Process automation method and system based on digital management and control, and electronic equipment

Abstract

The invention provides a process automation method and system based on digital control and electronic equipment, and relates to the technical field of process automation, and the method comprises the steps: obtaining a target workpiece model and a target workpiece model corresponding to a to-be-processed workpiece, and determining a target workpiece coordinate system corresponding to the target workpiece model, the target workpiece coordinate system is used for indicating the coordinate system of the to-be-processed workpiece; a reference track file corresponding to the target workpiece model is searched from a preset storage position, and under the condition that the reference track file is found or not found, corresponding operation is adopted, and a target track is obtained; and the target process treatment is performed on the to-be-treated workpiece by adopting the target track, so that the problem of low efficiency and accuracy of an existing process automation method is solved.

Description

Technical Field

[0001] This application relates to the field of process automation technology, specifically to a process automation method, system, and electronic equipment based on digital control. Background Technology

[0002] In modern industrial production, in order to improve the efficiency of production and the long-term pursuit of liberating manual labor, process automation has gradually emerged and been widely applied. Therefore, how to improve the efficiency of production has become one of the key research focuses of researchers in this field.

[0003] In related technologies, workpiece processing is a key process in automated production. To improve the efficiency of automation, technologies typically plan a trajectory based on the workpiece model when it enters the production line (i.e., the actual processing of the workpiece). Then, a robot is controlled to process the workpiece according to this trajectory, thus improving efficiency and avoiding manual operation. Currently, one method of automation is to plan a processing trajectory for each workpiece entering the production line in real-time. However, for workpieces of the same model in the same batch, this inevitably leads to time consumption due to repetitive planning. To further improve efficiency, another method involves applying the processing trajectory of the first workpiece in a batch of the same model to the next workpiece after a simple conversion. However, this process suffers from accuracy issues in trajectory conversion, affecting the overall accuracy of the automated process. Therefore, current automation methods still need improvement in both efficiency and accuracy. Summary of the Invention

[0004] This application provides a process automation method, system, and electronic device based on digital control, to at least solve the problems of low efficiency and low accuracy in existing process automation.

[0005] According to one aspect of the embodiments of this application, a process automation method based on digital control is provided, characterized by comprising: acquiring a target workpiece model and a target workpiece type corresponding to the workpiece to be processed, and determining a target workpiece coordinate system corresponding to the target workpiece model, wherein the target workpiece coordinate system is used to indicate the coordinate system of the workpiece to be processed itself; searching for a reference trajectory file corresponding to the target workpiece type from a preset storage location; if a reference trajectory file is found, converting the reference trajectory indicated by the reference trajectory file into a target trajectory corresponding to the target workpiece based on the target workpiece coordinate system; if a reference trajectory file is not found, planning the target trajectory corresponding to the workpiece to be processed according to the target workpiece model and the target process corresponding to the workpiece to be processed, generating a target trajectory file based on the target workpiece coordinate system and the target trajectory, and storing the target trajectory file and the target workpiece type corresponding to each other in a preset storage location; and performing target process processing on the workpiece to be processed using the target trajectory.

[0006] According to another aspect of the embodiments of this application, a process automation system based on digital control is also provided, comprising: an acquisition module, configured to acquire a target workpiece model and a target workpiece type corresponding to the workpiece to be processed, and determine a target workpiece coordinate system corresponding to the target workpiece model, wherein the target workpiece coordinate system is used to indicate the coordinate system of the workpiece to be processed itself; a search module, configured to search for a reference trajectory file corresponding to the target workpiece type from a preset storage location, and if a reference trajectory file is found, convert the reference trajectory indicated by the reference trajectory file into a target trajectory corresponding to the target workpiece based on the target workpiece coordinate system; a planning module, configured to, if a reference trajectory file is not found, plan the target trajectory corresponding to the workpiece to be processed according to the target workpiece model and the target process corresponding to the workpiece to be processed, generate a target trajectory file based on the target workpiece coordinate system and the target trajectory, and store the target trajectory file and the target workpiece type corresponding to the preset storage location; and a process processing module, configured to perform target process processing on the workpiece to be processed using the target trajectory.

[0007] Optionally, the acquisition module includes: an identification submodule, used to identify the position information of multiple workpieces on the processing production line at the current timestamp based on the trigger operation of the process; a workpiece determination submodule, used to determine the workpiece to be processed based on the multiple position information; and a model acquisition submodule, used to acquire the target workpiece model and target workpiece model corresponding to the workpiece to be processed from a preset storage location, wherein the preset storage location stores standard workpiece models, processing trajectory files, workpiece models, and real workpiece models constructed during the processing of various workpiece models.

[0008] Optionally, the acquisition module further includes: a feature point extraction submodule, used to extract multiple feature points from the target workpiece model based on feature point determination rules; and a coordinate system determination submodule, used to determine the target workpiece coordinate system based on multiple feature points and preset coordinate system establishment rules.

