Self-adaptive safety monitoring method, device and equipment for deformation of trailer body

Abstract

The invention discloses a trailer body deformation self-adaption safety monitoring method, device and equipment, and relates to the technical field of trailer body deformation monitoring, and the method comprises the steps: determining M risk deformation points of a first trailer; collaborative early warning analysis is carried out on the vehicle body deformation threshold value, the load and the road condition, and a collaborative mapping network is generated; executing compensation analysis under the influence of the vehicle body rigidity, and generating a compensation channel connected with the collaborative mapping network; analyzing the deformation characteristic values to generate M deformation characteristic values; and inputting the M deformation characteristic values into a collaborative mapping network for early warning trigger analysis, and generating first early warning information. According to the invention, the technical problem in the prior art that the deformation state of the trailer body cannot be accurately judged by using a fixed threshold value due to the highly dynamic change of the structure stress and deformation under different loads and working conditions is solved, and the dynamic self-adaptive safety monitoring of the deformation of the trailer body is realized; and the technical effect of deformation judgment accuracy under different loads and working conditions is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle body deformation monitoring, and particularly relates to a method, device and equipment for self-adaptive safety monitoring of trailer body deformation. Background Art

[0002] During the actual use of trailers, the loads they bear fluctuate greatly, and there are various situations such as no-load, full-load, and partial-load. At the same time, the road conditions are also complex and changeable, including potholes, highways, curves, etc. This makes the forces and deformations on the trailer structure show highly dynamic changes. In this case, the same deformation value may represent normal or abnormal states under different loads and working conditions, and the traditional technology using a fixed threshold method cannot accurately judge the body deformation state and is difficult to meet the actual monitoring requirements.

[0003] The prior art has the technical problem that due to the highly dynamic changes in the structural forces and deformations of trailers under different loads and working conditions, it is impossible to accurately judge the body deformation state using a fixed threshold. Summary of the Invention

[0004] This application provides a method, device and equipment for self-adaptive safety monitoring of trailer body deformation, which is used to solve the technical problem in the prior art that due to the highly dynamic changes in the structural forces and deformations of trailers under different loads and working conditions, it is impossible to accurately judge the body deformation state using a fixed threshold.

[0005] In view of the above problems, this application provides a method, device and equipment for self-adaptive safety monitoring of trailer body deformation.

[0006] In the first aspect of this application, a method for self-adaptive safety monitoring of trailer body deformation is provided. The method includes: Determine M risk deformation points of the first trailer; perform collaborative warning analysis on the body deformation threshold, load, and road conditions based on the M risk deformation points to generate a collaborative mapping network, including single-layer mapping of any deformation point and multi-layer collaboration of multiple deformation points; perform compensation analysis on the deformation threshold in the collaborative mapping network under the influence of body stiffness to generate a compensation channel connected to the collaborative mapping network; collect deformation data through the intelligent sensing system at the M risk deformation points, analyze the deformation characteristic values to generate M deformation characteristic values; perform optimization of the collaborative mapping network through the compensation channel, and then input the M deformation characteristic values into the collaborative mapping network for warning trigger analysis to generate the first warning information.

[0007] In the second aspect of this application, a device for self-adaptive safety monitoring of trailer body deformation is provided. The device includes: A risk deformation point determination module for determining M risk deformation points of the first trailer; a collaborative mapping network generation module for performing collaborative warning analysis of vehicle body deformation thresholds, loads, and road conditions based on the M risk deformation points to generate a collaborative mapping network, including single-layer mapping of any deformation point and multi-layer collaboration of multiple deformation points; a compensation channel generation module for performing compensation analysis on the deformation thresholds in the collaborative mapping network under the influence of vehicle body stiffness to generate a compensation channel connected to the collaborative mapping network; a deformation eigenvalue generation module for collecting deformation data through an intelligent sensing system at the M risk deformation points, analyzing deformation eigenvalues, and generating M deformation eigenvalues; a first warning information generation module for optimizing the collaborative mapping network through the compensation channel, then inputting the M deformation eigenvalues into the collaborative mapping network for warning trigger analysis, and generating the first warning information.

[0008] In a third aspect of the present application, an electronic device is provided, which includes: a processor; a memory for storing executable instructions of the processor; wherein, the processor is used to execute a method for self-adaptive safety monitoring of trailer body deformation provided by the present application.

[0009] One or more technical solutions provided in the present application have at least the following technical effects or advantages: Determine M risk deformation points of the first trailer; perform collaborative warning analysis of vehicle body deformation thresholds, loads, and road conditions based on the M risk deformation points to generate a collaborative mapping network; perform compensation analysis on the deformation thresholds in the collaborative mapping network under the influence of vehicle body stiffness to generate a compensation channel connected to the collaborative mapping network; collect deformation data, analyze deformation eigenvalues, and generate M deformation eigenvalues; optimize the collaborative mapping network through the compensation channel, then input the M deformation eigenvalues into the collaborative mapping network for warning trigger analysis, and generate the first warning information. It achieves the technical effect of realizing dynamic self-adaptive safety monitoring of trailer body deformation and improving the accuracy of deformation judgment under different loads and working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0011] Figure 1 It is a schematic flow chart of a method for self-adaptive safety monitoring of trailer body deformation provided by an embodiment of the present application.

[0012] Figure 2Schematic structural diagram of a self - adaptive safety monitoring device for trailer body deformation provided by an embodiment of the present application.

[0013] Figure 3 Schematic structural diagram of an electronic device provided by the present application.

