Intelligent processing system based on artificial intelligence visual technology and control method thereof

Abstract

According to the intelligent processing system based on the artificial intelligence visual technology and the control method of the intelligent processing system, the first step is that a local configuration file is read; a second step of acquiring user setting parameters; a third step of determining that processing is performed for the first time, and skipping to a fourth step; if not, skipping to the ninth step; 4, initializing a configuration file; 5, starting a target identification module; 6, whether the to-be-machined workpiece is consistent with the preset workpiece type or not is judged; 7, giving an alarm; 8, starting a stereoscopic vision detection module; 9, calling the local configuration file, and executing the processing module; 10, executing a quality inspection module; 11, judging that the quality inspection is qualified, and skipping to the step 12; if not, skipping to the step 13; 12, storing the configuration information to the local; 13, executing a compensation module; according to the invention, the processing quality and efficiency of small-batch and multi-type products are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial automation and intelligent manufacturing, and in particular to an intelligent processing system based on artificial intelligence vision technology and a control method thereof. Background Art

[0002] With the development of technology, the manufacturing industry is moving towards intelligence and automation. Traditional processing systems mostly rely on fixed processing processes and preset parameter configurations, which cannot meet the needs of multi-variety, small batch and complex parts processing. At the same time, the automated processing system based on traditional visual technology still has deficiencies in target recognition, positioning accuracy and dynamic parameter adjustment, making it difficult to balance processing efficiency and quality.

[0003] At present, with the rapid development of artificial intelligence technology, especially deep learning algorithms, computer vision has gradually been applied to the field of industrial processing. Through target recognition, 3D scanning modeling, path planning and other technologies, the level of intelligent processing can be greatly improved. However, such systems still face the following problems in practical applications: (1) Insufficient processing complexity: When processing parts with complex surfaces or multiple degrees of freedom, the robot’s own dynamic errors and insufficient path planning accuracy can easily lead to accumulated processing errors, making it difficult to meet the processing requirements of complex parts.

[0004] (2) Lack of flexibility in processing parameter configuration: usually requires manual preset or adjustment based on experience, which is difficult to meet the needs of dynamic environments and different materials.

[0005] (3) The existing processing system lacks dynamic monitoring and closed-loop feedback mechanism for the entire processing process, which can easily lead to processing deviations or quality problems.

[0006] (4) The contradiction between cost and flexible production: Although CNC machine tools have high processing accuracy, their high equipment cost and long debugging time lead to high production costs in small-batch, high-variety production scenarios. Robots have an advantage in flexible production due to their lower cost and higher flexibility, but their lack of accuracy limits their widespread application.

[0007] In order to meet the above challenges, an intelligent processing system based on robots, artificial intelligence and vision technology is urgently needed. By combining the flexibility of robots with the precise control of artificial intelligence vision, this system can achieve accurate identification and positioning of workpieces, dynamic parameter configuration and closed-loop control of the processing process, significantly improve processing accuracy and efficiency, and meet the needs of modern manufacturing for flexible production and intelligent processing. This system can reduce costs, improve production efficiency, and adapt to a wider range of production scenarios while ensuring processing quality. Summary of the invention

[0008] The present invention aims to solve at least one of the technical problems existing in the prior art.

[0009] To this end, the present invention proposes an intelligent processing system based on artificial intelligence vision technology and its control method to ensure the processing quality and efficiency of small batch and multi-variety products, which is suitable for flexible manufacturing scenarios of multi-variety, small batch and complex parts.

[0010] According to an embodiment of the present invention, a control method for intelligent processing based on artificial intelligence vision technology includes the following steps: Step 1: Read the local configuration file, parse the basic parameters, and display the parsing results through a visual interface; Step 2: Obtain the user's settings and adjustments to the parsed basic parameters, and update the corresponding configuration information according to the adjusted parameters; Step 3: Determine whether it is the first processing: If it is determined to be the first processing, the automatic processing parameters are obtained and the process goes to step 4; If it is determined that it is not the first processing, jump to step 9; Step 4: Initialize the configuration file; Step 5: 3D model analysis of workpiece drawings, start the target recognition module; Step 6: Determine whether the workpiece to be processed is consistent with the preset workpiece type: If it is determined that the workpiece to be processed is consistent with the preset workpiece type, jump to step 8; If it is determined that the workpiece to be processed is inconsistent with the preset workpiece type, jump to step 7; Step 7: Alarm prompt and manual intervention inspection; Step 8: Start the stereoscopic vision detection module, scan and calculate the spatial posture of the workpiece in sequence according to the initial target point; calculate the workpiece parameters according to the 3D model and the spatial posture; automatically generate the processing plan according to the processing procedure logic; update the processing plan information in the configuration file of the workpiece and store it locally; Step 9: call the local configuration file, update the dynamic configuration information, and execute the processing module according to the configuration information; Step 10: Execute the quality inspection module after processing is completed; Step 11: Determine whether the quality inspection is qualified: If the quality inspection is judged to be qualified, jump to step 12; If the quality inspection is judged to be unqualified, jump to step 13; Step 12: After passing the test, save the configuration information locally for subsequent use; Step 13: Execute the compensation module and then jump to step 10.

