vehicle tire condition data can provide a comprehensive perspective on the health status of tires. Heterogeneous wear is usually caused by uneven load or improper tire pressure. Timely identification of these problems can effectively reduce the risk of tire failure. The acquired tire pressure data is also an important indicator to ensure tire performance and safety. Appropriate tire pressure not only affects the grip and handling of the tire, but also the tread depth detection based on the tire heterogeneous wear data helps to evaluate the availability and safety of the tire. The tread depth directly affects the drainage capacity and grip of the tire. Insufficient depth leads to increased driving risks under slippery conditions. By regularly detecting the tread depth, the safe driving of the vehicle under various climatic conditions can be ensured. The subsequent tire grip attenuation calculation, using the tire tread depth and heterogeneous wear data, can accurately evaluate the vehicle's handling under different conditions. Understanding the attenuation trend of grip helps to adjust driving habits or replace tires in a timely manner, thereby improving driving safety. The tire deformation analysis based on the tire pressure data can reveal the performance of the tire under actual driving conditions. The rationality of tire deformation directly affects the comfort and stability of the vehicle. Excessive deformation leads to unnecessary wear or handling failure. Therefore, timely monitoring of tire deformation is crucial to ensure driving safety. Unevenness inspection based on tire deformation and tire pressure can help identify potential tire problems, such as bubbles and bulges, which will affect the vehicle's handling and safety. By promptly discovering and dealing with these unevenness, further damage and danger can be avoided. The prediction of tire degradation trends based on tire deformation, unevenness, and grip attenuation data provides important forward-looking guidance for vehicle maintenance. This analysis can not only help car owners predict the service life of tires, but also provide data support for timely replacement or maintenance, thereby ensuring the safety and stable performance of the vehicle during driving. Overall, the implementation of this series of steps has effectively improved the scientific nature of tire management.

[0063] Preferably, step S4 comprises the following steps:

[0064] Step S41: estimating the side slip probability according to the vehicle brake performance attenuation data and the vehicle tire condition data to obtain the vehicle side slip probability data;

[0065] Step S42: performing vehicle rollover simulation on the vehicle simulation model according to the vehicle driving condition data, the vehicle driving sideslip probability data and the vehicle braking performance attenuation data to obtain vehicle rollover simulation data;

[0066] Step S43: performing a vehicle safety performance degradation test and a driving safety assessment according to the vehicle rollover simulation data to obtain vehicle safety performance degradation data and driving safety data;

[0067] Step S44: optimizing the vehicle configuration of the vehicle simulation model according to the vehicle safety performance attenuation data, the driving safety data and the vehicle side slip probability data to obtain vehicle configuration optimization data.

[0068] The present invention can provide a scientific basis for evaluating the stability of the vehicle under different driving conditions by estimating the slip probability based on the vehicle's brake performance attenuation data and tire condition data. The slip probability is an important factor affecting driving safety. Excessive slip probability causes the vehicle to lose control, especially in sharp turns or slippery roads. Therefore, timely identification and estimation of slip risk helps the driver to take preventive measures, thereby reducing the possibility of accidents and enhancing driving safety. Rollover simulation based on vehicle driving conditions, slip probability and brake performance attenuation data provides important information for understanding the behavior of the vehicle under extreme driving conditions. This simulation can predict the rollover risk under different conditions and help design safer vehicle structures and stable suspension systems. Through in-depth analysis of rollover behavior, key factors affecting rollover can be identified, providing a basis for vehicle design improvements and improving the overall safety of the vehicle. Further, vehicle safety performance attenuation inspection and driver safety assessment performed by analyzing rollover simulation data can provide a quantitative evaluation of the vehicle's performance under extreme conditions. This comprehensive analysis can reveal the potential threat of the vehicle to the driver when encountering rollover risks, help formulate more effective safety design standards and driving training programs, and thus improve the safety protection level of the vehicle. The vehicle simulation model is configured and optimized based on safety performance degradation data, driver safety data, and skidding probability to ensure the best performance of the vehicle under various driving conditions. This optimization process can solve potential safety hazards in the design stage, improve vehicle stability and handling, and provide a safer driving experience for the driver. Overall, this series of steps ensures vehicle safety performance and driver protection through comprehensive analysis and simulation.

[0069] The present invention has beneficial effects. By acquiring vehicle log data and configuration parameter data, a comprehensive vehicle status file can be established to provide a basis for subsequent analysis. This step ensures the accuracy and integrity of the data, especially in the analysis of vehicle driving conditions, it can effectively identify driving behavior and environmental influencing factors, thereby providing a reliable basis for the subsequent construction of simulation models. Through semantic analysis, valuable information can be extracted to understand the performance of the vehicle under different conditions, which is helpful to evaluate its safety and performance. In mileage statistics, accurate data can reveal the frequency of vehicle use and its degree of wear, which is crucial for the estimation of brake disc wear. Accurately grasping the driving distance helps to predict the use of the brake system and identify potential risks in advance. Combined with the wear data of the brake disc to calculate the probability of rupture, it is possible to quantify the safety hazards of the brake system, provide data support for timely maintenance and replacement, reduce the risk of accidents, and improve the safety of the vehicle. The subsequent tire condition analysis provides important information for the overall evaluation of braking performance. The synergy between tires and the brake system directly affects the handling and safety of the vehicle. Through the comprehensive analysis of tire conditions and braking performance, the key factors affecting the braking effect can be identified, so as to take targeted optimization measures to ensure the stability and safety of the vehicle under various conditions. Further prediction of the probability of sideslip provides an important basis for understanding the performance of the vehicle under extreme conditions. By analyzing the risk of sideslip, drivers can take preventive measures to reduce the possibility of loss of control. Configuration optimization combined with brake performance attenuation data can not only improve the handling and stability of the vehicle, but also enhance the driver's confidence and lay the foundation for a safer driving environment. The integrated analysis of this series of steps makes the evaluation and optimization of vehicle safety performance more scientific. Therefore, the present invention is an optimization of the traditional inspection and testing service method based on semantic analysis, which solves the problems of inaccurate prediction of vehicle safety performance attenuation and inaccurate vehicle performance inspection and detection in the traditional inspection and testing service method based on semantic analysis, and improves the accuracy of vehicle safety performance attenuation prediction and vehicle performance inspection and detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 A schematic diagram of the steps of the inspection and testing service method based on semantic analysis;