[0014] Explanation of reference numerals: Risk deformation point determination module 10, collaborative mapping network generation module 20, compensation channel generation module 30, deformation eigenvalue generation module 40, first warning information generation module 50, processor 21, memory 22, input device 23, output device 24. Detailed implementation manners

[0015] The present application provides a method, device and equipment for self - adaptive safety monitoring of trailer body deformation, which is used to solve the technical problem that in the prior art, due to the highly dynamic changes in the structure stress and deformation of trailers under different loads and working conditions, it is impossible to accurately judge the body deformation state using a fixed threshold.

[0016] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0017] Embodiment 1, as Figure 1 shown, the present application provides a method for self - adaptive safety monitoring of trailer body deformation, and the method includes: Step S100: Determine M risk deformation points of the first trailer.

[0018] Specifically, when determining the M risk deformation points of the first trailer, first use ANSYS finite element analysis software to perform multi - condition simulation on the trailer body, simulate the stress distribution of the trailer under different load conditions such as no - load, full - load, and partial - load, and road conditions such as potholes, high - speed, and curves. Combine historical fault data to identify the key parts of the body structure where stress is concentrated and deformation is likely to occur; then perform modal analysis on the trailer body structure to determine the areas with large vibration responses. Based on the above analysis results, finally determine the M risk deformation points of the first trailer body, such as the connection parts of the frame longitudinal beams, suspension support points, body hinge joints, etc., which are prone to structural instability and irreversible deformation.

[0019] Step S200: Based on the M risk deformation points, perform collaborative warning analysis on the body deformation threshold, load, and road conditions to generate a collaborative mapping network, including single - layer mapping of any deformation point and multi - layer collaboration of multiple deformation points.

[0020] Specifically, when performing collaborative warning analysis of vehicle body deformation thresholds, loads, and road conditions based on M risk deformation points and generating a collaborative mapping network, first determine the vehicle body deformation threshold, load distribution, and road condition excitation as collaborative analysis elements. By constructing a twin simulation platform for trailer-load-road conditions, using the load-road condition database formed by the preset transportation route and load range (including typical working condition combinations such as offloading ≥ 15% and road surface unevenness above grade C), perform single-point simulation for each risk deformation point to determine the mapping relationship between the critical yield threshold and load-road conditions, and construct an M-layer single-layer mapping network; at the same time, perform multi-point deformation coupling analysis on the risk deformation points, form N groups of deformation points with a coupling safety influence degree > preset value, perform multi-point coupling boundary deformation simulation through the twin platform to obtain N groups of multi-point critical yield threshold-load-road condition mapping relationships, and then construct a multi-layer collaborative mapping network. Finally, fuse the single-layer and multi-layer networks to generate a collaborative mapping network, realizing the collaborative analysis of deformation thresholds under single-point and multi-point working conditions.

[0021] Step S300: Perform compensation analysis on the deformation threshold in the collaborative mapping network under the influence of vehicle body stiffness, and generate a compensation channel connected to the collaborative mapping network.

[0022] Specifically, when performing compensation analysis on the deformation threshold in the collaborative mapping network under the influence of vehicle body stiffness and generating a compensation channel, first establish a vehicle body stiffness attenuation model, consider the influence of factors such as material aging (elastic modulus decreases by 2% per year) and structural damage (such as local stiffness reduction of 10% - 30% due to weld cracks) on vehicle body stiffness, and obtain the change amount of the critical yield threshold of each risk deformation point under different stiffness attenuation degrees through finite element simulation; then construct a stiffness-threshold compensation matrix, define the mapping relationship between the stiffness attenuation rate and the deformation threshold correction coefficient (such as when the stiffness drops by 15%, the threshold correction coefficient is 1.2); finally, generate a compensation channel connected to the collaborative mapping network, and this channel dynamically adjusts the deformation threshold in the collaborative mapping network based on the real-time collected vehicle body stiffness monitoring data (such as measuring the elastic deformation amount of key parts through strain gauges), realizing the compensation for the influence of vehicle body stiffness and ensuring the accuracy of warning analysis.

[0023] Step S400: Collect deformation data through the intelligent sensing system on the M risk deformation points, analyze the deformation characteristic values, and generate M deformation characteristic values.

[0024] Specifically, when collecting deformation data through the intelligent sensing system at M risk deformation points and analyzing to generate M deformation characteristic values, first use the triaxial acceleration sensors (sampling frequency 1000 Hz), laser displacement sensors (accuracy 0.01 mm), and strain gauges (sensitivity coefficient 2.0) arranged at each risk deformation point to collect deformation monitoring data such as displacement, acceleration, and strain in real time, forming M deformation monitoring data sets containing time series; then use wavelet transform to denoise the original data, extract frequency domain features through Fourier transform, combine with principal component analysis for dimensionality reduction, identify key characteristic parameters such as deformation amount, deformation rate, main vibration frequency, and strain amplitude that can characterize the body deformation state, and finally generate M deformation characteristic values to provide data support for subsequent early warning analysis.

[0025] Step S500: Optimize the collaborative mapping network through the compensation channel, and then input the M deformation characteristic values into the collaborative mapping network for early warning trigger analysis to generate the first early warning information.

