Automobile wire harness belt detection method, system and device and storage medium

Abstract

The invention relates to an automobile bunching belt detection method, system and device and a storage medium, and the method comprises the steps: carrying out the initial detection of a bunching belt through a multi-mode sensing device, obtaining an initial detection result, and enabling the multi-mode sensing device to comprise an industrial CT, a high-frequency ultrasonic phased array and a fiber Bragg grating sensor; designing a multi-physics field cooperative loading working condition of a simulated bunch strip service environment to obtain multi-physics field loading data; constructing a dynamic damage accumulation model based on the multi-physical field loading data and the initial detection result; based on the dynamic damage accumulation model and a machine learning algorithm, predicting the remaining service life of the cable tie, and generating a service life prediction result of the cable tie; and generating a comprehensive detection report in combination with the initial detection result, the multi-physics field loading data and the life prediction result. The method and the device have the effect of improving the detection accuracy of the bunching belt.

Description

Technical Field

[0001] The present application relates to the technical field of automobile parts detection, and in particular to an automobile cable tie detection method, system, device and storage medium. Background Art

[0002] In modern automobile manufacturing, cable ties are used as key connection and fixing components in engine compartments, cabs, chassis and other parts to organize and protect complex electrical wiring systems. The performance of cable ties is directly related to the safety and reliability of automotive electrical systems, especially under extreme conditions such as high temperature, vibration, and humidity, where their strength and durability are particularly important. However, existing automotive cable tie testing methods are mostly limited to static strength tests or fatigue tests under a single working condition, such as only testing tensile strength or tear strength.

[0003] The above-mentioned existing technical solutions have the following defects: the existing cable tie detection method is difficult to effectively detect hidden damage inside the material. Such hidden damage may cause sudden failure during long-term service and affect the safety of the vehicle. Therefore, there is room for improvement. Summary of the invention

[0004] In order to improve the accuracy of cable tie detection, the present application provides a method, system, device and storage medium for detecting a vehicle cable tie.

[0005] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A method for detecting a cable tie for an automobile, the method comprising: Performing an initial detection on the cable tie by a multi-modal sensing device to obtain an initial detection result, wherein the multi-modal sensing device includes an industrial CT, a high-frequency ultrasonic phased array, and a fiber Bragg grating sensor; Design a multi-physics field collaborative loading condition that simulates the service environment of the cable tie to obtain multi-physics field loading data; Constructing a dynamic damage accumulation model based on the multi-physics field loading data and the initial detection results; Based on the dynamic damage accumulation model and the machine learning algorithm, the remaining service life of the cable tie is predicted, and a life prediction result of the cable tie is generated; A comprehensive test report is generated by combining the initial test results, the multi-physics field loading data and the life prediction results.

[0006] By adopting the above technical solution and using a multimodal sensing device to perform initial detection on the cable ties, the characteristics of industrial CT, high-frequency ultrasonic phased array and fiber Bragg grating sensors can be comprehensively utilized to achieve comprehensive perception of the internal structure, surface defects and stress state of the cable ties, effectively improving the detection accuracy and coverage; by simulating the multi-physical field collaborative loading conditions of the cable ties' service environment, the complex conditions such as temperature, stress, vibration, etc. that the cable ties are subjected to in actual work can be truly restored, thereby obtaining accurate multi-physical field loading data, effectively improving the authenticity of the model and the accuracy of the prediction; by combining multi-physical field loading data and initial detection results to construct a dynamic damage accumulation model, the cable ties can be dynamically tracked. The damage evolution process of the cable tie in a complex service environment can be analyzed to accurately quantify the key damage parameters and improve the scientificity and reliability of the predicted life model. By using the dynamic damage accumulation model and machine learning algorithm to predict the remaining service life of the cable tie, it can effectively explore the relationship between damage characteristics and life in a complex environment, generate accurate life prediction results, and provide data support for maintenance strategies and usage planning. By combining the initial test results, multi-physical field loading data and life prediction results to generate a comprehensive test report, it can fully reflect the health status, potential risks and service life of the cable tie, thereby providing users with a scientific and comprehensive decision-making basis, reducing the risk of sudden failures and improving system reliability.

[0007] In a preferred example, the present application may be further configured as follows: the initial detection of the cable tie by the multi-modal sensing device to obtain the initial detection result includes: Using the industrial CT scan to construct an initial internal structure model of the cable tie, generating an initial three-dimensional internal structure model of the cable tie, wherein the initial three-dimensional internal structure model of the cable tie can distinguish local defects and fiber weaving states of the cable tie; The cable tie is identified by using ultrasonic phased array technology to generate initial defect information of the cable tie, wherein the initial defect information includes the location and size of microcracks, voids and delamination; Arranging the fiber Bragg grating sensor to record the initial strain state of the cable tie and generate the initial strain and temperature change of the cable tie; The initial three-dimensional internal structure model, initial defect information, and initial strain and temperature changes are correlated and analyzed and classified using a multivariate statistical analysis method to obtain the initial detection result.

[0008] By adopting the above technical solution, the initial three-dimensional internal structure model of the cable tie is constructed through industrial CT scanning, and the internal detailed information of the cable tie can be obtained in a high-resolution and non-contact manner, and its local defects and fiber weaving state can be clearly distinguished, so as to fully reflect its structural integrity; by using ultrasonic phased array technology to identify the cable tie, the position and size of its internal microcracks, voids and delamination defects can be effectively detected, which is particularly suitable for internal non-destructive testing of complex materials, and helps to accurately locate initial defects and improve detection accuracy and defect identification efficiency; by arranging fiber Bragg grating sensors to record the initial strain state of the cable tie, high-precision strain and temperature change information can be collected in real time, which helps to accurately characterize its initial stress distribution and thermal environment adaptability, and provide key data support for subsequent damage analysis and life prediction; by using multivariate statistical analysis methods to correlate and analyze and classify the initial three-dimensional internal structure model, initial defect information and initial strain and temperature changes, the potential correlation between multimodal data can be explored, and the data integration and classification process can be optimized, so as to generate highly reliable initial detection results and provide comprehensive input data for subsequent modeling and prediction.

