A limit clamping control method and positioning control mechanism

Abstract

The present invention discloses a limit clamping control method and positioning control mechanism, which relates to the field of mechanical manufacturing automation. The method comprises: collecting the clamping surface image of the target workpiece, identifying it, and obtaining the workpiece feature information; collecting the clamping surface image of the clamping device, identifying it, and obtaining the clamping feature information; moving the target workpiece into the clamping device, optimizing the limit clamping parameters, and obtaining the optimal limit clamping parameters; controlling the clamping device to perform limit clamping and processing of the target workpiece, collecting and identifying to obtain updated workpiece feature information and updated clamping feature information; and updating the prediction model for predicting damage to the clamping device and the target workpiece. The method solves the technical problems of unstable clamping effect and difficult to predict damage in the existing limit clamping control, and achieves the technical effect of optimizing the limit clamping parameters, making the clamping device adapt to the characteristics of different workpieces and clamping devices, improving the clamping stability, and effectively reducing the damage to the workpiece and the clamping device.

Description

Technical Field

[0001] The present application relates to the field of mechanical manufacturing automation, and in particular to a limit clamping control method and a positioning control mechanism. Background Art

[0002] In the fields of mechanical manufacturing, processing and automated production lines, clamping devices are indispensable tools used to fix and position workpieces to ensure the stability and accuracy of the processing process. With the rapid development of the manufacturing industry, the requirements for clamping devices are becoming higher and higher. Not only do they need to be able to stably clamp the workpiece, but they also need to minimize damage to the workpiece and the clamping device itself during the clamping process. Traditional clamping methods usually rely on manual experience or fixed clamping parameter settings. Due to the different characteristics of the workpiece and the clamping device, fixed clamping parameters are often not applicable to all situations, resulting in unstable clamping effects, and it is impossible to accurately predict the degree of damage to the workpiece and the clamping device during the clamping process, which can easily lead to damage to the workpiece or excessive wear of the clamping device.

[0003] In the current related technologies, the limit clamping control has technical problems such as unstable clamping effect and unpredictable damage. Summary of the invention

[0004] The present application provides a limit clamping control method and a positioning control mechanism, collects workpiece feature information, collects clamping feature information, optimizes limit clamping parameters, uses optimal limit clamping parameters to limit clamp and process the target workpiece, and updates the prediction model after the processing is completed. The application achieves the technical effect of optimizing the limit clamping parameters, making the clamping device adapt to the characteristics of different workpieces and clamping devices, improving the clamping stability, and effectively reducing the damage to the workpiece and the clamping device.

[0005] The present application provides a limit clamping control method, comprising:

[0006] Collect a clamping surface image of the target workpiece to be clamped, identify it, and obtain workpiece feature information; collect a clamping surface image of the clamping device, identify it, and obtain clamping feature information; move the target workpiece into the clamping device, and optimize the limit clamping parameters according to the workpiece feature information and the clamping feature information to obtain optimal limit clamping parameters, wherein the optimal limit clamping parameters include optimal clamping position parameters and optimal clamping force parameters, and predict damage to the clamping surface of the clamping device and the target workpiece by combining the limit clamping parameters with the workpiece feature information and the clamping feature information, and optimize them; use the optimal limit clamping parameters to control the clamping device to perform limit clamping and processing of the target workpiece, and after the processing is completed, collect and identify to obtain updated workpiece feature information and updated clamping feature information; update the prediction model for predicting damage to the clamping device and the target workpiece according to the updated workpiece feature information and the updated clamping feature information.

[0007] In a possible implementation, the clamping surface image of the target workpiece to be clamped is collected, recognized, and the following processing is performed:

[0008] Based on historical detection data of clamped workpieces, a set of clamping surface images of sample workpieces is collected; surface features in the clamping surface images of sample workpieces are identified and marked to obtain a set of sample workpiece feature information, wherein the surface features include surface shape and surface roughness; a workpiece surface feature identifier is trained using the sample workpiece clamping surface image set and the sample workpiece feature information set; a clamping surface image of a target workpiece is collected, and the workpiece clamping surface image is identified using the workpiece surface feature identifier to obtain the workpiece feature information.

[0009] In a possible implementation, the clamping surface image of the clamping device is collected, recognized, and clamping feature information is obtained, and the following processing is performed:

[0010] Based on the usage data record of the clamping device, a set of clamping surface images of the sample device is collected; the surface features in the clamping surface images of the sample device are identified and marked to obtain a set of sample clamping feature information, and a clamping surface feature identifier is trained in combination with the clamping surface image set of the sample device; the clamping surface image of the clamping device is collected, and the clamping surface feature identifier is used to identify the device clamping surface image to obtain clamping feature information.

[0011] In a possible implementation, based on the workpiece feature information and the clamping feature information, the limit clamping parameters are optimized to obtain the optimal limit clamping parameters, and the following processing is performed:

[0012] The clamping position space and the clamping force space of the target workpiece for limited clamping are obtained, and the clamping parameter space is obtained by combining them, wherein the clamping position includes the first coordinate position, the second coordinate position and the third coordinate position, and the clamping force includes the clamping force of multiple clamping modules; based on reducing the damage to the clamping surface of the clamping device and the target workpiece after clamping, and improving the clamping stability, a clamping function is constructed, as shown in the following formula: ; Where LCF is the clamping fitness, is the workpiece damage weight, is the clamping damage weight, To stabilize the weight, To predict the damage coefficient of the target workpiece after clamping according to the optimized limit clamping parameters, is the clamping damage coefficient of the clamping device predicted after clamping according to the optimized limit clamping parameters, and C is the clamping stability parameter of clamping according to the optimized limit clamping parameters; according to the clamping parameter space and the clamping function, the limit clamping parameters are optimized to obtain the optimal limit clamping parameters, wherein the limit clamping parameters are combined with the workpiece feature information and the clamping feature information to predict the damage to the clamping surface of the clamping device and the target workpiece for optimization.