[0026] Specifically, when optimizing the collaborative mapping network through the compensation channel and inputting the deformation characteristic values for early warning trigger analysis to generate the first early warning information, first, based on the body stiffness attenuation model and the stiffness-threshold compensation matrix, use the real-time collected body stiffness monitoring data (such as the elastic deformation measured by the strain gauge at the key part), and dynamically adjust the deformation threshold in the collaborative mapping network through the compensation channel to correct the threshold deviation caused by the change in body stiffness; then input the M deformation characteristic values (including key parameters such as deformation amount and deformation rate) into the optimized collaborative mapping network, combine with the current load distribution (such as the degree of uneven load) and road condition data (such as the road surface unevenness level), and perform joint reasoning through the single-layer mapping network and the multi-layer collaborative mapping network to calculate the structural instability probability and irreversible deformation risk value of each risk deformation point; finally, according to the preset risk level determination standard (such as high risk corresponding to instability probability > 30% and deformation amount exceeding the critical threshold by 120%), generate the first early warning information including the warning level, the position of the risk deformation point, the load road condition impact factor, and the coping suggestions (such as deceleration, adjusting the load distribution), realizing the adaptive safety monitoring and early warning of the trailer body deformation.

[0027] In a possible implementation manner, step S200 further includes: Step S210: Determine the collaborative analysis elements, including the body deformation threshold, load distribution, and road condition excitation.

[0028] Step S220: For the M risk deformation points, based on the collaborative analysis elements, perform boundary deformation threshold analysis of structural instability and irreversible deformation in the single-point mode, and construct M layers of single-layer mapping networks.

[0029] Step S230: For the M risk deformation points, based on the collaborative analysis elements, perform boundary deformation threshold analysis of structural instability and irreversible deformation in the multi-point collaborative mode, and construct a multi-layer collaborative mapping network.

[0030] Step S240: Generate the collaborative mapping network with the M single-layer mapping networks and the multi-layer collaborative mapping network.

[0031] Specifically, when determining the collaborative analysis elements, considering the dynamic influencing factors in the actual operation of the trailer, the body deformation threshold, load distribution, and road condition excitation are taken as analysis elements. Among them, the body deformation threshold refers to the critical deformation amount that causes the structural instability or irreversible deformation of the trailer, which is used to define the safety boundary; the load distribution covers different load states such as no-load, full-load, and partial load (such as load deviation ≥ 15%); the road condition excitation includes typical road conditions such as potholed roads (roughness grade above C level), high-speed driving (vehicle speed > 80 km / h), and curves (radius of curvature < 200 m). By clarifying these three types of elements, a multi-dimensional data basis is laid for subsequent collaborative early warning analysis.

[0032] When performing boundary deformation threshold analysis in the single-point mode and constructing the M-layer single-layer mapping network for the M risk deformation points based on the collaborative analysis elements, first build a twin simulation platform including a three-dimensional model of the trailer, a load simulation module, and a road condition simulation module. This platform integrates multiple groups of load-road condition data (each group of data includes parameters such as partial load degree and road surface roughness grade) generated by a preset transportation route (such as including mountain curves, plain highways, etc.) and a load range (from no-load to 1.2 times the rated load); then input different load-road condition combinations to each risk deformation point in turn for single-point simulation, extract the stress-strain curve at the time of structural instability through finite element analysis, determine the critical deformation threshold that causes material yield, and form a ternary mapping relationship of critical yield threshold-load-road condition; finally, encapsulate the mapping relationships corresponding to the M risk deformation points into independent single-layer mapping networks respectively, and each network stores the boundary deformation threshold data of the corresponding point under different working conditions, providing a quantitative basis for single-point deformation early warning.

[0033] For M risk deformation points, when performing boundary deformation threshold analysis in the multi-point collaborative mode and constructing a multi-layer collaborative mapping network based on collaborative analysis elements, first calculate the deformation coupling coefficients between each pair of risk deformation points through finite element simulation. Divide the deformation points with a coupling safety influence degree greater than a preset threshold (such as 0.5) into N groups (N is a positive integer less than M). For example, divide the longitudinal beam of the vehicle frame and the suspension support point into one group. Then call the twin simulation platform containing the load-road condition database, apply multiple sets of typical working condition combinations (such as full load, potholed road surface, 15% off-load, cornering) to each group of deformation points, analyze the deformation transfer path when the structure becomes unstable through multi-point coupling simulation, and determine the critical yield threshold of this group of deformation points under collaborative action, forming a mapping relationship of multi-point critical yield threshold-load-road condition. Finally, encapsulate the N groups of mapping relationships into a multi-layer collaborative mapping network according to the coupling level. This network can characterize the boundary deformation characteristics of different groups of deformation points under multi-factor coupling, providing a model support for multi-point collaborative early warning.

[0034] When generating a collaborative mapping network from M single-layer mapping networks and a multi-layer collaborative mapping network, first establish a two-layer network fusion architecture. Take the M independent single-layer mapping networks as the underlying nodes, corresponding to the single-point boundary threshold data of each risk deformation point respectively. Then take the N groups of multi-layer collaborative mapping networks as the upper-layer nodes, characterizing the coupling boundary characteristics of multiple groups of deformation points. Then construct a single-point - multi-point collaborative association mechanism through topological connection, and set the coupling weight coefficient (determined based on the physical distance and mechanical correlation degree between deformation points), so that the upper-layer network can call the single-point data of the underlying nodes for collaborative calculation. The finally generated collaborative mapping network can process both single-point deformation data and multi-point coupled deformation data at the same time. Through the linkage analysis of the underlying and upper-layer networks, it realizes the collaborative early warning analysis of the deformation of the trailer body under single and multi working conditions, providing a comprehensive model support for the input analysis of subsequent deformation characteristic values.

[0035] In a possible implementation manner, step S220 further includes: Step S221: Construct a twin simulation platform for the trailer, the load on the trailer, and the road conditions.

[0036] Step S222: Based on the twin simulation platform, perform single-point simulation of the load-road condition database for each of the M risk deformation points, and determine the mapping relationship of the critical yield threshold-load-road condition that causes structural instability and irreversible deformation.