[0009] In a preferred example, the present application may be further configured as follows: the design simulates the multi-physics field collaborative loading condition of the cable tie service environment, and the multi-physics field loading data obtained includes: Applying multi-physics field loading in a simulation environment to simulate the actual working conditions of the cable tie under complex service conditions and generate a dynamic service performance spectrum; Acoustic emission sensors and infrared thermal imaging technology are used to synchronously monitor the microcrack extension and thermal anomaly areas of the cable tie during loading, and multi-modal fusion is used to locate and obtain key position data of the hidden damage of the cable tie; The dynamic service performance spectrum and the key position data of the hidden damage of the cable tie are processed by using data cleaning and multi-dimensional noise reduction algorithms to obtain the multi-physical field loading data.

[0010] By adopting the above technical solution and applying multi-physics field loading in a simulated environment, the actual working conditions of the cable tie under complex service conditions can be highly restored, a dynamic service performance spectrum can be generated, and the changing law of the material performance of the cable tie in a complex environment can be fully reflected; through the synchronous monitoring of acoustic emission sensors and infrared thermal imaging technology, the micro-crack extension and thermal anomaly areas of the cable tie during the loading process can be captured in real time, and combined with multi-modal data fusion technology, the key positions of the hidden damage of the cable tie can be accurately located, and the accuracy and integrity of the hidden damage detection can be improved; by using data cleaning and multi-dimensional noise reduction algorithms to process the dynamic service performance spectrum and the key position data of hidden damage, noise and redundant information can be effectively removed, and the accuracy and quality of the data can be improved. The processed multi-physics field loading data is more refined, providing high-quality basic input data for subsequent model analysis and life prediction.

[0011] In a preferred example, the present application can be further configured as follows: applying multi-physics field loading in a simulation environment, simulating the actual working conditions of the cable tie under complex service conditions, and generating a dynamic service performance spectrum includes: Simulating the temperature alternating loading process in the simulation environment, recording the thermal expansion and contraction characteristics of the cable tie at different temperatures, and generating thermal changes of the cable tie; Using a multi-axis collaborative loading device to simulate the stress response of the cable tie under tension, compression and torsion conditions in the simulation environment to generate a mechanical response of the cable tie; Applying electromagnetic radiation in the simulation environment by using an electromagnetic loading device, analyzing the influence of electromagnetic radiation on the performance of the cable tie material, and generating electromagnetic interference information of the cable tie; The thermal change, mechanical response and electromagnetic interference information of the cable tie are statistically analyzed to form the dynamic service performance spectrum.

[0012] By adopting the above technical scheme, by simulating the temperature alternating loading process in a simulated environment, the thermal expansion and contraction characteristics of the cable tie under different temperature conditions can be accurately recorded, thereby comprehensively reflecting the change law of its thermal performance, which is helpful to predict its reliability under complex temperature conditions; by simulating the stress response of the cable tie under tension, compression and torsion conditions through a multi-axis collaborative loading device, its force characteristics under various mechanical conditions can be truly reproduced, and the strength, stiffness and deformation capacity of the material can be revealed; by using electromagnetic loading equipment to apply electromagnetic radiation in a simulated environment, the influence of the electromagnetic environment on the performance of the cable tie material can be analyzed, and the effect of electromagnetic radiation on the strength, insulation and stability of the material can be quantified; by statistically analyzing the thermal changes, mechanical responses and electromagnetic interference information of the cable tie, multi-dimensional dynamic performance data can be fully integrated to form a dynamic performance spectrum reflecting the service performance of the cable tie in a complex environment, which can provide a complete performance evaluation framework and provide reliable comprehensive data support for damage analysis, design optimization and life prediction.

[0013] In a preferred example, the present application may be further configured as follows: constructing a dynamic damage accumulation model based on the multi-physics field loading data and the initial detection results includes: Inputting the initial detection results and the multi-physics field loading data into a finite element model to construct the stress-strain distribution of the cable tie under complex working conditions; The dynamic damage accumulation model is constructed by combining the stress-strain distribution and the material performance parameters of the cable tie using an adaptive neural fuzzy inference algorithm.

[0014] By adopting the above technical solution, by inputting the initial detection results and multi-physics field loading data into the finite element model, the stress-strain distribution of the cable tie under complex working conditions can be accurately simulated. The model can comprehensively reflect the stress concentration areas and deformation characteristics of the cable tie under various mechanical, thermal and electromagnetic environments, and provide important support for identifying potential damage sites and evaluating structural integrity. By combining the stress-strain distribution and the material performance parameters of the cable tie, and using an adaptive neural-fuzzy inference algorithm, the damage accumulation process under complex working conditions can be dynamically captured. The constructed dynamic damage accumulation model can adaptively optimize the accuracy and stability of damage prediction, and provide an efficient and intelligent modeling tool for the life prediction and service reliability analysis of the cable tie.

[0015] In a preferred example, the present application may be further configured as follows: the prediction of the remaining service life of the cable tie based on the dynamic damage accumulation model and the machine learning algorithm, and the generation of the life prediction result of the cable tie includes: Based on the dynamic damage accumulation model, extracting damage evolution parameters and loading history data of the cable tie; The nonlinear relationship of the damage evolution parameters is processed through a deep learning network, and the loading history data is featured and fitted in combination with a random forest algorithm, and a joint model is used to generate a prediction result of the remaining life of the cable tie.

[0016] By adopting the above technical solution, by extracting the damage evolution parameters and loading history data of the cable tie based on the dynamic damage accumulation model, the damage accumulation law and historical load characteristics of the cable tie under complex working conditions can be fully captured. The damage evolution parameters reflect the development trend of internal damage in the material, while the loading history data provides the dynamic influence of environmental and stress factors on damage, providing accurate input data for the life prediction model; by processing the nonlinear relationship of the damage evolution parameters through the deep learning network, the complex characteristics and internal patterns in the damage evolution process can be fully explored, and the prediction ability of the damage accumulation trend can be improved. At the same time, the random forest algorithm is combined to perform feature screening and fitting of the loading history data, which can effectively remove redundant information, retain key variables, and improve the efficiency and accuracy of the model. The remaining life prediction results generated by the joint modeling can more accurately reflect the life of the cable tie in the actual service environment.

