Van semitrailer steering synchronization angle closed-loop test calibration system

Abstract

The invention belongs to the technical field of vehicle steering control, and relates to a van semitrailer steering synchronization angle closed-loop test calibration system, which comprises the following steps of: firstly, executing a static steering test on a no-load combined vehicle, and constructing a mapping reference table of a saddle space position and an ideal hinge angle; then multi-working-condition dynamic steering testing is carried out on the load combination vehicle, vehicle frame deformation data are collected in real time, the deformation data are converted into a hinge angle compensation value through a pre-trained deformation mechanical model, selective correction is carried out on the actually-measured hinge angle based on a deformation compensation starting threshold value, a calibration target is generated to reversely analyze the target saddle position, and the target saddle position is corrected; the problem that in the prior art, inevitable elastic structure deformation and real mechanical steering asynchronous faults of the van semitrailer under the actual dynamic load working condition cannot be fully considered and distinguished is effectively solved, and then multi-working-condition driving verification data are collected, deformation mechanical model parameters are iteratively updated, and a compensation threshold value generation strategy is generated. And closed-loop optimization is realized.

Description

Technical Field

[0001] The invention belongs to the technical field of vehicle steering control and relates to a closed-loop testing and calibration system for steering synchronization angles of a van-type semi-trailer. Background Art

[0002] Box-type semi-trailers, with their high payload and multi-axle structure, have become a core piece of equipment in modern heavy-duty logistics transportation. However, during steering, the synchronization of steering angles between the tractor and semi-trailer is a critical factor affecting driving safety and handling stability. Misaligned steering angles can lead to vehicle deviation, increased abnormal tire wear, and, in severe cases, even accidents such as unstable handling. Therefore, precise closed-loop testing and calibration of steering synchronization angles is crucial.

[0003] Currently, some technical solutions have been attempted to apply closed-loop calibration of the steering synchronization angle of box-type semi-trailers. However, existing technical solutions have significant technical limitations: they fail to fully consider and effectively distinguish between the elastic structural deformation that inevitably occurs under actual dynamic load conditions and true mechanical steering asynchrony failures. Specifically, the following are the main manifestations: 1. Existing technologies rely on unloaded static conditions for testing and adjustment, ignoring the elastic deformation of the frame caused by load, road surface, and steering forces during actual fully loaded dynamic operation, resulting in the invalidation of calibration parameters during actual vehicle operation.

[0004] 2. Some existing technologies are aware of the potential deformation of structures such as the vehicle frame and attempt to filter out the effects of frame deformation. However, their calibration core is still based on the assumption that the vehicle is an ideal rigid body. This can easily misidentify the reasonable elastic deformation of the structure under load as an incoordination of the mechanical connection or actuators between the tractor and trailer. This erroneous compensation not only fails to eliminate the actual deviation, but also destroys the inherent correct synchronization relationship, introduces new errors, and deteriorates steering performance. Summary of the Invention

[0005] In view of this, in order to solve the problems raised in the above background technology, a closed-loop testing and calibration system for steering synchronization angle of a van-type semi-trailer is proposed.

[0006] The purpose of the present invention can be achieved through the following technical solutions: The present invention provides a box-type semi-trailer steering synchronization angle closed-loop test and calibration system, including: a benchmark establishment module, a dynamic monitoring module, an intelligent decision-making module, a calibration execution module and a closed-loop optimization module.

[0007] The benchmark establishment module is connected to the dynamic monitoring module, the dynamic monitoring module is connected to the intelligent decision-making module, the intelligent decision-making module is connected to the calibration execution module, and the calibration execution module is connected to the closed-loop optimization module.

[0008] The benchmark establishment module performs static steering tests on unloaded combination vehicles. By monitoring and calibrating the articulation angle between the tractor and semi-trailer, a mapping benchmark table between the saddle spatial position and the ideal articulation angle is constructed.