[0037] Step S223: Construct the M-layer single-layer mapping network with the mapping relationship of the critical yield threshold-load-road condition.

[0038] Specifically, when building a twin simulation platform for trailers, trailer loads, and road conditions, first use SolidWorks to establish a three-dimensional solid model of the trailer body, accurately restoring the geometric parameters and material properties of key structures such as the frame, suspension, and axle (such as the elastic modulus of Q345 steel is 210 GPa and the Poisson's ratio is 0.3); then integrate a load simulation module in ANSYS Workbench, which can simulate different load conditions such as no-load (0 load), full-load (rated load), and off-load (load distribution deviation ≥ 15%), and supports customizing the load application position and distribution form; at the same time, build a road condition simulation module, based on the ISO8608 road surface unevenness standard, generate road condition excitation models such as inertial loads corresponding to potholed roads above grade C (power spectral density index 2), high speed (vehicle speed > 80 km / h), and centrifugal force on curves (radius of curvature < 200 m); finally, couple the three-dimensional model, load module, and road condition module, and access the load-road condition database generated by the preset transportation route (such as including terrains such as mountains, plains, and hills) and load range (0 to 1.2 times the rated load) to form a twin simulation platform that can reproduce the actual operating conditions of the trailer, providing a simulation basis for subsequent single-point and multi-point deformation threshold analysis.

[0039] When performing single-point simulations of the load-road condition database for M risk deformation points based on the twin simulation platform and determining the critical yield threshold-load-road condition mapping relationship, first retrieve multiple sets of typical working condition data from the load-road condition database, including load states such as no-load, full-load, and off-load (load deviation ≥ 15%), and combinations of road conditions such as potholed roads (unevenness grade above C), high speed (vehicle speed > 80 km / h), and curves (radius of curvature < 200 m); then input each set of working condition data into the twin simulation platform in turn, apply the corresponding load and road condition excitation to each risk deformation point separately, and calculate the stress distribution and deformation amount of the point under different working conditions through finite element analysis; then track the critical deformation state when the material reaches the yield strength, record the deformation threshold, load parameters, and road condition parameters at this time, and form a triple mapping relationship (such as when the critical yield threshold is 1.2 mm, the corresponding load is 110% of the rated load and the road condition is a C-grade potholed road); finally, structurally store the mapping relationships of the M risk deformation points under all working conditions to provide quantitative data support for building a single-layer mapping network.

[0040] When constructing an M - layer single - layer mapping network based on the critical yield threshold - load - road condition mapping relationship, first, the critical yield threshold - load - road condition mapping relationships of each of the M risk deformation points are structured. Each risk deformation point corresponds to a set of critical yield threshold data under different load conditions (such as no - load, full - load, 15% partial load) and road conditions (such as C - level potholed road surface, driving at 80 km / h on the highway). Then, using a neural network architecture, with load parameters (such as load magnitude, distribution deviation) and road condition parameters (such as road surface unevenness level, driving speed) as input - layer nodes, and the critical yield threshold as the output - layer node, the number of hidden - layer nodes is set according to the data complexity (such as 3 hidden layers), and an independent single - layer mapping network for each risk deformation point is constructed. Finally, the M single - layer mapping networks are hierarchically divided according to the position numbers of the risk deformation points to form an M - layer single - layer mapping network. Each layer of the network can independently receive real - time load and road condition data and output the critical yield threshold of the corresponding risk deformation point, providing a dynamic threshold judgment basis for single - point deformation warning.

[0041] In a possible implementation manner, step S230 further includes: Step S231: Conduct multi - point deformation coupling analysis on the M risk deformation points to construct N groups of deformation points whose coupling safety influence degree is greater than a preset influence degree, where N is a positive integer less than M.

[0042] Step S232: Invoke the twin simulation platform, and use the load - road condition database to conduct multi - point coupling boundary deformation simulation of structural instability and irreversible deformation on the N groups of deformation points to determine N groups of multi - point critical yield threshold - load - road condition mapping relationships.

[0043] Step S233: Construct the multi - layer collaborative mapping network based on the N groups of multi - point critical yield threshold - load - road condition mapping relationships.

[0044] Specifically, when conducting multi - point deformation coupling analysis on the M risk deformation points and constructing N groups of deformation points, first use finite - element software to calculate the deformation transfer matrix of each risk deformation point under typical load conditions (such as 15% partial load of full - load) to obtain the deformation influence coefficient between points. At the same time, consider the attenuation effect of physical distance on the coupling effect (the distance weight is calculated as 1 / d², where d is the distance between two points), and calculate the coupling safety influence degree through weighted calculation of the two. Then set a preset threshold for the coupling safety influence degree (such as 0.4), and divide the deformation points with an influence degree greater than this threshold into a group. For example, the connection point of the frame longitudinal beam and the adjacent suspension support point form a group due to high - stress transfer coupling. Finally, N groups (N is a positive integer less than M) of deformation point groups with strong mechanical correlations are constructed, laying a foundation for subsequent multi - point collaborative deformation analysis.

[0045] When calling the twin simulation platform and using the load-road condition database to conduct multi-point coupled boundary deformation simulation on N sets of deformation points to determine the mapping relationship, first retrieve multiple sets of load-road condition data from the load-road condition database that include typical working condition combinations such as offloading ≥ 15% and road surface unevenness above grade C. Each set of data corresponds to different load distributions (such as no-load, full-load, offloading) and road condition excitations (such as potholed road surface, highway, curve); then input each set of data into the constructed trailer-load-road condition twin simulation platform, apply the corresponding loads and road condition excitations to the N sets of deformation points simultaneously, and analyze the deformation transfer path of the structure during the force-bearing process through multi-physical field coupled simulation; next, monitor the co-deformation state of each set of deformation points in real time, track the critical conditions when plastic deformation of the material or structural instability occurs, and record the comprehensive deformation amount of the N sets of deformation points at this time (i.e., the multi-point critical yield threshold) and the corresponding load parameters and road condition parameters, forming, for example, an N-set multi-point critical yield threshold-load-road condition ternary mapping relationship where the multi-point critical yield threshold is 2.3 mm, the corresponding load is 120% of the rated load, and the road condition is a curve with a curvature of 180 m, providing data support for constructing a multi-layer collaborative mapping network.