[0013] In a possible implementation, based on the clamping parameter space and the clamping function, the limit clamping parameters are optimized to obtain the optimal limit clamping parameters, and the following processing is performed:

[0014] According to the historical clamping parameter data of the same type of workpieces as the target workpiece, a plurality of historical limit clamping parameters are randomly selected to be used as a plurality of target limit clamping parameters; a plurality of basic limit clamping parameters are randomly generated in the clamping parameter space, and a mapping relationship with the plurality of target limit clamping parameters is randomly constructed; with the plurality of target limit clamping parameters as the adjustment direction, according to the mapping relationship, the plurality of basic limit clamping parameters are adjusted and updated according to a preset adjustment step length to obtain a plurality of adjusted limit clamping parameters; according to the mapping relationship, parameters are randomly selected from the plurality of adjusted limit clamping parameters and the plurality of target limit clamping parameters for cross-update to obtain a plurality of updated limit clamping parameters; according to the plurality of updated limit clamping parameters, in combination with the The workpiece feature information and the clamping feature information are used to predict and obtain multiple updated workpiece damage coefficients, multiple updated clamping damage coefficients and multiple updated clamping stability parameters, and multiple updated clamping fitnesses are calculated; multiple target clamping fitnesses of the multiple target limit clamping parameters are obtained by processing and calculating; based on the mapping relationship, a judgment is made according to the multiple updated clamping fitnesses and the multiple target clamping fitnesses, and the limit clamping parameters with large clamping fitnesses are used as the target limit clamping parameters to obtain multiple updated target limit clamping parameters; based on the multiple target limit clamping parameters, new basic limit clamping parameters are continuously randomly generated, and iterative optimization is performed until the convergence requirements are met, and the limit clamping parameters with the largest clamping fitness are output to obtain the optimal limit clamping parameters.

[0015] In a possible implementation, based on the multiple updated limit clamping parameters, combined with the workpiece feature information and the clamping feature information, multiple updated workpiece damage coefficients, multiple updated clamping damage coefficients and multiple updated clamping stability parameters are predicted and acquired, and the following processing is performed:

[0016] According to the clamping data record of the clamping device, a sample workpiece feature information set, a sample clamping feature information set, and a sample limit clamping parameter set are collected, and according to the clamping result, a sample workpiece damage coefficient set, a sample clamping damage coefficient set, and a sample clamping stability parameter set are collected as clamping prediction training data; the clamping prediction training data is used to train a limit clamping predictor, and the input prediction is performed on the multiple updated limit clamping parameters, workpiece feature information, and clamping feature information to obtain multiple updated workpiece damage coefficients, multiple updated clamping damage coefficients, and multiple updated clamping stability parameters.

[0017] In a possible implementation, according to the updated workpiece feature information and the updated clamping feature information, the prediction model for predicting damage to the clamping device and the target workpiece is updated, and the following processing is performed:

[0018] According to the updated workpiece feature information and the updated clamping feature information, in combination with the workpiece feature information and the clamping feature information, the real workpiece damage coefficient and the real clamping wear coefficient are calculated; the real workpiece damage coefficient and the real clamping wear coefficient are used, in combination with the optimal limit clamping parameters, to update the limit clamping predictor for training.

[0019] The present application also provides a positioning control mechanism, comprising:

[0020] A workpiece feature information acquisition module, the workpiece feature information acquisition module is used to collect the clamping surface image of the target workpiece to be clamped, identify it, and obtain the workpiece feature information; a clamping feature information acquisition module, the clamping feature information acquisition module is used to collect the clamping surface image of the clamping device, identify it, and obtain the clamping feature information; a limit clamping parameter optimization module, the limit clamping parameter optimization module is used to move the target workpiece into the clamping device, optimize the limit clamping parameters according to the workpiece feature information and the clamping feature information, and obtain the optimal limit clamping parameters, wherein the optimal limit clamping parameters include the optimal clamping position parameters and The optimal clamping force parameters are optimized by combining the limit clamping parameters with the workpiece feature information and the clamping feature information to predict the damage to the clamping device and the clamping surface of the target workpiece; an updated feature information acquisition module is used to use the optimal limit clamping parameters to control the clamping device to perform limit clamping and processing of the target workpiece, and after the processing is completed, collect and identify the updated workpiece feature information and the updated clamping feature information; a prediction model update module is used to update the prediction model for predicting the damage of the clamping device and the target workpiece according to the updated workpiece feature information and the updated clamping feature information.

[0021] The present application proposes a limit clamping control method and positioning control mechanism, which first collects the clamping surface image of the target workpiece to be clamped, identifies it, and obtains the workpiece feature information, then collects the clamping surface image of the clamping device, identifies it, and obtains the clamping feature information, then moves the target workpiece into the clamping device, optimizes the limit clamping parameters according to the workpiece feature information and the clamping feature information, and obtains the optimal limit clamping parameters, wherein the optimal limit clamping parameters include the optimal clamping position parameters and the optimal clamping force parameters, and the limit clamping parameters are combined with the workpiece feature information and the clamping feature information. , predict the damage to the clamping surface of the clamping device and the target workpiece, optimize it, and then use the optimal limit clamping parameters to control the clamping device to limit clamp and process the target workpiece, and after the processing is completed, collect and identify to obtain updated workpiece feature information and updated clamping feature information, and finally update the prediction model for predicting the damage of the clamping device and the target workpiece based on the updated workpiece feature information and updated clamping feature information, so as to achieve the technical effect of optimizing the limit clamping parameters, making the clamping device adapt to the characteristics of different workpieces and clamping devices, improving the clamping stability, and effectively reducing the damage to the workpiece and the clamping device. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the mechanism according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0023] Figure 1 A schematic flow chart of a limit clamping control method provided in an embodiment of the present application.

[0024] Figure 2 A structural schematic diagram of a positioning control mechanism provided in an embodiment of the present application.

[0025] Explanation of the reference numerals: workpiece feature information acquisition module 10 , clamping feature information acquisition module 20 , limit clamping parameter optimization module 30 , update feature information acquisition module 40 , prediction model update module 50 . DETAILED DESCRIPTION

[0026] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0027] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0028] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, mechanism, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0029] The present application embodiment provides a limit clamping control method, which is applied to a clamping device, such as Figure 1 As shown, the method includes:

[0030] Step S100, collect the clamping surface image of the target workpiece to be clamped, identify it, and obtain the workpiece feature information. Specifically, the target workpiece refers to the workpiece that needs to be clamped, which can be an object of various shapes, sizes and materials. The clamping surface is the part of the target workpiece that contacts the clamping device, which is used to achieve stable clamping of the target workpiece. Use a suitable image acquisition device, such as a high-resolution camera or an industrial camera, adjust the position, angle and focal length of the image acquisition device according to the size, shape and characteristics of the clamping surface of the target workpiece, adjust the exposure, focal length, white balance and other parameters of the image acquisition device according to the surface material and lighting conditions of the target workpiece, trigger the image acquisition device, and shoot the clamping surface image of the target workpiece from different angles. The captured clamping surface image is transmitted to a computer or image processing system, and image processing algorithms and techniques such as filtering, enhancement, edge detection, contour extraction, etc. are applied to pre-process the clamping surface image. Based on the pre-processed clamping surface image, the key features of the clamping surface of the target workpiece are identified, including surface shape, texture, roughness, size, edge shape, etc. The extracted workpiece features are encoded and converted into numerical workpiece feature information.