[0009] Optionally, the aforementioned process automation system based on digital control further includes: a first image acquisition module, used to acquire multiple first images captured by a camera device on multiple first workpieces on the processing production line during a first shooting time period, and to determine the first image type corresponding to each first image, with each first image corresponding to a shooting angle; a first preprocessing module, used to preprocess the multiple first images according to the first image type corresponding to the first images to obtain multiple point cloud data; a first point cloud clustering module, used to perform point cloud clustering on the multiple point cloud data to obtain different point cloud clustering results; and a workpiece model determination module, used to perform different post-processing operations on the multiple point cloud data according to the different point cloud clustering results, and to determine the workpiece model from the operation results.

[0010] Optionally, the above-mentioned workpiece model determination module includes: a data integration submodule, used to integrate point cloud data indicating that they belong to the same workpiece based on the point cloud clustering results to obtain multiple reference workpiece models; a reference model acquisition submodule, used to identify the workpiece model of each workpiece to be processed based on the processing technology corresponding to multiple workpieces on the processing production line, using an identification method corresponding to the processing technology, to obtain the reference workpiece model corresponding to each workpiece; a completeness submodule, used to obtain the standard workpiece model corresponding to each workpiece from a preset storage location according to each reference workpiece model, and to perform model completeness matching on multiple reference workpiece models based on each standard workpiece model to obtain the model completeness corresponding to each reference workpiece model; and a post-processing submodule, used to perform post-processing operations based on the completeness of multiple models.

[0011] Optionally, the post-processing submodule includes: a first storage submodule, used to store the reference workpiece model and the corresponding reference workpiece model to a preset storage location when the model completeness is greater than or equal to a preset completeness; an image capture submodule, used to acquire multiple second-shot images captured by the camera device on multiple second workpieces on the processing production line during a second shooting time period, and multiple third-shot images captured by the camera device on multiple third workpieces on the processing production line during a third shooting time period, wherein the second shooting time period is a time period adjacent to the first shooting time period, and the third shooting time period is a time period adjacent to the first shooting time period; an image processing submodule, used to perform image processing on the multiple second-shot images and multiple third-shot images using the same image processing method as the first-shot images, to obtain different multiple second point cloud clustering results, wherein image processing includes preprocessing and point cloud clustering; and a second storage submodule, used to match and stitch the reference workpiece models with a model completeness less than a preset completeness according to the multiple second point cloud clustering results, to obtain a stitched model, and to store the stitched model and the corresponding workpiece model to a preset storage location.

[0012] Optionally, the second storage submodule includes: a first model submodule, used to integrate point cloud data indicating that the second point cloud clustering results belong to the same workpiece to obtain multiple first reference workpiece models; a second model submodule, used to determine the second reference workpiece model corresponding to the reference workpiece model with a model completeness less than a preset completeness based on the position information of each first reference workpiece model on the processing production line; and a splicing model submodule, used to match and splice the second reference workpiece model with the reference workpiece model with a model completeness less than a preset completeness to obtain a spliced ​​model.

[0013] According to another aspect of the embodiments of this application, a computer-readable storage medium is provided, which stores computer instructions for causing a computer to perform the above-described process automation method based on digital control.

[0014] According to another aspect of the embodiments of this application, an electronic device is also provided, the electronic device including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable at least one process automation method based on digital control.

[0015] Compared with the prior art, the technical solution provided in this application embodiment may include the following beneficial effects: The above-mentioned process automation method based on digital control solves the problems of low efficiency and low accuracy of existing process automation methods, and improves the efficiency and accuracy of process automation methods.

[0016] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the hardware environment for an optional process automation method based on digital control according to an embodiment of the present invention; Figure 2 This is a flowchart of an optional process automation method based on digital control according to an embodiment of the present invention; Figure 3 This is a schematic diagram of an optional process automation method based on digital control according to an embodiment of the present invention; Figure 4 This is a schematic diagram of an optional process automation system based on digital control according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present invention. Detailed Implementation

[0019] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0020] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0021] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0022] To address the low efficiency and accuracy issues of existing process automation methods, this application provides a process automation method based on digital control. As an optional implementation, the aforementioned process automation method based on digital control can be applied, but is not limited to, to methods such as... Figure 1 The illustrated example is a process automation system based on digital control, consisting of terminal device 102 and server 104. (For example...) Figure 1 As shown, terminal device 102 is connected to server 104 via network 110. Network 110 may include, but is not limited to, wired networks and wireless networks. The wired network includes local area networks (LANs), metropolitan area networks (MANs), and wide area networks (WANs). The wireless network includes Bluetooth, Wi-Fi, and other networks that enable wireless communication. Terminal device 102 may include, but is not limited to, at least one of the following: mobile phones (such as Android phones, iOS phones, etc.), laptops, tablets, handheld computers, MIDs (Mobile Internet Devices), tablets, desktop computers, smart TVs, etc.