[0009] The dynamic monitoring module performs multi-condition dynamic steering tests on load-combined vehicles, collects deformation data in real time based on the frame strain sensor group, and converts the deformation data into articulation angle compensation values ​​through a pre-trained deformation mechanics model.

[0010] An intelligent decision-making module dynamically generates a deformation compensation activation threshold based on load distribution and road environment parameters, and performs selective correction on the measured articulation angle in multi-condition dynamic steering tests based on the threshold to generate a calibration target.

[0011] The calibration execution module queries the mapping reference table according to the calibration target, reversely analyzes the target saddle position and drives the three-dimensional actuator to adjust the spatial posture.

[0012] The closed-loop optimization module collects multi-condition driving verification data to iteratively update the deformation mechanics model parameters and compensation threshold generation strategy.

[0013] Compared with the existing technology, the beneficial effects of the present invention are as follows: (1) The present invention collects frame strain data in real time under multiple load conditions and quantifies the physical deformation into articulation angle compensation values ​​in combination with a pre-trained deformation mechanics model, thereby completely overcoming the drawback of the existing technology that relies on no-load static calibration. It directly models and compensates for the elastic deformation of the frame caused by cargo distribution, road excitation, etc. during actual full-load operation, ensuring that the calibration parameters truly reflect the steering geometry relationship under dynamic driving conditions.

[0014] (2) The present invention constructs a nonlinear deformation-angle mapping based on strain sensor data and a neural network, physically recognizes the elastic deformation properties of the frame, and activates the threshold value through dynamically generated deformation compensation. Compensation is initiated only when the deformation interference exceeds the critical value, thereby fundamentally avoiding the erroneous logic of the existing technology that misjudges reasonable elastic deformation as mechanical asynchrony, and prevents the destruction of the inherent synchronization of the system.

[0015] (3) The present invention iteratively updates the deformation model parameters and compensation threshold strategy based on multi-operating condition driving verification data, and endows the system with self-evolution capability to improve the robustness and life cycle accuracy of the calibration system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For passengers with ordinary technical skills in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 This is a schematic diagram of the system module connection of the present invention.

[0018] Figure 2 This is a logical schematic diagram of the deformation mechanics model constructed in the present invention.

[0019] Figure 3 This is a logical diagram of the reverse analysis of the target saddle position of the present invention. DETAILED DESCRIPTION

[0020] The above contents described below in conjunction with the implementation of the present invention are merely examples and explanations of the concept of the present invention. Technical passengers in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they shall fall within the scope of protection of the present invention.

[0021] See also Figure 1 As shown, the purpose of the present invention can be achieved through the following technical solutions: The present invention provides a box-type semi-trailer steering synchronization angle closed-loop test and calibration system, including: a benchmark establishment module, a dynamic monitoring module, an intelligent decision-making module, a calibration execution module and a closed-loop optimization module.

[0022] The benchmark establishment module is connected to the dynamic monitoring module, the dynamic monitoring module is connected to the intelligent decision-making module, the intelligent decision-making module is connected to the calibration execution module, and the calibration execution module is connected to the closed-loop optimization module.

[0023] The benchmark establishment module performs a static steering test on an unloaded combination vehicle, and constructs a mapping benchmark table between the saddle spatial position and the ideal articulation angle by monitoring and calibrating the articulation angle between the tractor and the semi-trailer.

[0024] In a preferred embodiment of the present invention, the static steering test includes the following steps: parking the unloaded combination vehicle on a level hard road surface, locking the semi-trailer wheels and releasing the tractor brakes, and positioning the saddle to a preset initial spatial position.

[0025] It should be noted that the above-mentioned preset initial spatial position is based on the saddle design coordinates provided by the tractor manufacturer. The spatial intersection of the center plane of the traction pin and the symmetry plane of the frame is measured by laser, and the saddle height is adjusted so that the empty ground clearance meets the standard value. The three-dimensional coordinates at this moment are locked as the preset initial spatial position.