[0031] In a possible implementation, step S100 further includes step S110, collecting a set of sample workpiece clamping surface images based on historical detection data of the clamped workpiece. Specifically, different types and states of workpiece clamping surface images are screened out from the historical detection data to form an image set. Step S120, surface features in the sample workpiece clamping surface image are identified and marked to obtain a sample workpiece feature information set, wherein the surface features include surface shape and surface roughness. Specifically, image processing technology (such as edge detection, texture analysis, etc.) is used to identify and extract surface features in the sample workpiece clamping surface image, and the extracted features are described and quantified, such as surface shape, surface roughness, etc., and they are matched with the sample workpiece clamping surface image to form a sample workpiece feature information set. Step S130, the sample workpiece clamping surface image set and the sample workpiece feature information set are used to train a workpiece surface feature identifier. Specifically, a machine learning algorithm suitable for image recognition and feature extraction, such as a convolutional neural network (CNN) or a support vector machine (SVM), is selected, and a set of sample workpiece clamping surface images and a set of sample workpiece feature information are used as training data to train the selected algorithm to obtain a trained workpiece surface feature identifier. Step S140, the clamping surface image of the target workpiece is collected, and the workpiece clamping surface image is identified by the workpiece surface feature identifier to obtain the workpiece feature information. Specifically, the clamping surface image of the target workpiece is collected using an image acquisition device, and the collected clamping surface image is subjected to necessary preprocessing, such as denoising, enhancement, etc., and the preprocessed clamping surface image is input into the trained workpiece surface feature identifier for feature recognition and extraction, and the feature information output by the workpiece surface feature identifier is matched with the target workpiece to form the workpiece feature information. This implementation method trains the workpiece surface feature identifier and uses a large amount of sample data to learn the surface features of the workpiece, thereby achieving the technical effect of improving the accuracy of the recognition of the clamping surface features of the target workpiece.

[0032] Step S200, collect the clamping surface image of the clamping device, identify it, and obtain the clamping feature information. Specifically, the clamping device is a mechanical device or component used to stably clamp the workpiece, and its clamping surface can contact the clamping surface of the workpiece and apply a clamping force to fix the workpiece. Ensure that the clamping device is in a state suitable for image acquisition, the clamping surface is clearly visible, and there are no obstructions. Use a suitable image acquisition device (such as a camera, scanner, etc.), adjust the position, angle and focal length of the image acquisition device according to the size of the clamping device and the characteristics of the clamping surface, trigger the image acquisition device, and shoot the image of the clamping surface of the clamping device. If there are multiple parts or areas on the clamping surface of the clamping device, perform image acquisition separately to ensure that each part is clearly visible. The collected clamping surface image is transmitted to a computer or image processing system, and image processing algorithms and techniques such as filtering, enhancement, edge detection, contour extraction, etc. are applied to pre-process the clamping surface image. Based on the pre-processed clamping surface image, the key features of the clamping surface are identified, including the shape, size, material, texture, degree of wear, etc. of the clamping surface. The extracted clamping features are encoded and converted into numerical clamping feature information.

[0033] In a possible implementation, step S200 further includes step S210, collecting a set of clamping surface images of a sample device based on the usage data record of the clamping device. Specifically, representative clamping surface images are screened out from the usage data record of the clamping device, that is, clamping surfaces with different usage states and different degrees of wear, to construct a set of clamping surface images of a sample device. Step S220, surface features in the clamping surface image of the sample device are identified and marked to obtain a set of sample clamping feature information, and a clamping surface feature identifier is trained in combination with the set of clamping surface images of the sample device. Specifically, image processing technology (such as edge detection, texture analysis, etc.) is used to identify and extract the surface features of the clamping surface in the clamping surface image of the sample device, including the degree of wear, cracks, deformation, etc., and the extracted features are described and quantified, such as the degree of wear, crack length, etc., and corresponded to the clamping surface image of the sample device, and the identified clamping feature information is organized into a set of sample clamping feature information. A clamping surface feature identifier is trained using a set of sample device clamping surface images and a corresponding set of sample clamping feature information. During the training process, the model parameters are continuously adjusted and optimized to improve the recognition accuracy and generalization ability of the clamping surface feature identifier. Step S230, the clamping surface image of the clamping device is collected, and the clamping surface feature identifier is used to identify the device clamping surface image to obtain the clamping feature information. Specifically, the clamping surface image of the clamping device is collected using an image acquisition device, and the collected clamping surface image is subjected to necessary preprocessing, such as denoising, enhancement, etc., to improve the image quality. The preprocessed clamping surface image is input into the trained clamping surface feature identifier to perform clamping surface feature recognition and extraction, and the clamping feature information output by the clamping surface feature identifier is matched with the clamping device to form the clamping feature information. This implementation method trains the clamping surface feature identifier and uses a large amount of sample data to learn the clamping surface features of the clamping device, thereby achieving the technical effect of improving the accuracy of the clamping surface feature recognition of the clamping device.

[0034] Step S300, the target workpiece is moved into the clamping device, and the limit clamping parameters are optimized according to the workpiece feature information and the clamping feature information to obtain the optimal limit clamping parameters, wherein the optimal limit clamping parameters include the optimal clamping position parameters and the optimal clamping force parameters, and the limit clamping parameters are combined with the workpiece feature information and the clamping feature information to predict the damage to the clamping surface of the clamping device and the target workpiece, and optimize. Specifically, the target workpiece is accurately moved to the predetermined position of the clamping device using appropriate tools or equipment (such as manipulators, conveyor belts, etc.), and the target workpiece is confirmed to be accurately placed and aligned with the clamping device through sensors or visual systems. According to the design requirements and experience of the clamping device, the initial clamping position parameters and clamping force parameters are set based on the average size, material and clamping surface characteristics of the target workpiece. According to the workpiece feature information and clamping feature information, a model is established to optimize the limit clamping parameters (the parameters used by the clamping device to clamp the workpiece, including the clamping position parameters and the clamping force parameters). The model is trained using historical data or simulation data so that it can predict the clamping effect under different limit clamping parameters (different clamping positions and clamping forces). Using the established model, different clamping positions and clamping forces are simulated and predicted to evaluate the degree of damage to the clamping device and the clamping surface of the workpiece under each combination of limit clamping parameters, including damage area, depth, deformation, etc., and combined with the stability of clamping, such as the shaking amplitude and position offset of the target workpiece during processing. According to the prediction results, the limit clamping parameters are adjusted through optimization algorithms (such as genetic algorithms, gradient descent algorithms, etc.) to find the optimal clamping position and clamping force parameters to minimize the damage to the clamping device and the clamping surface of the workpiece and ensure the stability of clamping. The optimized limit clamping parameters are used in combination with the workpiece feature information and the clamping feature information to predict the damage to the clamping device and the clamping surface of the target workpiece, and to evaluate whether the predicted damage level is acceptable, such as whether it exceeds a preset threshold. If the predicted damage level is unacceptable, continue to adjust the limit clamping parameters until the optimal limit clamping parameters are found.