[0023] The aforementioned terminal device 102 is also equipped with a display 106, a processor 108, and a memory 112. The display 106 can be used to display the target process processing area, the processor 108 can be used to process the workpiece model to be processed, and the memory 112 can be used to store various models and data involved in this application.

[0024] The aforementioned server 104 can be a single server, a server cluster consisting of multiple servers, or a cloud server. The aforementioned server 104 includes a database 114 and a processing engine 116. The database 114 can be used to store various models and data involved in this application, and the processing engine 116 is used to process data such as target trajectories corresponding to the various models.

[0025] According to one aspect of the present invention, the above-described process automation system based on digital control can further perform the following steps: First, the terminal device 102 executes S102, sending a target process processing request to the server 104 via the network 110; then the server 104 executes S104 to S108: obtaining the target workpiece model and target workpiece type corresponding to the workpiece to be processed, and determining the target workpiece coordinate system corresponding to the target workpiece model, wherein the target workpiece coordinate system is used to indicate the coordinate system of the workpiece to be processed itself; searching for a reference trajectory file corresponding to the target workpiece type from a preset storage location; if a reference trajectory file is found, converting the reference trajectory indicated by the reference trajectory file into a target trajectory corresponding to the target workpiece based on the target workpiece coordinate system; if no reference trajectory file is found, planning the target trajectory corresponding to the workpiece to be processed according to the target workpiece model and the target process corresponding to the workpiece to be processed, generating a target trajectory file based on the target workpiece coordinate system and the target trajectory, and storing the target trajectory file and the target workpiece type corresponding to the target process in a preset storage location; and using the target trajectory to process the workpiece to be processed using the target process.

[0026] In the above embodiments of the present invention, the process automation method based on digital control is adopted, which solves the problems of low efficiency and accuracy of existing process automation methods and improves the efficiency and accuracy of process automation.

[0027] The above is merely an example, and no limitations are made in this embodiment.

[0028] As an alternative implementation method, please refer to Figure 2 This document illustrates a flowchart of a process automation method based on digital control, provided in one embodiment of this application. The execution entities for each step of this method can be the terminal devices and servers described above. In the following method embodiments, for ease of description, the execution entity for each step will only be described as a "computer device." This method may include at least one of the following steps (S202 to S208): S202, obtain the target workpiece model and target workpiece type corresponding to the workpiece to be processed, and determine the target workpiece coordinate system corresponding to the target workpiece model. The target workpiece coordinate system is used to indicate the coordinate system of the workpiece to be processed itself. S204, search for the reference trajectory file corresponding to the target workpiece model from the preset storage location. If the reference trajectory file is found, convert the reference trajectory indicated by the reference trajectory file into the target trajectory corresponding to the target workpiece based on the target workpiece coordinate system. S206, If no reference trajectory file is found, after planning the target trajectory corresponding to the workpiece to be processed based on the target workpiece model and the target process corresponding to the workpiece to be processed, a target trajectory file is generated based on the target workpiece coordinate system and the target trajectory, and the target trajectory file and the target workpiece model are stored in the preset storage location. S208, the target trajectory is used to perform target process processing on the workpiece to be processed.

[0029] It should be noted that the target process includes processes such as spraying, sandblasting, grinding, measurement, and adhesive application to treat the workpiece. The target workpiece model in S202 is the model corresponding to the workpiece to be treated. The target workpiece model includes, but is not limited to, point cloud models, mesh models, surface models, and wireframe models. The target workpiece model is used to associate the target workpiece with the standard workpiece model and its reference trajectory through a unique identifier. The target workpiece model can be obtained by identification methods, including but not limited to identification by the target workpiece's number or label, or identification by feature matching between the target workpiece model and the pre-stored standard workpiece model. The target workpiece coordinate system is used to indicate the workpiece itself (i.e., with a certain point on the workpiece itself as the origin of the coordinate system). Specifically, the target workpiece coordinate system is determined based on the method of determining the preset coordinate system (the coordinate system of the standard workpiece model corresponding to the target workpiece). The coordinate system of the standard workpiece model can be established based on three feature points of the standard workpiece model; while the target workpiece coordinate system can be established based on the corresponding three feature points of the target workpiece model.