[0017] In a preferred example, the present application may be further configured as follows: the generating of a comprehensive test report by combining the initial test results, the multi-physics field loading data and the life prediction results includes: The three-dimensional internal structure model, initial defect information and strain state data of the initial detection result are integrated and analyzed with the multi-physics field loading data to generate a damage distribution map; Fitting the life prediction result with the parameters in the dynamic damage accumulation model to generate the remaining life curve of the cable tie under different working conditions; generating future use risk information according to the damage distribution map and the remaining life curve; By using data visualization technology, the damage distribution map, the remaining life curve and the future use risk information are generated into a visual comprehensive report.

[0018] By adopting the above technical solution, by fusing and analyzing the three-dimensional internal structure model of the initial detection results, the initial defect information and strain state data with the multi-physical field loading data, the damage distribution characteristics of the cable tie in a complex environment can be comprehensively reflected. The generated damage distribution map can accurately locate the key damage area and reveal the size, location and evolution trend of the damage; by fitting the life prediction results with the parameters in the dynamic damage accumulation model, the remaining life characteristics of the cable tie under different working conditions can be more accurately characterized, and the trend of life changing with time or working conditions can be dynamically displayed, providing a reliable quantitative basis for equipment use planning and life management under complex working conditions; by combining The damage distribution map and remaining life curve can analyze the impact of the key damage areas of the cable tie on its future service life, generate future use risk information, and evaluate the potential failure probability and failure time, providing a scientific basis for taking preventive measures in advance, thereby effectively reducing the possibility of failure during use; through data visualization technology, the damage distribution map, remaining life curve and future use risk information are graphically integrated into a visual comprehensive report, which can clearly and intuitively display the analysis results to help users quickly understand the health status and future use risks of the cable tie, provide decision makers with comprehensive and easy-to-interpret reference information, and improve the practical application value of the test results.

[0019] The second object of the invention is achieved by the following technical solutions: An automobile cable tie detection system, the automobile cable tie detection system comprising: An initial detection module, used to perform initial detection on the cable tie through a multi-modal sensing device to obtain an initial detection result, wherein the multi-modal sensing device includes an industrial CT, a high-frequency ultrasonic phased array and a fiber Bragg grating sensor; A loading module, used to design a multi-physics field collaborative loading condition simulating the service environment of the cable tie to obtain multi-physics field loading data; A model building module is used to build a dynamic damage accumulation model based on the multi-physics field loading data and the initial detection results; A prediction module, used for predicting the remaining service life of the cable tie based on the dynamic damage accumulation model and the machine learning algorithm, and generating a life prediction result of the cable tie; A report generation module is used to generate a comprehensive test report by combining the initial test results, the multi-physics field loading data and the life prediction results.

[0020] By adopting the above technical solution and using a multimodal sensing device to perform initial detection on the cable ties, the characteristics of industrial CT, high-frequency ultrasonic phased array and fiber Bragg grating sensors can be comprehensively utilized to achieve comprehensive perception of the internal structure, surface defects and stress state of the cable ties, effectively improving the detection accuracy and coverage; by simulating the multi-physical field collaborative loading conditions of the cable ties' service environment, the complex conditions such as temperature, stress, vibration, etc. that the cable ties are subjected to in actual work can be truly restored, thereby obtaining accurate multi-physical field loading data, effectively improving the authenticity of the model and the accuracy of the prediction; by combining multi-physical field loading data and initial detection results to construct a dynamic damage accumulation model, the cable ties can be dynamically tracked. The damage evolution process of the cable tie in a complex service environment can be analyzed to accurately quantify the key damage parameters and improve the scientificity and reliability of the predicted life model. By using the dynamic damage accumulation model and machine learning algorithm to predict the remaining service life of the cable tie, it can effectively explore the relationship between damage characteristics and life in a complex environment, generate accurate life prediction results, and provide data support for maintenance strategies and usage planning. By combining the initial test results, multi-physical field loading data and life prediction results to generate a comprehensive test report, it can fully reflect the health status, potential risks and service life of the cable tie, thereby providing users with a scientific and comprehensive decision-making basis, reducing the risk of sudden failures and improving system reliability.

[0021] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned automobile cable tie detection method are implemented.

[0022] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned automobile cable tie detection method are implemented.

[0023] In summary, the present application includes at least one of the following beneficial technical effects: 1. By using a multi-modal sensing device to perform initial detection on the cable tie, the characteristics of industrial CT, high-frequency ultrasonic phased array and fiber Bragg grating sensor can be comprehensively utilized to achieve comprehensive perception of the internal structure, surface defects and stress state of the cable tie, effectively improving the detection accuracy and coverage; by simulating the multi-physical field collaborative loading conditions of the cable tie service environment, the complex working conditions such as temperature, stress, vibration, etc. that the cable tie is subjected to in actual work can be truly restored, thereby obtaining accurate multi-physical field loading data, effectively improving the authenticity of the model and the accuracy of the prediction; 2. By combining multi-physics field loading data and initial test results to build a dynamic damage accumulation model, the damage evolution process of cable ties in complex service environments can be dynamically tracked, thereby achieving accurate quantification of key damage parameters and improving the scientificity and reliability of the predicted life model; by using the dynamic damage accumulation model and machine learning algorithm to predict the remaining service life of cable ties, the relationship between damage characteristics and life in complex environments can be effectively explored, accurate life prediction results can be generated, and data support can be provided for maintenance strategies and usage planning; by combining initial test results, multi-physics field loading data and life prediction results to generate a comprehensive test report, the health status, potential risks and service life of cable ties can be fully reflected, thereby providing users with a scientific and comprehensive decision-making basis, reducing the risk of sudden failures and improving system reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flow chart of a method for detecting a vehicle cable tie in one embodiment of the present application; Figure 2 This is a flowchart for implementing step S10 in a method for detecting a vehicle cable tie in one embodiment of the present application; Figure 3 is a flowchart for implementing step S20 in a method for detecting a vehicle cable tie in one embodiment of the present application; Figure 4 This is a flowchart for implementing step S21 in a method for detecting a vehicle cable tie in one embodiment of the present application; Figure 5 is a flowchart for implementing step S30 in a method for detecting a vehicle cable tie in one embodiment of the present application; Figure 6 is a flowchart for implementing step S40 in a method for detecting a vehicle cable tie in one embodiment of the present application; Figure 7 is a flowchart for implementing step S50 in a method for detecting a vehicle cable tie in one embodiment of the present application; Figure 8 This is a principle block diagram of an automobile cable tie detection system in one embodiment of the present application; Fig. 9 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The present application is further described in detail below in conjunction with the accompanying drawings.

