Efficient Processing Control Method, Device, Equipment and Storage Medium Based on Cloud Platform

Abstract

The present invention relates to the technical field of workpiece processing control, and in particular to an efficient processing control method, device, equipment and storage medium based on a cloud platform. The method includes the following steps: acquiring multi-directional monitoring images of workpiece processing and workpiece processing parameters; performing full-image brightness equalization calculation on the multi-directional monitoring images of workpiece processing and optimizing the details by high-frequency filtering to construct a detail-optimized workpiece image; performing three-dimensional geometric structure analysis on the detail-optimized workpiece image and carrying out three-dimensional point cloud modeling to construct a fine point cloud structure model of the workpiece; obtaining multi-stage processing operation data based on the workpiece processing parameters; performing global operation process reconstruction on the multi-stage processing operation data to construct a reconstructed processing operation series; and performing dynamic operation mapping on the fine point cloud structure model of the workpiece based on the reconstructed processing operation series to construct a dynamic workpiece processing twin model. The present invention realizes efficient and accurate workpiece processing control.

Description

Technical Field

[0001] The present invention relates to the technical field of workpiece processing control, and particularly relates to an efficient processing control method, device, equipment and storage medium based on a cloud platform. Background Technique

[0002] With the continuous improvement of industrial automation and intelligent manufacturing levels, various numerical control equipment and industrial robots are widely used in production processing, assembly and other links, playing a key role in improving manufacturing efficiency and product quality. Taking the numerical control processing technology as an example, as one of the core technologies in the manufacturing industry, it has long been responsible for high-precision and high-efficiency workpiece processing tasks, and the optimization of its processing quality and production efficiency directly affects the operation efficiency of the entire manufacturing system.

[0003] However, in actual production, the numerical control processing technology is easily affected by various factors, such as tool wear of machine tools, changes in material properties, fluctuations in environmental temperature and humidity, etc. These factors may cause deviations in workpiece processing quality and even serious processing defects. Traditional processing control methods often rely on experienced operators for manual intervention and adjustment, with low efficiency and difficult to achieve adaptive precise control. With the continuous improvement of the intelligence and automation levels of industrial production, there is an urgent need for an efficient workpiece processing control method based on intelligent technology to meet the continuous improvement requirements of modern manufacturing for product quality and production efficiency. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention proposes an efficient processing control method, device, equipment and storage medium based on a cloud platform to solve at least one of the above technical problems.

[0005] To achieve the above object, the present invention provides an efficient processing control method for a cloud platform, including the following steps:

[0006] Step S1: Obtain multi-directional monitoring images of workpiece processing and workpiece processing parameters; perform full-image brightness equalization calculation on the multi-directional monitoring images of workpiece processing, and perform high-frequency filtering detail optimization to construct a detail-optimized workpiece image;

[0007] Step S2: Perform three-dimensional geometric structure analysis on the detail-optimized workpiece image, and perform three-dimensional point cloud modeling to construct a fine point cloud structure model of the workpiece;

[0008] Step S3: Obtain multi-stage processing operation data based on the workpiece processing parameters; perform global operation process reconstruction on the multi-stage processing operation data to construct a reconstructed processing operation series;

[0009] Step S4: Perform dynamic operation mapping on the fine point cloud structure model of the workpiece based on the reconstructed processing operation series to construct a dynamic workpiece processing twin model;

[0010] Step S5: Perform multi-group parameter fine-tuning definitions based on workpiece processing parameters to obtain multiple fine-tuned processing parameters; perform dynamic machining path planning based on the multiple fine-tuned processing parameters to generate multiple machining planning paths;

[0011] Step S6: Make an optimal parameter adjustment decision for the dynamic workpiece machining twin model based on the multiple machining planning paths to obtain an optimal parameter adjustment strategy; execute the automated control operation of workpiece machining based on the optimal parameter adjustment strategy.

[0012] The present invention also provides an efficient machining control device based on a cloud platform, including:

[0013] An image enhancement module, which acquires multi-directional monitoring images of workpiece machining and workpiece processing parameters; performs full-image brightness equalization calculation on the multi-directional monitoring images of workpiece machining, and performs high-frequency filtering detail optimization to construct a detail-optimized workpiece image;

[0014] A three-dimensional structure module, which performs three-dimensional geometric structure analysis on the detail-optimized workpiece image and performs three-dimensional point cloud modeling to construct a fine workpiece point cloud structure model;

[0015] A process dependency mining module, which obtains multi-stage machining process data based on workpiece processing parameters; performs global process flow reconstruction on the multi-stage machining process data to construct a reconstructed machining process series;