[0030] The preset storage location in S204 above includes, but is not limited to, the PQPMS platform. The PQPMS platform is a digital process private cloud platform using a B / S architecture (users can access it by logging into the platform's URL). It can privately store process data and accurately record reference trajectories, model data, and model information for various workpiece models. Furthermore, the reference trajectory refers to the processing trajectory corresponding to the standard workpiece model, while the target trajectory refers to the processing trajectory corresponding to the target workpiece. Since the poses (positions and orientations) of the standard workpiece model and the target workpiece may be completely different, it is necessary to convert the reference trajectory into the target trajectory (e.g., converting the horizontal reference trajectory on a horizontally placed standard workpiece model into a vertical target trajectory on a vertically placed target workpiece). Specifically, the method for converting the reference trajectory indicated by the reference trajectory file into the target trajectory corresponding to the target workpiece based on the target workpiece coordinate system includes, but is not limited to: when the poses of the standard workpiece model and the target workpiece are completely different: the preset coordinate system is based on three features of the standard workpiece model. The coordinate system is established based on three feature points of the standard workpiece model. The target workpiece coordinate system is established based on three corresponding feature points of the target workpiece. Both the preset coordinate system and the target workpiece coordinate system are local coordinate systems. The transformation between these two local coordinate systems (feature point transformation) reflects the pose transformation between the standard workpiece model and the target workpiece, thus converting the reference trajectory of the standard workpiece model into the target trajectory of the target workpiece. The calculation method for the transformation between the two local coordinate systems includes, but is not limited to: First, obtaining the coordinates of the three feature points of the standard workpiece model and the corresponding three feature points of the target workpiece in the global coordinate system (i.e., the world coordinate system, corresponding to the fixed coordinate system of the workpiece assembly line or operating table). Then, based on these coordinates, calculating the transformation matrices of the two local coordinate systems (the preset coordinate system and the target workpiece coordinate system) relative to the global coordinate system. Let the transformation matrix from the preset coordinate system to the global coordinate system be T_ref, and the transformation matrix from the target workpiece coordinate system to the global coordinate system be T_tar. Therefore, the core of the transformation from the reference trajectory to the target trajectory is to calculate the coordinate transformation matrix T_transform, which satisfies the relationship: T_tar * T_transform = T_ref. From this, we can solve for T_transform = T_tar. -1 Finally, apply this transformation matrix T_transform to all path points on the reference trajectory to obtain the target trajectory suitable for the current pose of the target workpiece. If the standard workpiece model and the target workpiece differ only in position and not in pose, then it is only necessary to calculate the translation vectors of the feature points of the standard workpiece model and the feature points of the target workpiece in the world coordinate system to convert the reference trajectory into the target trajectory through translation.

[0031] In S206 above, the methods for planning the target trajectory include, but are not limited to, generating the target trajectory through PQArt. PQArt is an offline programming software suitable for programming domestically produced robots and can generate target trajectories for different types of target workpieces. In S208 above, the target process (spraying, sandblasting, etc.) can be performed through the robot actuator.

[0032] The following is combined Figure 3 The operations in S202 to S208 above are illustrated with an example: When spraying a wear-resistant and corrosion-resistant coating on the edge of an L-shaped workpiece, firstly, the target workpiece model 100 and the target workpiece model (LP-WIP) corresponding to the L-shaped workpiece are obtained through feature matching. Then, the target workpiece coordinate system is determined using feature points A, B, and C on the target workpiece model 100 (e.g., ...). Figure 3 With point A as the origin, x-axis (Using the y-axis and determining the z-axis using the right-hand rule), then, the reference trajectory file corresponding to LP-WIP is searched from the PQPMS platform. Assume that the three feature points in the standard workpiece model corresponding to the found reference trajectory file are A'(0, 0, 2), B'(0, 1, 2), and C'(2, 0, 2), and the reference trajectory indicated by the reference trajectory file is B'→A'→C' on the standard workpiece model (points A', B', and C' correspond to points A, B, and C on the target workpiece model, respectively). Through the... Given the keypoint coordinates A(0,0,0), B(0,1,0), C(2,0,0), A'(0,0,2), B'(0,1,2), and C'(2,0,2), it can be seen that, relative to the global coordinate system, the orientation of the standard workpiece model (corresponding to the preset coordinate system) and the target workpiece model (corresponding to the target workpiece coordinate system) are identical, with the translation vector being (0,0,-2). Therefore, the reference trajectory B'→A'→C' can be moved as a whole by (0,0,-2) to convert it into the target trajectory B→A→C. If the reference trajectory file is not found, the target trajectory B→A→C can be generated using PQArt, and the target trajectory file and workpiece model LP-WIP can be stored on the PQPMS platform. Finally, the wear-resistant and corrosion-resistant coating is applied by the robot along the target trajectory B→A→C.

[0033] It should be noted that after obtaining the target trajectory, a self-verification of the target trajectory is required to ensure that there are no collisions, unreachable conditions, or other faults. If the self-verification result is fault-free, the program can be remotely distributed, that is, the newly generated fault-free mod file (indicating the target trajectory) can be remotely transmitted to the robot, and the robot can then process the workpiece along the target trajectory. Preferably, the virtual debugging process, such as self-verification, can be performed through PQFactory, which is an intelligent production line design and virtual debugging software that supports production line modeling, signal mapping, and virtual debugging. The management of all the above data and equipment, as well as process monitoring, are completed through PQCC (a B / S architecture digital management and control platform). Preferably, the steps for generating the reference trajectory include: 1. Scene construction and signal definition (PQFactory): Scene construction: Build a 3D model of the production line scene, configure the robot's kinematic parameters and the signal and communication protocols between the equipment; Virtual debugging and verification: Simulate the coordinated movement of the robot-camera-slide table, set up a safety protection space, and perform signal debugging. 2. Scene import: Import the 3D scene model built in PQFactory into the PQArt software. 3. Reference trajectory planning: For a certain type of workpiece, import its workpiece model and drag the model to a suitable position within the robot's reachable area; plan its operation trajectory in the software and compile and simulate it to ensure that the trajectory is fault-free. In addition, it needs to be fine-tuned on the actual production line to ensure that the trajectory meets the actual operation requirements; define a preset coordinate system on the standard workpiece model in the software, and generate a reference trajectory based on the preset coordinate system.