[0071] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0072] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0073] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0074] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0075] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0076] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0077] To achieve this, please refer to Figures 1 to 3 , a semantic analysis-based inspection and testing service method, comprising the following steps:

[0078] Step S1: Acquire vehicle log data and vehicle configuration parameter data; perform vehicle driving condition analysis on the vehicle log data based on semantic analysis to obtain vehicle driving condition data; construct a vehicle simulation model based on the vehicle driving condition data and vehicle configuration parameter data to obtain a vehicle simulation model;

[0079] Step S2: performing vehicle mileage statistics according to the vehicle driving condition data to obtain vehicle mileage data; performing vehicle brake disc wear estimation on the vehicle simulation model according to the vehicle driving distance data to obtain vehicle brake disc wear data; performing brake disc rupture probability calculation according to the vehicle brake disc wear data to obtain brake disc rupture probability data;

[0080] Step S3: analyzing the vehicle tire condition according to the vehicle driving condition data to obtain the vehicle tire condition data; performing a brake performance attenuation test on the vehicle simulation model according to the vehicle tire condition data, the brake disc rupture probability data, and the brake disc wear data to obtain the vehicle brake performance attenuation data;

[0081] Step S4: Estimating the sideslip probability based on the vehicle brake performance attenuation data and the vehicle tire condition data to obtain vehicle sideslip probability data; optimizing the vehicle configuration of the vehicle simulation model based on the vehicle sideslip probability data and the vehicle brake performance attenuation data to obtain vehicle configuration optimization data.

[0082] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of the inspection and testing service method based on semantic analysis of the present invention. In this example, the inspection and testing service method based on semantic analysis includes the following steps:

[0083] Step S1: Acquire vehicle log data and vehicle configuration parameter data; perform vehicle driving condition analysis on the vehicle log data based on semantic analysis to obtain vehicle driving condition data; construct a vehicle simulation model based on the vehicle driving condition data and vehicle configuration parameter data to obtain a vehicle simulation model;

[0084] In an embodiment of the present invention, first, the log data and configuration parameters of the vehicle are collected, which can be obtained through the built-in OBD-II interface of the vehicle. Then, the vehicle log data is semantically analyzed, and the driving state information is parsed using natural language processing tools (such as NLTK or spaCy) to extract key indicators (such as speed, acceleration, fuel consumption, etc.). Based on these indicators, a vehicle driving status data set is constructed. Next, in combination with the vehicle's configuration parameters (such as engine type, transmission type, etc.), a vehicle simulation model is constructed using data analysis tools (such as Python's Pandas library) to form a basic vehicle behavior simulation.

[0085] Step S2: performing vehicle mileage statistics according to the vehicle driving condition data to obtain vehicle mileage data; performing vehicle brake disc wear estimation on the vehicle simulation model according to the vehicle driving distance data to obtain vehicle brake disc wear data; performing brake disc rupture probability calculation according to the vehicle brake disc wear data to obtain brake disc rupture probability data;

[0086] In the embodiment of the present invention, the vehicle driving condition data generated in the previous step is used to perform mileage statistics. Through time series analysis, the driving distance of each time period is calculated to form vehicle mileage data. Subsequently, the wear of the brake disc is evaluated based on the driving distance and the use of the brakes, and the brake disc wear data is obtained by applying a formula (such as a wear rate calculation formula). Next, using the wear data, a probability theory method (such as Bayesian analysis) is used to calculate the probability of brake disc rupture to form brake disc rupture probability data.

[0087] Step S3: analyzing the vehicle tire condition according to the vehicle driving condition data to obtain the vehicle tire condition data; performing a brake performance attenuation test on the vehicle simulation model according to the vehicle tire condition data, the brake disc rupture probability data, and the brake disc wear data to obtain the vehicle brake performance attenuation data;

[0088] In the embodiment of the present invention, the vehicle driving condition data is used to analyze the tire status, and the sensor data (such as tire pressure monitoring sensor) is used to monitor the tire pressure and wear to form tire condition data. Then, combined with the probability of rupture and wear data of the brake disc, a performance evaluation method is used to test the braking performance attenuation. By comparing the braking reaction time and braking force under different driving conditions, the attenuation trend is displayed using data visualization tools (such as Matplotlib), and finally the vehicle braking performance attenuation data is obtained.

[0089] Step S4: Estimating the sideslip probability based on the vehicle brake performance attenuation data and the vehicle tire condition data to obtain vehicle sideslip probability data; optimizing the vehicle configuration of the vehicle simulation model based on the vehicle sideslip probability data and the vehicle brake performance attenuation data to obtain vehicle configuration optimization data.

[0090] In the embodiment of the present invention, the side slip probability is estimated based on the above brake performance attenuation data and tire condition data. A statistical model (such as a logistic regression model) is used to analyze the side slip situation under different driving conditions to obtain driving side slip probability data. Then, the vehicle configuration is optimized in combination with the side slip probability and brake performance attenuation data. By simulating different configuration parameters (such as tire type, brake system), an optimization algorithm (such as a genetic algorithm) is applied to achieve vehicle configuration optimization, and finally generate vehicle configuration optimization data.

