A visual positioning-based pump pliers clamping assistance method and system

Abstract

The application provides a water pump clamp holding auxiliary method and system based on visual positioning, and relates to the field of machine vision. The method comprises the following steps: in a three-dimensional holding simulation platform, a pipe holding simulation space is constructed according to a pipe three-dimensional model and a jaw three-dimensional model; based on the holding parameter adjustment space and the pipe holding simulation space, the holding parameters of the water pump clamp are iteratively optimized and searched with the maximum pipe holding stability and pressure distribution uniformity as the target, the optimal holding parameters are output, and the water pump clamp is controlled to perform a holding operation on the pipe to be held according to the optimal holding parameters. The technical problem that the traditional water pump clamp holding relies on manual experience and it is difficult to balance the holding accuracy, uniformity and stability is solved. Through the above method, the accurate matching of the geometric characteristics of the pipe and the jaw and the intelligent adjustment of the holding parameters can be realized, the pipe surface damage rate can be reduced, and the holding accuracy and reliability can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of machine vision, and particularly relates to a water pump clamp holding auxiliary method and system based on visual positioning. BACKGROUND

[0002] The water pump clamp is a commonly used pipe clamping tool, which is widely used in pipe fixing, cutting, welding and assembly operations. In the traditional clamping process, the operator mainly relies on experience to determine the clamping position, clamping force and closing amount. This method is greatly affected by human operation differences, which easily leads to insufficient clamping accuracy and affects the processing or assembly quality.

[0003] Due to the lack of scientific quantification and optimization mechanism, the traditional water pump clamp is not uniform in the contact pressure distribution between the clamp and the pipe during clamping, which easily causes scratches, indentations or deformation on the surface of the pipe. Especially for thin-walled, precise or easily damaged pipes, such uneven pressure causes serious damage to the workpiece. At the same time, the traditional method is difficult to balance the clamping stability and surface protection, and is difficult to adapt to pipes of different materials, sizes and surface characteristics, which limits the reliability and repeatability of automatic clamping. SUMMARY

[0004] The purpose of the present application is to provide a water pump clamp holding auxiliary method and system based on visual positioning, which solves the technical problem that the traditional water pump clamp holding relies on manual experience and is difficult to balance the clamping accuracy, uniformity and stability, which includes:

[0005] In a first aspect, the present application provides a water pump clamp holding auxiliary method based on visual positioning, which includes: collecting a pipe surface image of a pipe to be clamped, and simulating and constructing a pipe three-dimensional model in combination with pipe size information and pipe material information; collecting a clamp surface image of a water pump clamp, and simulating and constructing a clamp three-dimensional model in combination with clamp tooth size information and clamp tooth material; constructing a pipe clamping simulation space in a three-dimensional clamping simulation platform according to the pipe three-dimensional model and the clamp three-dimensional model; based on a clamping parameter adjustment space and the pipe clamping simulation space, iteratively optimizing and searching the clamping parameters of the water pump clamp with the maximum pipe clamping stability and pressure distribution uniformity as the target, outputting the optimal clamping parameters, and controlling the water pump clamp to perform clamping work on the pipe to be clamped according to the optimal clamping parameters.

[0006] Preferably, the water pump clamp holding auxiliary method based on visual positioning further includes: collecting multi-angle pipe surface images of the pipe to be clamped by an industrial camera; inputting the multi-angle pipe surface images into a first surface feature recognition plug-in to output pipe surface feature distribution, wherein the first surface feature recognition plug-in is constructed based on a convolutional neural network; and simulating and constructing the pipe three-dimensional model according to the pipe surface feature distribution, pipe size information and pipe material information.

[0007] Preferably, the water pump clamp holding auxiliary method based on visual positioning further comprises: collecting multi-angle jaw surface images of the water pump clamp by an industrial camera; inputting the multi-angle jaw surface images into a second surface feature recognition plug-in to output a jaw surface feature distribution, wherein the second surface feature recognition plug-in is constructed based on a convolutional neural network; and constructing a jaw three-dimensional model according to the jaw surface feature distribution, jaw tooth size information, and jaw tooth material simulation.

[0008] Preferably, the water pump clamp holding auxiliary method based on visual positioning further comprises: configuring a holding parameter adjustment space, wherein the holding parameter adjustment space comprises a holding point threshold, a holding angle threshold, a clamping force threshold, and a jaw closing amount threshold.

[0009] Preferably, the water pump clamp holding auxiliary method based on visual positioning further comprises: randomly selecting any parameter within the holding point threshold, the holding angle threshold, the clamping force threshold, and the jaw closing amount threshold for combination to obtain a first initial holding parameter, and iteratively selecting Q initial holding parameters, wherein Q is an integer greater than 200; performing pipe fitting holding simulation according to the Q initial holding parameters in the pipe fitting holding simulation space respectively to output Q simulated anti-slip margins and Q simulated pressure distributions; setting a minimum anti-slip margin index based on a holding task, screening the Q simulated anti-slip margins to obtain K qualified holding parameters; constructing a parameter quality evaluation function with the objective of maximizing pipe fitting holding stability and pressure distribution uniformity, and evaluating K parameter quality coefficients according to the K simulated anti-slip margins and the K simulated pressure distributions of the K qualified holding parameters; and performing iterative optimization search on the holding parameters of the water pump clamp based on the holding parameter adjustment space and the pipe fitting holding simulation space according to the K qualified holding parameters and the K parameter quality coefficients to output an optimal holding parameter.