[0034] Through the above-described embodiments of this application, the process automation method based on digital control solves the problems of low efficiency and accuracy in existing process automation methods, and improves the efficiency and accuracy of process automation.

[0035] As an optional implementation, the above-mentioned acquisition of the target workpiece model and target workpiece type corresponding to the workpiece to be processed includes: S1, based on the trigger operation of the process processing, identifies the position information of multiple workpieces on the processing production line at the current timestamp; S2, determine the workpiece to be processed based on multiple location information; S3. Obtain the target workpiece model and target workpiece model corresponding to the workpiece to be processed from the preset storage location. The preset storage location stores standard workpiece models, machining trajectory files, workpiece models, and real workpiece models constructed during the machining process for various workpiece models.

[0036] Since it is common for multiple workpieces to exist simultaneously on automated production lines, and the models and processes of the workpieces may differ, it is necessary to identify the position information of multiple workpieces simultaneously in step S1 to prevent confusion and errors. Then, in step S2, the workpiece to be processed is accurately determined based on the multiple position information combined with preset logic (such as "the workpiece closest to the machine tool entrance" or "the workpiece corresponding to the next process number"). In other words, the system needs to know the arrangement order and relative position of all workpieces to determine the next workpiece to be processed, thereby ensuring a smooth and efficient workpiece processing flow. Preferably, the workpiece position information can be obtained through Mech-Vision software, a 3D vision processing software with built-in advanced algorithm modules such as 3D vision and deep learning, enabling rapid workpiece positioning. Other methods can also be used to obtain workpiece position information, which are not limited in this application.

[0037] In S3 above, the preset storage location includes, but is not limited to, the PQPMS platform. The PQPMS platform stores standard workpiece models, machining trajectory files, workpiece models, and real workpiece models built during the machining process for various workpiece models.

[0038] Preferably, the above-mentioned triggering operation can be based on, for example, Figure 1 The target process processing request sent by the terminal device 102 shown can also be other trigger operations. After the target process processing is triggered by the trigger operation, the program communication involved includes Mech-Vision, PQFactory, and PQCC software. Among them, Mech-Vision: Open the Mech-Vision software on the host computer, confirm whether the camera is connected, and open the pre-written algorithm flow that can identify the actual user coordinate system of the workpiece. Import the workpiece model, the position information of the workpiece model relative to the robot, and the coordinate system information from PQArt into Mech-Vision to define a standard workpiece model; PQFactory: Open the PQFactory software and the built working environment on the host computer, perform signal debugging, and confirm the communication with the PLC, camera, and robot; PQCC: Open the PQCC production line digital control system on the host computer. After the workpiece is placed on the workbench, select the workpiece model, click the start button in PQCC, and view the system progress on the PQCC page based on the collected PLC and equipment signals.

[0039] As an optional implementation, the above-described determination of the target workpiece coordinate system corresponding to the target workpiece model includes: S1, extract multiple feature points from the target workpiece model based on feature point determination rules; S2, establishes rules based on multiple feature points and a preset coordinate system to determine the target workpiece coordinate system.

[0040] In S1 above, the feature point determination rule is used to extract feature points of the target workpiece model. These feature points are generally extreme points or center points of the geometric shape, such as model vertices, model center points, intersections of two lines, etc. Figure 3 The feature points of the target workpiece model 100 are vertices A, B, and C.

[0041] In S2 above, the preset coordinate system establishment rules are used to determine the target workpiece coordinate system. For example, the coordinate system establishment rules are as follows: the feature point at the bottom left corner of the model, closest to the machine tool entrance, is taken as the origin of the coordinate system; the positive direction of the x-axis is determined by pointing from the origin to the point at the right rear of the model; the positive direction of the y-axis is determined by pointing from the origin to the point at the bottom left corner of the model; and the z-axis is obtained by cross-product of the x-axis and y-axis using the right-hand rule. The target workpiece coordinate system can be determined using these coordinate system establishment rules and the feature points.

[0042] As an optional implementation, before obtaining the target workpiece model and target workpiece type corresponding to the workpiece to be processed, the following steps are also included: S103, acquire multiple first images captured by the camera device on multiple first workpieces on the processing production line during the first shooting time period, and determine the first image type corresponding to each first image, with each first image corresponding to a shooting angle. S105, preprocess multiple first captured images according to the first image type corresponding to the first captured image to obtain multiple point cloud data; S107, perform point cloud clustering on multiple point cloud datasets to obtain different point cloud clustering results; S109: Perform different post-processing operations on multiple point cloud data based on different point cloud clustering results, and determine the workpiece model from the operation results.