[0016] A dynamic process mapping module, which performs dynamic process mapping on the fine workpiece point cloud structure model based on the reconstructed machining process series to construct a dynamic workpiece machining twin model;

[0017] An iterative simulation module, which performs multi-group parameter fine-tuning definitions based on workpiece processing parameters to obtain multiple fine-tuned processing parameters; performs dynamic machining path planning based on the multiple fine-tuned processing parameters to generate multiple machining planning paths;

[0018] An optimal parameter adjustment module, which makes an optimal parameter adjustment decision for the dynamic workpiece machining twin model based on the multiple machining planning paths to obtain an optimal parameter adjustment strategy; executes the automated control operation of workpiece machining based on the optimal parameter adjustment strategy.

[0019] The present invention also provides a computer device, including a memory and a processor, where a computer program is stored in the memory, and when the processor executes the computer program, the steps of the efficient machining control method based on the cloud platform described in any one of the above are implemented.

[0020] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the efficient machining control method based on the cloud platform described in any one of the above are implemented.

[0021] The efficient machining control method, device, equipment and storage medium based on the cloud platform provided by the present invention have the following beneficial effects: Through full-image brightness equalization calculation and high-frequency filtering detail optimization, it helps to improve the image quality, making the surface details of the workpiece clearer. Constructing a detail-optimized workpiece image helps to accurately analyze the features and defects on the surface of the workpiece, providing a more accurate data basis for subsequent steps. Three-dimensional geometric structure analysis and point cloud modeling help to obtain the geometric information of the workpiece, providing an accurate reference for subsequent machining processes. Constructing a fine point cloud structure model of the workpiece can provide precise three-dimensional model data for subsequent processes, improving the machining accuracy and efficiency. Global process flow reconstruction helps to optimize the machining process, improving the machining efficiency and quality. Constructing a reconstructed machining process series can make the machining process more orderly and controllable, reducing potential errors and waste. Dynamic process mapping helps to effectively match the process with the workpiece structure, improving the machining accuracy and efficiency. Constructing a dynamic workpiece machining twin model can achieve virtual simulation, helping to optimize the machining process and reduce risks in actual machining. Multiple groups of parameter fine-tuning definitions can optimize machining parameters, improving the machining quality and efficiency. Dynamic machining path planning can generate diverse machining paths according to different parameter settings, providing more choices for selecting the optimal path. The optimal parameter adjustment strategy can ensure the best effect of the machining process, improving the machining quality and efficiency. Executing the automatic control operation of workpiece machining can reduce human intervention, improving the automation level and consistency of production. Description of the Drawings

[0022] Figure 1 It is a schematic flow chart of the steps of an efficient machining control method based on the cloud platform according to the present invention;

[0023] Figure 2 It is a schematic detailed implementation step flow chart of step S1;

[0024] Figure 3 It is a schematic detailed implementation step flow chart of step S2;

[0025] Figure 4 It is a schematic detailed implementation step flow chart of step S3. Detailed Embodiments

[0026] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0027] The embodiments of the present application provide an efficient processing control method, device, equipment, and storage medium based on a cloud platform. The execution subjects of the efficient processing control method, device, equipment, and storage medium based on the cloud platform include, but are not limited to, the following that are equipped with this system: mechanical equipment, data processing platforms, cloud server nodes, network upload devices, etc., which can be regarded as general computing nodes of the present application. The data processing platform includes, but is not limited to, at least one of an audio and image management system, an information management system, and a cloud data management system.

[0028] In the embodiments of the present invention, refer to Figure 1 , which is a schematic diagram of the step flow of an efficient processing control method based on a cloud platform of the present invention. In this example, the steps of the efficient processing control method based on the cloud platform include:

[0029] Step S1: Obtain multi-directional monitoring images of workpiece processing and workpiece processing parameters; perform full-image brightness equalization calculation on the multi-directional monitoring images of workpiece processing, and perform high-frequency filtering detail optimization to construct a detail-optimized workpiece image;

[0030] In this embodiment, a multi-angle camera or other image acquisition device is used to obtain multi-directional monitoring images during workpiece processing. At the same time, workpiece processing parameters are recorded, such as processing speed, processing depth, processing time, etc. The brightness histogram of each image is analyzed to determine the brightness distribution of the image. A brightness equalization algorithm, such as histogram equalization, adaptive histogram equalization, etc., is used to perform brightness equalization processing on the image. A brightness-equalized workpiece image is generated to make the brightness distribution of the image more uniform, improve the contrast and clarity of the image. A suitable image high-frequency filter, such as a Laplacian operator, Gaussian filter, etc., is selected to enhance the detail information of the image. High-frequency filtering processing is performed on the brightness-equalized image to enhance the detail information such as edges and textures of the image. A detail-optimized workpiece image is generated to make the details of the image clearer, which is beneficial to subsequent image analysis and recognition.