[0026] The tractor's steering wheel angle is controlled according to a preset classification rule, and the ideal articulation angle corresponding to each steering wheel angle state is quantified based on the tractor's wheelbase and the distance from the saddle to the semi-trailer's rear axle axis.

[0027] It should be noted that the above-mentioned preset classification rule specifically refers to allocating sampling density according to the rate of change of the steering wheel angle within the effective steering wheel angle range, and the maximum corner point is forcibly included in the sampling sequence. The sampling density can be exemplarily allocated as follows: The interval does not exceed is the sampling interval, The interval does not exceed is the sampling interval, The above range does not exceed is the sampling interval.

[0028] It should also be noted that the specific quantification process of the ideal articulation angle corresponding to each steering wheel angle state is mainly based on Ackerman steering geometry calculation, and its calculation formula can be exemplified as follows: ,in Respectively represent the wheelbase of the tractor and the distance from the saddle to the rear axle axis of the semi-trailer. is the steering wheel angle.

[0029] Fix the steering wheel angle of the tractor and synchronously collect the measured articulation angle between the tractor and semi-trailer. Control the saddle to adjust its position in three-dimensional space until the measured articulation angle equals the ideal articulation angle. Record the spatial displacement vector of the saddle relative to the initial position when the ideal articulation angle is reached.

[0030] In a preferred embodiment of the present invention, the mapping reference table of the saddle position and the ideal articulation angle includes the following associated data items: different steering wheel angle states under the graded control of the tractor.

[0031] The measured articulation angle and the ideal articulation angle corresponding to each rotation angle state.

[0032] The spatial displacement vector of the saddle that makes the measured articulation angle match the ideal articulation angle at each rotation angle state.

[0033] The dynamic monitoring module performs a multi-condition dynamic steering test on a load combination vehicle, collects deformation data in real time based on a frame strain sensor group, and converts the deformation data into an articulation angle compensation value through a pre-trained deformation mechanics model.

[0034] In a preferred embodiment of the present invention, the multi-condition dynamic steering test includes the following: setting a combination of conditions including different road adhesion conditions, load mass distribution patterns and driving speed parameters.

[0035] It should be noted that the above-mentioned different road adhesion conditions include low-adhesion, variable-adhesion and high-adhesion road types. Low-adhesion road surfaces can be exemplified by ice- and snow-covered roads, flooded asphalt roads or loose gravel roads. Variable-adhesion road surfaces can be exemplified by mixed roads with half hardened and half muddy roads or bridge joint transition areas. High-adhesion road surfaces can be exemplified by dry asphalt roads or concrete roads.

[0036] The load mass distribution mode includes axial overload, longitudinal overload and combined overload modes under different load weights. The axial overload mode refers to the concentrated distribution of cargo mass in the front axle area or the rear axle area of ​​the semi-trailer. The longitudinal overload mode refers to the uneven distribution of cargo mass along the length of the vehicle body, such as heavy front and light rear or light front and heavy rear. The combined overload mode refers to the asymmetric distribution of superposition of axial and longitudinal overload.

[0037] The driving speed parameters include low-speed domain, medium-speed domain and high-speed domain. The low-speed domain is used to simulate the site moving condition, exemplified by 0-20km / h; the medium-speed domain is used to simulate the urban road turning condition, exemplified by 30-50km / h; the high-speed domain is used to simulate the highway lane changing condition, exemplified by 60-80km / h.

[0038] The steering wheel angle of the tractor is controlled in stages under combined working conditions, and the measured articulation angle between the tractor and semi-trailer at each steering wheel angle state is synchronously collected.

[0039] See also Figure 2 As shown, in a preferred embodiment of the present invention, the process of constructing the deformation mechanics model is:

[0040] a) A deformation pattern generator applies multiple sets of controllable deformation loads to the vehicle frame structure. Deformation data from a strain sensor group is simultaneously collected. A displacement measurement device is used to calibrate the relative rotation angle between the tractor's rear frame segment and the semitrailer's front frame segment as the true value for articulation angle compensation. The strain sensor group deformation data and the true value for compensation are divided into a training set and a validation set according to a preset ratio.