[0035] In a possible implementation, based on the workpiece feature information and the clamping feature information, the limit clamping parameters are optimized to obtain the optimal limit clamping parameters, and step S300 further includes step S310, obtaining the clamping position space and the clamping force space for the target workpiece to be clamped, and combining to obtain the clamping parameter space, wherein the clamping position includes a first coordinate position, a second coordinate position and a third coordinate position, and the clamping force includes the clamping force of multiple clamping modules. Specifically, according to the size, shape and processing requirements of the target workpiece, the first coordinate position (X), the second coordinate position (Y) and the third coordinate position (R, i.e., the rotation angle of the rotating workpiece) of the target workpiece in the clamping device are determined, and these coordinate positions constitute a three-dimensional clamping position space for describing the position of the target workpiece in the clamping device. According to the design of the clamping device, the clamping force range that each clamping module can provide is determined, and the clamping forces of multiple clamping modules are combined to form a multi-dimensional clamping force space for describing the clamping force of the clamping device on the target workpiece. The clamping position space and the clamping force space are combined to form a multi-dimensional clamping parameter space, which is used to describe all possible limit clamping parameter combinations. Each point in the clamping parameter space represents a set of limit clamping parameters. Step S320, based on reducing the damage to the clamping surface of the clamping device and the target workpiece after clamping, and improving the clamping stability, a clamping function is constructed as follows:

[0036] ;

[0037] Among them, LCF is the clamping fitness, is the workpiece damage weight, is the clamping damage weight, To stabilize the weight, To predict the damage coefficient of the target workpiece after clamping according to the optimized limit clamping parameters, is the clamping damage coefficient of the clamping device predicted after clamping according to the optimized limit clamping parameters, and C is the clamping stability parameter of clamping according to the optimized limit clamping parameters. Specifically, the workpiece damage, clamping device damage and clamping stability are used as evaluation indicators of clamping fitness. According to actual needs, different weights are set for workpiece damage, clamping device damage and clamping stability to reflect their respective importance in the clamping process. According to the set weights and evaluation indicators, the clamping function LCF is constructed to output the clamping fitness value. Among them, the clamping fitness is used to evaluate the clamping effect, the workpiece damage coefficient and the clamping damage coefficient are used to quantify the degree of damage of the target workpiece and the clamping device after clamping according to the optimized limit clamping parameters, and the clamping stability parameter is used to quantify the stability of the clamping device when clamping according to the optimized limit clamping parameters. Step S330, according to the clamping parameter space and the clamping function, the limit clamping parameters are optimized to obtain the optimal limit clamping parameters, wherein the limit clamping parameters are combined with the workpiece feature information and the clamping feature information to predict the damage to the clamping surface of the clamping device and the target workpiece, and then optimized. Specifically, one or more initial limit clamping parameter combinations are randomly selected in the clamping parameter space, and the damage to the clamping surface of the clamping device and the target workpiece is predicted by combining the initial limit clamping parameter combination, the workpiece feature information and the clamping feature information, and the prediction result is substituted into the clamping function to calculate the corresponding clamping fitness value. An optimization algorithm (such as a genetic algorithm, a particle swarm algorithm, etc.) is used to search for the optimal limit clamping parameter combination in the clamping parameter space. In each iteration, the limit clamping parameters are adjusted according to the clamping fitness value, and the clamping fitness value is recalculated. When the convergence condition (such as reaching the maximum number of iterations, the clamping fitness value is stable, etc.) is met, the iteration is stopped, and the optimal limit clamping parameter combination is output. This implementation method takes into account the damage to the clamping surface of the clamping device and the target workpiece and the clamping stability by constructing a clamping function, realizes a comprehensive quantitative evaluation of the clamping results, and achieves the technical effect of improving the accuracy of optimizing the limit clamping parameters.