[0043] The camera device in S103 described above can accurately measure detailed information such as the three-dimensional shape, position, and depth of an object. During shooting, the appropriate resolution, working distance, and field of view can be selected as needed. Preferably, a Mech-Mind NANO ULTRA 3D camera with a resolution of 2400×1800, a working distance of 400-800mm, a near-field field of view of 400×270mm, and a far-field field of view of 770×550mm can be used. Furthermore, a servo slide system can be used to control the camera for precise multi-position movement and shooting. Preferably, the servo slide system includes a 1m travel guide rail (for camera movement) and a Siemens 1214 DC / DC / DC PLC (for intelligent automatic control of the camera). In addition, workpieces on the processing production line can be moved, gripped, and adjusted by industrial robots. Preferably, an ABB IRB 120 industrial robot (3kg load, 0.01mm accuracy, supports 7-axis linkage trajectory planning) can be used. The information acquisition, analysis, and determination of specific operations of the entire system can be completed by a host computer. Preferably, the host computer model is AMD Ryzen 9 7945HX / 64GB RAM.

[0044] The first captured image obtained by the aforementioned camera device is a 3D image. The first captured image includes multiple first workpieces, so that the first captured image does not capture an isolated workpiece, but multiple workpieces and their spatial distribution relationship on the production line. Furthermore, each first captured image has a corresponding first image type and shooting angle. The first image type includes, but is not limited to, depth map, color map, point cloud, structured light image, etc., while the shooting angle records the spatial relationship between the camera device and the workpiece being photographed. The recording of the shooting angle parameters ensures that not only the shape of the workpiece is recorded, but also the accurate pose of the workpiece can be accurately obtained.

[0045] In step S105 above, preprocessing methods include, but are not limited to, point filtering (removing noise and reducing point cloud density), point normals (estimating the local geometric orientation of the point cloud surface), decoding, and coordinate transformation. Point filtering methods include, but are not limited to, Gaussian filtering (applying a Gaussian weighted average to the neighborhood of each point to suppress high-frequency noise); point normals methods include, but are not limited to, PCA (calculating the covariance matrix for the neighborhood of each point, with the eigenvector corresponding to the smallest eigenvalue being the normal vector), and least squares. It should be noted that different preprocessing methods can be used for different types of first images. By calling the most suitable preprocessing method, the raw data in the first captured image can be accurately and efficiently converted into high-quality point cloud data, avoiding the accuracy loss caused by fixed preprocessing methods. The resulting point cloud data is a collection of a large number of independent data points with three-dimensional coordinates. These numerous data points can concisely and accurately represent the three-dimensional contour and shape of objects, improving the computational efficiency of subsequent steps. The point cloud data obtained through S105 is the sum of all point clouds corresponding to multiple workpieces, processing lines, etc.

[0046] In S107 above, point cloud clustering refers to automatically dividing all the obtained point cloud data into different groups based on features such as the three-dimensional spatial distance between points using a point cloud clustering algorithm. Each group corresponds to an independent object (an independent workpiece or processing line). Point cloud clustering methods include, but are not limited to: clustering based on distance thresholds (such as Euclidean clustering), clustering based on density (such as DBSCAN), region growing clustering, machine learning, etc.

[0047] In S109 above, since the obtained point cloud clustering results correspond to different workpiece integritys (not every workpiece in the first captured image is necessarily complete), different post-processing operations need to be performed on the point cloud data, and the workpiece model needs to be determined.

[0048] As an optional implementation, the above-mentioned post-processing operations on multiple point cloud data based on different point cloud clustering results include: S1091, integrate the point cloud data that indicate the point cloud clustering results belong to the same workpiece to obtain multiple reference workpiece models; S1092, based on the processing technology corresponding to multiple workpieces on the processing production line, the workpiece model is identified by the identification method corresponding to the processing technology for each workpiece to be processed, and the reference workpiece model corresponding to each workpiece is obtained. S1093, retrieve the standard workpiece model corresponding to each workpiece from the preset storage location according to each reference workpiece model, and perform model integrity matching on multiple reference workpiece models based on each standard workpiece model to obtain the model integrity corresponding to each reference workpiece model; S1094 performs post-processing operations based on the completeness of multiple models.

[0049] In step S1091 above, point cloud data belonging to the same workpiece are integrated based on the point cloud clustering results. Specific methods include, but are not limited to, the iterative nearest point algorithm. The integration of point cloud data can be understood as follows: since multiple first-shot images may have captured the same workpiece multiple times from different angles, multiple point cloud fragments of the same workpiece are stitched together into a complete and unified 3D model, i.e., the reference workpiece model, through point cloud data integration.