[0046] When constructing a multi-layer collaborative mapping network based on the N-set multi-point critical yield threshold-load-road condition mapping relationship, first perform structured processing on the multi-point critical yield threshold of each set of deformation points and the corresponding load and road condition parameters to form a data set containing coupled deformation characteristics; then adopt a graph neural network architecture, use the N sets of deformation points as network nodes, and use the coupled safety influence degree between deformation point groups as edge weights to construct a multi-level topological structure, where the input layer receives parameters such as load distribution (such as offloading rate) and road condition excitation (such as road surface unevenness grade), the hidden layer calculates the deformation coupling effect between nodes through a message passing mechanism, and the output layer generates the multi-point critical yield threshold of the corresponding group; finally, encapsulate the N-set mapping relationships into different network layers according to the coupling levels (such as primary coupling group, secondary coupling group) to form a multi-layer collaborative mapping network that can characterize the collaborative effect of multiple deformation points. This network can dynamically calculate the critical yield threshold of multiple deformation point groups based on real-time load-road condition data, providing model support for multi-point collaborative early warning of trailer body deformation.

[0047] In a possible implementation manner, step S222 further includes: Step S2221: The load-road condition database includes multiple sets of load-road condition data, and each set of load-road condition data includes a combination of load and road condition obtained based on the preset transportation route and preset load range of the first trailer.

[0048] Specifically, the multiple sets of load-road condition data included in the load-road condition database are combinations of load and road conditions generated based on the preset transportation route and preset load range of the first trailer. The preset transportation route covers typical road condition scenarios such as mountain curves (radius of curvature < 200 m), plain highways (vehicle speed > 80 km / h), and hilly potholes (road surface unevenness above grade C). The road condition feature library is constructed by collecting the actual road condition parameters (such as road surface power spectral density, curve curvature) of each section on the route. The preset load range covers no-load (0 load) to 1.2 times the rated load, including the offloading condition (load distribution deviation ≥ 15%). The load distribution parameters are determined by simulating different cargo loading schemes. The road condition features of the preset transportation route are combined with the load states of the preset load range to form multiple sets of load-road condition data such as "rated load, 15% offloading, curve with a curvature of 150 m" and "0.8 times the rated load, road surface unevenness of grade D". Each set of data includes parameters such as load magnitude, offloading rate, road surface grade, and driving speed, providing input data close to the actual operating conditions for the twin simulation platform.

[0049] In a possible implementation manner, step S400 further includes: Step S410: Read the M deformation monitoring data sets collected by the intelligent sensing system, including displacement, acceleration, and strain data.

[0050] Step S420: Identify deformation feature values based on the M deformation monitoring data sets to generate the M deformation feature values.

[0051] Specifically, when reading the M deformation monitoring data sets collected by the intelligent sensing system, the original data including displacement, acceleration, and strain are obtained in real time through the sensor array arranged at M risk deformation points of the first trailer. Among them, the laser displacement sensor (accuracy 0.01 mm) continuously collects the linear displacement changes of each point relative to the reference position. The three-axis acceleration sensor (sampling frequency 1000 Hz) records the vibration acceleration signals in the three-dimensional space. The resistance strain gauge (sensitivity coefficient 2.0) monitors the strain state of the structure surface. These data form M independent deformation monitoring data sets according to the time series, providing the original information for subsequent feature analysis.

[0052] When identifying deformation characteristic values using M deformation monitoring data sets, first perform noise reduction processing on the original data using wavelet transform to eliminate high-frequency interference and baseline drift; then convert the time-domain signal into frequency-domain characteristics through Fourier transform, and extract frequency characteristic parameters such as the main vibration frequency and multiple-frequency components of each point; at the same time, calculate the time-varying gradient of the displacement data to obtain the deformation rate, and obtain the strain amplitude through the peak value statistics of the strain data; finally, use principal component analysis (PCA) to reduce the dimension of multi-dimensional characteristics, screen out key indicators such as deformation amount, deformation rate, main vibration frequency, and strain amplitude that can best represent the body deformation state, generate deformation characteristic values corresponding to each risk deformation point, and provide quantitative input for the early warning analysis of the collaborative mapping network.

[0053] In a possible implementation manner, step S420 further includes: Step S421: Determine a second trailer that is connected to the first trailer and is in front of the first trailer.

[0054] Step S422: Collect the hook wear information of the first trailer and the second trailer.

[0055] Step S423: Based on the hook wear information, perform connection jitter and vibration coupling analysis to determine the connection perturbation influence area and influence indicators.

[0056] Step S424: Perform deformation judgment correction of the M deformation characteristic values with the connection perturbation influence area and influence indicators.

[0057] Specifically, when determining the second trailer that is connected to the first trailer and is in front of it, obtain the vehicle formation information through the vehicle-mounted communication module, combine sensors installed at the trailer connection (such as proximity switches, RFID tag readers) to identify the physical connection state, and determine the second trailer immediately in front of the first trailer according to the dynamic characteristics of the vehicle during driving (such as the traction torque transmission direction when the vehicle in front brakes) and the relative position data of the positioning system (GPS / Beidou). At the same time, obtain information such as the vehicle type parameters, wheelbase, and suspension system type of the second trailer, providing an object basis for subsequent hook wear analysis and vibration coupling analysis.