[0038] In a possible implementation, according to the clamping parameter space and the clamping function, the limit clamping parameters are optimized to obtain the optimal limit clamping parameters. Step S330 further includes step S331, according to the historical clamping parameter data of the target workpiece and the same workpiece, a plurality of historical limit clamping parameters are randomly selected as a plurality of target limit clamping parameters. Specifically, the historical clamping parameter data (including position coordinates, clamping force, etc.) of the target workpiece and the same workpiece are obtained from the database, and a plurality of historical limit clamping parameters are randomly selected from the historical data, and these historical limit clamping parameters are used as the initial reference points. Step S332, a plurality of basic limit clamping parameters are randomly generated in the clamping parameter space, and a mapping relationship with the plurality of target limit clamping parameters is randomly constructed. Specifically, a plurality of basic limit clamping parameters are randomly generated in the clamping parameter space, that is, randomly generated initial clamping parameters for further optimization. Each basic limit clamping parameter is randomly associated with a historical limit clamping parameter to form a mapping relationship, that is, a corresponding relationship between the basic limit clamping parameter and the historical limit clamping parameter. Step S333, taking the multiple target limit clamping parameters as the adjustment direction, adjusting and updating the multiple basic limit clamping parameters according to the mapping relationship and the preset adjustment step length, and obtaining multiple adjustment limit clamping parameters. Specifically, taking the target limit clamping parameters (i.e., historical limit clamping parameters) as the adjustment direction, adjusting and updating the basic limit clamping parameters according to the mapping relationship and the preset adjustment step length (the amount or range of parameter change at each adjustment), and obtaining multiple adjustment limit clamping parameters. Step S334, according to the mapping relationship, randomly selecting parameters from the multiple adjustment limit clamping parameters and the multiple target limit clamping parameters for cross-update, and obtaining multiple update limit clamping parameters. Specifically, randomly selecting parameters from the adjustment limit clamping parameters and the target limit clamping parameters, cross-combining or replacing the selected parameters, and obtaining multiple update limit clamping parameters, that is, generating a new limit clamping parameter combination by exchanging or combining some elements in different limit clamping parameters. For example, a certain coordinate value or clamping force value in two limit clamping parameters can be exchanged. Step S335, based on the multiple updated limit clamping parameters, combined with the workpiece feature information and the clamping feature information, predict and obtain multiple updated workpiece damage coefficients, multiple updated clamping damage coefficients and multiple updated clamping stability parameters, and calculate and obtain multiple updated clamping fitnesses. Specifically, based on the updated limit clamping parameters, combined with the workpiece feature information and the clamping feature information, a model or algorithm is used to predict workpiece damage, clamping device damage and clamping stability, and multiple updated clamping fitnesses are calculated based on the prediction results. Step S336, process and calculate to obtain multiple target clamping fitnesses of the multiple target limit clamping parameters. Specifically, the target limit clamping parameters are also predicted to obtain the corresponding workpiece damage, clamping device damage and clamping stability, and calculate multiple target clamping fitnesses.Step S337, based on the mapping relationship, according to the multiple updated clamping fitness and the multiple target clamping fitness, the limit clamping parameter with the larger clamping fitness is used as the target limit clamping parameter to obtain the updated multiple target limit clamping parameters. Specifically, the updated clamping fitness and the target clamping fitness are compared, and based on the mapping relationship, the limit clamping parameter with the larger clamping fitness is used as the new target limit clamping parameter. Step S338, based on the multiple target limit clamping parameters, new basic limit clamping parameters are continuously randomly generated, and iterative optimization is performed until the convergence requirements are met, and the limit clamping parameters with the largest clamping fitness are output to obtain the optimal limit clamping parameters. Specifically, based on the updated target limit clamping parameters, new basic limit clamping parameters are continuously randomly generated, and steps S332 to S337 are repeated to perform iterative optimization. When the convergence requirements are met (such as the clamping fitness is slowly improved, the preset number of iterations is reached, etc.), the iteration is stopped, and the limit clamping parameters with the largest clamping fitness are output as the optimal limit clamping parameters. This implementation method provides valuable reference points for the optimization process by utilizing historical clamping parameter data, thereby accelerating the optimization process. It increases the diversity of the search space by randomly generating basic limit clamping parameters and constructing mapping relationships. Through cross-updating, new and potentially better limit clamping parameter combinations are generated, further expanding the search scope. At the same time, the information of existing better solutions is used to adjust the search direction, making the search process more efficient and targeted, thereby achieving the technical effect of improving the optimization effect and helping to quickly find the global optimal solution.

[0039] In a possible implementation, based on the multiple updated limit clamping parameters, combined with the workpiece feature information and the clamping feature information, multiple updated workpiece damage coefficients, multiple updated clamping damage coefficients and multiple updated clamping stability parameters are predicted and obtained, and step S335 further includes step S3351, according to the clamping data record of the clamping device, a sample workpiece feature information set, a sample clamping feature information set, and a sample limit clamping parameter set are collected, and according to the clamping result, a sample workpiece damage coefficient set, a sample clamping damage coefficient set and a sample clamping stability parameter set are collected as clamping prediction training data. Specifically, from the clamping data record of the clamping device, various parameters and result information used in the historical clamping process are collected, and according to the historical data, a sample workpiece feature information set is collected, including the size, shape, material, etc. of the workpiece clamping surface, and at the same time, a sample clamping feature information set is collected, including the clamping surface type, shape, size, etc. of the clamping device, and the limit clamping parameters used in the historical clamping process are collected to form a sample limit clamping parameter set. According to the results after clamping, a set of sample workpiece damage coefficients, a set of sample clamping damage coefficients and a set of sample clamping stability parameters are collected. These parameters reflect the degree of damage to the workpiece and the clamping device during the clamping process and the stability of the clamping. Step S3352, using the clamping prediction training data, train the limit clamping predictor, input prediction of the multiple updated limit clamping parameters, workpiece feature information and clamping feature information, and obtain multiple updated workpiece damage coefficients, multiple updated clamping damage coefficients and multiple updated clamping stability parameters. Specifically, select a suitable machine learning or deep learning model as the limit clamping predictor, use the clamping prediction training data collected in step S3351 to train the limit clamping predictor, and during the training process, the model learns the mapping relationship from the workpiece feature information, clamping feature information and limit clamping parameters to the workpiece damage coefficient, clamping damage coefficient and clamping stability parameters. Multiple updated limit clamping parameters, workpiece feature information, and clamping feature information are used as inputs to the trained limit clamping predictor, and multiple updated workpiece damage coefficients, multiple updated clamping damage coefficients, and multiple updated clamping stability parameters are obtained as outputs through model calculation. This implementation method collects historical clamping data as training data and uses a data-driven method to predict the clamping effect under new limit clamping parameters, making full use of historical experience and achieving the technical effect of improving the accuracy and reliability of prediction.

[0040] Step S400, using the optimal limit clamping parameters, controlling the clamping device to perform limit clamping and processing of the target workpiece, and after the processing is completed, collecting and identifying to obtain updated workpiece feature information and updated clamping feature information. Specifically, the optimal limit clamping parameters are loaded, including the optimal clamping position parameters and the optimal clamping force parameters, and the loaded optimal limit clamping parameters are set to the control system of the clamping device, and the clamping device is driven by the control system so that the clamping part of the clamping surface moves to the corresponding position of the target workpiece according to the optimal clamping position parameters. After the clamping device reaches the optimal clamping position, it applies an appropriate clamping force according to the optimal clamping force parameters so that the target workpiece is stably clamped on the clamping device. After the target workpiece is stably clamped, the processing equipment (mechanical equipment used to cut, grind, drill, etc. the target workpiece, such as a machine tool, cutting machine, etc.) is started to process the target workpiece. After the processing is completed, the same image acquisition and processing technology as steps S100 and S200 is used to re-capture the clamping surface image of the processed target workpiece, and identify it to obtain updated workpiece feature information, such as the size, shape, surface roughness, etc. after processing. Similarly, images of wear, deformation, etc. that may be generated by the clamping device during the clamping and processing process are collected, identified and processed to obtain updated clamping feature information.