[0091] Preferably, step S1 comprises the following steps:

[0092] Step S11: Acquire vehicle log data and vehicle configuration parameter data;

[0093] Step S12: analyzing the vehicle driving condition of the vehicle log data based on semantic analysis to obtain vehicle driving condition data;

[0094] Step S13: performing aerodynamic characteristic analysis according to the vehicle configuration parameter data to obtain vehicle aerodynamic characteristic data;

[0095] Step S14: constructing a vehicle simulation model according to the vehicle driving condition data, the vehicle aerodynamic characteristic data and the vehicle parameters to obtain a vehicle simulation model.

[0096] In an embodiment of the present invention, the OBD-II interface of the vehicle is used to obtain real-time vehicle log data, including information such as speed, engine speed, fuel consumption and driving time. At the same time, the configuration parameter data of the vehicle, such as vehicle brand, model, engine type, transmission type, etc., are collected. After the data is collected through a dedicated data acquisition device or interface, it is stored in a database for subsequent processing. Ensure that all data are complete and consistent to avoid data loss or errors. Use natural language processing technology to perform semantic analysis on vehicle log data and identify key features of driving status. Use the NLTK library in Python to perform word segmentation and part-of-speech tagging on the log text to extract key behavior indicators such as acceleration, braking, steering and other information. Classify the extracted data through rules or machine learning models to form vehicle driving status data. According to the vehicle configuration parameter data, aerodynamic characteristics analysis is performed. Use computational fluid dynamics (CFD) software to model the vehicle shape and simulate air flow conditions. By setting different vehicle speed and wind direction conditions, analyze the aerodynamic parameters such as the vehicle's drag coefficient and lift. In this process, a grid generation tool is used to refine the model to ensure the accuracy of the simulation results. Finally, the vehicle aerodynamic characteristic data is formed, and the vehicle simulation model is constructed by combining the vehicle driving condition data, aerodynamic characteristic data and vehicle configuration parameters. The system dynamics method is used to integrate different driving behaviors and aerodynamic characteristics to form a dynamic simulation model. Software tools (such as MATLAB / Simulink) are used to program and verify the model to ensure that the model can reflect the actual vehicle behavior and performance. Through multiple iterations and verifications, the model parameters are optimized and an accurate vehicle simulation model is finally generated.

[0097] Preferably, step S13 comprises the following steps:

[0098] Step S131: extracting the vehicle body structure according to the vehicle parameter data to obtain vehicle body structure data;

[0099] Step S132: performing a vehicle front face shape analysis and a vehicle body shape analysis according to the vehicle body structure data to obtain vehicle front face shape data and vehicle body shape data;

[0100] Step S133: simulating the flow distribution of the vehicle's running airflow according to the vehicle's front face shape data and the vehicle's body shape data to obtain the flow distribution data of the vehicle's running airflow;

[0101] Step S134: Calculating the vehicle lift coefficient using the vehicle running airflow fluid distribution data to obtain vehicle lift coefficient data;

[0102] Step S135: Perform an aerodynamic characteristic analysis based on the vehicle lift coefficient data and the vehicle running airflow fluid distribution data to obtain the vehicle aerodynamic characteristic data.

[0103] In the embodiment of the present invention, firstly, information about the geometric features of the vehicle, including wheelbase, vehicle width, vehicle height, etc., is extracted from the database. Computer-aided design (CAD) software is used to perform three-dimensional modeling on these parameters to form a detailed model of the vehicle body structure. Next, a feature extraction algorithm is applied to analyze the various components of the vehicle body (such as the roof, door, chassis, etc.) to generate vehicle body structure data. According to the acquired vehicle body structure data, the front face shape and the overall body shape of the vehicle are analyzed. A geometric analysis tool is used to perform a detailed analysis of the front face area and the overall shape of the vehicle body to extract key geometric features (such as curvature, slope, edge profile, etc.). Combined with the streamline analysis method, the influence of the front face shape on the air flow is evaluated to obtain the vehicle front face shape data and body shape data. Based on the vehicle front face shape data and body shape data, the fluid distribution of the vehicle running airflow is simulated. Using CFD software (such as ANSYS Fluent), boundary conditions such as vehicle speed and air density are set to construct the fluid domain of the vehicle model. Through meshing, the flow domain is subdivided into multiple small units to ensure the accuracy of the simulation. Use fluid dynamics equations to simulate the flow path of airflow when the vehicle is driving, and finally generate the fluid distribution data of the vehicle's driving airflow. Use the fluid distribution data of the vehicle's driving airflow to calculate the vehicle's lift coefficient. According to the basic formula of fluid dynamics, the lift coefficient is calculated in combination with the vehicle's speed and airflow characteristics. Use fluid characteristics (such as flow rate and flow pressure) to measure at various key positions of the vehicle, and form a specific value of the lift coefficient by integrating the force of the airflow on the vehicle body. This value reflects the stability and air resistance characteristics of the vehicle during driving. By comparing the lift coefficients at different vehicle speeds and shape parameters, the aerodynamic performance of the vehicle under different conditions is evaluated. Use professional aerodynamic analysis software to draw an airflow distribution diagram, analyze the overall impact of the fluid on the vehicle, and identify potential fluid separation areas. Finally, comprehensive vehicle aerodynamic characteristic data is formed.

[0104] Preferably, step S14 comprises the following steps:

[0105] Step S141: Calculating the average vehicle load and the average vehicle speed according to the vehicle driving condition data to obtain the average vehicle load data and the average vehicle speed data;

[0106] Step S142: extracting the vehicle tire size according to the vehicle configuration parameter data to obtain the vehicle tire size data;

[0107] Step S143: performing a vehicle side wind sensitivity analysis based on the vehicle tire size data, the vehicle average load data and the vehicle aerodynamic characteristic data to obtain vehicle driving side wind sensitivity data;

[0108] Step S144: performing vehicle driving stability analysis according to the vehicle driving side wind sensitivity data and the vehicle driving average speed data to obtain vehicle driving stability data;

[0109] Step S145: constructing a vehicle simulation model according to the vehicle driving stability data, the vehicle configuration parameter data and the vehicle aerodynamic characteristic data to obtain a vehicle simulation model.