[0058] When collecting the hook wear information of the first trailer and the second trailer, use visual sensors (resolution ≥ 1080P) and contact displacement sensors arranged at the hook connection part to periodically scan parameters such as the wear amount of the pin hole of the hook, the scratch depth of the contact surface, and the deformation of the spring assembly, and combine the wear degree rating of manual inspection (such as ISO 16030 standard) to form a hook wear data set containing information such as wear position, wear amount, and wear rate.

[0059] When performing connection jitter and vibration coupling analysis based on hook wear information to determine the connection perturbation influence area and influence indicators, first substitute the hook wear amount (such as pin hole ovality, lock tongue wear depth) into the connection clearance - jitter amplitude mathematical model to calculate the jitter displacement amount under different wear states (such as when the wear amount increases by 0.1 mm, the jitter amplitude increases by 15%). At the same time, collect the vibration spectrum of the hook area through an acceleration sensor to identify abnormal frequency components generated by wear (such as low - frequency jitter components in the range of 10 - 20 Hz); then use the finite element method to simulate the vibration transfer path of the worn hook under typical road conditions (such as Class C potholed road surface) to determine the connection perturbation influence area where the vibration energy is concentrated (usually the connection between the longitudinal frame of the vehicle frame and the suspension within 1.5 meters around the hook); finally, define the perturbation influence indicators, including quantization parameters such as vibration amplification factor (the ratio of the vibration amplitude in the wear state to the normal state), energy transfer efficiency (the proportion of the hook vibration energy transferred to the body structure), etc., to provide a basis for subsequent correction of deformation eigenvalue.

[0060] When performing M deformation eigenvalue deformation judgment corrections based on the connection perturbation influence area and influence indicators, first add fiber Bragg grating sensors as buffer deformation monitoring points in the connection perturbation influence area (such as the vehicle frame structure within 1.5 meters around the hook) to collect additional vibration deformation data caused by hook wear in real - time; then establish a perturbation judgment mechanism based on the influence indicators (such as vibration amplification factor, energy transfer efficiency), and set the perturbation identification process to be triggered when the vibration amplification factor exceeds 1.3 or the energy transfer efficiency is greater than 25%; finally, analyze the M deformation eigenvalues based on this mechanism, isolate the high - frequency noise components generated by connection jitter (such as abnormal vibration characteristics in the range of 10 - 20 Hz) through the wavelet transform filtering algorithm, and correct the original deformation eigenvalues according to the wear amount - deformation error mapping relationship (such as 0.05 mm deformation error corresponding to every 0.1 mm wear depth) to eliminate the false deformation signals caused by hook wear and ensure the accuracy of deformation judgment.

[0061] In a possible implementation manner, step S424 further includes: Step S4241: Configure buffer deformation monitoring points in the connection perturbation influence area.

[0062] Step S4242: Configure a perturbation judgment mechanism for hook connection perturbation and structural body deformation based on the influence indicators.

[0063] Step S4243: Perform hook connection perturbation identification and isolation on the M deformation eigenvalues based on the perturbation judgment mechanism.

[0064] Specifically, when configuring buffer deformation monitoring points in the connection disturbance influence area, first, based on the analysis results of connection jitter and vibration coupling, determine the area where vibration energy is concentrated due to hook wear (usually parts such as the longitudinal frame of the vehicle body and the suspension support within 1.5 meters around the hook). Then, evenly arrange high-precision fiber Bragg grating sensors or MEMS acceleration sensors in this area to form an array with a density of no less than 2 monitoring points per square meter, and collect real-time additional deformation data caused by hook wear, such as vibration displacement, strain fluctuation, etc., to provide real-time dynamic monitoring data support for the accurate identification of subsequent hitch disturbances.

[0065] When configuring a disturbance judgment mechanism for hitch disturbances and structural body deformations based on influence indicators, first, based on influence indicators such as the vibration amplification coefficient and energy transfer efficiency obtained from the analysis of connection jitter and vibration coupling, set a quantitative judgment threshold (for example, when the vibration amplification coefficient exceeds 1.3 and the energy transfer efficiency is greater than 25%, it is determined that there is a significant disturbance). Then, combined with the mapping relationship between the hook wear amount and the deformation error (such as for every 0.1 mm increase in wear depth, the deformation error increases by 0.05 mm), construct a logical judgment model. When the deformation characteristic values monitored in real time meet the preset threshold conditions, trigger the disturbance identification process to achieve the accurate distinction between hitch disturbances and vehicle body deformations.

[0066] When performing hitch disturbance identification and isolation on M deformation characteristic values based on the disturbance judgment mechanism, an algorithm combining wavelet transform and band-pass filtering is used: First, input the real-time deformation characteristic value sequence into the discrete wavelet transform (DWT) algorithm, decompose it into components of different frequency bands, and extract the hook wear characteristic frequency component of 10 - 20 Hz. Then, through an IIR band-pass filter with a passband of 10 - 20 Hz and a stopband attenuation ≥ 30 dB, filter the deformation characteristic values to isolate the high-frequency component containing hitch disturbances. Finally, according to the mapping function between the hook wear amount and the deformation error (such as the linear function Δδ = 0.5 × wear depth), linearly correct the filtered deformation characteristic values to eliminate the false deformation amount caused by hook wear, achieve the accurate identification and effective isolation of hitch disturbances, and ensure that the deformation characteristic values input into the collaborative mapping network only reflect the true deformation state of the vehicle body structure.