[0010] Preferably, the water pump clamp holding auxiliary method based on visual positioning further comprises: performing pipe fitting surface damage resistance evaluation according to pipe fitting material information, jaw tooth size information, and jaw tooth material to output a pipe fitting surface damage resistance strength; setting a ratio of the pipe fitting surface damage resistance strength to a preset standard damage resistance strength as a first weight adjustment coefficient, and compensating a first initial weight to obtain a first adaptive weight according to the first weight adjustment coefficient, wherein the first adaptive weight is a weight of pressure distribution uniformity; obtaining a second adaptive weight by subtracting the first adaptive weight from 1, wherein the second adaptive weight is a weight of pipe fitting holding stability; and constructing a parameter quality evaluation function with the objective of maximizing pipe fitting holding stability and pressure distribution uniformity based on the first adaptive weight and the second adaptive weight.

[0011] Preferably, the water pump clamp holding auxiliary method based on visual positioning further comprises: setting a qualified clamping parameter as an initial solution, arranging the K initial solutions in descending order of parameter quality coefficients to generate an initial solution sequence; selecting a first solution in the initial solution sequence as a superior solution, and setting the remaining K-1 initial solutions as inferior solutions; taking the superior solution as an adjustment direction, adjusting the K-1 inferior solutions according to a preset optimization step to obtain K-1 updated inferior solutions, and calculating K-1 parameter quality coefficients; reordering the superior solution and the K-1 updated inferior solutions based on the K-1 parameter quality coefficients to obtain an updated solution sequence, eliminating inferior solutions in the updated solution sequence at a preset proportion, and supplementing parameters in the clamping parameter adjustment space, wherein the preset proportion decreases as the number of optimization increases; continuing to perform iterative optimization based on the superior solution selection-inferior solution updating-reordering-inferior solution elimination-inferior solution supplementing optimization mechanism until a preset convergence number is reached, and outputting the superior solution of the current updated solution sequence as the optimal clamping parameter.

[0012] In a second aspect, the present application further provides a water pump clamp holding auxiliary system based on visual positioning, which is used to execute the water pump clamp holding auxiliary method based on visual positioning as described in the first aspect, and comprises: a pipe three-dimensional model construction module, which is used to collect pipe surface images of a pipe to be clamped, and simulate and construct a pipe three-dimensional model in combination with pipe size information and pipe material information; a jaw three-dimensional model construction module, which is used to collect jaw surface images of a water pump clamp, and simulate and construct a jaw three-dimensional model in combination with jaw tooth size information and jaw tooth material; a clamping simulation space construction module, which is used to construct a pipe clamping simulation space in a three-dimensional clamping simulation platform according to the pipe three-dimensional model and the jaw three-dimensional model; and a clamping parameter optimization search module, which is used to perform iterative optimization search on clamping parameters of the water pump clamp based on a clamping parameter adjustment space and the pipe clamping simulation space, to maximize pipe clamping stability and pressure distribution uniformity, output optimal clamping parameters, and control the water pump clamp to perform clamping work on the pipe to be clamped according to the optimal clamping parameters.

[0013] Embodiments of the present application include the following advantages:

[0014] By collecting the pipe surface image of the pipe to be clamped, the pipe three-dimensional model is simulated and constructed in combination with the pipe size information and the pipe material information. On the other hand, the jaw surface image of the water pump clamp is collected, and the jaw three-dimensional model is simulated and constructed in combination with the jaw tooth size information and the jaw tooth material. Then, in the three-dimensional clamping simulation platform, the pipe clamping simulation space is constructed according to the pipe three-dimensional model and the jaw three-dimensional model. Then, based on the clamping parameter adjustment space and the pipe clamping simulation space, the clamping parameters of the water pump clamp are iteratively optimized and searched to maximize the pipe clamping stability and the pressure distribution uniformity, and the optimal clamping parameters are output. Finally, the water pump clamp is controlled to clamp the pipe to be clamped according to the optimal clamping parameters. That is, through visual collection, three-dimensional modeling and multi-objective optimization of clamping parameters, the accurate matching of the pipe and the jaw geometric features and the intelligent adjustment of the clamping parameters can be realized, so that the clamping stability is maximized, the pressure distribution uniformity is improved, and the pipe surface damage rate is reduced, and the clamping precision and reliability are improved. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 The step flow chart of the water pump clamp clamping auxiliary method based on visual positioning of the present application;

[0016] Figure 2 The structure diagram of the water pump clamp clamping auxiliary system based on visual positioning of the present application.

[0017] Explanation of reference signs:

[0018] Pipe three-dimensional model construction module 11, jaw three-dimensional model construction module 12, clamping simulation space construction module 13, and clamping parameter optimization search module 14. DETAILED DESCRIPTION

[0019] The present application provides a water pump clamp clamping auxiliary method and system based on visual positioning, which solves the technical problem that the traditional water pump clamp clamping relies on manual experience and is difficult to balance the clamping precision, uniformity and stability. Through visual collection, three-dimensional modeling and multi-objective optimization of clamping parameters, the accurate matching of the pipe and the jaw geometric features and the intelligent adjustment of the clamping parameters can be realized, so that the clamping stability is maximized, the pressure distribution uniformity is improved, and the pipe surface damage rate is reduced, and the clamping precision and reliability are improved.

[0020] Below, the technical solutions in the present application will be described clearly and completely with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application. In addition, it should be noted that, for the convenience of description, only the parts related to the present application are shown in the drawings, not all.

[0021] Embodiment one, please refer to the attached Figure 1 The present application provides a water pump clamp holding auxiliary method based on visual positioning, applied to a water pump clamp holding auxiliary system based on visual positioning, specifically comprising the following steps:

[0022] S100: Collect the pipe surface image of the pipe to be clamped, and simulate and construct a pipe three-dimensional model combining pipe size information and pipe material information.