[0041] b) A residual neural network is constructed with the deformation data of the strain sensor group as input and the curvature of the discrete nodes as output. The curvature value output by the neural network is substituted into the segmented beam integral formula to quantify the relative rotation angle between the rear frame segment of the tractor and the front frame segment of the semi-trailer, which is used as the network output compensation value.

[0042] It should be noted that the execution logic of the above-mentioned segmented beam integral formula is defined as follows: along the length direction of the tractor rear frame, the discrete node curvature values ​​output by the neural network are spatially accumulated. The spatial accumulation operation represents the angular contribution of the curvature distribution to the frame deformation. The accumulated result is the rotation angle of the tractor rear frame segment relative to the saddle connection point.

[0043] Similarly, the same spatial accumulation operation is performed on the discrete node curvature values ​​along the length direction of the semi-trailer front frame, and the accumulated result represents the rotation angle of the semi-trailer front frame segment relative to the saddle connection point.

[0044] The algebraic difference between the rotation angle of the rear frame section of the tractor and the rotation angle of the front frame section of the semi-trailer is calculated. The difference is the articulation angle deviation caused by the deformation and serves as the final output articulation angle compensation value.

[0045] c) The neural network is trained using the training set data, and a damage function is constructed based on the mean square error between the network output compensation value and the true compensation value and the curvature distribution smoothness constraint.

[0046] It should be noted that the above curvature distribution smoothness constraint is achieved by penalizing the sudden changes in the curvature values ​​of adjacent nodes.

[0047] d) Use the validation set data to verify the pre-trained neural network. When the damage error is lower than the preset allowable threshold, freeze the network parameters to complete the construction of the deformation mechanics model.

[0048] The embodiments of the present invention collect frame strain data in real time under multiple load conditions and quantify the physical deformation into articulation angle compensation values ​​in combination with a pre-trained deformation mechanics model. This completely overcomes the drawback of the existing technology that relies on no-load static calibration. It directly models and compensates for the elastic deformation of the frame caused by cargo distribution, road surface excitation, etc. during actual full-load operation, ensuring that the calibration parameters truly reflect the steering geometry relationship under dynamic driving conditions.

[0049] The intelligent decision-making module dynamically generates a deformation compensation activation threshold based on load distribution and road environment parameters, and performs selective correction on the measured articulation angle in the multi-condition dynamic steering test based on the threshold to generate a calibration target.

[0050] In a preferred embodiment of the present invention, the process of generating the deformation compensation activation threshold includes: respectively analyzing load distribution characteristics, road adhesion characteristics, and vehicle motion characteristics under multiple combined working conditions.

[0051] It should be noted that the above-mentioned load distribution characteristics are the coupling characteristics of the lateral offset and longitudinal position of the center of mass on the frame stiffness, the road adhesion characteristics are the vehicle instability characteristics under the conditions of road adhesion coefficient and road curvature radius, and the vehicle motion characteristics are the abnormal fluctuation detection characteristics of the vehicle's longitudinal acceleration and yaw angular velocity.

[0052] Based on the feature correlation, load sensitivity factor, road sensitivity factor and motion inhibition factor are generated.

[0053] It should be noted that the above-mentioned load sensitivity factor refers to the adjustment instruction value for lowering the compensation threshold based on the degree of increase in the lateral offset of the center of mass or the forward movement of the longitudinal position; the road sensitivity factor refers to the correction instruction value for tightening the compensation threshold when the road adhesion coefficient decreases or the road curvature radius decreases; the motion inhibition factor refers to the inhibition instruction value for temporarily raising the threshold if the longitudinal acceleration or yaw angular velocity exceeds the system's preset critical range.