[0067] Embodiment 2, based on the same inventive concept as a trailer body deformation adaptive safety monitoring method in the foregoing embodiment, as Figure 2 shown, the present application provides a trailer body deformation adaptive safety monitoring device. The device in the embodiment of the present application and the method embodiment are based on the same inventive concept. Among them, the device includes: A risk deformation point determination module 10, configured to determine M risk deformation points of the first trailer.

[0068] The collaborative mapping network generation module 20 is configured to perform collaborative warning analysis on the vehicle body deformation threshold, load, and road conditions based on the M risk deformation points, and generate a collaborative mapping network, including single-layer mapping of any deformation point and multi-layer collaboration of multiple deformation points.

[0069] The compensation channel generation module 30 is configured to perform compensation analysis on the deformation threshold in the collaborative mapping network under the influence of vehicle body stiffness, and generate a compensation channel connected to the collaborative mapping network.

[0070] The deformation eigenvalue generation module 40 is configured to collect deformation data through the intelligent sensing system on the M risk deformation points, analyze the deformation eigenvalues, and generate M deformation eigenvalues.

[0071] The first warning information generation module 50 is configured to optimize the collaborative mapping network through the compensation channel, and then input the M deformation eigenvalues into the collaborative mapping network for warning trigger analysis, and generate the first warning information.

[0072] Furthermore, the device is also used to implement the following functions: Determine the collaborative analysis elements, including the vehicle body deformation threshold, load distribution, and road condition excitation; for the M risk deformation points, based on the collaborative analysis elements, perform boundary deformation threshold analysis of structural instability and irreversible deformation in the single-point mode, and construct an M-layer single-layer mapping network; for the M risk deformation points, based on the collaborative analysis elements, perform boundary deformation threshold analysis of structural instability and irreversible deformation in the multi-point collaborative mode, and construct a multi-layer collaborative mapping network; generate the collaborative mapping network with the M-layer single-layer mapping network and the multi-layer collaborative mapping network.

[0073] Furthermore, the device is also used to implement the following functions: Build a twin simulation platform for the trailer, trailer load, and road conditions; based on the twin simulation platform, perform single-point simulation of the load-road condition database for the M risk deformation points respectively, and determine the critical yield threshold-load-road condition mapping relationship that causes structural instability and irreversible deformation; form the M-layer single-layer mapping network with the critical yield threshold-load-road condition mapping relationship.

[0074] Furthermore, the device is also used to implement the following functions: Perform multi-point deformation coupling analysis on the M risk deformation points, and construct N groups of deformation points whose coupling safety influence degree is greater than the preset influence degree, where N is a positive integer less than M; call the twin simulation platform, and use the load-road condition database to perform multi-point coupling boundary deformation simulation of structural instability and irreversible deformation on the N groups of deformation points, and determine the mapping relationship between the N groups of multi-point critical yield thresholds, loads, and road conditions; construct the multi-layer collaborative mapping network based on the mapping relationship between the N groups of multi-point critical yield thresholds, loads, and road conditions.

[0075] Further, the device is also used to implement the following functions: The load-road condition database includes multiple groups of load-road condition data, and each group of load-road condition data includes a combination of load and road conditions obtained based on the preset transportation route and preset load range of the first trailer.

[0076] Further, the device is also used to implement the following functions: Read the M deformation monitoring data sets collected by the intelligent sensing system, including displacement, acceleration, and strain data; identify deformation eigenvalue with the M deformation monitoring data sets, and generate the M deformation eigenvalues.

[0077] Further, the device is also used to implement the following functions: Determine the second trailer connected to the first trailer and located in front of the first trailer; collect the hook wear information of the first trailer and the second trailer; perform connection jitter and vibration coupling analysis based on the hook wear information, and determine the connection perturbation influence area and influence index; perform deformation judgment correction on the M deformation eigenvalues with the connection perturbation influence area and influence index.

[0078] Further, the device is also used to implement the following functions: Configure buffer deformation monitoring points in the connection perturbation influence area; configure a perturbation judgment mechanism for hitch perturbation and structural body deformation with the influence index; perform hitch perturbation identification and isolation on the M deformation eigenvalues based on the perturbation judgment mechanism.

[0079] Embodiment III Figure 3 It is a schematic structural diagram of an electronic device provided for a method for adaptively monitoring the deformation of a trailer body according to the present invention, showing a block diagram of an exemplary electronic device suitable for implementing the embodiments of the present invention. Figure 3 The displayed electronic device is only an example and should not bring any restrictions to the functions and usage scope of the embodiments of the present invention. As Figure 3 shown, the electronic device includes a processor 21, a memory 22, an input device 23, and an output device 24; the number of processors 21 in the electronic device can be one or more. Figure 3Taking a processor 21 as an example, the processor 21, the memory 22, the input device 23, and the output device 24 in the electronic device can be connected through a bus or other means. Figure 3 Taking the connection through the bus as an example.

[0080] It should be noted that the above-mentioned order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above description of specific embodiments of this specification has been made. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0081] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0082] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. An adaptive safety monitoring method for trailer body deformation, characterized in that Including: Determine M risk deformation points of the first trailer; Based on the M risk deformation points, conduct collaborative warning analysis of vehicle body deformation threshold, load, and road conditions, and generate a collaborative mapping network, including single-layer mapping of any deformation point and multi-layer collaboration of multiple deformation points; Perform compensation analysis under the influence of vehicle body stiffness on the deformation threshold in the collaborative mapping network, and generate a compensation channel connected to the collaborative mapping network; Collect deformation data through the intelligent sensing system at the M risk deformation points, analyze the deformation eigenvalue, and generate M deformation eigenvalues; Optimize the collaborative mapping network through the compensation channel, and then input the M deformation eigenvalues into the collaborative mapping network for warning trigger analysis to generate the first warning information.