[0023] Further, the step S100 of the present application further comprises:

[0024] S110: Collect the multi-angle pipe surface image of the pipe to be clamped by an industrial camera; S120: input the multi-angle pipe surface image into a first surface feature recognition plug-in, and output the pipe surface feature distribution, wherein the first surface feature recognition plug-in is constructed based on a convolutional neural network; S130: simulate and construct a pipe three-dimensional model according to the pipe surface feature distribution, pipe size information and pipe material information.

[0025] Specifically, first, the multi-angle surface image of the pipe to be clamped is collected by the industrial camera, and the shooting distance and focal length are adjusted according to the pipe size to ensure that the pipe surface features are clearly imaged, and the multi-angle pipe surface image is obtained.

[0026] Then, a first surface feature recognition plug-in is constructed based on a convolutional neural network, the first surface feature recognition plug-in is composed of a plurality of convolutional layers (for extracting local texture features), a pooling layer (for dimension reduction and feature set), a batch normalization layer (for accelerating training and stabilizing convergence), and an activation function layer (such as ReLU, for introducing nonlinearity), which can effectively identify the micro and macro features of the pipe surface and be trained to convergence through sample data; then, after the collected multi-angle pipe surface image sequence is input into the first surface feature recognition plug-in, the network performs feature extraction and classification analysis on the image to generate a pipe surface feature distribution map, the recognized surface features include surface texture morphology, scratch position and length, pit or protrusion height and diameter, weld direction and width, surface roughness grade, and feature spatial distribution density and confidence value, and each feature point is labeled with its specific position and geometric parameters, thereby providing accurate data basis for subsequent three-dimensional model simulation construction and clamping pressure distribution calculation based on pipe size and material.

[0027] Then, in the three-dimensional modeling platform, a basic geometric shape model (such as a cylinder or a whole pipe contour) of the pipe is generated according to the pipe size information, the surface feature distribution is further mapped to the model surface to form a point cloud, and a Poisson surface reconstruction method is used to convert the point cloud into a continuous and smooth three-dimensional surface while retaining the true geometric morphology of local microscopic features such as scratches, pits, protrusions, and welds; finally, material properties are assigned to the model surface for subsequent clamping mechanics simulation and pressure distribution analysis, thereby obtaining a complete pipe three-dimensional model with accurate geometric features and material physical properties, which provides basic data for intelligent clamping parameter optimization.

[0028] S200: Collecting the jaw surface images of the water pump clamp, combining the jaw tooth size information and the jaw tooth material simulation to construct a three-dimensional model of the jaw.

[0029] Further, the step S200 of the present application further comprises:

[0030] S210: Collecting multi-angle jaw surface images of the water pump clamp through an industrial camera; S220: inputting the multi-angle jaw surface images into a second surface feature recognition plug-in and outputting a jaw surface feature distribution, wherein the second surface feature recognition plug-in is constructed based on a convolutional neural network; S230: constructing a three-dimensional model of the jaw according to the jaw surface feature distribution, the jaw tooth size information, and the jaw tooth material simulation.

[0031] Specifically, multi-angle jaw surface images of the water pump clamp are collected through an industrial camera, and the shooting distance, focal length, and exposure parameters are adjusted according to the jaw size to ensure that the tooth details and surface texture are clear and visible; finally, a multi-angle jaw surface image sequence is output, which provides a data basis for subsequent jaw feature recognition and three-dimensional modeling.

[0032] Then, a second surface feature recognition plug-in based on a convolutional neural network is constructed for extracting geometric features and tooth features of the jaws of the water pump pliers. The second surface feature recognition plug-in is composed of multiple convolutional layers (for capturing local details of the tooth), pooling layers (for dimension reduction and feature set), batch normalization layers (for accelerating training and stabilizing convergence), and activation function layers (such as ReLU, for introducing nonlinearity). The plug-in can simultaneously identify key parameters such as the shape, pitch, height, and angle of the tooth, and accurately analyze the surface texture, wear, or defect location of the jaws. Subsequently, the collected multi-angle jaw surface images are input into the second surface feature recognition plug-in. The network extracts features from the images and classifies them, outputting a jaw surface feature distribution map. The output features include the geometric dimensions, spatial position, direction, pitch, tooth angle, and local surface wear information of each tooth, along with the feature confidence and distribution density. This provides an accurate data basis for subsequent jaw three-dimensional modeling and clamping parameter optimization.

[0033] Then, in the three-dimensional simulation platform, a jaw overall geometric contour model is generated according to the tooth size information (such as tooth height, pitch, width, and tooth angle). The tooth features are then mapped to the model surface to form a point cloud, and a continuous and smooth three-dimensional surface is generated through Poisson surface reconstruction, while preserving the microscopic geometric features and wear information of the tooth. Finally, the tooth material properties are assigned to the model surface for subsequent pipe clamping mechanics analysis and pressure distribution simulation, resulting in a complete jaw three-dimensional model that contains accurate geometric features and material physical properties, providing a data basis for clamping parameter optimization.

[0034] S300: In the three-dimensional clamping simulation platform, a pipe clamping simulation space is constructed based on the pipe three-dimensional model and the jaw three-dimensional model.