[0054] The load sensitivity factor, road sensitivity factor, and motion inhibition factor are implemented by combining hierarchical interval mapping with instruction assignment, as follows:

[0055] The spatial coordinates of the center of mass of the semi-trailer carrying goods under multiple combination working conditions are collected through the on-board weighing device, and compared with the standard center of mass position coordinates of the semi-trailer, the lateral offset and longitudinal forward movement of the center of mass are determined. The corresponding numerical ranges of the lateral slight offset level, lateral moderate offset level and lateral significant offset level defined by the absolute value of the lateral offset of the center of mass, and the corresponding numerical ranges of the longitudinal rear level, neutral level and forward level defined by the longitudinal forward movement are used to retrieve the lateral and longitudinal level attributes corresponding to the center of mass offset under multiple combination working conditions, and the level combination of lateral slight offset and longitudinal rear level, the level combination of lateral moderate offset and longitudinal neutral level, and the level combination of lateral significant offset and longitudinal forward level are marked as the first, second and third level combinations respectively. The absolute value of the adjustment instruction for reducing the compensation threshold is increased in sequence, which can be exemplified as -0.1, -0.3, and -0.5.

[0056] The vehicle's road adhesion coefficient under multiple combinations of working conditions is sensed by tire sensors, and the road curvature radius under multiple combinations of working conditions is identified by digital maps. Both the road adhesion coefficient and the road curvature radius have numerical ranges defined by low, medium, and high risk levels. The correction instructions for tightening the compensation threshold are assigned absolute values ​​in the following order from large to small: monitoring for double high risk, single high risk, double medium risk, and other combined risks, which can be exemplified as -0.5, -0.3, -0.2, and -0.1.

[0057] The longitudinal acceleration and yaw rate of the semi-trailer under multiple combined working conditions are collected, and the excess of the longitudinal acceleration and yaw rate relative to the system's preset critical range is quantified. The vehicle movement hazard level is determined by the sum of the excess of the two, including the first-order hazard level, the second-order hazard level and the third-order hazard level. The higher the hazard level, the larger the suppression instruction value of the temporary increase threshold, which can be exemplified as 0.1, 0.3, and 0.5.

[0058] The deformation compensation decision function is constructed by integrating multiple factors, and the deformation compensation activation threshold corresponding to each combined working condition is output.

[0059] It should also be noted that the above-mentioned process of fusing multiple factors to construct a deformation compensation decision function may exemplarily include any of the following mechanisms: i. Linear weighted fusion mechanism, which allocates linear fusion weights to each factor according to industry experience to perform weighted calculations.

[0060] ii. The logic gate cascade mechanism establishes a factor priority sequence. When a high-level factor is activated, the influence of the low-level factors is shielded. For example, if the motion inhibition factor triggers the threshold increase instruction, the load and road factors are ignored.

[0061] iii. Fuzzy membership mechanism, which converts each factor instruction into fuzzy language variables, synthesizes the fuzzy decision table based on the membership function, and outputs it after defuzzification.

[0062] Taking the linear weighted fusion mechanism as an example, according to industry experience, the priority of factor weight distribution of linear weighted fusion should follow the principle that the motion suppression factor has the highest weight, the road sensitivity factor has the second highest weight, and the load sensitivity factor has the lowest weight, and the cumulative value of the weight is 1. The deformation compensation decision function can be expressed as ,in Enables the threshold for preset base deformation compensation. For the The linear distribution weights and instruction values ​​of the factors, is the number of each factor, .

[0063] Assuming that the centroid offset of a van semi-trailer under a certain combination of working conditions is the first-level combination, the monitored road environment has a double high risk, and the vehicle motion hazard level is the second-order hazard level, then the load sensitivity factor, road sensitivity factor, and motion inhibition factor correspond to the instruction values ​​of -0.1, -0.5, and 0.3, and the corresponding weight distribution is 0.2, 0.3, and 0.5. The specific calculation process for the deformation compensation activation threshold is as follows: .

[0064] In a preferred embodiment of the present invention, the selective correction of the measured articulation angle in the multi-condition dynamic steering test based on the threshold includes the following contents: extracting the measured articulation angle between the tractor and the semi-trailer under each steering wheel angle state in each working condition dynamic steering test, the articulation angle compensation value and the deformation compensation activation threshold.