[0026] In one embodiment, if Figure 1 As shown, the present application discloses a method for detecting a car cable tie, which specifically includes the following steps: S10: Performing an initial detection on the cable tie by means of a multi-modal sensing device to obtain an initial detection result, wherein the multi-modal sensing device includes an industrial CT, a high-frequency ultrasonic phased array, and a fiber Bragg grating sensor.

[0027] Specifically, the cable ties are initially inspected through a multimodal sensing device, and industrial CT is selected to detect the internal structure of the cable ties, including internal defects such as tiny cracks and pores. High-frequency ultrasonic phased arrays are used to finely detect material stratification, separation or other surface and internal micro-defects. Fiber Bragg grating sensors detect environmental parameters such as temperature, strain and pressure in real time, and the detected data are integrated to obtain initial detection results.

[0028] S20: Design a multi-physics collaborative loading condition to simulate the service environment of the cable tie and obtain multi-physics loading data.

[0029] Specifically, multiple physical factors are considered simultaneously during the simulation process, such as mechanical stress, temperature changes, humidity effects, etc., in order to approximate the complex environment in actual use. Different physical fields are applied to the cable tie at the same time to simulate the comprehensive stress and environmental changes that it may withstand during actual service. The response data of the cable tie under the action of different physical fields is obtained through experiments or numerical simulations, including stress-strain distribution, temperature changes, material fatigue, etc., that is, multi-physical field loading data.

[0030] S30: Construct a dynamic damage accumulation model based on multi-physics field loading data and initial detection results.

[0031] Specifically, the initial detection results are combined with multi-physical field loading data, and the response of the cable tie under different working conditions is comprehensively considered. A mathematical or physical model is established to describe how the internal damage of the cable tie gradually accumulates and expands under continuous or repeated loading conditions. A dynamic damage accumulation model is constructed, which not only considers the current damage state, but also predicts the future damage evolution process during continuous use.

[0032] S40: Based on the dynamic damage accumulation model and machine learning algorithm, the remaining service life of the cable tie is predicted and the life prediction result of the cable tie is generated.

[0033] Specifically, historical data and simulation data are used to train machine learning models to enable them to identify key factors that affect life. Based on the current damage status and loading conditions, the model can predict the remaining service life under specific working conditions in the future, provide specific predictions of remaining usage time or number of uses, and identify potential risk factors that may lead to premature failure, providing a basis for maintenance and replacement decisions.

[0034] S50: Generate a comprehensive test report by combining the initial test results, multi-physics field loading data and life prediction results.

[0035] Specifically, all test and analysis results are summarized, including initial status, loading response, damage model prediction and life assessment. The current status and future trends of the cable ties are intuitively displayed through charts, images and text descriptions. Based on the analysis results, suggestions for maintenance, replacement or further testing are made to ensure the safety and reliability of the cable ties during use.

[0036] By adopting the above technical solution and using a multimodal sensing device to perform initial detection on the cable ties, the characteristics of industrial CT, high-frequency ultrasonic phased array and fiber Bragg grating sensors can be comprehensively utilized to achieve comprehensive perception of the internal structure, surface defects and stress state of the cable ties, effectively improving the detection accuracy and coverage; by simulating the multi-physical field collaborative loading conditions of the cable ties' service environment, the complex conditions such as temperature, stress, vibration, etc. that the cable ties are subjected to in actual work can be truly restored, thereby obtaining accurate multi-physical field loading data, effectively improving the authenticity of the model and the accuracy of the prediction; by combining multi-physical field loading data and initial detection results to construct a dynamic damage accumulation model, the cable ties can be dynamically tracked. The damage evolution process of the cable tie in a complex service environment can be analyzed to accurately quantify the key damage parameters and improve the scientificity and reliability of the predicted life model. By using the dynamic damage accumulation model and machine learning algorithm to predict the remaining service life of the cable tie, it can effectively explore the relationship between damage characteristics and life in a complex environment, generate accurate life prediction results, and provide data support for maintenance strategies and usage planning. By combining the initial test results, multi-physical field loading data and life prediction results to generate a comprehensive test report, it can fully reflect the health status, potential risks and service life of the cable tie, thereby providing users with a scientific and comprehensive decision-making basis, reducing the risk of sudden failures and improving system reliability.

[0037] In one embodiment, if Figure 2 As shown, in step S10, the cable tie is initially detected by a multi-modal sensing device to obtain an initial detection result. The multi-modal sensing device includes an industrial CT, a high-frequency ultrasonic phased array and a fiber Bragg grating sensor, specifically including: S11: An initial internal structure model of the cable tie is constructed by using industrial CT scanning to generate an initial three-dimensional internal structure model of the cable tie. The initial three-dimensional internal structure model of the cable tie can distinguish local defects and fiber weaving states of the cable tie.

[0038] Specifically, industrial computed tomography (CT) equipment is used to perform non-destructive inspection on cable ties. Industrial CT can capture the internal structure of cable ties with high resolution. X-rays penetrate the cable ties and scan them multiple times at different angles to generate a large number of two-dimensional slice images. These two-dimensional slice images are processed and reconstructed through professional software to generate an initial three-dimensional internal structure model of the cable ties. The model shows in detail the fiber weaving state and possible local defects inside the cable ties. Image processing algorithms are used to analyze the three-dimensional model to identify and distinguish between normal fiber weaving structures and possible local defects, such as pores, cracks, etc.