[0011] The beneficial effect of the present invention is to solve the problems existing in the existing processing systems in terms of complexity, flexibility, dynamic monitoring and cost control. By introducing artificial intelligence vision technology and multi-sensor fusion, high-precision target recognition, dynamic path planning and adaptive parameter adjustment can be achieved to ensure processing quality and efficiency. It is suitable for flexible manufacturing scenarios of multiple varieties, small batches and complex parts.

[0012] According to an embodiment of the present invention, in the first step, the local configuration file contains data information required for the processing; if the configuration file cannot be found locally, a prompt will be given and the process that is not the first processing will be closed.

[0013] According to an embodiment of the present invention, in the second step, except for the position parameter, each parameter value is indexed in the local configuration file, waiting for the user to change its parameter information, and after the change is completed, the user's modified value is re-obtained to update the dynamic configuration information.

[0014] According to an embodiment of the present invention, in the fourth step, except for the parameters set by the user, each dynamic configuration information in the configuration file is cleared.

[0015] According to one embodiment of the present invention, in the fifth step, a 2D camera is used to collect image information of the object to be processed, and then deep learning is used to infer the material information of the workpiece to be processed and the preliminary target point of the object to be processed.

[0016] According to one embodiment of the present invention, in step 8, trajectory planning is performed according to the initial target point, and the robot carrying the 3D camera scans sequentially along the trajectory to accurately obtain the parameters within the field of view of the target point, which are used to calculate the machining allowance.

[0017] According to an embodiment of the present invention, in the twelfth step, the configuration information includes a processing trajectory, target recognition information, 3D image information, and quality inspection results.

[0018] An intelligent processing system for realizing a control method of intelligent processing based on artificial intelligence visual technology comprises: a target recognition module, which is used for model training and optimization testing before the system, and for image acquisition, image processing algorithm library calling and model reasoning after image processing during the working process, and combines 3D model analysis processing drawings to determine whether the workpiece is a preset workpiece to be processed, and effectively divides the workpiece space area, and outputs the center point of each area as the initial target point; a stereoscopic vision detection module, which is used to use a 3D vision camera to cooperate with a collaborative robot to sequentially scan the point cloud model of the workpiece in space according to the trajectory generated by the initial target point, and calculate the processing parameters in combination with the raw material drawing and the processing drawing; a processing module, which is used to read the processing parameters, match the task strategy, automatically plan the trajectory of the processing robot, and supervise and control the robot to perform the processing task; a quality inspection module, which is used to use a 3D vision camera to offset the initial target point according to the processing parameters and then scan it, generate a point cloud model of the workpiece in space after processing, and analyze whether the processing is accurate and whether there are defects such as burrs; a compensation module, which is used to dynamically adjust and optimize the processing problems caused by errors in the processing process.

[0019] According to one embodiment of the present invention, the target recognition module, the visual positioning detection module and the quality inspection module all call an image acquisition service module with an image acquisition function and an image processing algorithm library function; the visual positioning detection module and the quality inspection module both call a collaborative robot trajectory automatic planning function; the processing module and the compensation module both call a task strategy matching function; the target recognition module and the quality inspection module both call a reasoning service module with a model reasoning function.

[0020] According to one embodiment of the present invention, the image acquisition service module provides a unified interface for the target recognition module, the visual positioning detection module and the quality inspection module to call; the reasoning service module provides a unified interface for the target recognition module and the quality inspection module to call.

[0021] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and the drawings.

[0022] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 It is a schematic diagram of the main functional components of the user-side software of the intelligent processing system of the present invention; Figure 2 It is a flow chart of a control method of an intelligent processing system based on artificial intelligence vision technology of the present invention; Figure 3 It is a schematic diagram of the calling method of dynamic configuration information and the composition of the configuration file of the intelligent processing system based on artificial intelligence vision technology of the present invention; Figure 4 It is a schematic diagram of the module functional structure of the intelligent processing system of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] The following describes in detail the intelligent processing system and control method based on artificial intelligence vision technology according to the embodiment of the present invention with reference to the accompanying drawings.

[0027] The user interface of the intelligent processing system consists of Figure 1 As shown in the figure, its design fully combines the actual application needs and provides users with an intuitive operation platform, covering the full process functions from workpiece identification to processing quality inspection. The user interface integrates functional modules such as deep learning, stereo vision, robot control and 3D model analysis. The various functions cooperate with each other to achieve full visualization and convenient operation of the processing process.

[0028] Through the user interface, the system provides target recognition functions, supports sample set collection, labeling, cleaning and training, and also has the function of selecting appropriate training model algorithms. The recognition module can infer the material type and spatial posture information of the workpiece (X, Y position and Z direction angle of ROI) based on the data uploaded by the user. Combined with the recognition results, the system determines whether the material of the workpiece to be processed is consistent with the preset material. If consistent, the system automatically loads the processing parameters of the material (such as processing speed, cutting amount, etc.) and displays them on the interface; if inconsistent, the interface issues an alarm prompt to prevent processing errors.