[0035] Specifically, in the three-dimensional clamping simulation platform, the pipe three-dimensional model and the jaw three-dimensional model are first imported into a unified coordinate system and subjected to initial positioning and attitude correction to ensure that the relative positions of the pipe and the jaw are consistent with the actual clamping state. Then, based on the geometric shape, surface features, and material properties of the pipe, as well as the tooth geometry and material characteristics of the jaw, the contact surface, contact area, and friction conditions are defined to provide a physical basis for clamping mechanics calculation, and the pipe stress and deformation are preliminarily simulated through finite element or rigid body dynamics methods. Subsequently, a pipe clamping simulation space is generated in the simulation platform for dynamically simulating the clamping state of the water pump pliers under different clamping parameter conditions, including clamping point position, clamping angle, closing amount, and clamping force. The simulation space can calculate the contact pressure distribution, stress uniformity, and potential sliding or tilting trend of the jaw and pipe in real time, and visually display the clamping state and potential stress concentration areas, providing a quantitative basis for clamping parameter optimization and achieving accurate simulation analysis that balances clamping stability and workpiece surface protection.

[0036] S400: Based on the clamping parameter adjustment space and the pipe clamping simulation space, iteratively optimize and search the clamping parameters of the water pump clamp, aiming to maximize the pipe clamping stability and pressure distribution uniformity, output the optimal clamping parameters, and control the water pump clamp to clamp the pipe according to the optimal clamping parameters.

[0037] Further, the step S400 of the present application further comprises:

[0038] S410: Configure a clamping parameter adjustment space, wherein the clamping parameter adjustment space includes a clamping point position threshold value, a clamping angle threshold value, a clamping force threshold value, and a jaw closing amount threshold value.

[0039] Specifically, the clamping parameter adjustment space is configured in the three-dimensional clamping simulation platform, which is used to systematically define the adjustable parameter range of the water pump clamp when clamping the pipe. The clamping parameter adjustment space includes a clamping point position threshold value, a clamping angle threshold value, a clamping force threshold value, and a jaw closing amount threshold value. The clamping point position threshold value is used to limit the selectable clamping position of the jaw on the pipe surface. The clamping angle threshold value is used to constrain the inclination angle range of the jaw relative to the center axis of the pipe. The clamping force threshold value is used to define the clamping force range applied by the jaw on the pipe. The jaw closing amount threshold value is used to control the opening and closing amplitude of the jaw to ensure stable clamping and avoid excessive extrusion of the pipe. By defining the above parameter threshold values, the clamping parameter adjustment space can support systematic and controllable iterative optimization search, providing operable constraint conditions for subsequent clamping parameter optimization.

[0040] Further, the step S400 of the present application further comprises:

[0041] S420: Randomly select any parameter within the clamping point position threshold value, clamping angle threshold value, clamping force threshold value, and jaw closing amount threshold value to obtain a first initial clamping parameter, and iteratively select Q initial clamping parameters, wherein Q is an integer greater than 200; S430: In the pipe clamping simulation space, respectively simulate pipe clamping according to the Q initial clamping parameters, output Q simulated anti-slip margins and Q simulated pressure distributions; S440: Based on the clamping task, set a minimum anti-slip margin index, and filter the Q simulated anti-slip margins to obtain K qualified clamping parameters.

[0042] Specifically, first, specific values of each parameter are randomly selected and combined within the allowable range of the clamping point threshold, clamping angle threshold, clamping force threshold and jaw closing amount threshold to generate a first set of initial clamping parameters for simulating the pipe clamping state; then, the process is repeated by iteration to generate Q sets of initial clamping parameters, where Q is an integer greater than 200, to ensure that the parameter space is fully covered and the diversity of the search is increased, providing a rich set of candidate parameters for subsequent optimization algorithms based on clamping stability and pressure distribution uniformity, thereby improving the efficiency and accuracy of clamping parameter optimization.

[0043] Next, the Q sets of initial clamping parameters are input into the pipe clamping simulation space in turn, and pipe clamping simulation is performed for each set of parameters. During the simulation process, the force condition and friction distribution of the jaw and pipe contact area are calculated, and the anti-slip performance of the pipe during clamping is evaluated, and the corresponding simulation anti-slip margin is output. At the same time, the pressure distribution on the pipe surface is calculated, including pressure size, uniformity and potential stress concentration area. Through simulation analysis of the Q sets of initial parameters, Q anti-slip margin values and Q pressure distribution data are obtained, providing quantitative basis for subsequent clamping parameter optimization and multi-objective optimization.

[0044] Then, the minimum anti-slip margin index is set according to the requirements of the specific clamping task to ensure that the pipe has sufficient stability and anti-slip ability during clamping; then, the Q simulation anti-slip margin values are compared and screened one by one with the minimum index, and the clamping parameter combinations that are lower than the minimum anti-slip margin requirement are eliminated, and the clamping parameters that meet the conditions are retained. After screening, K sets of qualified clamping parameters are obtained, which provide candidate solutions for subsequent multi-objective optimization based on pressure distribution uniformity and surface protection under the premise of ensuring pipe clamping stability.

[0045] S450: Construct a parameter quality evaluation function with the goal of maximizing pipe clamping stability and pressure distribution uniformity, and obtain K parameter quality coefficients according to the K simulation anti-slip margins and K simulation pressure distributions of the K qualified clamping parameters.

[0046] Further, the step S450 of the present application further comprises:

[0047] S451: performing pipe surface damage resistance evaluation according to the pipe material information, the jaw tooth size information, and the jaw tooth material, and outputting pipe surface damage resistance strength; S452: setting a ratio of the pipe surface damage resistance strength to a preset standard damage resistance strength as a first weight adjustment coefficient, and compensating a first initial weight according to the first weight adjustment coefficient to obtain a first adaptive weight, wherein the first adaptive weight is a weight of pressure distribution uniformity; S453: obtaining a second adaptive weight by subtracting the first adaptive weight from 1, wherein the second adaptive weight is a weight of pipe clamping stability; and S454: constructing a parameter quality evaluation function based on the first adaptive weight and the second adaptive weight, and taking maximizing the pipe clamping stability and the pressure distribution uniformity as an objective.