[0050] In step S1092 above, the processing technology (spraying, welding, quality inspection, etc.) corresponding to multiple workpieces is first determined. Then, the corresponding recognition method is determined according to different processing technologies. For example, the spraying process corresponds to a recognition method based on contour and pose, the welding process corresponds to a recognition method based on edge extraction and trajectory recognition, and the quality inspection corresponds to a recognition method based on local feature enhancement. Through recognition, the reference workpiece model corresponding to each workpiece can be obtained.

[0051] In step S1093 above, the standard workpiece model can be understood as a complete model of this type of workpiece. It can be obtained from the PQPMS platform using a reference workpiece model. Multiple reference workpiece models are matched with each standard workpiece model to determine the model completeness (e.g., 98%), which determines whether the reference workpiece model can be used directly. Step S1094 allows for different post-processing operations on models with different completeness levels.

[0052] The above post-processing operations based on the completeness of multiple models include: S1. If the model completeness is greater than or equal to the preset completeness, store the reference workpiece model and the reference workpiece model corresponding to the reference workpiece model in the preset storage location. S2, when the model completeness is less than the preset completeness, acquire multiple second images of multiple second workpieces on the processing production line captured by the camera device in the second shooting time period, and multiple third images of multiple third workpieces on the processing production line captured by the camera device in the third shooting time period, wherein the second shooting time period is the adjacent time period before the first shooting time period, and the third shooting time period is the adjacent time period after the first shooting time period. S3, using the same image processing method as the first captured image, perform image processing on multiple second captured images and multiple third captured images to obtain different multiple second point cloud clustering results. The image processing includes preprocessing and point cloud clustering. S4. Based on multiple second-point cloud clustering results, match and stitch together reference workpiece models whose model completeness is less than the preset completeness to obtain a stitched model, and store the stitched model and the workpiece model corresponding to the stitched model in the preset storage location.

[0053] First, the completeness of the reference workpiece model is judged. By using a pre-set acceptable model completeness threshold (preset completeness), it can be determined whether the reference workpiece model is complete enough. The preset completeness can be manually set according to specific processes, workpiece requirements, etc. When the reference workpiece model is complete enough (model completeness is greater than or equal to the preset completeness), it is stored with the corresponding reference workpiece model through the above S1 step. When the reference workpiece model is not complete enough (model completeness is less than the preset completeness), it is necessary to acquire more images taken at different time periods to complete the reference workpiece model. Acquiring more images specifically includes: acquiring multiple second images taken by the camera device at multiple second workpieces on the processing production line during the second shooting time period, and multiple third images taken by the camera device at multiple third workpieces on the processing production line during the third shooting time period. The second shooting time period is the adjacent time period before the first shooting time period, and the third shooting time period is the adjacent time period after the first shooting time period. That is, images taken before and after the first shooting time period (second shooting images and third shooting images) are acquired.

[0054] In step S3, the second point cloud clustering result is obtained through the second and third captured images. The specific process (preprocessing, point cloud clustering) is the same as that for obtaining the first point cloud clustering result, and will not be repeated here. Then, in step S4, the reference workpiece model with a model completeness less than the preset completeness is matched and stitched according to the multiple second point cloud clustering results. This can be understood as follows: In the first captured image, only half of workpiece A was captured, so the completeness of the reference workpiece model of workpiece A is insufficient. However, in the second (or third) captured image, the other half of workpiece A was captured. Therefore, the original reference workpiece model is stitched together. The matching process for the two different parts of workpiece A can include: First, applying a coarse matching algorithm, i.e., quickly finding the initial correspondence between two captured images (point cloud images) through a feature point-descriptor-matching strategy-mismatch removal process. Feature points refer to unique and stable feature points detected in the two point cloud images using algorithms such as SIFT (Scale Invariant Feature Transform) and SURF (Accelerated Robust Feature Transform), feature points with unique geometric structures in the 3D point cloud detected using ISS (Internal Shape Descriptor), and 3D interest points (such as corner points) detected in the point cloud using Harris3D. Descriptors refer to the 128-dimensional gradient histogram of the region surrounding the keypoint calculated using the SIFT descriptor, used to describe the texture of the region. The system generates a local geometric description based on normal vectors (e.g., whether it belongs to a plane, cylinder, or edge) through FPFH / PPFH (Fast Point Feature Histogram); the matching strategy refers to finding the most similar feature points by brute force matching (calculating the distance of all feature pairs and taking the nearest neighbor) or FLANN (Fast Approximate Nearest Neighbor Search); removing mismatches refers to removing outliers by RANSAC (Random Sample Consensus Algorithm) to resist interference, estimating the coarse pose transformation from the source point cloud to the target point cloud and obtaining a set of reliable matching pairs. RANSAC is an iterative algorithm that calculates the pose transformation by randomly selecting a set of corresponding point pairs and evaluating the fit of the transformation, and finally selecting the transformation with the best fit as the final result. Secondly, a fine matching algorithm is used, that is, the coarse matching result is optimized by ICP or deep learning to improve the registration accuracy. The specific process includes, but is not limited to: (1) Data preparation: input point cloud with normal vectors and target point cloud (template point cloud), and the transformation evidence of the initial coarse pose obtained in coarse matching. (2) Algorithm matching: Starting from the initial pose, the selected fine matching algorithm (ICP) is used for iterative optimization. In each iteration: Find corresponding point pairs between the source point cloud and the target point cloud. Based on the corresponding point pairs, calculate the current error metric (such as the sum of squared distances between point pairs or the sum of squared distances from a point to a surface). Calculate the rigid body transformation (rotation matrix and translation vector) that minimizes the error metric and update the pose of the source point cloud. Repeat the above steps until the convergence condition is met (such as the error metric being less than a preset threshold or the number of iterations reaching the upper limit).(3) Calculate the transformation: After the iteration, the transformation matrix obtained is the transformation between the current pose and the template pose. (4) Determine the gripping point pose: The coordinates of the gripping point of the workpiece in the template point cloud are known; the final transformation matrix is ​​used to transform the gripping point from the template point cloud coordinate system to the current point cloud coordinate system to obtain the gripping point pose of the workpiece in the current scene. (5) Calculate the confidence: 1. Matching Error Measurement Point-to-point distance: Calculates the average or maximum distance between corresponding point pairs in the source and target point clouds after registration. The smaller the distance, the more accurate the matching and the higher the pose confidence.