[0029] The stereo vision function provides 3D camera parameter settings and ROI area adjustment options through the interface. During the processing, the system calls the 3D camera to collect point cloud data of the target area and displays the 3D model of the workpiece in real time through the user interface. Using this data, the system supports subsequent processing path planning and spatial dimension analysis, and users can intuitively view the data and analysis results.

[0030] The robot control function includes the parameter settings of the processing robot and the collaborative robot, as well as the intuitive display of the robot's trajectory information and other parameters. The system automatically generates the processing path based on the material information, point cloud, and the raw material drawings and processing drawings of the workpiece, and updates it in real time on the interface. At the same time, the collaborative robot carries a 3D camera to perform the mapping task according to the planned path, and the user can view the mapping trajectory of the workpiece in real time through the interface.

[0031] Through the user interface, the system realizes the visualization function of 3D model analysis. The analysis results include the three-dimensional spatial data of the raw workpiece and the processed workpiece, and the interface displays the comparative analysis results of the theoretical processing volume and the actual processing volume. When processing deviation is found, the system generates a compensation strategy, and the compensation operation and its effect will be fed back in real time on the interface for users to view and confirm.

[0032] The user interface also displays the dynamic data of the processing process in real time, including the acquisition trajectory, processing trajectory, quality inspection results and compensation results. The quality inspection function determines whether there are defects such as processing deviation and burrs by displaying the point cloud model after processing, and intuitively presents relevant information on the interface. The compensation function automatically plans the compensation path after discovering the problem, and prompts the user to confirm the execution through the interface to ensure that the final processing result meets the requirements.

[0033] The above user interface design is both practical and professional, and can effectively guide users to complete processing operations. At the same time, it provides real-time processing monitoring and feedback, greatly improving the intelligence and reliability of processing.

[0034] The flow chart of the control method of the intelligent processing system based on artificial intelligence vision technology is as follows Figure 2 As shown, the following steps are included: Step 1: Read the local configuration file, parse the basic parameters, and display the parsing results through a visual interface; the local configuration file contains the data information needed in the processing process; at this time, if the configuration file cannot be found locally, a prompt will be displayed and the process that is not the first processing will be closed, and a blank configuration file will be generated according to the existing configuration file format.

[0035] Step 2: Get the parameters set by the user, update the configuration file, parse the parameters and display them: Get the user's settings and adjustments to the parsed basic parameters, and update the corresponding configuration information according to the adjusted parameters. Except for the position parameters, index each parameter value in the local configuration file, wait for the user to change its parameter information, and re-obtain the user's modified value after the change is completed to update the dynamic configuration information.

[0036] Step 3: Call the conditional control module, select the condition based on the return value of whether it is the first processing, and determine whether it is the first processing: if it is the first processing, it is necessary to obtain the automatic processing parameters and jump to step 4; if it is not the first processing, it will be processed with the parameters in the configuration file (mostly used for small batch processing), and jump to step 9; it should be noted that the first processing means: due to the small batch production, new products often come, and the first processing requires the formulation of a processing plan for the product. If such a product is to be processed again, it can be processed directly according to the processing plan, reducing the time for formulating the processing plan.

[0037] Step 4: Initialize the configuration file. Except for the parameters set by the user, clear all dynamic configuration information in the configuration file. Except for the parameters set by the user, clear all dynamic configuration information in the configuration file.

[0038] Step 5: 3D model analysis of workpiece drawings (raw material drawings and processing drawings), start the target recognition module: use 2D cameras to collect image information of the objects to be processed, and then use deep learning to infer the material information of the workpieces to be processed and the preliminary target points of the objects to be processed. Specifically, start the target recognition module, use 2D cameras to collect image information of the objects to be processed, and then use deep learning to infer the material information of the workpieces to be processed, and combine the results of the 3D model analysis of the workpiece drawings to determine the preliminary target points. The preliminary target points are obtained by the size, shape and processing method of the workpiece. It mainly acts on the collaborative robot carrying a 3D visual camera to generate the spatial point position of the map collection trajectory, and secondly, the map collection trajectory reference function during quality inspection. The target point of quality inspection only needs to have a certain offset capability. It should be supplemented that target recognition not only has recognition, but also reasonably divides the area of ​​the workpiece according to the recognition results, and obtains the center position in the area as the target point. The collaborative robot will refer to the (x, y) position of these target points. Of course, the position accuracy of the target recognition output is relatively low.

[0039] Step 6: Call the condition control module to determine whether the workpiece to be processed is consistent with the preset workpiece type based on the returned result (to prevent the user from placing the wrong workpiece): If the workpiece to be processed is determined to be consistent with the preset workpiece type, jump to step 8; if the workpiece to be processed is determined to be inconsistent with the preset workpiece type, jump to step 7; specifically, determine whether the material and size of the inferred workpiece to be processed are consistent with the preset material, raw material size and other factors. If not, jump to step 7; if yes, jump to step 8.