[0065] If the articulation angle compensation value is greater than or equal to the deformation compensation activation threshold, it means that the measured articulation angle is strongly interfered by the deformation and the measured articulation angle needs to be corrected. The correction process is to superimpose the measured articulation angle and the articulation angle compensation value while driving the measured articulation angle to converge toward the ideal articulation angle, and use the corrected measured articulation angle as the calibration target.

[0066] On the contrary, if the articulation angle compensation value is less than the deformation compensation activation threshold, the measured articulation angle is directly used as the calibration target.

[0067] The calibration execution module queries the mapping reference table according to the calibration target, reversely analyzes the target saddle position and drives the three-dimensional actuator to adjust the spatial posture.

[0068] See also Figure 3 As shown, in a preferred embodiment of the present invention, the target saddle position reverse analysis process includes: parsing the unit articulation angle deviation-saddle displacement conversion coefficient based on a mapping reference table, and the conversion coefficient is calibrated by the mapping relationship between the deviation value of the measured articulation angle and the ideal articulation angle in the static steering test and the saddle displacement vector.

[0069] Based on the conversion coefficient, the deviation value of the measured articulation angle under the same steering angle state between the calibration target and the mapping reference table is converted into a saddle space displacement optimization vector.

[0070] The original saddle spatial displacement vector under the same steering angle state in the mapping reference table is extracted, and the optimized vector is superimposed to generate the target displacement vector.

[0071] The target displacement vector is adjusted based on the preset initial spatial position of the saddle to determine the target saddle position.

[0072] The embodiment of the present invention constructs a nonlinear deformation-angle mapping based on strain sensor data and a neural network, physically recognizes the elastic deformation properties of the frame, and activates compensation through a dynamically generated deformation compensation activation threshold. Compensation is initiated only when the deformation interference exceeds the critical value, fundamentally avoiding the erroneous logic of existing technologies that misjudges reasonable elastic deformation as mechanical asynchrony, preventing the destruction of the system's inherent synchronization.

[0073] The closed-loop optimization module collects multi-condition driving verification data to iteratively update the deformation mechanics model parameters and compensation threshold generation strategy.

[0074] In a preferred embodiment of the present invention, the multi-condition driving verification data collection process is: after the three-dimensional actuator completes the saddle posture adjustment, the deviation value between the measured articulation angle and the ideal articulation angle after the saddle adjustment is collected and used as the driving verification data.

[0075] In a preferred embodiment of the present invention, the iterative updating of deformation mechanics model parameters and compensation threshold generation strategy includes:

[0076] The proportion of operating conditions in which the calibrated articulation angle exceeds the permitted range in the multi-operating condition driving verification data is counted, and an update instruction is triggered when the proportion of the operating conditions is higher than a preset non-minor operating condition ratio.

[0077] It should be noted that the above-mentioned allowable range is a two-way tolerance interval set with the ideal articulation angle in the benchmark establishment module as the reference value. Its boundary is determined by the vehicle dynamics stability constraint, mainly involving various physical parameters such as vehicle wheelbase, center of mass height, tire lateral stiffness, etc. The non-minor operating condition ratio refers to the proportion of failure conditions that can affect the safety of the system. The specific values ​​of the allowable range and non-minor operating condition ratio are manually calibrated before the system is developed.

[0078] The pre-trained deformation mechanics model is incrementally trained using the newly added deformation dataset until the validation set error meets the accuracy requirements.

[0079] The load sensitivity factor, road sensitivity factor and motion suppression factor in the compensation threshold generation strategy are dynamically adjusted based on the misjudgment rate.

[0080] It should be noted that the process of dynamically adjusting the compensation threshold generation strategy based on the false positive rate may illustratively include the following steps: taking the ratio of the number of decisions requiring deformation compensation but not enabled to the total number of compensation decision triggering times as the false positive rate.