[0031] Step S2: Perform three-dimensional geometric structure analysis on the detail-optimized workpiece image, and perform three-dimensional point cloud modeling to construct a fine point cloud structure model of the workpiece;

[0032] In this embodiment, the multi-directional monitoring images are registered, and the images at different angles are stitched into a complete workpiece image. Image feature extraction algorithms, such as edge detection, corner detection, etc., are used to extract feature points in the workpiece image. Three-dimensional geometric structure reconstruction algorithms, such as stereo vision, structured light scanning, etc., are used to reconstruct the three-dimensional geometric structure of the workpiece according to the extracted feature points. According to the reconstructed three-dimensional geometric structure, a point cloud model of the workpiece is generated, and each point represents a point on the surface of the workpiece. The generated point cloud model is optimized, such as removing noise points, filling missing points, etc., to improve the quality of the point cloud model. A fine point cloud structure model of the workpiece is constructed, which contains all the point cloud data on the surface of the workpiece and the coordinate information of each point.

[0033] Step S3: Obtain multi-stage machining process data based on the workpiece machining parameters; perform global process flow reconstruction on the multi-stage machining process data to construct a reconstructed machining process series;

[0034] In this embodiment, the workpiece machining parameters, such as machining speed, machining depth, machining path, etc., are analyzed to identify different machining stages. According to different machining stages, the corresponding machining process data is extracted, such as the machining time, machining path, machining tool, etc. for each stage. Multi-stage machining process data is generated, with each stage corresponding to a set of process data, which is used as the input data for the subsequent steps. The multi-stage machining process data is analyzed to identify the machining objectives and machining sequences for each stage. According to the machining objectives and machining sequences, the process flow is optimized, such as adjusting the machining sequence, merging repeated processes, etc. A reconstructed machining process series is constructed, which contains the optimized machining process sequence and the detailed data for each process, and is used as the input data for the subsequent steps.

[0035] Step S4: Perform dynamic process mapping on the fine point cloud structure model of the workpiece based on the reconstructed machining process series to construct a dynamic workpiece machining twin model;

[0036] In this embodiment, according to the processing objectives and processing paths of each process in the reconstructed processing process series, process mapping rules are defined. For example, each process is mapped to a specific area in the point cloud model, or each process is mapped to a specific feature point in the point cloud model. According to the defined process mapping rules, each process in the reconstructed processing process series is dynamically mapped to the fine point cloud structure model of the workpiece, realizing the association between the process and the point cloud model. Dynamic process mapping data is generated to record the point cloud model area or feature point information corresponding to each process, serving as the input data for subsequent steps. A suitable dynamic workpiece processing twin model framework is selected, such as a physics-based framework, a machine learning-based framework, etc. According to the reconstructed processing process series, the fine point cloud structure model of the workpiece, and the dynamic process mapping data, the parameters of the twin model are set, such as processing speed, processing depth, processing path, etc. The twin model is trained using training data, such as historical processing data, simulation data, etc. A dynamic workpiece processing twin model is constructed, which can simulate the workpiece processing process and predict the processing results according to different processing parameters.

[0037] Step S5: Based on the workpiece processing parameters, multiple groups of parameter fine-tuning definitions are performed to obtain multiple fine-tuned processing parameters; based on the multiple fine-tuned processing parameters, dynamic processing path planning is carried out to generate multiple processing planning paths;

[0038] In this embodiment, according to the actual situation of the workpiece processing parameters, the fine-tuning range of each parameter is determined. For example, the fine-tuning range of the processing speed can be ±10%, and the fine-tuning range of the processing depth can be ±0.1 mm. According to the fine-tuning range of each parameter, multiple parameter combinations are generated. For example, 10 groups of parameter combinations can be generated, and each group of parameter combinations corresponds to a fine-tuned processing parameter. Multiple fine-tuned processing parameters are generated, and each fine-tuned processing parameter corresponds to a parameter combination, serving as the input data for subsequent steps. A suitable dynamic processing path planning algorithm is selected, such as a geometric constraint-based algorithm, an optimization objective-based algorithm, etc. According to each fine-tuned processing parameter, the parameters of the path planning algorithm are set, such as processing speed, processing depth, processing path, etc. Using the dynamic path planning algorithm, according to each fine-tuned processing parameter, multiple processing planning paths are generated, and each processing planning path corresponds to a fine-tuned processing parameter, serving as the input data for subsequent steps.