[0040] Step 7: Alarm prompt and manual intervention inspection, that is, triggering an alarm and prompting manual intervention.

[0041] Step 8: Start the stereoscopic vision detection module, scan and calculate the spatial posture of the workpiece in sequence according to the initial target point; calculate the parameters of the workpiece according to the 3D model and the spatial posture; automatically generate the processing plan according to the logic of the processing procedure; update the processing plan information in the configuration file of the workpiece and store it locally; perform trajectory planning according to the initial target point, execute the robot to carry the 3D camera to scan along the trajectory in sequence, accurately obtain the parameters in the field of view of the target point, and use it to calculate the processing allowance. Specifically, start the stereoscopic vision detection module, the collaborative robot automatically generates a map collection path according to the initial target point, and automatically scans the initial target point on the map collection trajectory with a 3D camera according to a certain running speed and waiting time to generate a point cloud model, accurately obtain the height (thickness) and other parameters in the field of view of the target point, and calculate the processing allowance in combination with the processing drawing model of the workpiece. Automatically generate the processing plan according to the processing logic of this type of workpiece, dynamically configure the information to update the information of the processing plan, and save the dynamic configuration information to the local specified folder after naming it with the serial number of the workpiece.

[0042] Step 9: Call the local configuration file, update the dynamic configuration information, and execute the processing module according to the configuration file information: the processing module calls the configuration file of the corresponding workpiece, executes the processing module, and the processing robot performs processing according to the processing plan. At the same time, the system monitors the processing robot to perform the processing task.

[0043] Step 10, execute the quality inspection module after processing is completed: Specifically, execute the quality inspection module, the collaborative robot carries a 3D vision camera to collect images along the quality inspection trajectory, the quality inspection trajectory is composed of quality inspection target points, and the quality inspection target points are obtained by offsetting the initial target points according to information such as the processing volume.

[0044] Step 11, call the condition judgment module, and judge whether the quality inspection is qualified according to the returned result: if the quality inspection is qualified, jump to step 12; if the quality inspection is unqualified, jump to step 13; specifically, the quality inspection will be based on unreasonable processing dimensions, burrs, etc. The detection result is given by the visual positioning detection module, and the visual positioning detection module includes a target recognition module and a stereoscopic vision detection module, in which the detection devices used are 2D vision cameras and 3D vision cameras respectively.

[0045] Step 12: After passing the test, save the configuration information locally for subsequent use: Specifically, after passing the test, save the processing trajectory, quality inspection trajectory and other parameters to the configuration file of the workpiece, and at the same time, save the target recognition information, 3D image information, quality inspection information and other parameters to the specified folder. The configuration information includes the processing trajectory, target recognition information, 3D image information and quality inspection results.

[0046] Step 13, execute the compensation module, and then jump to step 10: Specifically, execute the compensation module, and after the compensation is completed, jump to step 10 and start the quality inspection module again until it is qualified. Specifically, the compensation module uses the robot to compensate according to the compensation trajectory and related strategy information. Specifically, the compensation trajectory is regenerated according to the processing trajectory according to the compensation task strategy matching, and the compensation trajectory of the processing robot only refers to a part of the processing trajectory. The compensation trajectory and the processing trajectory are similar in planning, but they are two completely different planning methods. Specifically, the processing trajectory is determined by the processing plan, and it matches the task strategy library of the processing plan. The compensation trajectory is determined by the compensation plan, and it matches the task strategy library of the compensation plan. Specifically, the compensation module is not necessarily able to compensate successfully. If it exceeds the working range of the compensation module, an alarm will be issued, and manual intervention will be prompted to find the problem. Specifically, exceeding the working range of the compensation module means that the actual size after processing exceeds the maximum allowable error range, or there is no compensation plan for the defect in the compensation task strategy library.

[0047] The calling method of the software's dynamic configuration information and the composition diagram of the configuration file are as follows: Figure 3 As shown in the figure, when the system is initialized, it will automatically generate dynamic configuration information according to the predefined format of the configuration file, and serve as the core basis for the operation of subsequent processing, quality inspection, compensation and other modules. For the workpiece to be processed, the system will first query the configuration file records in the existing workpiece library. If a matching configuration file is found, the system will directly extract its content and dynamically load it as the dynamic configuration information for the current processing; if the corresponding record is not found in the workpiece library, the system will automatically create a new dynamic configuration information and gradually supplement and improve the relevant content during the processing. After the processing task is completed, the dynamic configuration information will be stored as a formal configuration file, providing a reference for subsequent workpiece processing and system optimization.

[0048] Specifically, the newly created configuration file includes basic information, target recognition results, stereoscopic vision detection results, processing plans, quality inspection plans, compensation plans, etc.