[0110] In the embodiment of the present invention, the load information of each trip is extracted from the driving condition data, and the average load data of the vehicle is calculated by counting the loads of each trip. Next, the time and distance information in the driving record is used to calculate the average speed of the vehicle, and the formula is that the average speed is equal to the total driving distance divided by the total driving time. First, the specific model and configuration parameters of the vehicle are extracted, and the vehicle manual or manufacturer database is consulted to obtain the size information such as the width, height and diameter of the tire. The tire size information is sorted into a standard format using a data sorting tool (such as an SQL database or Excel) to ensure data consistency. The vehicle crosswind sensitivity analysis is performed using the vehicle tire size data, average load data and aerodynamic characteristic data. A crosswind influence model is established using engineering calculation software (such as MATLAB), and the tire size and load parameters are input to simulate the vehicle's response under different crosswind conditions. According to the aerodynamic characteristic data, the influence of wind speed on the lateral stability of the vehicle is calculated. Through multiple simulations, the crosswind sensitivity data of the vehicle under different crosswind conditions are obtained. Combined with the crosswind sensitivity data, a dynamic model is used to evaluate the crosswind influence on the vehicle when driving. Through the analysis of vehicle dynamic behavior, stability indicators at specific speeds, such as lateral acceleration and lateral slip angle, are determined. Data visualization tools (such as Matplotlib) are used to display stability changes under different speeds and crosswind conditions to obtain the final vehicle driving stability data. First, the above analysis results are used to integrate various types of data and establish a system dynamics model. Simulation software (such as Simulink) is selected to program the dynamic characteristics of the vehicle and simulate the vehicle performance under different working conditions. Through repeated iterations and verification, it is ensured that the model can accurately reflect the behavior of the vehicle under various working conditions, and finally a comprehensive vehicle simulation model is obtained.

[0111] Preferably, step S2 comprises the following steps:

[0112] Step S21: Counting the vehicle mileage according to the vehicle driving condition data to obtain the vehicle mileage data;

[0113] Step S22: performing driving habit analysis on the vehicle driving condition data based on semantic analysis to obtain vehicle driving habit data;

[0114] Step S23: Predicting the wear of the vehicle brake disc by using the vehicle simulation model according to the vehicle travel distance data and the vehicle driving habit data, and obtaining the wear data of the vehicle brake disc;

[0115] Step S24: Calculate the probability of brake disc rupture according to the vehicle brake disc wear data to obtain brake disc rupture probability data.

[0116] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0117] Step S21: Counting the vehicle mileage according to the vehicle driving condition data to obtain the vehicle mileage data;

[0118] In an embodiment of the present invention, real-time driving data of the vehicle is collected, including vehicle speed, driving time, road condition information, etc. These data are collected through the vehicle's on-board diagnostic system (OBD-II) and recorded in a database. Then, the collected data is sorted using a data processing tool (such as Python's Pandas library), and redundant information and missing values ​​are removed by cleaning and formatting the data. In the sorted data, the distance traveled each time is calculated, and the total mileage of the vehicle is finally obtained by accumulating the distance of each section of travel.

[0119] Step S22: performing driving habit analysis on the vehicle driving condition data based on semantic analysis to obtain vehicle driving habit data;

[0120] In an embodiment of the present invention, it is necessary to perform semantic analysis on the vehicle driving condition data. Through natural language processing (NLP) technology, key behavior data in the driving process, such as acceleration, braking, steering frequency, etc., are extracted. Application tools such as NLTK or SpaCy are used to segment and tag driving data to identify driving behavior patterns. Subsequently, a driving habit feature model is constructed in combination with the speed changes and direction changes in the driving data. By performing cluster analysis on the data, the driving styles of different drivers, such as smooth driving, aggressive driving, etc., are identified, and corresponding driving habit data are generated.

[0121] Step S23: Predicting the wear of the vehicle brake disc by using the vehicle simulation model according to the vehicle travel distance data and the vehicle driving habit data, and obtaining the wear data of the vehicle brake disc;

[0122] In the embodiment of the present invention, a brake disc wear estimation model is established based on the vehicle's driving distance data and driving habit data. The relationship between the brake operation frequency and the degree of wear is analyzed by collecting historical wear data and corresponding driving conditions. The linear regression analysis tool is used to establish the correlation between driving habits and brake disc wear. The Python SciPy library is used for regression calculation, and the estimated wear amount of the brake disc is output by inputting the driving distance and driving habit characteristics.

[0123] Step S24: Calculate the probability of brake disc rupture according to the vehicle brake disc wear data to obtain brake disc rupture probability data.

[0124] In the embodiment of the present invention, in the calculation of the probability of brake disc rupture, the rupture risk of the brake disc is evaluated based on the aforementioned brake disc wear data, combined with material mechanics and fatigue theory, the material properties of the brake disc and the stress data it bears are collected, and the strength changes under different degrees of wear are analyzed. A statistical method is used to establish a relationship model between the degree of wear and the probability of rupture, and the binomial distribution or normal distribution is used to calculate the probability of rupture. Through Python simulation calculation, the probability of brake disc rupture under specific wear conditions is obtained.