[0048] Specifically, first, the surface stress and possible deformation of the pipe during clamping are analyzed by combining the pipe material information (such as hardness, elastic modulus, yield strength, etc.), the jaw tooth size information (such as tooth height, tooth pitch, tooth width, and tooth tip angle), and the jaw tooth material properties (such as hardness, elastic modulus, and friction coefficient), and a pipe surface damage resistance evaluation model is established; then, the pipe surface damage resistance strength index is output by calculating the local stress, friction force distribution, and deformation amplitude of the contact area between the jaw and the pipe, which can quantify the ability of the pipe surface to resist scratches, indentations, or microscopic damage under the action of clamping force, and provide a reliable reference for clamping parameter optimization and pressure distribution adjustment.

[0049] Then, a ratio of the pipe surface damage resistance strength to a preset standard damage resistance strength is set as a first weight adjustment coefficient, which is used to reflect the relative advantages and disadvantages of the current clamping parameters on the pipe surface protection ability; subsequently, the initially set pressure distribution uniformity weight is dynamically compensated according to the first weight adjustment coefficient to generate a first adaptive weight, so that the evaluation of pressure distribution uniformity can automatically adjust its importance in multi-objective optimization according to the pipe damage resistance ability, thereby realizing the balance between ensuring pipe surface protection and considering pressure distribution optimization during clamping. Further, a second adaptive weight is obtained by subtracting the first adaptive weight from 1, wherein the second adaptive weight is a weight of pipe clamping stability. This method realizes the dynamic balance of the two types of evaluation indexes, that is, when the pressure distribution uniformity weight increases, the clamping stability weight decreases accordingly; conversely, when the clamping stability weight increases, the pressure distribution uniformity weight decreases accordingly, so as to automatically coordinate the weight distribution between pressure uniformity and clamping stability in the multi-objective optimization process, and ensure that the optimization result considers both pipe surface protection and clamping reliability.

[0050] Then a parameter quality evaluation function is constructed based on the first adaptive weight (pressure distribution uniformity weight) and the second adaptive weight (pipe clamping stability weight), the parameter quality evaluation function aims to maximize pipe clamping stability and pressure distribution uniformity, and quantifies the two types of indicators in a weighted manner, so that in multi-objective optimization, both clamping mechanical stability and uniform stress and protection of the pipe surface can be considered. Finally, the parameter quality evaluation function is used to obtain K parameter quality coefficients according to the K simulated anti-skid margins and the K simulated pressure distributions of the K qualified clamping parameters, wherein each parameter quality coefficient reflects the comprehensive performance of the set of clamping parameters in terms of clamping stability and pressure uniformity, providing a quantitative basis for subsequent iterative optimization search and optimal clamping parameter output.

[0051] S460: Based on the clamping parameter adjustment space and the pipe clamping simulation space, the clamping parameters of the water pump clamp are iteratively optimized and searched according to the K qualified clamping parameters and the K parameter quality coefficients, and the optimal clamping parameters are output.

[0052] Further, the step S460 of the present application further comprises:

[0053] S461: Set the qualified clamping parameters as initial solutions, arrange the K initial solutions in descending order of parameter quality coefficients to generate an initial solution sequence; S462: Select the first solution in the initial solution sequence as the optimal solution, and the remaining K-1 initial solutions as inferior solutions; S463: Take the optimal solution as the adjustment direction, adjust the K-1 inferior solutions according to the preset optimization step size to obtain K-1 updated inferior solutions, and calculate K-1 parameter quality coefficients; S464: Based on the K-1 parameter quality coefficients, re-arrange the optimal solution and the K-1 updated inferior solutions to obtain an updated solution sequence, eliminate the inferior solutions in the last preset proportion of the updated solution sequence, and supplement the parameters by the clamping parameter adjustment space, wherein the preset proportion decreases with the increase of the optimization number; S465: Continue the iterative optimization based on the optimization mechanism of optimal solution selection-inferior solution updating-rearrangement-inferior solution elimination-inferior solution supplementing, until the preset convergence number is reached, and the optimal solution of the current updated solution sequence is output as the optimal clamping parameter.

[0054] Specifically, first, K qualified clamping parameters are taken as initial solutions, and the initial solutions are sorted from large to small according to the K parameter quality coefficients, to generate an initial solution sequence, reflecting the advantages and disadvantages of each set of clamping parameters in terms of clamping stability and uniformity of pressure distribution. Subsequently, the first solution with the highest parameter quality coefficient is selected from the initial solution sequence as the optimal solution, representing the current optimal clamping parameter combination, and the remaining K-1 initial solutions are marked as inferior solutions for subsequent iterative optimization or local search to gradually approach the global optimal clamping parameters. Then, the selected optimal solution is taken as the adjustment direction, and the remaining K-1 inferior solutions in the initial solution sequence are updated according to the preset optimization step, that is, according to the differences between the optimal solution and each inferior solution in the parameter space of clamping points, clamping angles, clamping forces, and jaw closing amounts, the parameters of the inferior solutions are fine-tuned in the direction of the optimal solution to generate K-1 updated inferior solutions. Subsequently, each updated inferior solution is input into the parameter quality evaluation function to recalculate its parameter quality coefficient, which is used to evaluate the comprehensive performance of the updated clamping parameters in terms of clamping stability and uniformity of pressure distribution, providing a quantitative basis for the next round of iterative optimization, and obtaining K-1 parameter quality coefficients.