2. The adaptive safety monitoring method for trailer body deformation according to claim 1, characterized in that Based on the M risk deformation points, conduct collaborative warning analysis of vehicle body deformation threshold, load, and road conditions, and generate a collaborative mapping network, including single-layer mapping of any deformation point and multi-layer collaboration of multiple deformation points, including: Determine collaborative analysis elements, including vehicle body deformation threshold, load distribution, and road condition excitation; For the M risk deformation points, based on the collaborative analysis elements, perform boundary deformation threshold analysis of structural instability and irreversible deformation in single-point mode, and construct an M-layer single-layer mapping network; For the M risk deformation points, based on the collaborative analysis elements, perform boundary deformation threshold analysis of structural instability and irreversible deformation in multi-point collaboration mode, and construct a multi-layer collaborative mapping network; Generate the collaborative mapping network with the M-layer single-layer mapping network and the multi-layer collaborative mapping network.

3. The adaptive safety monitoring method for trailer body deformation according to claim 2, wherein For the M risk deformation points, based on the collaborative analysis elements, perform boundary deformation threshold analysis of structural instability and irreversible deformation in single-point mode, and construct an M-layer single-layer mapping network, including: Construct a twin simulation platform for the trailer, trailer load, and road conditions; Based on the twin simulation platform, perform single-point simulation of the load-road condition database for the M risk deformation points respectively, and determine the critical yield threshold-load-road condition mapping relationship that causes structural instability and irreversible deformation; Form the M-layer single-layer mapping network with the critical yield threshold-load-road condition mapping relationship.

4. The self-adaptive safety monitoring method for a trailer body deformation according to claim 3, characterized in that For the M risk deformation points, based on the collaborative analysis elements, perform boundary deformation threshold analysis of structural instability and irreversible deformation in multi-point collaboration mode, and construct a multi-layer collaborative mapping network, including: Conduct multi-point deformation coupling analysis on the M risk deformation points, and construct N groups of deformation points with a coupling safety influence degree greater than the preset influence degree, where N is a positive integer less than M; Call the twin simulation platform, and perform multi-point coupling boundary deformation simulation of structural instability and irreversible deformation on the N groups of deformation points using the load-road condition database, and determine the N groups of multi-point critical yield threshold-load-road condition mapping relationships; Construct the multi-layer collaborative mapping network with the N groups of multi-point critical yield threshold-load-road condition mapping relationships.

5. The self-adaptive safety monitoring method for the deformation of a trailer body according to claim 4, characterized in that The load-road condition database includes multiple groups of load-road condition data, and each group of load-road condition data includes a combination of load and road conditions obtained based on the preset transportation route and preset load range of the first trailer.

6. The self-adaptive safety monitoring method for the deformation of a trailer body according to claim 1, characterized in that, Collect deformation data through the intelligent sensing system at the M risk deformation points, analyze the deformation characteristic values, and generate M deformation characteristic values, including: Read the M deformation monitoring data sets collected by the intelligent sensing system, including displacement, acceleration, and strain data; Identify the deformation characteristic values with the M deformation monitoring data sets and generate the M deformation characteristic values.

7. The adaptive safety monitoring method for trailer body deformation according to claim 1, characterized in that, After generating the M deformation characteristic values, including: Determine the second trailer connected to the first trailer and located in front of the first trailer; Collect the hook wear information of the first trailer and the second trailer; Perform connection jitter and vibration coupling analysis based on the hook wear information to determine the connection disturbance influence area and influence index; Execute the deformation judgment correction of the M deformation characteristic values with the connection disturbance influence area and influence index.

8. The self - adaptive safety monitoring method for trailer body deformation according to claim 7, characterized in that, Execute the deformation judgment correction of the M deformation characteristic values with the connection disturbance influence area and influence index, including: Configure buffer deformation monitoring points in the connection disturbance influence area; Configure a disturbance judgment mechanism for hitch disturbance and structural body deformation with the influence index; Identify and isolate the hitch disturbance of the M deformation characteristic values based on the disturbance judgment mechanism.

9. An adaptive safety monitoring device for the deformation of a trailer body, characterized in that, The device is used to implement the adaptive safety monitoring method for the deformation of a trailer body according to any one of claims 1-8. The device includes: A risk deformation point determination module for determining M risk deformation points of the first trailer; A cooperative mapping network generation module for performing cooperative early warning analysis of the vehicle body deformation threshold, load, and road conditions based on the M risk deformation points to generate a cooperative mapping network, including single-layer mapping of any deformation point and multi-layer cooperation of multiple deformation points; A compensation channel generation module for performing compensation analysis under the influence of vehicle body stiffness on the deformation threshold in the cooperative mapping network to generate a compensation channel connected to the cooperative mapping network; A deformation characteristic value generation module for collecting deformation data through the intelligent sensing system at the M risk deformation points, analyzing the deformation characteristic values, and generating M deformation characteristic values; A first early warning information generation module for optimizing the cooperative mapping network through the compensation channel, then inputting the M deformation characteristic values into the cooperative mapping network for early warning trigger analysis, and generating the first early warning information.

10. An electronic device, characterized in that, The electronic device includes: A processor; A memory for storing the executable instructions of the processor; Wherein, the processor is used to execute the adaptive safety monitoring method for the deformation of a trailer body according to any one of claims 1 to 8.

Images