[0125] Preferably, step S23 includes the following steps:

[0126] Step S231: obtaining brake disc material data and brake caliper material data;

[0127] Step S232: Calculating the brake friction coefficient according to the brake disc material data and the brake caliper material data to obtain the vehicle brake friction coefficient data;

[0128] Step S233: Counting excessive sudden braking according to the vehicle driving habit data to obtain vehicle excessive sudden braking data;

[0129] Step S234: Calculating the friction heat according to the vehicle over-sudden braking data and the vehicle brake friction coefficient data to obtain the vehicle brake friction heat data;

[0130] Step S235: The vehicle brake disc wear is estimated on the vehicle simulation model according to the vehicle travel distance data and the vehicle brake friction heat data to obtain the vehicle brake disc wear data.

[0131] In the embodiment of the present invention, it is necessary to physically inspect the brake system of the vehicle to identify the specific materials used. By consulting the technical manual provided by the manufacturer, the material information of the brake disc and the brake caliper is obtained. This information usually includes the chemical composition, mechanical properties (such as hardness, tensile strength) and the like of the material. Then, a material database (such as MatWeb) is used for further confirmation to ensure the accuracy and reliability of the acquired data. In addition, the samples are inspected by experimental methods such as mass spectrometry and metallographic analysis to obtain more detailed material data. According to the acquired material data of the brake disc and the brake caliper, a friction testing device (such as a friction tester) is used to conduct experiments. In the experiment, the samples of the brake disc and the brake caliper are contacted, and a specific pressure and speed are applied to measure the ratio of friction force to normal force to calculate the friction coefficient. The experimental results are processed and visualized using data analysis software (such as MATLAB), and the friction coefficient data under different conditions are extracted. It is necessary to analyze the driving data of the vehicle, especially the data of the braking operation. The vehicle's on-board diagnostic system (OBD-II) is used to collect real-time brake signals and speed change data. Set the definition criteria for emergency braking, such as the vehicle speed suddenly drops from a certain value to zero in a short period of time, or the braking force exceeds the set threshold. Use data processing tools (such as Python's Pandas library) to filter and count the collected data, identify all events that meet the emergency braking conditions, and count the frequency and cumulative number of occurrences. Finally, generate a data report on excessive emergency braking, which requires combining the vehicle's excessive emergency braking data with the brake friction coefficient data. According to the principles of thermodynamics, the heat generated by friction during braking can be calculated by the formula Q = F × d, where Q is heat, FFF is the braking force, and d is the braking distance. By reading the value of the braking force and the braking distance in the excessive emergency braking data, the heat generated in each emergency braking is calculated. To ensure data accuracy, set experimental conditions and conduct multiple tests, and take the average value to generate heat data. Combine the vehicle's driving distance data with the brake friction heat data. By analyzing historical data, establish a relationship model between brake disc wear and heat. In the specific implementation, apply linear regression analysis methods to establish a functional relationship between heat and wear degree. By obtaining the driving distance and the corresponding friction heat data, use the calculation formula to predict the amount of wear under given driving conditions.

[0132] Preferably, step S24 includes the following steps:

[0133] Step S241: calculating the wear thickness of the brake disc according to the wear data of the vehicle brake disc to obtain the wear thickness data of the brake disc;

[0134] Step S242: performing brake disc deformation analysis according to the vehicle brake disc wear thickness data to obtain brake disc deformation data;

[0135] Step S243: performing brake disc degradation analysis according to the brake disc deformation data and the vehicle brake disc wear thickness data to obtain vehicle brake disc degradation data;

[0136] Step S244: Calculate the probability of brake disc rupture according to the vehicle brake disc degradation data and the brake disc deformation data to obtain brake disc rupture probability data.

[0137] In an embodiment of the present invention, firstly, the wear data of the brake disc of the vehicle is collected, including the initial thickness and actual wear amount of the brake disc. These data can be obtained through regular inspection of the brake system, and the actual thickness of the brake disc is usually measured using a digital thickness gauge. The wear thickness is calculated by comparing the initial thickness with the actual measured thickness. The specific calculation formula is: wear thickness = initial thickness - actual thickness. According to the thickness data of the brake disc, combined with the use of the brake, especially the performance under sudden braking and high temperature conditions. The brake disc is photographed and analyzed by a laser rangefinder and image processing software (such as OpenCV) to capture the deformation generated during use. The shape of the brake disc in the image is compared with the standard shape to calculate the degree of deformation. Specifically, the deformation data can be obtained by a shape matching algorithm, and the deformation data of the brake disc is combined with the wear thickness data to evaluate the overall state of the brake disc. The multi-parameter analysis method is used to convert the wear thickness and deformation degree into a degradation score. By setting the degradation standard, for example, if the wear thickness exceeds the safety threshold or the deformation reaches a certain proportion, it is determined to be degraded. Data analysis tools (such as R language or Python) can be used for statistical analysis to generate degradation data reports. It is necessary to comprehensively analyze the degradation data and deformation data of the brake disc. Use reliability analysis methods to build a brake disc rupture risk model. The specific steps are: first collect data on historical rupture events, and record the corresponding wear and deformation states, and use survival analysis methods to calculate the probability of rupture under a specific degree of degradation. Calculate through statistical software to obtain the probability data of brake disc rupture under given conditions.

[0138] Preferably, step S3 comprises the following steps:

[0139] Step S31: analyzing the vehicle tire condition according to the vehicle driving condition data and the vehicle mileage data to obtain the vehicle tire condition data;

[0140] Step S32: estimating the vehicle tire degradation trend according to the vehicle tire condition data to obtain the vehicle tire degradation trend data;

[0141] Step S33: performing disc performance attenuation detection according to the brake disc rupture probability data and the vehicle brake disc wear data to obtain vehicle disc performance attenuation data;

[0142] Step S34: performing a brake performance attenuation test on the vehicle simulation model according to the vehicle tire degradation data and the vehicle disc performance attenuation data to obtain the vehicle brake performance attenuation data.