[0041] Step S500, based on the updated workpiece feature information and the updated clamping feature information, the prediction model for predicting the damage of the clamping device and the target workpiece is updated. Specifically, the updated workpiece feature information and the updated clamping feature information are pre-processed such as cleaning and standardization to ensure the quality and consistency of the data. The existing prediction model for predicting the damage of the clamping device and the target workpiece (a model built based on historical data and a machine learning algorithm, used to predict the damage that may occur to the clamping device and the target workpiece during the clamping and processing process) is loaded from the storage system, and the prediction performance of the current model is verified using historical data or a part of the new updated data, such as calculating indicators such as accuracy and recall rate, comparing the model prediction results with the actual damage situation, analyzing the cause of the prediction error, adjusting the parameters of the model such as weights, learning rates, etc. according to the results of the error analysis, to improve the prediction performance of the model, using the new updated data (which may include part of the historical data) to retrain the model, allowing the model to learn new features and patterns, using a part of the new updated data as a verification set to evaluate the prediction performance of the updated model, comparing the prediction results of the updated model with the actual damage situation, evaluating whether the performance of the model has improved, and saving the updated model to the storage system for subsequent use. The embodiment of the present application adopts technical means such as collecting workpiece feature information, collecting clamping feature information, optimizing limit clamping parameters, using optimal limit clamping parameters to limit clamp and process the target workpiece, and updating the prediction model after the processing is completed. The technical effect of optimizing the limit clamping parameters, making the clamping device adapt to the characteristics of different workpieces and clamping devices, improving the clamping stability, and effectively reducing the damage to the workpiece and the clamping device is achieved.

[0042] In a possible implementation, step S500 further includes step S510, according to the updated workpiece feature information and the updated clamping feature information, combined with the workpiece feature information and the clamping feature information, calculate and obtain the real workpiece damage coefficient and the real clamping wear coefficient. Specifically, through physical measurement, equipment detection, expert evaluation or model algorithm, the target workpiece and the clamping device after clamping are evaluated according to the updated workpiece feature information and the updated clamping feature information, and the actual damage degree of the workpiece and the wear degree of the clamping device are determined. Based on the actual evaluation results, combined with the workpiece feature information and the clamping feature information before the clamping operation, the real workpiece damage coefficient and the real clamping wear coefficient are calculated, wherein the real workpiece damage coefficient is a quantitative index indicating the damage degree of the target workpiece in the actual clamping process; the real clamping wear coefficient is a quantitative index indicating the wear degree of the clamping device in the actual clamping process, and these two coefficients reflect the actual effect of the clamping operation. Step S520, using the real workpiece damage coefficient and the real clamping wear coefficient, combined with the optimal limit clamping parameters, the limit clamping predictor is updated and trained. Specifically, the calculated real workpiece damage coefficient and real clamping wear coefficient are combined with the corresponding workpiece feature information, clamping feature information and optimal limit clamping parameters to form new training data, and the limit clamping predictor is updated and trained using the new training data, so that the limit clamping predictor can learn the latest clamping operation experience and effects, thereby improving its prediction accuracy. After the update training is completed, a portion of new data that has not participated in the training can be used to verify the limit clamping predictor to ensure that its prediction performance has been improved. This implementation method continuously collects actual data and updates the limit clamping predictor, so that the limit clamping predictor can continuously adapt to changes in the actual production process, thereby achieving the technical effect of maintaining the effectiveness and accuracy of the limit clamping predictor's prediction performance.

[0043] In the above, refer to Figure 1 A limit clamping control method according to an embodiment of the present invention is described in detail. Figure 2 A positioning control mechanism according to an embodiment of the present invention is described.

[0044] A positioning control mechanism according to an embodiment of the present invention is used to solve the technical problems of unstable clamping effect and unpredictable damage in existing limited clamping control, so as to achieve the technical effect of optimizing the limited clamping parameters, making the clamping device adapt to the characteristics of different workpieces and clamping devices, improving the clamping stability, and effectively reducing the damage to the workpiece and the clamping device. A positioning control mechanism includes: a workpiece feature information acquisition module 10, a clamping feature information acquisition module 20, a limited clamping parameter optimization module 30, an update feature information acquisition module 40, and a prediction model update module 50.

[0045] The workpiece feature information acquisition module 10 is used to collect the clamping surface image of the target workpiece to be clamped, identify it, and obtain the workpiece feature information; the clamping feature information acquisition module 20 is used to collect the clamping surface image of the clamping device, identify it, and obtain the clamping feature information; the limit clamping parameter optimization module 30 is used to move the target workpiece into the clamping device, optimize the limit clamping parameters according to the workpiece feature information and the clamping feature information, and obtain the optimal limit clamping parameters, wherein the optimal limit clamping parameters include the optimal clamping position parameters and the optimal clamping force parameters , by combining the limit clamping parameters with the workpiece feature information and the clamping feature information, the damage to the clamping device and the clamping surface of the target workpiece is predicted and optimized; the updated feature information acquisition module 40 is used to adopt the optimal limit clamping parameters to control the clamping device to perform limit clamping and processing of the target workpiece, and after the processing is completed, collect and identify the updated workpiece feature information and the updated clamping feature information; the prediction model update module 50 is used to update the prediction model for predicting damage to the clamping device and the target workpiece according to the updated workpiece feature information and the updated clamping feature information.

[0046] The specific configuration of the workpiece feature information acquisition module 10 will be described in detail below. As described above, the clamping surface image of the target workpiece to be clamped is collected for identification. The workpiece feature information acquisition module 10 may further include: a sample workpiece clamping surface image set acquisition unit for collecting a sample workpiece clamping surface image set based on the historical detection data of the clamped workpiece; a sample workpiece feature information set acquisition unit for identifying and marking the surface features in the sample workpiece clamping surface image to obtain a sample workpiece feature information set, wherein the surface features include surface shape and surface roughness; a workpiece surface feature identifier training unit for training a workpiece surface feature identifier using the sample workpiece clamping surface image set and the sample workpiece feature information set; a workpiece clamping surface image recognition unit for collecting the clamping surface image of the target workpiece, using the workpiece surface feature identifier to recognize the workpiece clamping surface image to obtain the workpiece feature information.

[0047] The specific configuration of the clamping feature information acquisition module 20 will be described in detail below. As described above, the clamping surface image of the clamping device is collected, identified, and the clamping feature information is obtained. The clamping feature information acquisition module 20 may further include: a sample device clamping surface image set acquisition unit is used to collect a sample device clamping surface image set based on the use data record of the clamping device; a sample clamping feature information set acquisition unit is used to identify and mark the surface features in the sample device clamping surface image, obtain a sample clamping feature information set, and train a clamping surface feature identifier in combination with the sample device clamping surface image set; a device clamping surface image recognition unit is used to collect the clamping surface image of the clamping device, use the clamping surface feature identifier to identify the device clamping surface image, and obtain clamping feature information.