[0039] Step S6: Based on the multiple processing planning paths, an optimal parameter adjustment decision is made for the dynamic workpiece processing twin model to obtain an optimal parameter adjustment strategy; based on the optimal parameter adjustment strategy, automated control operations for workpiece processing are executed.

[0040] In this embodiment, a dynamic workpiece machining twin model is used to simulate each machining planning path and predict the machining results of each path, such as machining time, machining accuracy, machining cost, etc. According to the simulation results of the twin model, the parameter adjustment strategies corresponding to each machining planning path are evaluated. For example, the evaluation can be carried out according to indicators such as machining time, machining accuracy, and machining cost. According to the evaluation results, the optimal parameter adjustment strategy is selected. For example, the selection can be made according to comprehensive indicators or specific indicators. According to the optimal parameter adjustment strategy, a parameter adjustment instruction is generated. For example, parameters such as machining speed, machining depth, and machining path are adjusted. The parameter adjustment instruction is sent to an automated control system, such as a numerically controlled machine tool, a robot, etc., to perform the workpiece machining operation. The machining process is monitored in real time. For example, parameters such as machining speed, machining depth, and machining path are monitored to ensure that the machining process meets the expectations.

[0041] In this embodiment, refer to Figure 2 , which is a schematic diagram of the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0042] Step S11: Obtain multi-directional monitoring images of workpiece machining and workpiece machining parameters;

[0043] Step S12: Perform full-image brightness equalization calculation on the multi-directional monitoring images of workpiece machining to obtain the average image brightness;

[0044] Step S13: Perform brightness distribution enhancement processing on the workpiece machining monitoring images based on the average image brightness to generate a brightness-enhanced workpiece image;

[0045] Step S14: Perform contour visual recognition on the brightness-enhanced workpiece image to extract the workpiece contour line;

[0046] Step S15: Perform high-frequency filtering detail optimization based on the workpiece contour line to construct a detail-optimized workpiece image.

[0047] In this embodiment, during the workpiece processing, multiple cameras are used to monitor and photograph the workpiece in all directions. At the same time, various parameters of the workpiece processing equipment are collected, such as processing speed, feed rate, current, etc. The global brightness distribution of each monitoring image is analyzed, and the average brightness value of each image is calculated as the reference basis for subsequent brightness enhancement. According to the calculated average brightness value, the global brightness of the original monitoring image is adjusted, and methods such as histogram equalization or gamma correction are used to improve the overall brightness and contrast of the image, generating a workpiece image with enhanced brightness, providing a good visual basis for subsequent contour recognition. Computer vision techniques such as edge detection and contour extraction are used to extract the contour line of the workpiece from the brightness-enhanced image, obtaining the precise contour information of the workpiece shape. The extracted workpiece contour line is smoothed to remove high-frequency noise and burrs, and methods such as edge-preserving filtering are used to optimize the detail quality of the workpiece image, generating a workpiece image with optimized details.

[0048] In this embodiment, refer to Figure 3 , which is a schematic diagram of the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0049] Step S21: Mark the key points of the workpiece on the workpiece image with optimized details, and extract multiple workpiece feature points;

[0050] Step S22: Conduct multi-directional visual difference analysis on multiple workpiece feature points to obtain multi-directional parallax feature data of the image;

[0051] Step S23: Conduct three-dimensional geometric structure analysis on the workpiece image with optimized details based on the multi-directional parallax feature data of the image, thereby generating three-dimensional geometric structure data of the workpiece;

[0052] Step S24: Conduct three-dimensional point cloud modeling on the three-dimensional geometric structure data of the workpiece to generate an initial structure model of the workpiece;

[0053] Step S25: Conduct local iterative refinement on the initial structure model of the workpiece to construct a fine point cloud structure model of the workpiece.