[0143] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0144] Step S31: analyzing the vehicle tire condition according to the vehicle driving condition data and the vehicle mileage data to obtain the vehicle tire condition data;

[0145] In the embodiment of the present invention, it is first necessary to collect the driving condition data and mileage data of the vehicle. These data are usually obtained through the OBD-II interface of the vehicle, and the recorded information includes driving speed, acceleration mode, braking frequency and total driving distance. Next, the collected data is cleaned and sorted using data analysis tools (such as Python's Pandas library) to extract key indicators related to tires, such as tire wear, air pressure changes and temperature fluctuations. By constructing a tire condition assessment model, combining historical maintenance records with real-time data, analyzing the overall condition of the tire, and generating a detailed vehicle tire condition data report.

[0146] Step S32: estimating the vehicle tire degradation trend according to the vehicle tire condition data to obtain the vehicle tire degradation trend data;

[0147] In the embodiment of the present invention, the wear rate and usage pattern of the tire are first analyzed based on the tire condition data obtained in the previous step. The tire wear condition is modeled using a time series analysis method, and the trend of accelerated degradation is identified by setting an early warning threshold. Data visualization tools (such as Matplotlib) are used to display the changing trend of historical wear data to help identify potential problems. In addition, the tire usage is predicted using a machine learning algorithm (such as linear regression) to obtain tire degradation trend data for a period of time in the future.

[0148] Step S33: performing disc performance attenuation detection according to the brake disc rupture probability data and the vehicle brake disc wear data to obtain vehicle disc performance attenuation data;

[0149] In the embodiment of the present invention, firstly, the brake disc rupture probability data and wear data are collected. These data are obtained through regular inspection and real-time monitoring of the brake system, covering the frequency of brake use, braking force and the record of historical rupture events. The multivariate analysis method is used to combine the rupture probability with the wear data, and the performance of the brake disc is evaluated by constructing an evaluation model. The performance attenuation calculation is performed using data analysis tools (such as R language or Python's Scikit-learn) to generate vehicle disc performance attenuation data.

[0150] Step S34: performing a brake performance attenuation test on the vehicle simulation model according to the vehicle tire degradation data and the vehicle disc performance attenuation data to obtain the vehicle brake performance attenuation data.

[0151] In the embodiment of the present invention, firstly, a comprehensive evaluation model is established by combining the tire degradation data and the disc performance attenuation data of the vehicle. The data of the two are integrated, and the physical model and statistical analysis method are used to analyze the joint influence of the tire and the brake disc on the braking performance. A dynamic simulation test of the braking performance is performed using a simulation tool (such as MATLAB or Simulink) to evaluate the braking effect under different conditions. By performing statistical analysis on the simulation results, the braking performance attenuation data is generated.

[0152] Preferably, step S32 includes the following steps:

[0153] Step S321: performing tire heterogeneous wear analysis and tire pressure extraction according to the vehicle tire condition data to obtain tire heterogeneous wear data and vehicle tire pressure data;

[0154] Step S322: performing tread depth detection according to the tire heterogeneous wear data to obtain vehicle tire tread depth data;

[0155] Step S323: calculating the vehicle tire grip attenuation on the vehicle simulation model according to the vehicle tire tread depth data and the tire heterogeneous wear data to obtain the vehicle tire grip attenuation data;

[0156] Step S324: performing tire deformation analysis according to the tire pressure data of the vehicle tire to obtain the tire deformation data of the vehicle;

[0157] Step S325: performing tire unevenness inspection according to the vehicle tire deformation data and the vehicle tire pressure data to obtain vehicle tire unevenness data;

[0158] Step S326: The vehicle tire degradation trend is estimated based on the vehicle tire deformation data, the vehicle tire unevenness data and the vehicle tire grip attenuation data to obtain the vehicle tire degradation trend data.

[0159] In an embodiment of the present invention, firstly, the tire condition data of the vehicle is collected, including the tire usage history, wear condition and driving conditions. The tire pressure data is obtained by using the vehicle-mounted sensor, and the tire pressure data is correlated with the driving data for analysis. The collected data is sorted and cleaned by using a data processing tool (such as Python's Pandas library) to identify the heterogeneous wear patterns of the tire, such as outer wear, inner wear and center wear. By comparing the wear data of different tires, the tire heterogeneous wear data is obtained, and the tire pressure condition of each tire and its impact on vehicle performance are recorded. The tire to be tested is selected according to the tire heterogeneous wear data. A professional tread depth measuring instrument is used to accurately measure the tread depth of each position of the tire. This process should ensure the accuracy of the measurement, and obtain comprehensive data through the detection of multiple measuring points. The measurement results are input into a data analysis tool (such as Excel or MATLAB) for statistical analysis to generate tire tread depth data. It is necessary to combine the vehicle tire tread depth data and the tire heterogeneous wear data. Using the friction mechanics model, the tire tread depth and wear information are input to calculate the tire's grip. The grip changes under different road conditions can be simulated using data analysis software (such as MATLAB or Simulink). By combining the grip attenuation results with driving data, the grip attenuation data of the vehicle under different conditions can be obtained. According to the tire pressure data of the vehicle, the deformation of the tire under different pressures is measured. The deformation of the tire during driving is recorded using a pressure sensor and a laser rangefinder. Deformation data is collected by dynamically testing the tire under different tire pressures. The collected data is processed and analyzed using data analysis tools (such as Python's NumPy library) to evaluate the deformation of the tire under different working conditions and generate a detailed tire deformation data report. Based on the tire deformation data and tire pressure data obtained above, the overall unevenness of the tire is evaluated. By setting an unevenness threshold, the deformation data is analyzed to see if it exceeds the set standard. Use data processing software (such as MATLAB) to evaluate the unevenness and conduct a comprehensive analysis in combination with historical tire data. Statistical methods can be used to model the effects of deformation and tire pressure to determine the degree of unevenness of the tire. The generated tire unevenness data is used to comprehensively analyze tire deformation data, tire unevenness data, and tire grip attenuation data. The time series analysis method is used to model the previous test data and predict future degradation trends. Data analysis tools (such as R language) are used to perform regression analysis on the data to obtain specific indicators of degradation trends. The analysis results are organized into a report to record the tire degradation trend data, which is convenient for maintenance personnel to monitor and warn of tire status.