[0049] The basic information includes the operator's identity information, the serial number of the workpiece to be processed, the information number and the contract number. The operator information and the processing task number are entered by the user when logging in, and then the system obtains them through indexing. The date and time are automatically generated by the system. The key parameters such as the material and processing items of the workpiece to be processed are directly entered by the user to ensure the accuracy of the initial parameters.

[0050] Specifically, the target recognition result module includes the initial parameters and target point information of the workpiece. The material, size and other key parameters of the workpiece to be processed are obtained through model reasoning, and the initial target point coordinates of the workpiece are output in combination with the image segmentation results. All information in this part is automatically obtained and dynamically updated during the system operation process.

[0051] Specifically, the stereoscopic vision inspection results are completed by the collaborative robot and the 3D vision camera, which include three major elements: the trajectory of the collaborative robot performing the scanning task, the current point cloud data of the workpiece after processing, and the ideal processing point cloud data based on model analysis. Among them, the scanning trajectory of the collaborative robot is automatically planned based on parameters such as the initial target point; the current point cloud data of the workpiece is obtained by scanning with a 3D camera; and the ideal processing point cloud data is derived from the 3D modeling analysis of the processing design drawings as a benchmark for evaluating processing quality.

[0052] Specifically, the processing plan covers core elements such as processing procedures, processing parameters and processing trajectories. The processing procedures are flexibly configured by the user according to actual needs; the processing parameters are automatically generated by calculating the error between the actual point cloud and the ideal point cloud; the processing trajectory of each process is automatically generated by the system for the processing robot in combination with the process definition and processing parameters to ensure high-precision trajectory control and processing operations.

[0053] Specifically, the quality inspection solution module includes the quality inspection trajectory and quality inspection results of the collaborative robot. Among them, the quality inspection trajectory generates the quality inspection target point by integrating the initial target point, processing allowance and other parameters, and then the collaborative robot automatically generates the quality inspection path based on the target point. The quality inspection results are analyzed by model reasoning and analysis of the processed point cloud data to determine whether there are dimensional errors, unevenness, burrs or other processing defects.

[0054] The compensation scheme consists of compensation type, compensation parameters and compensation trajectory of the processing robot. The compensation type includes classification of processing size inadequacy, processing defects (such as burrs, unevenness, etc.) and size deviation. If the system determines that the problem can be solved by compensation, it will re-plan the processing robot trajectory based on the preset compensation strategy and perform compensation operations; if compensation is not possible, it will be marked and archived for subsequent inspection and recording.

[0055] Specifically, since the quality inspection and compensation process requires multiple iterations, the configuration information needs to be stored in batches. For example, the first quality inspection and compensation, and the second quality inspection and compensation need to be recorded separately to provide complete data support and traceability basis for subsequent processing analysis.

[0056] Specifically, dynamic configuration information is highly scalable and can flexibly adapt to changing system functional requirements. In the later development or functional expansion of the system, it is only necessary to adjust the structure or content of the configuration file and implement the corresponding new functional modules without making large-scale changes to the existing software architecture. Through this design, dynamic configuration information not only significantly reduces the complexity of functional upgrades and maintenance, but also provides strong compatibility and maintainability for the continuous optimization and functional expansion of the system. This feature is particularly important in complex industrial application scenarios and can significantly improve the system's development efficiency and lifecycle management capabilities.

[0057] The module functional structure diagram of the intelligent processing system is as follows: Figure 4 As shown in the figure, the system adopts a modular design, divides functions into independent modules, and abstracts and integrates the core functional units of shared calls (such as image acquisition, image processing algorithm library, collaborative robot trajectory planning, task strategy matching and model reasoning) to build a unified component. The modular design has high independence and low coupling, which significantly improves development efficiency and system stability, while reducing redundant design and optimizing resource utilization. In addition, the modular design enhances the scalability and maintainability of the system, and realizes efficient collaboration through standardized interfaces. When adding new functions or adapting to different application scenarios, there is no need to significantly modify the system architecture, thereby meeting the needs of flexible production and intelligent manufacturing.

[0058] Specifically, the modules of the intelligent processing system based on artificial intelligence vision technology include a target recognition module, a stereoscopic vision detection module, a processing module, a quality inspection module and a compensation module.

[0059] Specifically, the target recognition module is used for model training and optimization testing before the system is installed, as well as for image acquisition during the work process, calling of the image processing algorithm library, and model reasoning after image processing. It combines the 3D model to analyze the processing drawings, determines whether the workpiece is the preset workpiece to be processed, and effectively divides the workpiece space area, and outputs the center point of each area as the initial target point. It should be noted that the initial target point mentioned in the present invention is the position where the 3D camera in the stereoscopic vision module should be located to scan the workpiece, etc. There are multiple initial target points. After the 3D camera is located at multiple initial points and scans them separately, a point cloud model of the workpiece can be constructed. During quality inspection, the scan is also performed after offsetting a certain distance based on the initial target point.