[0054] In this embodiment, image processing algorithms, such as SIFT feature point detection algorithm, ORB feature point detection algorithm, etc., are used to mark key points on the workpiece image for detail optimization, identify the feature points of the workpiece, extract the marked key points, and record their coordinate information as the input data for subsequent steps. The workpiece images obtained from different angles are matched. For example, the feature point matching algorithm is used to find the corresponding relationship of the corresponding feature points in different images. According to the matching result, the disparity of the corresponding feature points in different images is calculated to obtain the multi-directional disparity feature data of the image. Three-dimensional reconstruction algorithms, such as stereo vision reconstruction algorithm, multi-view geometry reconstruction algorithm, etc., are used to perform three-dimensional geometric structure analysis on the workpiece according to the multi-directional disparity feature data of the image, and generate three-dimensional geometric structure data of the workpiece, such as point cloud data, mesh model, etc. Point cloud modeling algorithms, such as Poisson reconstruction algorithm, triangular meshing algorithm, etc., are used to perform point cloud modeling on the three-dimensional geometric structure data of the workpiece to generate the initial structure model of the workpiece. The initial structure model of the workpiece is generated as the input data for subsequent steps. The local iterative refinement algorithm, such as the refinement algorithm based on surface fitting, the refinement algorithm based on geometric constraints, etc., is used to perform local iterative refinement on the initial structure model of the workpiece to improve the accuracy and details of the model. A fine point cloud structure model of the workpiece is generated for subsequent workpiece quality assessment and defect detection.

[0055] In this embodiment, refer to Figure 4 , which is a schematic diagram of the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0056] Step S31: Perform a temporal variation analysis on the workpiece processing parameters to generate temporal variation processing parameters;

[0057] Step S32: Identify the phased process for the temporal variation processing parameters to obtain multi-stage processing operation data;

[0058] Step S33: Dig deep into the process dependence depth of the multi-stage processing operation data to generate the dependence relationship between stage processes;

[0059] Step S34: Analyze the operation characteristics of the multi-stage processing operation data to obtain the operation characteristic parameters of each stage process;

[0060] Step S35: Based on the dependence relationship between stage processes, globally reconstruct the operation characteristic parameters of each stage process to construct a reconstructed processing operation series.

[0061] In this embodiment, a time series analysis method, such as the moving average method, the exponential smoothing method, etc., is used to perform time series change analysis on the collected parameter data to identify the change trend of the parameters over time. According to the time series analysis results, time series change processing parameters are generated, such as the change curve of the processing speed over time, the change curve of the processing depth over time, etc. An operation identification algorithm, such as cluster analysis, pattern recognition, etc., is used to analyze the time series change processing parameters to identify different processing stages. According to the operation identification results, multi-stage processing operation data is generated, such as the processing time, processing speed, processing depth, etc. of each stage. A dependency mining algorithm, such as the association rule mining algorithm, the causal reasoning algorithm, etc., is used to analyze the multi-stage processing operation data to mine the dependency relationships between the operations of different stages. According to the dependency mining results, the dependency relationships between the stage operations are generated, such as the processing speed of stage 1 affects the processing depth of stage 2, etc. A feature analysis method, such as statistical analysis, machine learning, etc., is used to analyze the operation data of each stage to extract the operation characteristic parameters of the operation of this stage, such as the average value of the processing speed, the standard deviation of the processing depth, etc. The operation characteristic parameters of each stage operation are generated as the input data for the subsequent steps. A process reconstruction algorithm, such as the constraint-based process reconstruction algorithm, the optimization-based process reconstruction algorithm, etc., is used to perform global process reconstruction on the operation characteristic parameters of each stage operation according to the dependency relationships between the stage operations to optimize the process flow and improve the processing efficiency. A reconstructed processing operation series is generated for subsequent workpiece processing optimization and control.

[0062] In this embodiment, step S4 includes the following steps:

[0063] Step S41: Dynamically perform process machining positioning on the fine point cloud structure model of the workpiece based on the reconstructed processing operation series to obtain point cloud machining positioning points;

[0064] Step S42: Perform machining form change analysis on the point cloud machining positioning points to obtain positioning point form change data;

[0065] Step S43: Perform position and attitude change analysis on the positioning point form change data to obtain positioning point position and attitude change data;

[0066] Step S44: Perform dynamic operation mapping on the fine point cloud structure model of the workpiece according to the positioning point position and attitude change data to construct a dynamic workpiece machining twin model.