[0081] The difference between the false positive rate and the preset reference false positive rate is used as the numerator, and the preset reference false positive rate is used as the denominator. A ratio operation is performed and the operation result is used as the relative deviation of the false positive rate.

[0082] The product of the preset learning rate adjustment factor and the relative deviation of the misjudgment rate is used as the factor adjustment amount.

[0083] The sum of the previous generation factor value and the factor adjustment amount is used to generate the new generation factor value.

[0084] The embodiment of the present invention iteratively updates deformation model parameters and compensation threshold strategies based on multi-condition driving verification data, and endows the system with self-evolution capabilities to improve the robustness and lifecycle accuracy of the calibration system.

[0085] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0086] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0087] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0088] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0089] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0090] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A closed-loop test and calibration system for steering synchronization angle of a van semi-trailer, characterized in that: include: The benchmark establishment module performs static steering tests on unloaded combination vehicles, monitors and calibrates the articulation angle between the tractor and semi-trailer through intelligent sensors, and constructs a benchmark table mapping the saddle's spatial position to the ideal articulation angle. A dynamic monitoring module performs multi-condition dynamic steering tests on a load-combined vehicle, collects deformation data in real time based on a frame strain sensor group, and converts the deformation data into articulation angle compensation values ​​using a pre-trained deformation mechanics model; An intelligent decision-making module dynamically generates deformation compensation activation thresholds based on load distribution and road environment parameters. Based on these thresholds, it selectively corrects the measured articulation angles during multi-condition dynamic steering tests to generate calibration targets. a calibration execution module, which queries the mapping reference table according to the calibration target, reversely analyzes the target saddle position and drives the three-dimensional actuator to adjust the spatial posture; The closed-loop optimization module collects multi-condition driving verification data to iteratively update the deformation mechanics model parameters and compensation threshold generation strategy.

2. A closed-loop test and calibration system for steering synchronization angle of a van-type semi-trailer according to claim 1, characterized in that: The static steering test includes the following steps: Park the unloaded combination vehicle on a level hard surface, lock the semi-trailer wheels and release the tractor brakes, and position the saddle to the preset initial spatial position; Control the tractor's steering wheel angle according to a preset classification rule, and quantify the ideal articulation angle corresponding to each steering wheel angle state based on the tractor's wheelbase and the distance from the saddle to the semi-trailer's rear axle axis; Fix the steering wheel angle of the tractor and synchronously collect the measured articulation angle between the tractor and semi-trailer. Control the saddle to adjust its position in three-dimensional space until the measured articulation angle equals the ideal articulation angle. Record the spatial displacement vector of the saddle relative to the initial position when the ideal articulation angle is reached.

3. The closed-loop test and calibration system for steering synchronization angle of a van-type semi-trailer according to claim 2, characterized in that: The mapping reference table between the saddle position and the ideal articulation angle includes the following associated data items: Different steering wheel angle states under graded control of tractor; The measured articulation angle and the ideal articulation angle corresponding to each rotation angle state; The spatial displacement vector of the saddle that makes the measured articulation angle match the ideal articulation angle at each rotation angle state.

4. The closed-loop test and calibration system for steering synchronization angle of a van-type semi-trailer according to claim 3, characterized in that: The multi-condition dynamic steering test includes the following contents: Set up combined operating conditions including different road adhesion conditions, load mass distribution patterns and driving speed parameters; The steering wheel angle of the tractor is controlled in stages under combined working conditions, and the measured articulation angle between the tractor and semi-trailer at each steering wheel angle state is synchronously collected.