[0048] The specific configuration of the limit clamping parameter optimization module 30 will be described in detail below. As described above, according to the workpiece feature information and the clamping feature information, the limit clamping parameters are optimized to obtain the optimal limit clamping parameters. The limit clamping parameter optimization module 30 may further include: a clamping parameter space acquisition unit for acquiring the clamping position space and the clamping force space for the target workpiece to perform limit clamping, and combining to obtain the clamping parameter space, wherein the clamping position includes the first coordinate position, the second coordinate position and the third coordinate position, and the clamping force includes the clamping force of multiple clamping modules; a clamping function construction unit for constructing a clamping function based on reducing the damage to the clamping surface of the clamping device and the target workpiece after clamping, and improving the clamping stability, as shown in the following formula: , where LCF is the clamping fitness, is the workpiece damage weight, is the clamping damage weight, To stabilize the weight, To predict the damage coefficient of the target workpiece after clamping according to the optimized limit clamping parameters, is the clamping damage coefficient of the clamping device predicted after clamping according to the optimized limit clamping parameters, C is the clamping stability parameter of clamping according to the optimized limit clamping parameters; the limit clamping parameter optimization unit is used to optimize the limit clamping parameters according to the clamping parameter space and the clamping function to obtain the optimal limit clamping parameters, wherein the limit clamping parameters are combined with the workpiece feature information and the clamping feature information to predict the damage to the clamping surface of the clamping device and the target workpiece for optimization.

[0049] Among them, according to the clamping parameter space and the clamping function, the limit clamping parameters are optimized to obtain the optimal limit clamping parameters, and the limit clamping parameter optimization unit may further include: a historical limit clamping parameter random selection subunit is used to randomly select and obtain multiple historical limit clamping parameters as multiple target limit clamping parameters based on the historical clamping parameter data of the same type of workpieces as the target workpiece; a basic limit clamping parameter random generation subunit is used to randomly generate multiple basic limit clamping parameters in the clamping parameter space, and randomly construct a mapping relationship with the multiple target limit clamping parameters; an adjustment and update subunit is used to adjust and update the multiple basic limit clamping parameters according to the preset adjustment step size based on the mapping relationship with the multiple target limit clamping parameters as the adjustment direction, and obtain multiple adjusted limit clamping parameters; a cross-update subunit is used to randomly select parameters from the multiple adjustment limit clamping parameters and the multiple target limit clamping parameters according to the mapping relationship for cross-update, and obtain multiple updated Limit clamping parameters; multiple updated clamping fitness acquisition subunits are used to predict and obtain multiple updated workpiece damage coefficients, multiple updated clamping damage coefficients and multiple updated clamping stability parameters according to the multiple updated limit clamping parameters, combined with the workpiece feature information and the clamping feature information, and calculate and obtain multiple updated clamping fitnesses; multiple target clamping fitness acquisition subunits are used to process and calculate to obtain multiple target clamping fitnesses of the multiple target limit clamping parameters; the target limit clamping parameter updating subunit is used to distinguish according to the multiple updated clamping fitnesses and the multiple target clamping fitnesses based on the mapping relationship, and use the limit clamping parameters with large clamping fitness as the target limit clamping parameters to obtain the updated multiple target limit clamping parameters; the optimal limit clamping parameter acquisition subunit is used to continue to randomly generate new basic limit clamping parameters based on the multiple target limit clamping parameters, perform iterative optimization until the convergence requirements are met, output the limit clamping parameters with the largest clamping fitness, and obtain the optimal limit clamping parameters.

[0050] Among them, according to the multiple updated limit clamping parameters, combined with the workpiece feature information and the clamping feature information, multiple updated workpiece damage coefficients, multiple updated clamping damage coefficients and multiple updated clamping stability parameters are predicted and obtained, and multiple updated clamping fitness acquisition sub-units may further include: a clamping prediction training data acquisition micro-unit is used to collect a sample workpiece feature information set, a sample clamping feature information set, and a sample limit clamping parameter set according to the clamping data record of the clamping device, and according to the clamping result, collect a sample workpiece damage coefficient set, a sample clamping damage coefficient set and a sample clamping stability parameter set as clamping prediction training data; an input prediction micro-unit is used to use the clamping prediction training data to train a limit clamping predictor, perform input prediction on the multiple updated limit clamping parameters, workpiece feature information and clamping feature information, and obtain multiple updated workpiece damage coefficients, multiple updated clamping damage coefficients and multiple updated clamping stability parameters.

[0051] The specific configuration of the prediction model update module 50 will be described in detail below. As described above, according to the updated workpiece feature information and the updated clamping feature information, the prediction model for predicting damage to the clamping device and the target workpiece is updated, and the prediction model update module 50 may further include: a damage wear coefficient calculation unit for calculating the real workpiece damage coefficient and the real clamping wear coefficient according to the updated workpiece feature information and the updated clamping feature information, combined with the workpiece feature information and the clamping feature information; an update training unit for using the real workpiece damage coefficient and the real clamping wear coefficient, combined with the optimal limit clamping parameters, to update the limit clamping predictor.

[0052] A positioning control mechanism provided in an embodiment of the present invention can execute a limit clamping control method provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects of the execution method.