[0039] S12: The cable tie is identified using ultrasonic phased array technology to generate initial defect information of the cable tie, including the location and size of microcracks, voids, and delamination.

[0040] Specifically, a high-frequency ultrasonic phased array probe is used to scan the cable tie. Phased array technology controls the time and phase of multiple ultrasonic transmitting and receiving units to achieve high-resolution imaging inside the material, analyze ultrasonic reflection and scattering signals, and identify defects such as microcracks, voids, and delamination in the cable tie. The location and size of these defects are determined through signal processing technology.

[0041] S13: Arrange a fiber Bragg grating sensor to record the initial strain state of the cable tie, and generate the initial strain and temperature change of the cable tie.

[0042] Specifically, fiber Bragg grating (FBG) sensors are arranged at key locations of the cable tie. The FBG sensors can monitor the strain and temperature changes of the material in real time. Through the optical fiber sensing system, the strain and temperature data of the cable tie in the initial state are continuously recorded. These data reflect the initial stress distribution and thermal state of the material under static or dynamic loads. S14: Use multivariate statistical analysis to correlate and classify the initial three-dimensional internal structure model, initial defect information, and initial strain and temperature changes to obtain initial detection results.

[0043] Specifically, the initial three-dimensional internal structure model, initial defect information (including the location and size of microcracks, voids, and delamination), and initial strain and temperature change data are integrated, and multivariate statistical analysis methods, such as principal component analysis (PCA), cluster analysis, and discriminant analysis, are used to perform correlation analysis on the integrated data to identify the correlation and influence between different variables. Based on the analysis results, the health status of the cable ties is classified and evaluated to obtain initial detection results and determine their current structural integrity and potential risk areas.

[0044] In one embodiment, if Figure 3As shown, in step S20, a multi-physics field collaborative loading condition simulating the service environment of the cable tie is designed to obtain multi-physics field loading data, which specifically includes: S21: Apply multi-physics field loading in the simulation environment to simulate the actual working conditions of the cable tie under complex service conditions and generate a dynamic service performance spectrum.

[0045] Specifically, a controllable laboratory environment is established, equipped with multi-physical field loading equipment, such as temperature control systems, mechanical loading devices, humidity control equipment, etc., and the physical parameters of loading are determined according to the actual application scenarios, including temperature, stress, strain, vibration frequency, humidity, etc., to simulate the various working conditions that the cable ties may encounter in actual use. At the same time, multiple physical fields are applied, such as mechanical stress, electromagnetic field, temperature change, etc., to simulate the working state of the cable ties in a complex environment. The loading parameters of the loading process will change with time, and the changes in physical quantities during the loading process will be collected in real time. The collected data will be processed by frequency domain analysis, time domain analysis, etc. to generate a dynamic service performance spectrum, which reflects the response characteristics of the cable ties under the action of different physical fields.

[0046] S22: Use acoustic emission sensors and infrared thermal imaging technology to synchronously monitor the microcrack extension and thermal anomaly areas of the cable tie during loading, and use multi-modal fusion to locate the key position data of the hidden damage of the cable tie.

[0047] Specifically, the acoustic emission sensor is fixed at the key position of the cable tie to detect the acoustic emission signals such as micro-crack extension and fiber breakage inside the material. The acoustic emission signal is collected in real time, and useful information such as signal amplitude and frequency characteristics are extracted through signal processing techniques such as filtering and amplification to determine the type and degree of damage. Infrared thermal imagers are arranged around the cable tie to capture the temperature distribution on the surface of the cable tie in real time. By analyzing the thermal image, the area where the temperature rises or falls abnormally is identified. Multimodal fusion technology is applied to integrate the acoustic emission signal with the thermal imaging data. Data association, feature fusion and other methods are used to improve the accuracy and reliability of damage detection. Through the fused data, the positioning algorithm is used to accurately determine the key position of the hidden damage and obtain the specific position and range of the damage.

[0048] S23: Data cleaning and multi-dimensional noise reduction algorithms are used to process the key position data of the dynamic service performance spectrum and the hidden damage of the cable tie to obtain multi-physical field loading data.

[0049] Specifically, check whether there are missing values ​​in the dynamic service performance spectrum and damage location data, use interpolation, filling and other methods to process, identify and eliminate abnormal data points caused by sensor failure or environmental interference, apply image denoising algorithm to infrared thermal imaging data to improve the clarity and signal-to-noise ratio of thermal images, use dimensionality reduction techniques such as principal component analysis or independent component analysis to extract key features and reduce data redundancy, integrate the processed dynamic service performance spectrum with the key position data of hidden damage, and obtain multi-physical field loading data.

[0050] In one embodiment, if Figure 4 As shown, in step S21, multi-physics field loading is applied in the simulation environment to simulate the actual working conditions of the cable tie under complex service conditions and generate a dynamic service performance spectrum, which specifically includes: S211: Simulate the temperature alternating loading process in a simulation environment, record the thermal expansion and contraction characteristics of the cable tie at different temperatures, and generate the thermal changes of the cable tie.

[0051] Specifically, in a simulation environment, alternating temperature loading is applied to the cable tie, and the thermal expansion and contraction behaviors at different temperatures are recorded. Through thermal characteristic data analysis, a thermal change model of the cable tie is generated to obtain the thermal changes of the cable tie.

[0052] S212: A multi-axis collaborative loading device is used to simulate the stress response of the cable tie under tension, compression and torsion conditions in a simulation environment to generate the mechanical response of the cable tie.

[0053] Specifically, a multi-axis loading device is used to simulate the stress response of the cable tie under tension, compression and torsion conditions, and stress-strain data are collected to form a complete mechanical response spectrum, evaluate the mechanical properties of the cable tie, and finally generate the mechanical response of the cable tie.

[0054] S213: Apply electromagnetic radiation in a simulated environment using an electromagnetic loading device, analyze the influence of electromagnetics on the performance of cable ties, and generate electromagnetic interference information of the cable ties.