5. The closed-loop test and calibration system for steering synchronization angle of a van-type semi-trailer according to claim 1, characterized in that: The construction process of the deformation mechanics model is as follows: a) applying multiple sets of controllable deformation loads to the vehicle frame structure using a deformation pattern generator, while simultaneously collecting deformation data from a strain sensor group. Using a displacement measurement device, the relative rotation angle between the tractor's rear frame segment and the semitrailer's front frame segment is calibrated as a true value for articulation angle compensation. The strain sensor group deformation data and the true value for compensation are divided into a training set and a validation set according to a preset ratio. b) Construct a residual neural network that uses the deformation data of the strain sensor group as input and the curvature of the discrete nodes as output. Substitute the curvature value output by the neural network into the segmented beam integral formula to quantify the relative rotation angle between the rear frame segment of the tractor and the front frame segment of the semi-trailer as the network output compensation value; c) Use the training set data to train the neural network and construct the damage function based on the mean square error between the network output compensation value and the compensation true value and the curvature distribution smoothness constraint; d) Use the validation set data to verify the pre-trained neural network. When the damage error is lower than the preset allowable threshold, the network parameters are frozen to complete the construction of the deformation mechanics model.

6. The closed-loop test and calibration system for steering synchronization angle of a van-type semi-trailer according to claim 1, characterized in that: The process of generating the deformation compensation enabling threshold includes: Analyze the load distribution characteristics, road adhesion characteristics and vehicle motion characteristics under multiple combined working conditions respectively; Generate load sensitivity factor, road sensitivity factor and motion inhibition factor based on feature correlation; The deformation compensation decision function is constructed by integrating multiple factors, and the deformation compensation activation threshold corresponding to each combined working condition is output.

7. The closed-loop test and calibration system for steering synchronization angle of a van-type semi-trailer according to claim 4, characterized in that: The selectively correcting the measured articulation angle in the multi-condition dynamic steering test based on the threshold value includes the following steps: Extract the measured articulation angle, articulation angle compensation value, and deformation compensation activation threshold between the tractor and semi-trailer at each steering wheel angle state in each working condition dynamic steering test; If the articulation angle compensation value is greater than or equal to the deformation compensation activation threshold, it indicates that the measured articulation angle is significantly affected by deformation interference and needs to be corrected. The correction process involves superimposing the measured articulation angle with the articulation angle compensation value while driving the measured articulation angle to converge toward the ideal articulation angle. The corrected measured articulation angle is then used as the calibration target. On the contrary, if the articulation angle compensation value is less than the deformation compensation activation threshold, the measured articulation angle is directly used as the calibration target.

8. The closed-loop test and calibration system for steering synchronization angle of a van-type semi-trailer according to claim 7, characterized in that: The target saddle position reverse analysis process includes: Analyzing the unit articulation angle deviation-saddle displacement conversion coefficient based on the mapping reference table. The conversion coefficient is calibrated by the mapping relationship between the deviation value of the measured articulation angle and the ideal articulation angle in the static steering test and the saddle displacement vector; Based on the conversion coefficient, the deviation value of the measured articulation angle under the same steering angle state between the calibration target and the mapping reference table is converted into a saddle spatial displacement optimization vector; Extract the original saddle spatial displacement vector under the same steering angle state from the mapping reference table, and superimpose the optimized vector to generate the target displacement vector; The target displacement vector is adjusted based on the preset initial spatial position of the saddle to determine the target saddle position.

9. The closed-loop test and calibration system for steering synchronization angle of a van-type semi-trailer according to claim 1, characterized in that: The multi-operational driving verification data collection process is as follows: After the three-dimensional actuator completes the saddle posture adjustment, the deviation value between the measured articulation angle after saddle adjustment and the ideal articulation angle is collected and used as driving verification data.

10. A closed-loop test and calibration system for steering synchronization angle of a van-type semi-trailer according to claim 9, characterized in that: The iterative updating of deformation mechanics model parameters and compensation threshold generation strategy includes: Counting the percentage of operating conditions in which the calibrated articulation angle exceeds the permitted range in the multi-operational driving verification data, and triggering an update instruction when the percentage of such operating conditions exceeds a preset non-minor operating condition ratio; Use the newly added deformation dataset to incrementally train the pre-trained deformation mechanics model until the validation set error meets the accuracy requirements; The load sensitivity factor, road sensitivity factor and motion suppression factor in the compensation threshold generation strategy are dynamically adjusted based on the misjudgment rate.

Images