[0067] In this embodiment, the series of reconstruction processing operations is mapped onto the fine point cloud structure model of the workpiece to determine the region corresponding to each operation on the point cloud model. According to the dynamic changes of the operations, such as machining speed, machining depth, etc., the position of the operation on the point cloud model is dynamically adjusted to determine the point cloud machining positioning points. The point cloud machining positioning points are generated as the input data for the subsequent steps. The morphological analysis algorithm is used, such as the morphological analysis algorithm based on geometric features, the morphological analysis algorithm based on deep learning, etc., to perform morphological change analysis on the point cloud machining positioning points. According to the morphological analysis results, the morphological change data of the positioning points is generated, such as the change information of the shape, size, position, etc. of the point cloud. The attitude change analysis algorithm is used, such as the attitude change analysis algorithm based on feature point matching, the attitude change analysis algorithm based on inertial measurement unit, etc., to perform position and attitude change analysis on the morphological change data of the positioning points. According to the attitude change analysis results, the position and attitude change data of the positioning points is generated, such as the change information of the position, direction, rotation, etc. of the point cloud. The dynamic mapping algorithm is used, such as the dynamic mapping algorithm based on geometric transformation, the dynamic mapping algorithm based on physical simulation, etc., to perform dynamic operation mapping on the fine point cloud structure model of the workpiece according to the position and attitude change data of the positioning points. A dynamic workpiece machining twin model is constructed, which can reflect the dynamic changes during the workpiece machining process in real time, and is used to simulate and predict the machining process, and to optimize and control it.

[0068] In this embodiment, the specific steps of step S5 are as follows:

[0069] Step S51: Define multiple groups of parameter fine-tuning based on the workpiece machining parameters, so as to obtain multiple fine-tuned machining parameters;

[0070] Step S52: Perform iterative parameter adjustment simulation on the dynamic workpiece machining twin model based on multiple fine-tuned machining parameters, so as to obtain iterative machining simulation data;

[0071] Step S53: Perform dynamic machining path planning on the iterative machining simulation data to generate multiple machining planning paths.

[0072] In this embodiment, according to the actual situation of workpiece processing parameters, the fine-tuning range of each parameter is determined. For example, the fine-tuning range of the processing speed is ±5%, and the fine-tuning range of the processing depth is ±0.1 mm, etc. According to the parameter range, multiple groups of parameter combinations are defined. For example, 10 groups of different parameter combinations can be defined, and each group of parameter combinations corresponds to different processing speeds and processing depths. Multiple fine-tuning processing parameters are generated, and each parameter combination corresponds to a fine-tuning processing parameter, which is used as the input data for the subsequent steps. Using simulation algorithms, such as algorithms based on physical simulation, algorithms based on machine learning, etc., iterative parameter adjustment simulation is performed on the dynamic workpiece processing twin model. Each fine-tuning processing parameter is applied to the dynamic workpiece processing twin model respectively for simulation calculation, and the simulation results are observed, such as processing time, processing quality, processing efficiency, etc. Iterative processing simulation data is generated, and the simulation results corresponding to each fine-tuning processing parameter are recorded, which is used as the input data for the subsequent steps. Using path planning algorithms, such as path planning algorithms based on geometric constraints, path planning algorithms based on optimization algorithms, etc., dynamic processing path planning is performed on the iterative processing simulation data. According to the iterative processing simulation data, such as processing time, processing quality, etc., the optimal processing parameter combination is selected, and the processing path is planned according to this parameter combination. Multiple processing planning paths are generated, and each path corresponds to a different processing parameter combination, which is used for the subsequent selection and optimization of the processing process.

[0073] In this embodiment, the specific steps of step S6 are as follows:

[0074] Step S61: Perform a comprehensive evaluation of the processing simulation of the dynamic workpiece processing twin model based on multiple processing planning paths, so as to obtain multiple groups of planning path evaluation values;

[0075] Step S62: Extract the optimal planning path based on multiple groups of planning path evaluation values;

[0076] Step S63: Make an optimal parameter adjustment decision on the optimal planning path, so as to obtain an optimal parameter adjustment strategy;

[0077] Step S64: Upload the optimal parameter adjustment strategy to the cloud platform to execute the automated control operation of workpiece processing.

[0078] In this embodiment, a simulation evaluation algorithm is used, for example, an evaluation algorithm based on a simulation model, an evaluation algorithm based on machine learning, etc., to perform machining simulation on the dynamic workpiece machining twin model, and comprehensively evaluate each machining planning path. Appropriate evaluation indicators are selected, such as machining time, machining quality, machining efficiency, cost, etc., to evaluate each machining planning path. Multiple sets of planning path evaluation values are generated, with each planning path corresponding to a set of evaluation values, which are used as input data for subsequent steps. The multiple sets of planning path evaluation values are compared. For example, the path with the shortest machining time, the best machining quality, the highest machining efficiency, and the lowest cost is selected. According to the comparison result of the evaluation values, the optimal planning path is extracted and used as input data for subsequent steps. According to the optimal planning path, the optimal parameter adjustment strategy is determined, such as adjusting parameters such as machining speed, machining depth, and machining path to optimize the machining process. The optimal parameter adjustment strategy is generated and used as input data for subsequent steps. The optimal parameter adjustment strategy is applied to the workpiece machining automation control cloud platform, such as a numerically controlled machine tool, a robot, etc., to control the machining process. The workpiece machining automation control operation is executed, and the machining process is controlled according to the optimal parameter adjustment strategy to achieve the best machining effect.