[0160] Preferably, step S4 comprises the following steps:

[0161] Step S41: estimating the side slip probability according to the vehicle brake performance attenuation data and the vehicle tire condition data to obtain the vehicle side slip probability data;

[0162] Step S42: performing vehicle rollover simulation on the vehicle simulation model according to the vehicle driving condition data, the vehicle driving sideslip probability data and the vehicle braking performance attenuation data to obtain vehicle rollover simulation data;

[0163] Step S43: performing a vehicle safety performance degradation test and a driving safety assessment according to the vehicle rollover simulation data to obtain vehicle safety performance degradation data and driving safety data;

[0164] Step S44: optimizing the vehicle configuration of the vehicle simulation model according to the vehicle safety performance attenuation data, the driving safety data and the vehicle side slip probability data to obtain vehicle configuration optimization data.

[0165] In the embodiment of the present invention, it is necessary to collect the braking performance attenuation data and tire condition data of the vehicle. These data are obtained in real time through the sensor system and OBD-II interface of the vehicle, covering information such as braking response, tire wear and tire pressure. Statistical analysis methods are used to analyze the influence of braking performance and tire condition on vehicle side slip in combination with the principle of friction mechanics. By establishing a mathematical model, inputting relevant variables for calculation, the side slip probability of the vehicle under different driving conditions is obtained. Finally, the calculation results are recorded as driving side slip probability data, and the vehicle driving condition data, side slip probability data and braking performance attenuation data are combined. A vehicle dynamic model is established using simulation software (such as MATLAB / Simulink), and corresponding parameters are set, including center of gravity height, steering angle and side slip probability. The dynamic response of the vehicle is observed by simulating different driving scenarios, such as sharp turns or sudden braking. During the simulation process, the system will calculate the rollover risk of the vehicle in real time, and generate detailed rollover simulation data by comparing the actual dynamic behavior with the preset standard. These data will be used to evaluate the safety and stability of the vehicle under extreme conditions. The overall safety performance of the vehicle is evaluated using rollover simulation data. By setting safety performance standards, the stability and carrying capacity of the vehicle under rollover conditions are analyzed. Combine the driver's behavior data (such as driving habits and reaction time) to evaluate their safety in emergency situations. Use data analysis tools (such as R language) to perform statistical analysis on the simulation results to generate vehicle safety performance degradation data and driver safety data reports. The report includes potential risks and improvement suggestions, and comprehensively analyzes vehicle safety performance degradation data, driver safety data, and driving side slip probability data. Use multivariable optimization algorithms to set optimization goals, such as improving rollover stability or reducing side slip risks. Use simulation software to simulate and test different configuration schemes to evaluate their impact on vehicle dynamic performance. Select the configuration scheme with the best performance and generate vehicle configuration optimization data.

[0166] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for inspection and testing services based on semantic analysis, characterized in that: The following steps are involved: Step S1: Acquire vehicle log data and vehicle configuration parameter data; Performing vehicle driving condition analysis on vehicle log data based on semantic analysis to obtain vehicle driving condition data; A vehicle simulation model is constructed according to the vehicle driving condition data and the vehicle configuration parameter data to obtain a vehicle simulation model; Step S2: performing vehicle mileage statistics according to the vehicle driving condition data to obtain vehicle mileage data; performing vehicle brake disc wear estimation on the vehicle simulation model according to the vehicle driving distance data to obtain vehicle brake disc wear data; performing brake disc rupture probability calculation according to the vehicle brake disc wear data to obtain brake disc rupture probability data; Step S3: Analyze the vehicle tire condition according to the vehicle driving condition data to obtain the vehicle tire condition data; According to the vehicle tire condition data, brake disc rupture probability data and brake disc wear data, the vehicle simulation model is tested for brake performance attenuation to obtain the vehicle brake performance attenuation data; Step S4: estimating the side slip probability according to the vehicle brake performance attenuation data and the vehicle tire condition data to obtain the vehicle side slip probability data; The vehicle configuration of the vehicle simulation model is optimized according to the vehicle sideslip probability data and the vehicle braking performance attenuation data to obtain the vehicle configuration optimization data.

2. The inspection and testing service method based on semantic analysis according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Acquire vehicle log data and vehicle configuration parameter data; Step S12: analyzing the vehicle driving condition of the vehicle log data based on semantic analysis to obtain vehicle driving condition data; Step S13: performing aerodynamic characteristic analysis according to the vehicle configuration parameter data to obtain vehicle aerodynamic characteristic data; Step S14: constructing a vehicle simulation model according to the vehicle driving condition data, the vehicle aerodynamic characteristic data and the vehicle parameters to obtain a vehicle simulation model.

3. The inspection and testing service method based on semantic analysis according to claim 1 is characterized in that: Step S13 includes the following steps: Step S131: extracting the vehicle body structure according to the vehicle parameter data to obtain vehicle body structure data; Step S132: performing a vehicle front face shape analysis and a vehicle body shape analysis according to the vehicle body structure data to obtain vehicle front face shape data and vehicle body shape data; Step S133: simulating the flow distribution of the vehicle's running airflow according to the vehicle's front face shape data and the vehicle's body shape data to obtain the flow distribution data of the vehicle's running airflow; Step S134: Calculating the vehicle lift coefficient using the vehicle running airflow fluid distribution data to obtain vehicle lift coefficient data; Step S135: Perform an aerodynamic characteristic analysis based on the vehicle lift coefficient data and the vehicle running airflow fluid distribution data to obtain the vehicle aerodynamic characteristic data.