[0055] Specifically, electromagnetic radiation is applied using electromagnetic loading equipment, changes in cable tie material properties are recorded, the impact of the electromagnetic environment on the mechanical and thermal properties of the cable tie is analyzed, and electromagnetic interference information is generated.

[0056] S214: Statistically analyze the thermal changes, mechanical responses, and electromagnetic interference information of the cable tie to form a dynamic service performance spectrum.

[0057] Specifically, the thermal changes, mechanical responses and electromagnetic interference information are integrated through statistical analysis methods to generate a dynamic service performance spectrum, providing basic data for evaluating the service performance of cable ties in complex environments.

[0058] In one embodiment, if Figure 5 As shown, in step S30, a dynamic damage accumulation model is constructed based on multi-physics field loading data and initial detection results, specifically including: S31: Input the initial test results and multi-physics field loading data into the finite element model to construct the stress and strain distribution of the cable tie under complex working conditions.

[0059] Specifically, a three-dimensional finite element model of the cable tie is established using finite element analysis (FEA) software, the geometric model is meshed in the finite element software, and the appropriate unit type (such as shell unit or solid unit) and mesh density are selected to balance the calculation accuracy and efficiency. The geometric model is imported according to the initial inspection results to ensure that all known initial defects are included in the model. According to the multi-physics field loading data, the corresponding mechanical loads, temperature fields, etc. are applied, and reasonable boundary conditions, such as fixed ends, free ends, or constrained ends, are set to simulate actual working conditions. Finite element analysis is run to calculate the stress and strain distribution inside the cable tie under complex working conditions, and key stress and strain data are extracted from the finite element analysis results. The results are post-processed, such as identification of stress concentration areas and visualization of strain distribution.

[0060] S32: Combining the stress-strain distribution and the material performance parameters of the cable tie, a dynamic damage accumulation model is constructed using an adaptive neural-fuzzy inference algorithm.

[0061] Specifically, the stress-strain distribution data obtained from the finite element analysis, including the stress and strain values ​​at different positions and time points; the material performance parameters of the cable tie, such as the elastic modulus, yield strength, fatigue life, fracture toughness, etc. of the material, are preliminarily designed based on the adaptive neural-fuzzy inference algorithm according to the material mechanics and damage mechanism. The ANFIS model is trained using historical data or simulation data, and the trained ANFIS model is verified using an independent data set. The real-time or latest stress-strain data is input into the ANFIS model, and the damage accumulation status is dynamically updated to finally construct a dynamic damage accumulation model.

[0062] In one embodiment, if Figure 6 As shown, in step S40, the remaining service life of the cable tie is predicted based on the dynamic damage accumulation model and the machine learning algorithm, and the life prediction result of the cable tie is generated, which specifically includes: S41: Based on the dynamic damage accumulation model, the damage evolution parameters and loading history data of the cable tie are extracted.

[0063] Specifically, key parameters reflecting the damage accumulation process, such as cumulative damage index and damage rate, are extracted from the output of the ANFIS model. Historical data recording various loading conditions experienced by the cable tie during its service are also extracted, including time series information such as temperature changes, mechanical loads, and electromagnetic field strength, that is, the damage evolution parameters and loading history data of the cable tie.

[0064] S42: The nonlinear relationship of damage evolution parameters is processed through deep learning network, and the feature screening and fitting of loading history data are performed in combination with random forest algorithm, and the remaining life prediction results of cable ties are generated by joint modeling.

[0065] Specifically, a deep learning model suitable for processing time series and complex nonlinear relationships, such as long short-term memory networks or convolutional neural networks, is selected. The nonlinear relationship of damage evolution parameters is processed through the deep learning network, and the loading history data is screened and fitted with the random forest algorithm. The feature importance evaluation function of the random forest is used to screen out the loading history features that have the greatest influence on the remaining life prediction. The prediction results of the deep learning model and the random forest model are integrated, and weighted averaging, voting mechanism or stacking are used to combine the advantages of the two methods to improve the accuracy and robustness of the prediction, and finally the remaining life prediction results of the cable tie are generated.

[0066] In one embodiment, if Figure 7 As shown, in step S50, a comprehensive test report is generated by combining the initial test results, multi-physics field loading data and life prediction results, specifically including: S51: The three-dimensional internal structure model, initial defect information and strain state data of the initial detection results are integrated and analyzed with the multi-physics field loading data to generate a damage distribution map.

[0067] Specifically, data fusion technology is used to integrate the three-dimensional internal structure model, initial defect information, strain state data and multi-physical field loading data obtained from the initial inspection. Based on the fused data, finite element analysis and dynamic damage accumulation model are used to evaluate the damage degree of the cable tie under the current working conditions. Visualization tools are used to display the damage assessment results in a graphical form, showing the distribution of damage in various parts of the cable tie. Color coding or other visual identification is used to highlight high-damage areas, which facilitates intuitive understanding of the damage distribution.

[0068] S52: Fit the life prediction result with the parameters in the dynamic damage accumulation model to generate the remaining life curve of the cable tie under different working conditions.

[0069] Specifically, the remaining life prediction results are fitted and analyzed with the relevant parameters in the dynamic damage accumulation model, and the mathematical relationship between the remaining life and the damage parameters is established using statistical methods or regression analysis. Based on the fitting results, the remaining life curve of the cable tie is drawn under different working conditions. The curve can represent the changing trend of the life under different working conditions and help evaluate the life performance under different operating conditions.

[0070] S53: Generate future use risk information based on the damage distribution map and the remaining life curve.

[0071] Specifically, the risk matrix is ​​combined with the damage distribution map and the remaining life curve to evaluate the risks that may be encountered during future use, and generate specific risk indicators, such as failure probability, risk level, etc., to provide a basis for decision-making.

[0072] S54: Through data visualization technology, damage distribution map, remaining life curve and future use risk information are generated into a visual comprehensive report.

[0073] Specifically, through data visualization technology, the damage distribution map, remaining life curve and future use risk information are generated into a visual comprehensive report, the distribution of damage in the structure is displayed in the form of a three-dimensional graph or heat map, the life prediction under different working conditions is displayed in the form of a line graph or curve graph, the risk assessment results are displayed in a risk matrix, bar chart or other forms, and text descriptions, chart displays and conclusion suggestions are provided.