[0079] In this embodiment, the present invention also provides an efficient machining control device based on a cloud platform, including:

[0080] An image enhancement module, which acquires multi-directional monitoring images of workpiece machining and workpiece machining parameters; performs full-image brightness equalization calculation on the multi-directional monitoring images of workpiece machining, and performs high-frequency filtering detail optimization, so as to construct a detail-optimized workpiece image;

[0081] A three-dimensional structure module, which performs three-dimensional geometric structure analysis on the detail-optimized workpiece image, and performs three-dimensional point cloud modeling to construct a fine workpiece point cloud structure model;

[0082] A process dependency mining module, which obtains multi-stage machining process data based on the workpiece machining parameters; performs global process flow reconstruction on the multi-stage machining process data to construct a reconstructed machining process series;

[0083] A dynamic process mapping module, which performs dynamic process mapping on the fine workpiece point cloud structure model based on the reconstructed machining process series to construct a dynamic workpiece machining twin model;

[0084] An iterative simulation module, which performs multiple sets of parameter fine-tuning definitions based on the workpiece machining parameters to obtain multiple fine-tuned machining parameters; performs dynamic machining path planning based on the multiple fine-tuned machining parameters to generate multiple machining planning paths;

[0085] The optimal parameter adjustment module makes an optimal parameter adjustment decision for the dynamic workpiece machining twin model based on multiple machining planning paths, so as to obtain an optimal parameter adjustment strategy; and executes the automatic control operation of workpiece machining based on the optimal parameter adjustment strategy.

[0086] The present invention also provides a computer device, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps of the efficient machining control based on the cloud platform described in any one of the above are implemented.

[0087] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the efficient machining control based on the cloud platform described in any one of the above are implemented.

[0088] Those skilled in the art clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, systems, and units described above refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0089] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it is stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application essentially or the part that contributes to the prior art or all or part of the technical solution is embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that store program codes.

[0090] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be encompassed within the present invention.

[0091] As described above, these are only the specific implementation manners of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention 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.

Claims

1. An efficient processing control method based on a cloud platform, characterized in that It includes the following steps: Step S1: Obtain multi-directional monitoring images of workpiece machining and workpiece machining parameters; perform full-image brightness equalization calculation on the multi-directional monitoring images of workpiece machining, and perform high-frequency filtering detail optimization to construct a detail-optimized workpiece image; Step S2: Perform three-dimensional geometric structure analysis on the detail-optimized workpiece image, and perform three-dimensional point cloud modeling to construct a fine workpiece point cloud structure model; Step S3: Obtain multi-stage machining process data based on the workpiece machining parameters; perform global process flow reconstruction on the multi-stage machining process data to construct a reconstructed machining process series; Step S4: Perform dynamic process mapping on the fine workpiece point cloud structure model based on the reconstructed machining process series to construct a dynamic workpiece machining twin model; Step S5: Define multiple groups of parameter fine-tuning based on the workpiece machining parameters to obtain multiple fine-tuned machining parameters; perform dynamic machining path planning based on the multiple fine-tuned machining parameters to generate multiple machining planning paths; Step S6: Make an optimal parameter adjustment decision on the dynamic workpiece machining twin model based on the multiple machining planning paths to obtain an optimal parameter adjustment strategy; execute the automatic control operation of workpiece machining based on the optimal parameter adjustment strategy; Among them, the specific steps of Step S3 are: Step S31: Perform time-series change analysis on the workpiece machining parameters to generate time-series change machining parameters; Step S32: Identify stage processes for the time-series change machining parameters to obtain multi-stage machining process data; Step S33: Deeply mine the process dependencies of the multi-stage machining process data to generate the dependency relationships between stage processes; Step S34: Analyze the operation characteristics of the multi-stage machining process data to obtain the operation characteristic parameters of each stage process; Step S35: Perform global process flow reconstruction on the operation characteristic parameters of each stage process based on the dependency relationships between stage processes to construct a reconstructed machining process series; Among them, the specific steps of Step S4 are: Step S41: Perform dynamic process machining positioning on the fine workpiece point cloud structure model based on the reconstructed machining process series to obtain point cloud machining positioning points; Step S42: Analyze the machining form changes of the point cloud machining positioning points to obtain the form change data of the positioning points; Step S43: Analyze the position and attitude changes of the form change data of the positioning points to obtain the position and attitude change data of the positioning points; Step S44: Perform dynamic process mapping on the fine workpiece point cloud structure model according to the position and attitude change data of the positioning points to construct a dynamic workpiece machining twin model.