4. The inspection and testing service method based on semantic analysis according to claim 2 is characterized in that: Step S14 includes the following steps: Step S141: Calculating the average vehicle load and the average vehicle speed according to the vehicle driving condition data to obtain the average vehicle load data and the average vehicle speed data; Step S142: extracting the vehicle tire size according to the vehicle configuration parameter data to obtain the vehicle tire size data; Step S143: performing a vehicle side wind sensitivity analysis based on the vehicle tire size data, the vehicle average load data and the vehicle aerodynamic characteristic data to obtain vehicle driving side wind sensitivity data; Step S144: performing vehicle driving stability analysis according to the vehicle driving side wind sensitivity data and the vehicle driving average speed data to obtain vehicle driving stability data; Step S145: constructing a vehicle simulation model according to the vehicle driving stability data, the vehicle configuration parameter data and the vehicle aerodynamic characteristic data to obtain a vehicle simulation model.

5. The inspection and testing service method based on semantic analysis according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: Counting the vehicle mileage according to the vehicle driving condition data to obtain the vehicle mileage data; Step S22: performing driving habit analysis on the vehicle driving condition data based on semantic analysis to obtain vehicle driving habit data; Step S23: Predicting the wear of the vehicle brake disc by using the vehicle simulation model according to the vehicle travel distance data and the vehicle driving habit data, and obtaining the wear data of the vehicle brake disc; Step S24: Calculate the probability of brake disc rupture according to the vehicle brake disc wear data to obtain brake disc rupture probability data.

6. The inspection and testing service method based on semantic analysis according to claim 5 is characterized in that: Step S23 includes the following steps: Step S231: obtaining brake disc material data and brake caliper material data; Step S232: Calculating the brake friction coefficient according to the brake disc material data and the brake caliper material data to obtain the vehicle brake friction coefficient data; Step S233: Counting excessive sudden braking according to the vehicle driving habit data to obtain vehicle excessive sudden braking data; Step S234: Calculating the friction heat according to the vehicle over-sudden braking data and the vehicle brake friction coefficient data to obtain the vehicle brake friction heat data; Step S235: The vehicle brake disc wear is estimated on the vehicle simulation model according to the vehicle travel distance data and the vehicle brake friction heat data to obtain the vehicle brake disc wear data.

7. The inspection and testing service method based on semantic analysis according to claim 5 is characterized in that: Step S24 includes the following steps: Step S241: calculating the wear thickness of the brake disc according to the wear data of the vehicle brake disc to obtain the wear thickness data of the brake disc; Step S242: performing brake disc deformation analysis according to the vehicle brake disc wear thickness data to obtain brake disc deformation data; Step S243: performing brake disc degradation analysis according to the brake disc deformation data and the vehicle brake disc wear thickness data to obtain vehicle brake disc degradation data; Step S244: Calculate the probability of brake disc rupture according to the vehicle brake disc degradation data and the brake disc deformation data to obtain brake disc rupture probability data.

8. The inspection and testing service method based on semantic analysis according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: analyzing the vehicle tire condition according to the vehicle driving condition data and the vehicle mileage data to obtain the vehicle tire condition data; Step S32: estimating the vehicle tire degradation trend according to the vehicle tire condition data to obtain the vehicle tire degradation trend data; Step S33: performing disc performance attenuation detection according to the brake disc rupture probability data and the vehicle brake disc wear data to obtain vehicle disc performance attenuation data; Step S34: performing a brake performance attenuation test on the vehicle simulation model according to the vehicle tire degradation data and the vehicle disc performance attenuation data to obtain the vehicle brake performance attenuation data.

9. The inspection and testing service method based on semantic analysis according to claim 8, characterized in that: Step S32 includes the following steps: Step S321: performing tire heterogeneous wear analysis and tire pressure extraction according to the vehicle tire condition data to obtain tire heterogeneous wear data and vehicle tire pressure data; Step S322: performing tread depth detection according to the tire heterogeneous wear data to obtain vehicle tire tread depth data; Step S323: performing vehicle tire grip attenuation calculation on the vehicle simulation model according to the vehicle tire tread depth data and the tire heterogeneous wear data to obtain vehicle tire grip attenuation data; Step S324: performing tire deformation analysis according to the tire pressure data of the vehicle tire to obtain the tire deformation data of the vehicle; Step S325: performing tire unevenness inspection according to the vehicle tire deformation data and the vehicle tire pressure data to obtain vehicle tire unevenness data; Step S326: The vehicle tire degradation trend is estimated based on the vehicle tire deformation data, the vehicle tire unevenness data and the vehicle tire grip attenuation data to obtain the vehicle tire degradation trend data.

10. The inspection and testing service method based on semantic analysis according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: estimating the side slip probability according to the vehicle brake performance attenuation data and the vehicle tire condition data to obtain the vehicle side slip probability data; Step S42: performing vehicle rollover simulation on the vehicle simulation model according to the vehicle driving condition data, the vehicle driving sideslip probability data and the vehicle braking performance attenuation data to obtain vehicle rollover simulation data; Step S43: performing a vehicle safety performance degradation test and a driving safety assessment according to the vehicle rollover simulation data to obtain vehicle safety performance degradation data and driving safety data; Step S44: optimizing the vehicle configuration of the vehicle simulation model according to the vehicle safety performance attenuation data, the driving safety data and the vehicle side slip probability data to obtain vehicle configuration optimization data.

Images