[0074] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0075] In one embodiment, a vehicle cable tie detection system is provided, and the vehicle cable tie detection system corresponds one-to-one to the vehicle cable tie detection method in the above embodiment. Figure 8 As shown, the automotive cable tie detection system includes an initial detection module, a loading module, a model building module, a prediction module and a report generation module. The detailed description of each functional module is as follows: An initial detection module, used to perform initial detection on the cable tie through a multi-modal sensing device to obtain an initial detection result, wherein the multi-modal sensing device includes an industrial CT, a high-frequency ultrasonic phased array, and a fiber Bragg grating sensor; Loading module, used to design multi-physics field collaborative loading conditions to simulate the service environment of cable ties and obtain multi-physics field loading data; The model building module is used to build a dynamic damage accumulation model based on multi-physics field loading data and initial detection results; A prediction module, which is used to predict the remaining service life of the cable tie based on a dynamic damage accumulation model and a machine learning algorithm, and generate a life prediction result of the cable tie; A reporting module that combines initial test results, multiphysics loading data, and life prediction results to generate a comprehensive test report.

[0076] Optionally, the initial detection module includes: The CT submodule is used to construct an initial internal structure model of the cable tie by using industrial CT scanning, and generate an initial three-dimensional internal structure model of the cable tie, which can distinguish local defects and fiber weaving states of the cable tie; The defect recognition submodule is used to identify the cable tie using ultrasonic phased array technology and generate initial defect information of the cable tie, including the location and size of microcracks, voids and delamination; The grating submodule is used to arrange a fiber Bragg grating sensor to record the initial strain state of the cable tie and generate the initial strain and temperature change of the cable tie; The statistical classification submodule is used to use multivariate statistical analysis to correlate and classify the initial three-dimensional internal structure model, initial defect information, and initial strain and temperature changes to obtain initial detection results.

[0077] Optionally, load modules include: The loading condition submodule is used to apply multi-physics field loading in the simulation environment, simulate the actual working conditions of the cable tie under complex service conditions, and generate a dynamic service performance spectrum; The positioning submodule is used to synchronously monitor the micro-crack extension and thermal anomaly areas of the cable tie during loading using acoustic emission sensors and infrared thermal imaging technology, and to obtain the key position data of the hidden damage of the cable tie by combining multi-modal fusion method; The data processing submodule is used to process the key position data of the dynamic service performance spectrum and the hidden damage of the cable tie by using data cleaning and multi-dimensional noise reduction algorithms to obtain multi-physical field loading data.

[0078] Optionally, the loading condition submodule includes: The temperature control unit is used to simulate the temperature alternating loading process in a simulated environment, record the thermal expansion and contraction characteristics of the cable tie at different temperatures, and generate the thermal changes of the cable tie; A force adjustment unit, used to simulate the stress response of the cable tie under tension, compression and torsion conditions in a simulation environment using a multi-axis coordinated loading device, and generate a mechanical response of the cable tie; A magnetic modulation unit is used to apply electromagnetic radiation in a simulated environment using an electromagnetic loading device, analyze the influence of electromagnetics on the performance of cable ties, and generate electromagnetic interference information of the cable ties; The statistical unit is used to collect statistics on the thermal changes, mechanical responses and electromagnetic interference information of the cable tie to form a dynamic service performance spectrum.

[0079] Optionally, build model modules including: The finite element analysis submodule is used to input the initial test results and multi-physics field loading data into the finite element model to construct the stress and strain distribution of the cable tie under complex working conditions; A submodule is constructed to combine the stress-strain distribution and the material performance parameters of the cable tie to construct a dynamic damage accumulation model based on an adaptive neuro-fuzzy inference algorithm.

[0080] Optionally, the prediction module includes: The data extraction submodule is used to extract the damage evolution parameters and loading history data of the cable tie based on the dynamic damage accumulation model; The fitting submodule is used to process the nonlinear relationship of damage evolution parameters through a deep learning network, and combines the random forest algorithm to perform feature screening and fitting on the loading history data, and jointly model to generate the remaining life prediction results of the cable tie.

[0081] Optionally, report generation modules include: A distribution map submodule is obtained, which is used to fuse and analyze the three-dimensional internal structure model, initial defect information and strain state data of the initial detection results with the multi-physics field loading data to generate a damage distribution map; The curve generation submodule is used to fit the life prediction results with the parameters in the dynamic damage accumulation model to generate the remaining life curve of the cable tie under different working conditions; A future risk submodule is obtained, which is used to generate future use risk information based on the damage distribution map and the remaining life curve; The data visualization submodule is used to generate a visual comprehensive report of the damage distribution map, remaining life curve and future use risk information through data visualization technology.

[0082] The specific definition of an automobile cable tie detection system can be found in the definition of an automobile cable tie detection method mentioned above, which will not be repeated here. Each module in the above-mentioned automobile cable tie detection system can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0083] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig. 9As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for detecting an automobile cable tie is implemented.

[0084] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Performing initial detection on the cable tie by a multi-modal sensing device to obtain initial detection results, the multi-modal sensing device including industrial CT, high-frequency ultrasonic phased array and fiber Bragg grating sensor; Design multi-physics collaborative loading conditions to simulate the service environment of cable ties and obtain multi-physics loading data; Construct a dynamic damage accumulation model based on multi-physics loading data and initial test results; Based on the dynamic damage accumulation model and machine learning algorithm, the remaining service life of the cable tie is predicted and the life prediction result of the cable tie is generated; Combine initial inspection results, multiphysics loading data, and life prediction results to generate a comprehensive inspection report.

[0085] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Performing initial detection on the cable tie by a multi-modal sensing device to obtain initial detection results, the multi-modal sensing device including industrial CT, high-frequency ultrasonic phased array and fiber Bragg grating sensor; Design multi-physics collaborative loading conditions to simulate the service environment of cable ties and obtain multi-physics loading data; Construct a dynamic damage accumulation model based on multi-physics loading data and initial test results; Based on the dynamic damage accumulation model and machine learning algorithm, the remaining service life of the cable tie is predicted and the life prediction result of the cable tie is generated; Combine initial inspection results, multiphysics loading data, and life prediction results to generate a comprehensive inspection report.