[0060] The target recognition module specifically includes the training, optimization and testing functions of the model, and needs to support the development of sample set related operation tools, such as sample cleaning, sample labeling and sample collection, to improve the training data set management of the model. The module needs to have model training and reasoning capabilities, and perform target recognition tasks by calling pre-trained or real-time trained models. In addition, the interface provided by the module also supports the rapid configuration of more advanced training models in current technology during software updates to ensure that the system always maintains a certain technical level in terms of target recognition performance and technical applicability. In addition, the target recognition module should also support image acquisition and processing functions, obtain the region of interest (ROI) of the workpiece to be processed by calling model reasoning, and further extract the length, width and angle information of the workpiece. At the same time, the module can identify the material properties of the workpiece to be processed, and provide the necessary basis for the task strategy matching function of the processing module, so as to achieve precise processing of workpieces of different materials and shapes.

[0061] Specifically, the stereoscopic vision detection module is used to use a 3D vision camera to cooperate with the collaborative robot to scan the point cloud model of the workpiece in space in accordance with the trajectory generated by the initial target point, and calculate the processing parameters in combination with the raw material drawing and the processing drawing. It should be noted that the collaborative robot completes the scanning of the initial target point with a 3D camera, and the obtained point cloud data can be formed into the actual model of the workpiece by splicing and other methods.

[0062] The stereoscopic vision detection module includes the collaborative robot trajectory automatic planning function, image acquisition function and image algorithm processing function. The collaborative robot trajectory automatic planning function relies on the 3D model parsing capability to parse the raw material drawings and processing drawings, and intercepts the model area within the field of view range in combination with the field of view parameters of the 3D camera to generate the corresponding point cloud data. The target initial points in the point cloud are extracted through a specific algorithm, such as selecting representative points based on the geometric boundary features of the model, the curvature change area, or by uniformly dividing the space, and finally these initial target points are output in the form of coordinates to provide support for the trajectory planning of the collaborative robot. The collaborative robot moves to the designated target point with the 3D vision camera according to the generated trajectory, and performs precise scanning to collect point cloud data. The image algorithm processing function splices and optimizes the collected point cloud data, and generates the actual three-dimensional point cloud model of the workpiece to be processed in combination with the position information of the initial target point. Based on the model, the system calculates the processing parameters such as cutting amount and processing allowance, and provides them to the processing module as reference data to support subsequent precise processing operations.

[0063] Specifically, the processing module is used to read processing parameters, match task strategies, automatically plan processing robot trajectories, and supervise and control the robot to perform processing tasks.

[0064] The processing module specifically includes the functions of processing parameter acquisition, processing plan task strategy matching, and automatic generation of processing robot trajectory. Among them, the processing parameter acquisition function is mainly responsible for receiving and processing key parameter information transmitted by other modules, such as the initial target point, the length, width and angle of the workpiece, the cutting amount and cutting speed. These parameters provide data support for the generation and execution of the processing plan. The task strategy matching function of the processing plan matches the processing task strategy according to the user's preset processing method library. The preset processing method library contains a variety of processing technologies such as drilling, milling, and composite grinding. According to the task requirements, the system selects the appropriate processing technology from the processing method library and generates the corresponding processing plan. The processing robot automatically generates the processing trajectory by parsing the above parameters and the processing plan. The generated trajectory not only ensures the processing accuracy, but also optimizes the path planning to improve efficiency. After the processing trajectory is generated, the system monitors the processing robot and executes the processing task according to the planned trajectory to achieve high-precision processing operations on the workpiece.

[0065] The quality inspection module is used to use a 3D vision camera to offset the initial target point according to the processing parameters and then scan it, generate a point cloud model of the workpiece in space after processing, and analyze whether the processing is accurate and whether there are defects such as burrs; specifically, the quality inspection module uses a 3D vision camera combined with processing parameters to offset the initial target point and then perform a scanning operation to generate a spatial point cloud model of the workpiece after processing, which is used to analyze the processing accuracy and detect whether there are defects such as burrs. The collaborative robot carries a 3D camera to complete the scanning task according to the planned trajectory. In the case of processing failure, for example, the goal is to process a 500mm cylinder to 395mm, but the actual processing result is still 500mm. At this time, the initial target point should be adjusted to 560mm and the quality inspection target point should be 455mm. However, due to system abnormalities, performing quality inspection according to the 455mm target point may cause abnormal situations. To avoid such accidents, the 3D camera housing carried by the collaborative robot has a protection mechanism when performing scanning. When the protective housing approaches the surface of the workpiece, the system triggers an alarm and stops the operation urgently to ensure the safety of the equipment and the workpiece and prevent the occurrence of processing accidents.