[0053] Although the present application makes various references to certain modules in the mechanism according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0054] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A limit clamping control method, characterized in that: The method is applied to a clamping device, and the method comprises: Collecting the clamping surface image of the target workpiece to be clamped, performing recognition, and obtaining the workpiece feature information; Collecting the clamping surface image of the clamping device, performing identification, and obtaining clamping feature information; The target workpiece is moved into the clamping device, and the limit clamping parameters are optimized according to the workpiece feature information and the clamping feature information to obtain the optimal limit clamping parameters, wherein the optimal limit clamping parameters include the optimal clamping position parameters and the optimal clamping force parameters, and the damage to the clamping surface of the clamping device and the target workpiece is predicted and optimized by combining the limit clamping parameters with the workpiece feature information and the clamping feature information; The optimal limit clamping parameters are used to control the clamping device to perform limit clamping and processing of the target workpiece, and after the processing is completed, the updated workpiece feature information and the updated clamping feature information are collected and identified; updating a prediction model for predicting damage to the clamping device and the target workpiece according to the updated workpiece feature information and the updated clamping feature information; According to the workpiece feature information and the clamping feature information, the limit clamping parameters are optimized to obtain the optimal limit clamping parameters, including: Obtaining a clamping position space and a clamping force space for limited clamping of a target workpiece, and combining them to obtain a clamping parameter space, wherein the clamping position includes a first coordinate position, a second coordinate position, and a third coordinate position, and the clamping force includes the clamping force of multiple clamping modules; Based on reducing the damage to the clamping device and the clamping surface of the target workpiece after clamping and improving the clamping stability, a clamping function is constructed as follows: ； Among them, LCF is the clamping fitness, is the workpiece damage weight, is the clamping damage weight, To stabilize the weight, To predict the damage coefficient of the target workpiece after clamping according to the optimized limit clamping parameters, is the clamping damage coefficient of the clamping device predicted after clamping according to the optimized limit clamping parameters, and C is the clamping stability parameter of clamping according to the optimized limit clamping parameters; According to the clamping parameter space and the clamping function, the limit clamping parameters are optimized to obtain the optimal limit clamping parameters, wherein the limit clamping parameters are combined with the workpiece feature information and the clamping feature information to predict the damage to the clamping surface of the clamping device and the target workpiece, and then the optimization is performed; According to the clamping parameter space and the clamping function, the limit clamping parameters are optimized to obtain the optimal limit clamping parameters, including: According to the historical clamping parameter data of the same type of workpiece as the target workpiece, a plurality of historical limit clamping parameters are randomly selected to be used as a plurality of target limit clamping parameters; Randomly generating a plurality of basic limit clamping parameters in the clamping parameter space, and randomly constructing a mapping relationship with the plurality of target limit clamping parameters; Taking the multiple target limit clamping parameters as adjustment directions, adjusting and updating the multiple basic limit clamping parameters according to the mapping relationship and a preset adjustment step length, to obtain multiple adjusted limit clamping parameters; According to the mapping relationship, randomly select parameters from the multiple adjustment limit clamping parameters and the multiple target limit clamping parameters for cross-update to obtain multiple updated limit clamping parameters; According to the multiple updated limit clamping parameters, in combination with the workpiece feature information and the clamping feature information, multiple updated workpiece damage coefficients, multiple updated clamping damage coefficients and multiple updated clamping stability parameters are predicted and obtained, and multiple updated clamping fitnesses are calculated; Processing and calculating to obtain multiple target clamping adaptabilities of the multiple target limit clamping parameters; Based on the mapping relationship, a judgment is made according to the multiple updated clamping fitnesses and the multiple target clamping fitnesses, and the limit clamping parameter with a large clamping fitness is used as the target limit clamping parameter to obtain the updated multiple target limit clamping parameters; Based on the multiple target limit clamping parameters, continue to randomly generate new basic limit clamping parameters, perform iterative optimization until convergence requirements are met, output the limit clamping parameters with the maximum clamping fitness, and obtain the optimal limit clamping parameters; Among them, according to the multiple updated limit clamping parameters, combined with the workpiece feature information and the clamping feature information, predicting and obtaining multiple updated workpiece damage coefficients, multiple updated clamping damage coefficients and multiple updated clamping stability parameters, including: According to the clamping data record of the clamping device, a sample workpiece feature information set, a sample clamping feature information set, and a sample limit clamping parameter set are collected, and according to the clamping result, a sample workpiece damage coefficient set, a sample clamping damage coefficient set, and a sample clamping stability parameter set are collected as clamping prediction training data; The clamping prediction training data is used to train a limit clamping predictor, and the multiple updated limit clamping parameters, workpiece feature information and clamping feature information are input for prediction to obtain multiple updated workpiece damage coefficients, multiple updated clamping damage coefficients and multiple updated clamping stability parameters; Wherein, updating the prediction model for predicting damage of the clamping device and the target workpiece according to the updated workpiece feature information and the updated clamping feature information includes: According to the updated workpiece feature information and the updated clamping feature information, combined with the workpiece feature information and the clamping feature information, a real workpiece damage coefficient and a real clamping wear coefficient are calculated; The limit clamping predictor is updated and trained by using the real workpiece damage coefficient and the real clamping wear coefficient in combination with the optimal limit clamping parameters.

2. A limit clamping control method according to claim 1, characterized in that: Collect the clamping surface image of the target workpiece to be clamped and identify it, including: Based on the historical inspection data of the clamped workpiece, a set of clamping surface images of the sample workpiece is collected; Identify and mark the surface features in the clamping surface image of the sample workpiece to obtain a sample workpiece feature information set, wherein the surface features include surface shape and surface roughness; Using the sample workpiece clamping surface image set and the sample workpiece feature information set to train a workpiece surface feature identifier; The clamping surface image of the target workpiece is collected, and the workpiece surface feature identifier is used to identify the workpiece clamping surface image to obtain the workpiece feature information.

3. A limit clamping control method according to claim 1, characterized in that: Collect the clamping surface image of the clamping device, identify it, and obtain clamping feature information, including: Based on the usage data record of the clamping device, a set of images of the clamping surface of the sample device is collected; Identify and mark the surface features in the sample device clamping surface image to obtain a sample clamping feature information set, and train a clamping surface feature identifier in combination with the sample device clamping surface image set; The clamping surface image of the clamping device is collected, and the clamping surface feature identifier is used to identify the clamping surface image of the device to obtain clamping feature information.

4. A positioning control mechanism, characterized in that: The positioning control mechanism is used to implement a limit clamping control method according to any one of claims 1 to 3, and the positioning control mechanism comprises: A workpiece feature information acquisition module, which is used to collect a clamping surface image of a target workpiece to be clamped, perform identification, and obtain workpiece feature information; A clamping feature information acquisition module, which is used to collect a clamping surface image of the clamping device, perform identification, and obtain clamping feature information; A limit clamping parameter optimization module, the limit clamping parameter optimization module is used to move the target workpiece into the clamping device, optimize the limit clamping parameters according to the workpiece feature information and the clamping feature information, and obtain the optimal limit clamping parameters, wherein the optimal limit clamping parameters include the optimal clamping position parameters and the optimal clamping force parameters, and the limit clamping parameters are combined with the workpiece feature information and the clamping feature information to predict the damage to the clamping surface of the clamping device and the target workpiece, and optimize the optimization; An updated feature information acquisition module, the updated feature information acquisition module is used to use the optimal limit clamping parameters to control the clamping device to perform limit clamping and processing of the target workpiece, and after the processing is completed, collect and identify updated workpiece feature information and updated clamping feature information; A prediction model updating module is used to update the prediction model for predicting damage to the clamping device and the target workpiece according to the updated workpiece feature information and the updated clamping feature information.

Images