[0055] Further based on the calculated parameter quality coefficients of the K-1 updated inferior solutions, the optimal solution and the updated inferior solutions are re-ordered to generate a new updated solution sequence. During the sorting process, the optimal solution is still located at the front end of the sequence, and the inferior solutions ranked at the back are marked as potential elimination objects for controlling the gradual convergence of the search space, thereby ensuring the overall improvement of the clamping parameter quality in each iteration. Then, the inferior solutions in the updated solution sequence are eliminated by a preset proportion, and equivalent parameters are supplemented through the clamping parameter adjustment space to reduce the interference of low-quality parameters on iterative optimization. The preset proportion decreases with the increase of the number of optimization, that is, a higher proportion is adopted in the early stage of optimization to expand the search range and increase the parameter diversity, and the proportion is gradually reduced in the later stage of optimization to improve the search accuracy and make the parameter update more concentrated in the high-quality solution area. At the same time, the eliminated inferior solutions are supplemented with equivalent parameters through the clamping parameter adjustment space to ensure the stability of the solution sequence and provide sufficient candidate parameters for the next round of iterative optimization.

[0056] Then, based on the iterative optimization mechanism constructed in steps S462 to S464, the clamping parameter optimization is continuously performed according to the process of "optimal solution selection- inferior solution update- reordering- inferior solution elimination- inferior solution supplement", wherein in each round of iteration, the optimal solution guides the inferior solution to converge to the high-quality parameter region, the parameters of the inferior solution are updated and the parameter quality coefficient is recalculated, then the solution sequence is sorted and the inferior solution is eliminated, and new equivalent inferior solutions are supplemented through the clamping parameter adjustment space to ensure the dynamic adjustment of the search space and the stability of the optimization direction; the iteration process continues until the preset convergence number is reached or the convergence condition is met, ensuring that the optimization effect of the clamping parameter fully reflects the stability and uniformity of the pressure; after the iteration ends, the optimal solution with the highest parameter quality coefficient in the current updated solution sequence is output as the final optimal clamping parameter, which is used to control the clamping operation of the water pump clamp on the pipe, realizing the comprehensive optimization of the workpiece surface protection, uniform pressure distribution and clamping stability in the clamping process.

[0057] Finally, the clamping point position, clamping angle, clamping force and jaw closing amount of the jaw are set according to the optimal clamping parameter, the water pump clamp is driven to move accurately and complete the clamping action, ensuring that the jaw contacts the pipe according to the predetermined posture, realizing uniform pressure distribution, minimizing pipe surface damage and maximizing clamping stability in the clamping process, thereby completing the automatic pipe clamping operation with high precision and high reliability.

[0058] In summary, the water pump clamp clamping auxiliary method based on visual positioning provided by the present application has the following technical effects:

[0059] By collecting the pipe surface image of the pipe to be clamped, combining the pipe size information and pipe material information to simulate and construct a pipe three-dimensional model; on the other hand, collecting the jaw surface image of the water pump clamp, combining the jaw tooth size information and the jaw tooth material to simulate and construct a jaw three-dimensional model; then in the three-dimensional clamping simulation platform, constructing a pipe clamping simulation space according to the pipe three-dimensional model and the jaw three-dimensional model; then based on the clamping parameter adjustment space and the pipe clamping simulation space, iteratively optimizing and searching the clamping parameters of the water pump clamp to maximize the pipe clamping stability and pressure distribution uniformity, and outputting the optimal clamping parameters; finally, controlling the water pump clamp to clamp the pipe to be clamped according to the optimal clamping parameters. That is, through visual acquisition, three-dimensional modeling and multi-objective optimization of clamping parameters, accurate matching of pipe and jaw geometric features and intelligent adjustment of clamping parameters can be realized, so as to maximize clamping stability, improve pressure distribution uniformity, reduce pipe surface damage rate and improve clamping precision and reliability.

[0060] Embodiment two, based on the same inventive concept as the water pump clamp clamping auxiliary method based on visual positioning in the foregoing embodiments, the present application also provides a water pump clamp clamping auxiliary system based on visual positioning, please refer to the accompanying Figure 2, comprising: a pipe three-dimensional model construction module 11 for collecting pipe surface images of a pipe to be clamped, and simulating and constructing a pipe three-dimensional model in combination with pipe size information and pipe material information; a jaw three-dimensional model construction module 12 for collecting jaw surface images of a water pump jaw, and simulating and constructing a jaw three-dimensional model in combination with jaw tooth size information and jaw tooth material; a clamping simulation space construction module 13 for constructing a pipe clamping simulation space in a three-dimensional clamping simulation platform according to the pipe three-dimensional model and the jaw three-dimensional model; and a clamping parameter optimization search module 14 for performing iterative optimization search on clamping parameters of the water pump jaw based on a clamping parameter adjustment space and the pipe clamping simulation space, with the goal of maximizing pipe clamping stability and pressure distribution uniformity, outputting optimal clamping parameters, and controlling the water pump jaw to clamp the pipe to be clamped according to the optimal clamping parameters.

[0061] Further, the water pump jaw clamping auxiliary system based on visual positioning is further used for: collecting multi-angle pipe surface images of a pipe to be clamped by an industrial camera; inputting the multi-angle pipe surface images into a first surface feature recognition plug-in to output pipe surface feature distribution, wherein the first surface feature recognition plug-in is constructed based on a convolutional neural network; and simulating and constructing a pipe three-dimensional model according to the pipe surface feature distribution, pipe size information, and pipe material information.

[0062] Further, the water pump jaw clamping auxiliary system based on visual positioning is further used for: collecting multi-angle pipe surface images of a pipe to be clamped by an industrial camera; inputting the multi-angle pipe surface images into a first surface feature recognition plug-in to output pipe surface feature distribution, wherein the first surface feature recognition plug-in is constructed based on a convolutional neural network; and simulating and constructing a pipe three-dimensional model according to the pipe surface feature distribution, pipe size information, and pipe material information.