[0066] The quality inspection module specifically includes functions such as collaborative robot trajectory automatic planning, image acquisition, image algorithm processing and model reasoning. Different from the collaborative robot trajectory automatic planning of the stereoscopic vision inspection module, the trajectory planning of the quality inspection module offsets the initial target point to a certain extent based on the processing amount, generates the quality inspection target point, and automatically generates the quality inspection trajectory based on this. The collaborative robot carries a 3D vision camera to perform point cloud acquisition tasks according to the planned quality inspection trajectory to obtain the surface data of the workpiece after processing. After the image acquisition is completed, the quality inspection module analyzes the size and geometric characteristics of the workpiece surface through image preprocessing, feature extraction and segmentation operations to determine whether it meets the design requirements. Through the model reasoning function, the system further detects whether there are defects such as uneven processing, burrs, overcutting or incomplete processing on the workpiece surface. In addition, the quality inspection module can compare the overall point cloud data of the workpiece with the processing drawings or models to accurately evaluate the processing errors. If the quality inspection results show that the workpiece has defects, the system will generate a repair plan through the compensation module, such as adjusting the processing trajectory to repair the unprocessed area, or using post-processing methods such as deburring to ensure that the workpiece meets the quality standards. Through the closed-loop feedback mechanism, the quality inspection module can continuously optimize the processing accuracy and improve the processing quality and stability of the entire system.

[0067] Specifically, the compensation module is used to dynamically adjust and optimize the processing problems caused by errors during the processing process. The system uses the post-processing point cloud model generated by scanning with a 3D visual camera, combined with the preset processing parameters, to perform real-time analysis of the processing accuracy. If an area that is not processed in place is detected, the system will automatically calculate the compensation path and compensation processing amount, and re-plan the trajectory of the processing tool, and perform secondary processing to ensure that the processing is in place. For the detected burr defects, the system will accurately locate the burr position based on the comparison between the point cloud model and the target model, and automatically plan the processing path to remove the burr. After removing the burrs, the system scans again to verify the processing quality of the workpiece to ensure that it meets the accuracy requirements. The compensation module also supports multiple rounds of compensation processing, and continuously adjusts the processing trajectory and parameters through a closed-loop control mechanism until the processing is fully up to standard. For workpieces that are difficult to repair or exceed the processing tolerance range, the system will generate an alarm and mark the workpiece as a defective part to ensure the quality of the final product.

[0068] The compensation module often needs to be executed repeatedly until the processing is completed according to factors such as the processing process allowance. The compensation module specifically includes functions such as task strategy matching and automatic compensation trajectory planning. Among them, the task strategy matching function compares the inspection results output by the quality inspection module with the preset compensation task strategy library. The compensation task strategy library contains specific compensation schemes for different processing defects (such as incomplete processing, burrs, overcutting, etc.). The system selects the corresponding compensation scheme based on the matching results, and indexes the required parameters (such as compensation processing volume, path adjustment parameters, etc.) to generate a compensation trajectory. The automatic compensation trajectory planning function uses the defect position data provided by the quality inspection module and combines the processing parameters in the compensation scheme to generate a specific compensation path. The processing robot performs repair operations on the workpiece according to the planned compensation trajectory to ensure processing accuracy and quality. When the task strategy library cannot match the applicable compensation scheme, or the system detects that the workpiece can no longer be further processed, the system will trigger the alarm function to prompt the operator to intervene manually or terminate the processing.

[0069] Specifically, the work between the quality inspection module and the compensation module is highly correlated, and usually needs to be repeatedly executed based on factors such as processing procedures and allowances to form a closed-loop control. Through continuous quality inspection and compensation, the system can gradually correct the processing errors, ultimately ensuring that the workpiece meets the design requirements and completes the entire processing task.

[0070] The target recognition module, visual positioning detection module and quality inspection module all call the image acquisition service module and image processing algorithm library function with image acquisition function; the visual positioning detection module and quality inspection module all call the collaborative robot trajectory automatic planning function. The collaborative robot will automatically generate a trajectory according to the position of the target initial point, and move the 3D camera through each target point in turn; the processing module and the compensation module all call the task strategy matching function, which is used to dynamically match the corresponding processing strategy according to the preset processing method and process requirements, including tool selection, tool replacement, operation parameter adjustment, etc., to meet the execution requirements of different processing tasks; the target recognition module and the quality inspection module all call the reasoning service module with model reasoning function. The image acquisition service module provides a unified interface for the target recognition module, visual positioning detection module and quality inspection module to call; the reasoning service module provides a unified interface for the target recognition module and quality inspection module to call. It should be noted that the target recognition module, visual positioning detection module and quality inspection module all complete the corresponding function execution by calling the image acquisition function unit and the image processing algorithm library interface. The stereoscopic vision detection module and the quality inspection module both call the collaborative robot trajectory automatic planning function to support their task execution process.

[0071] The intelligent processing system and control method based on artificial intelligence vision technology of the present invention solve the problems of existing processing systems in terms of complexity, flexibility, dynamic monitoring and cost control. By introducing artificial intelligence vision technology and multi-sensor fusion, high-precision target recognition, dynamic path planning and adaptive parameter adjustment are achieved to ensure the processing quality and efficiency of small batch and multi-variety products. It is suitable for flexible manufacturing scenarios of multi-variety, small batch and complex parts.