2. The efficient processing control method based on a cloud platform according to claim 1, wherein The specific steps of Step S1 are: Step S11: Obtain multi-directional monitoring images of workpiece machining and workpiece machining parameters; Step S12: Perform full-image brightness equalization calculation on the multi-directional monitoring images of workpiece machining to obtain the average image brightness; Step S13: Perform brightness distribution enhancement processing on the workpiece machining monitoring image based on the average image brightness to generate a brightness-enhanced workpiece image; Step S14: Perform contour visual recognition on the brightness-enhanced workpiece image to extract the workpiece contour line; Step S15: Perform high-frequency filtering detail optimization based on the workpiece contour line to construct a detail-optimized workpiece image.

3. The efficient processing control method based on a cloud platform according to claim 1, characterized in that The specific steps of step S2 are as follows: Step S21: Mark the key points of the workpiece on the image of the workpiece for detail optimization, and extract multiple workpiece feature points; Step S22: Conduct multi-directional visual difference analysis on multiple workpiece feature points to obtain multi-directional parallax feature data of the image; Step S23: Conduct three-dimensional geometric structure analysis on the image of the workpiece for detail optimization based on the multi-directional parallax feature data of the image, so as to generate three-dimensional geometric structure data of the workpiece; Step S24: Conduct three-dimensional point cloud modeling on the three-dimensional geometric structure data of the workpiece to generate an initial structure model of the workpiece; Step S25: Conduct local iterative refinement on the initial structure model of the workpiece to construct a fine point cloud structure model of the workpiece.

4. The efficient processing control method based on a cloud platform according to claim 1, wherein The specific steps of step S5 are as follows: Step S51: Define multiple groups of parameter fine-tuning based on the workpiece processing parameters to obtain multiple fine-tuned processing parameters; Step S52: Conduct iterative parameter adjustment simulation on the dynamic workpiece processing twin model based on multiple fine-tuned processing parameters to obtain iterative processing simulation data; Step S53: Conduct dynamic processing path planning on the iterative processing simulation data to generate multiple processing planning paths.

5. The efficient processing control method based on a cloud platform according to claim 1, characterized in that The specific steps of step S6 are as follows: Step S61: Conduct comprehensive evaluation of the processing simulation of the dynamic workpiece processing twin model based on multiple processing planning paths to obtain multiple groups of planning path evaluation values; Step S62: Extract the optimal planning path based on multiple groups of planning path evaluation values; Step S63: Make an optimal parameter adjustment decision on the optimal planning path to obtain an optimal parameter adjustment strategy; Step S64: Upload to the cloud platform based on the optimal parameter adjustment strategy to execute the automatic control operation of workpiece processing.

6. An efficient processing control device based on a cloud platform, characterized in that, Including: An image enhancement module, which acquires multi-directional monitoring images of workpiece processing and workpiece processing parameters; conducts full-image brightness equalization calculation on the multi-directional monitoring images of workpiece processing, and conducts high-frequency filtering for detail optimization, so as to construct an image of the workpiece for detail optimization; A three-dimensional structure module, which conducts three-dimensional geometric structure analysis on the image of the workpiece for detail optimization, and conducts three-dimensional point cloud modeling to construct a fine point cloud structure model of the workpiece; A process dependency mining module, which obtains multi-stage processing process data based on the workpiece processing parameters; conducts global process flow reconstruction on the multi-stage processing process data to construct a reconstructed processing process series; A dynamic process mapping module, which conducts dynamic process mapping on the fine point cloud structure model of the workpiece based on the reconstructed processing process series to construct a dynamic workpiece processing twin model; An iterative simulation module, which defines multiple groups of parameter fine-tuning based on the workpiece processing parameters to obtain multiple fine-tuned processing parameters; Conducts dynamic processing path planning based on multiple fine-tuned processing parameters to generate multiple processing planning paths; An optimal parameter adjustment module, which makes an optimal parameter adjustment decision on the dynamic workpiece processing twin model based on multiple processing planning paths to obtain an optimal parameter adjustment strategy; executes the automatic control operation of workpiece processing based on the optimal parameter adjustment strategy.

7. A computer device, comprising a memory and a processor, wherein a computer program is stored in the memory, characterized in that, When the processor executes the computer program, it implements the steps of the cloud platform-based efficient processing control method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the efficient processing control method based on a cloud platform according to any one of claims 1 to 5.

Images