[0063] Further, the water pump jaw clamping auxiliary system based on visual positioning is further used for: configuring a clamping parameter adjustment space, wherein the clamping parameter adjustment space includes a clamping point threshold, a clamping angle threshold, a clamping force threshold, and a jaw closing amount threshold.

[0064] Further, the water pump clamp holding auxiliary system based on visual positioning is further used for: randomly selecting any parameter in combination within the clamping point threshold, clamping angle threshold, clamping force threshold and jaw closing amount threshold to obtain a first initial clamping parameter, and iteratively selecting Q initial clamping parameters, wherein Q is an integer greater than 200; in the pipe fitting clamping simulation space, respectively according to the Q initial clamping parameters, respectively perform pipe fitting clamping simulation, output Q simulation anti-skid margins and Q simulation pressure distributions; based on the minimum anti-skid margin index set by the clamping task, the Q simulation anti-skid margins are screened to obtain K qualified clamping parameters; the parameter quality evaluation function is constructed with the maximum pipe fitting clamping stability and pressure distribution uniformity as the target, and K parameter quality coefficients are obtained according to the K simulation anti-skid margins and K simulation pressure distributions of the K qualified clamping parameters; based on the clamping parameter adjustment space and the pipe fitting clamping simulation space, the clamping parameters of the water pump clamp are iteratively optimized and searched according to the K qualified clamping parameters and K parameter quality coefficients, and the optimal clamping parameters are output.

[0065] Further, the water pump clamp holding auxiliary system based on visual positioning is further used for: according to the pipe fitting material information, the jaw tooth size information and the jaw tooth material, the pipe fitting surface damage resistance is evaluated, and the pipe fitting surface damage resistance strength is output; the ratio of the pipe fitting surface damage resistance strength to the preset standard damage resistance strength is set as a first weight adjustment coefficient, and the first initial weight is compensated to obtain a first adaptive weight according to the first weight adjustment coefficient, wherein the first adaptive weight is the weight of the pressure distribution uniformity; the second adaptive weight is obtained by subtracting the first adaptive weight from 1, wherein the second adaptive weight is the weight of the pipe fitting clamping stability; based on the first adaptive weight and the second adaptive weight, the parameter quality evaluation function is constructed with the maximum pipe fitting clamping stability and pressure distribution uniformity as the target.

[0066] Further, the water pump clamp holding auxiliary system based on visual positioning is further used for: setting the qualified clamping parameter as an initial solution, arranging the K initial solutions in descending order of the parameter quality coefficients to generate an initial solution sequence; selecting a first solution in the initial solution sequence as a superior solution, and setting the remaining K-1 initial solutions as inferior solutions; taking the superior solution as an adjustment direction, adjusting the K-1 inferior solutions according to a preset optimization step to obtain K-1 updated inferior solutions, and calculating K-1 parameter quality coefficients; reordering the superior solution and the K-1 updated inferior solutions based on the K-1 parameter quality coefficients to obtain an updated solution sequence, eliminating inferior solutions in the updated solution sequence in a preset proportion, and supplementing parameters in the clamping parameter adjustment space, wherein the preset proportion decreases as the number of optimization increases; continuing to perform iterative optimization based on the optimization mechanism of selecting a superior solution, updating an inferior solution, reordering, eliminating an inferior solution, and supplementing an inferior solution, until a preset convergence number is reached, and outputting a superior solution in the current updated solution sequence as an optimal clamping parameter.

[0067] The embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The water pump clamp holding auxiliary system based on visual positioning in the foregoing embodiment one is also applicable to the water pump clamp holding auxiliary system based on visual positioning in the present embodiment. The water pump clamp holding auxiliary system based on visual positioning in the present embodiment can be clearly understood by the person skilled in the art through the foregoing detailed description of the water pump clamp holding auxiliary method based on visual positioning. Therefore, for the sake of brevity of the specification, the water pump clamp holding auxiliary system based on visual positioning in the present embodiment is not described in detail. For the system disclosed in the embodiments, the description is relatively simple because the system corresponds to the method disclosed in the embodiments. Therefore, refer to the method part for relevant description.

[0068] The above description of the disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications to the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0069] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application also intends to include these modifications and variations.

Claims

1. A visual positioning-based water pump clamping assistance method, characterized in that the method... include: Acquire images of the pipe surface to be clamped, and simulate and construct a three-dimensional model of the pipe by combining the pipe size information and pipe material information; Collect images of the jaw surface of the water pump clamp, and construct a three-dimensional model of the jaw by combining the jaw tooth size information and jaw tooth material simulation. Within the three-dimensional clamping simulation platform, a pipe clamping simulation space is constructed based on the three-dimensional model of the pipe fitting and the three-dimensional model of the jaws. Based on the clamping parameter adjustment space and the pipe clamping simulation space, with the goal of maximizing the pipe clamping stability and pressure distribution uniformity, the clamping parameters of the water pump clamp are iteratively optimized and searched to output the optimal clamping parameters, and the water pump clamp is controlled to perform clamping operations on the pipe to be clamped according to the optimal clamping parameters. The clamping parameter adjustment space includes clamping point threshold, clamping angle threshold, clamping force threshold, and jaw closure amount threshold. Specifically, based on the clamping parameter adjustment space and the pipe clamping simulation space, with the goal of maximizing pipe clamping stability and pressure distribution uniformity, the clamping parameters of the water pump clamp are iteratively optimized and searched to output the optimal clamping parameters, including: Randomly select any parameter from the clamping point threshold, clamping angle threshold, clamping force threshold, and jaw closure threshold to obtain the first initial clamping parameter, and iteratively select Q initial clamping parameters, where Q is an integer greater than 200; Within the pipe clamping simulation space, pipe clamping simulations are performed according to the Q initial clamping parameters, and Q simulated anti-slip margins and Q simulated pressure distributions are output. Based on the minimum anti-slip margin index set for the clamping task, the Q simulated anti-slip margins are screened to obtain K qualified clamping parameters; A parametric quality evaluation function is constructed with the goal of maximizing the clamping stability and pressure distribution uniformity of the pipe fittings. The K parameter quality coefficients are obtained by evaluating the K simulated anti-slip margins and K simulated pressure distributions of the K qualified clamping parameters. Based on the clamping parameter adjustment space and the pipe clamping simulation space, the clamping parameters of the water pump clamp are iteratively optimized and searched according to the K qualified clamping parameters and K parameter quality coefficients, and the optimal clamping parameters are output.