[0086] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0087] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0088] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for detecting automobile cable ties, characterized in that: The automotive cable tie detection method comprises: Performing an initial detection on the cable tie by a multi-modal sensing device to obtain an initial detection result, wherein the multi-modal sensing device includes an industrial CT, a high-frequency ultrasonic phased array, and a fiber Bragg grating sensor; Design a multi-physics field collaborative loading condition that simulates the service environment of the cable tie to obtain multi-physics field loading data; Constructing a dynamic damage accumulation model based on the multi-physics field loading data and the initial detection results; Based on the dynamic damage accumulation model and the machine learning algorithm, predict the remaining service life of the cable tie and generate a life prediction result of the cable tie; A comprehensive test report is generated by combining the initial test results, the multi-physics field loading data and the life prediction results.

2. The method for detecting a car cable tie according to claim 1, characterized in that: The initial detection of the cable tie by the multi-modal sensing device to obtain the initial detection result includes: Using the industrial CT scan to construct an initial internal structure model of the cable tie, generating an initial three-dimensional internal structure model of the cable tie, wherein the initial three-dimensional internal structure model of the cable tie can distinguish local defects and fiber weaving states of the cable tie; The cable tie is identified by using ultrasonic phased array technology to generate initial defect information of the cable tie, wherein the initial defect information includes the location and size of microcracks, voids and delamination; Arranging the fiber Bragg grating sensor to record the initial strain state of the cable tie and generate the initial strain and temperature change of the cable tie; The initial three-dimensional internal structure model, initial defect information, and initial strain and temperature changes are correlated and analyzed and classified using a multivariate statistical analysis method to obtain the initial detection result.

3. The automotive cable tie detection method according to claim 1, characterized in that: The design simulates the multi-physics field collaborative loading condition of the cable tie service environment, and the multi-physics field loading data obtained includes: Applying multi-physics field loading in a simulation environment to simulate the actual working conditions of the cable tie under complex service conditions and generate a dynamic service performance spectrum; Acoustic emission sensors and infrared thermal imaging technology are used to synchronously monitor the microcrack extension and thermal anomaly areas of the cable tie during loading, and multi-modal fusion is used to locate and obtain key position data of the hidden damage of the cable tie; The dynamic service performance spectrum and the key position data of the hidden damage of the cable tie are processed by using data cleaning and multi-dimensional noise reduction algorithms to obtain the multi-physical field loading data.

4. The method for detecting a car cable tie according to claim 3, characterized in that: Applying multi-physics field loading in a simulation environment to simulate the actual working condition of the cable tie under complex service conditions and generating a dynamic service performance spectrum includes: Simulating the temperature alternating loading process in the simulation environment, recording the thermal expansion and contraction characteristics of the cable tie at different temperatures, and generating thermal changes of the cable tie; Using a multi-axis collaborative loading device to simulate the stress response of the cable tie under tension, compression and torsion conditions in the simulation environment to generate a mechanical response of the cable tie; Applying electromagnetic radiation in the simulation environment by using an electromagnetic loading device, analyzing the influence of electromagnetic radiation on the performance of the cable tie material, and generating electromagnetic interference information of the cable tie; The thermal change, mechanical response and electromagnetic interference information of the cable tie are statistically analyzed to form the dynamic service performance spectrum.

5. The method for detecting a car cable tie according to claim 1, characterized in that: The constructing of a dynamic damage accumulation model based on the multi-physics field loading data and the initial detection results comprises: Inputting the initial detection results and the multi-physics field loading data into a finite element model to construct the stress-strain distribution of the cable tie under complex working conditions; The dynamic damage accumulation model is constructed by combining the stress-strain distribution and the material performance parameters of the cable tie using an adaptive neural fuzzy inference algorithm.

6. The method for detecting a car cable tie according to claim 1, characterized in that: The predicting the remaining service life of the cable tie based on the dynamic damage accumulation model and the machine learning algorithm, and generating the life prediction result of the cable tie includes: Based on the dynamic damage accumulation model, extracting damage evolution parameters and loading history data of the cable tie; The nonlinear relationship of the damage evolution parameters is processed through a deep learning network, and the loading history data is featured and fitted in combination with a random forest algorithm, and a joint model is used to generate a prediction result of the remaining life of the cable tie.

7. The method for detecting a car cable tie according to claim 1, characterized in that: The generating of a comprehensive test report by combining the initial test results, the multi-physics field loading data and the life prediction results comprises: The three-dimensional internal structure model, initial defect information and strain state data of the initial detection result are integrated and analyzed with the multi-physics field loading data to generate a damage distribution map; Fitting the life prediction result with the parameters in the dynamic damage accumulation model to generate the remaining life curve of the cable tie under different working conditions; generating future use risk information according to the damage distribution map and the remaining life curve; By using data visualization technology, the damage distribution map, the remaining life curve and the future use risk information are generated into a visual comprehensive report.

8. An automotive cable tie detection system, characterized in that: The automotive cable tie detection system comprises: An initial detection module, used to perform initial detection on the cable tie through a multi-modal sensing device to obtain an initial detection result, wherein the multi-modal sensing device includes an industrial CT, a high-frequency ultrasonic phased array, and a fiber Bragg grating sensor; A loading module, used to design a multi-physics field collaborative loading condition simulating the service environment of the cable tie to obtain multi-physics field loading data; A model building module is used to build a dynamic damage accumulation model based on the multi-physics field loading data and the initial detection results; A prediction module, used for predicting the remaining service life of the cable tie based on the dynamic damage accumulation model and the machine learning algorithm, and generating a life prediction result of the cable tie; A report generation module is used to generate a comprehensive test report by combining the initial test results, the multi-physics field loading data and the life prediction results.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the vehicle cable tie detection method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the vehicle cable tie detection method according to any one of claims 1 to 7 are implemented.

Images