[0072] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A control method for intelligent processing based on artificial intelligence vision technology, characterized in that: The following steps are involved: Step 1: Read the local configuration file, parse the basic parameters, and display the parsing results through a visual interface; Step 2: Obtain the user's settings and adjustments to the parsed basic parameters, and update the corresponding configuration information according to the adjusted parameters; Step 3: Determine whether it is the first processing: If it is determined to be the first processing, the automatic processing parameters are obtained and the process goes to step 4; If it is determined that it is not the first processing, jump to step 9; Step 4: Initialize the configuration file; Step 5: 3D model analysis of workpiece drawings, start the target recognition module; Step 6: Determine whether the workpiece to be processed is consistent with the preset workpiece type: If it is determined that the workpiece to be processed is consistent with the preset workpiece type, jump to step 8; If it is determined that the workpiece to be processed is inconsistent with the preset workpiece type, jump to step 7; Step 7: Alarm prompt and manual intervention inspection; Step 8: Start the stereoscopic vision detection module, scan and calculate the spatial posture of the workpiece in sequence according to the initial target point; calculate the workpiece parameters according to the 3D model and the spatial posture; automatically generate the processing plan according to the processing procedure logic; update the processing plan information in the configuration file of the workpiece and store it locally; Step 9: call the local configuration file, update the dynamic configuration information, and execute the processing module according to the configuration file information; Step 10: Execute the quality inspection module after processing is completed; Step 11: Determine whether the quality inspection is qualified: If the quality inspection is judged to be qualified, jump to step 12; If the quality inspection is judged to be unqualified, jump to step 13; Step 12: After passing the test, save the configuration information locally for subsequent use; Step 13: Execute the compensation module and then jump to step 10.

2. The control method for intelligent processing based on artificial intelligence vision technology as claimed in claim 1, characterized in that: In the first step, the local configuration file contains data information required in the processing; if the configuration file cannot be found locally, a prompt will be given and the process that is not the first processing will be closed.

3. The control method for intelligent processing based on artificial intelligence vision technology as claimed in claim 1, characterized in that: In the second step, except for the position parameter, each parameter value is indexed in the local configuration file, waiting for the user to change its parameter information, and after the change is completed, the user's modified value is re-obtained to update the dynamic configuration information.

4. The control method for intelligent processing based on artificial intelligence vision technology as claimed in claim 1, characterized in that: In the fourth step, except for the parameters set by the user, the dynamic configuration information is left blank.

5. The control method for intelligent processing based on artificial intelligence vision technology as claimed in claim 1, characterized in that: In the fifth step, a 2D camera is used to collect image information of the object to be processed, and then deep learning is used to infer the material information of the workpiece to be processed and the preliminary target point of the object to be processed.

6. The control method for intelligent processing based on artificial intelligence vision technology as claimed in claim 1, characterized in that: In the eighth step, trajectory planning is performed according to the initial target point, and the robot carrying the 3D camera scans sequentially along the trajectory to accurately obtain point cloud data within the field of view of the target point, and the machining allowance is calculated using the point cloud and the machining model of the workpiece.

7. The control method for intelligent processing based on artificial intelligence vision technology as claimed in claim 1, characterized in that: In the twelfth step, the configuration information includes processing trajectory, target recognition information, 3D image information and quality inspection results.

8. An intelligent processing system for implementing the control method of intelligent processing based on artificial intelligence vision technology as claimed in claim 1, characterized in that: include: The target recognition module is used for model training and optimization testing before the system is installed, as well as for image acquisition during the work process, calling the image processing algorithm library, and model reasoning after image processing. It combines the 3D model to analyze the processing drawings to determine whether the workpiece is the preset workpiece to be processed. At the same time, it effectively divides the workpiece space area and outputs the center point of each area as the initial target point; The stereoscopic vision inspection module is used to use a 3D vision camera in conjunction with a collaborative robot to sequentially scan the point cloud model of the workpiece in space according to the trajectory generated by the initial target point, and calculate the processing parameters in combination with the raw material drawings and processing drawings; The processing module is used to read processing parameters, match task strategies, automatically plan processing robot trajectories, and monitor and control the robot to perform processing tasks; The quality inspection module is used to use a 3D visual camera to offset the initial target point according to the processing parameters and then scan it, generate a point cloud model of the workpiece in space after processing, and analyze whether the processing is accurate and whether there are defects such as burrs; The compensation module is used to dynamically adjust and optimize the processing problems caused by errors during the processing.

9. The intelligent processing system according to claim 8, characterized in that: The target recognition module, the visual positioning detection module and the quality inspection module all call an image acquisition service module with an image acquisition function and an image processing algorithm library function; The visual positioning detection module and the quality inspection module both call the collaborative robot trajectory automatic planning function; The processing module and the compensation module both call a task strategy matching function; The target recognition module and the quality inspection module both call a reasoning service module having a model reasoning function.

10. The intelligent processing system according to claim 9, characterized in that: The image acquisition service module provides a unified interface for the target recognition module, the visual positioning detection module and the quality inspection module to call; The reasoning service module provides a unified interface for the target recognition module and the quality inspection module to call.

Images