2. The visual positioning-based water pump clamp holding assistance method according to claim 1, characterized by, Acquire images of the pipe surface to be clamped, and combine these images with the pipe's dimensions and material information to simulate and construct a 3D model of the pipe, including: Multi-angle images of the pipe fitting surface to be clamped are captured using an industrial camera. The multi-angle pipe fitting surface image is input into the first surface feature recognition plugin, and the pipe fitting surface feature distribution is output. The first surface feature recognition plugin is constructed based on a convolutional neural network. A three-dimensional model of the pipe fitting is constructed based on the surface feature distribution, size information, and material information of the pipe fitting.

3. The visual positioning-based water pump clamp holding assistance method according to claim 1, characterized by, Images of the jaws of the water pump clamp were collected, and a 3D model of the jaws was constructed by combining the jaw tooth size information and jaw tooth material simulation, including: Multi-angle images of the jaw surface of the water pump clamp were captured using an industrial camera. The multi-angle jaw surface image is input into the second surface feature recognition plugin, which outputs the jaw surface feature distribution. The second surface feature recognition plugin is constructed based on a convolutional neural network. According to the jaw surface feature distribution, the jaw tooth size information, and the jaw tooth material simulation, a three-dimensional model of the jaw is constructed.

4. The visual positioning-based water pump clamp holding assistance method according to claim 1, characterized by, A parameter quality evaluation function is constructed with the objectives of maximizing pipe clamping stability and pressure distribution uniformity, including: According to the pipe material information, the jaw tooth size information, and the jaw tooth material, a pipe surface damage resistance evaluation is performed, and a pipe surface damage resistance strength is output. A first weight adjustment coefficient is set as the ratio of the pipe surface damage resistance strength to a preset standard damage resistance strength, and a first adaptive weight is obtained by compensating a first initial weight according to the first weight adjustment coefficient, wherein the first adaptive weight is the weight of pressure distribution uniformity. A second adaptive weight is obtained by subtracting the first adaptive weight from 1, wherein the second adaptive weight is the weight of pipe clamping stability. A parameter quality evaluation function is constructed with the objectives of maximizing pipe clamping stability and pressure distribution uniformity based on the first adaptive weight and the second adaptive weight.

5. The visual positioning-based water pump clamp holding assistance method according to claim 1, characterized by, Based on the clamping parameter adjustment space and the pipe clamping simulation space, the clamping parameters of the water pump jaw are iteratively optimized and searched according to the K qualified clamping parameters and the K parameter quality coefficients, and the optimal clamping parameters are output, including: The qualified clamping parameters are set as initial solutions, the K initial solutions are arranged in descending order of parameter quality coefficients, and an initial solution sequence is generated; The first solution in the initial solution sequence is selected as a superior solution, and the remaining K-1 initial solutions are set as inferior solutions; The superior solution is used as the adjustment direction, and the K-1 inferior solutions are adjusted according to a preset optimization step to obtain K-1 updated inferior solutions, and K-1 parameter quality coefficients are calculated; Based on the K-1 parameter quality coefficients, the superior solution and the K-1 updated inferior solutions are reordered to obtain an updated solution sequence, and the inferior solutions in the last preset proportion of the updated solution sequence are eliminated, and the parameters are supplemented by the clamping parameter adjustment space, wherein the preset proportion decreases as the optimization number increases; The optimization mechanism of superior solution selection-inferior solution updating-reordering-inferior solution elimination-inferior solution supplementation is continued to iteratively optimize until a preset convergence number is reached, and the superior solution of the current updated solution sequence is output as the optimal clamping parameter.

6. A vision-based positioning system for assisting a pump clamp hold, characterized by, Steps for implementing the water pump jaw clamping auxiliary method based on visual positioning in any one of claims 1-5, including: A pipe three-dimensional model construction module is configured to collect pipe surface images of a pipe to be clamped, and construct a pipe three-dimensional model by combining pipe size information and pipe material information; A jaw three-dimensional model construction module is configured to collect jaw surface images of a water pump jaw, and construct a jaw three-dimensional model by combining jaw tooth size information and jaw tooth material; A clamping simulation space construction module is configured to construct a pipe clamping simulation space in a three-dimensional clamping simulation platform according to the pipe three-dimensional model and the jaw three-dimensional model; The clamping parameter optimization search module is configured to perform iterative optimization search on the clamping parameters of the water pump clamp based on the clamping parameter adjustment space and the pipe clamping simulation space, so as to maximize the pipe clamping stability and the pressure distribution uniformity, output optimal clamping parameters, and control the water pump clamp to clamp the pipe to be clamped according to the optimal clamping parameters.

Images