[0055] Overlap region error: Evaluates the matching error of the overlapping regions between the source and target point clouds. For example, it calculates the mean square error of point pairs within the overlapping region. The smaller the error, the higher the confidence level.

[0056] 2. Corresponding point pairs in quantity and quality Number of corresponding point pairs: The more corresponding point pairs there are, the richer the matching information and the higher the reliability of the pose.

[0057] Distribution of corresponding point pairs: The more evenly corresponding point pairs are distributed in the point cloud, the higher the confidence level of the pose. If corresponding point pairs are concentrated in local areas, it may lead to inaccurate pose estimation.

[0058] 3. Iterative convergence status Convergence speed: If the fine matching algorithm converges to a small error within a few iterations, it indicates that the pose estimation is relatively reliable and has a high degree of confidence.

[0059] Convergence stability: Observe the change in error in each iteration. If the error decreases monotonically and changes steadily, it indicates that the convergence process is stable and the pose confidence is high.

[0060] After the above coarse matching and fine matching processes are completed, reference workpiece models with a model completeness less than the preset completeness can be matched and spliced ​​to obtain a spliced ​​model. It should be noted that after obtaining the spliced ​​model, the completeness of the spliced ​​model still needs to be verified based on the standard workpiece model. If the completeness of the spliced ​​model is greater than or equal to the preset completeness, the spliced ​​model and the workpiece model corresponding to the spliced ​​model are stored. If the completeness of the spliced ​​model is less than the preset completeness, the splicing operation needs to continue.

[0061] As an optional implementation, the above-mentioned matching and splicing of reference workpiece models with model completeness less than a preset completeness based on multiple second point cloud clustering results includes: first, integrating the point cloud data indicating that they belong to the same workpiece according to the second point cloud clustering results to obtain multiple first reference workpiece models; then, determining the second reference workpiece model corresponding to the reference workpiece model with model completeness less than the preset completeness based on the position information of each first reference workpiece model on the processing production line; finally, matching and splicing the second reference workpiece model with the reference workpiece model with model completeness less than the preset completeness to obtain a spliced ​​model. Among these methods, determining the second reference workpiece model corresponding to the reference workpiece model through position information can greatly improve matching efficiency and accuracy.

[0062] In the above embodiments of the present invention, the process automation method based on digital control solves the problems of low efficiency and accuracy in existing process automation methods, and can also achieve: Self-correcting trajectory: Integrating 3D vision with offline programmed trajectory, it automatically corrects trajectory deviations caused by inconsistent workpiece pose.

[0063] Multi-model workpiece mixed-line production: Supports the production of multiple workpiece models. The system automatically matches trajectory templates, reducing manual intervention.

[0064] Digital process management: The PQPMS platform enables the digital integration and management of trajectory templates.

[0065] Open architecture: Supports integration with other information systems.

[0066] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0067] According to another aspect of the present invention, a process automation system for implementing the above-described process automation method based on digital control is also provided, such as... Figure 4 As shown, the system includes: The acquisition module 402 is used to acquire the target workpiece model and target workpiece model corresponding to the workpiece to be processed, and to determine the target workpiece coordinate system corresponding to the target workpiece model. The target workpiece coordinate system is used to indicate the coordinate system of the workpiece to be processed itself. The lookup module 404 is used to look up a reference trajectory file corresponding to the target workpiece model from a preset storage location. If the reference trajectory file is found, the reference trajectory indicated by the reference trajectory file is converted into the target trajectory corresponding to the target workpiece based on the target workpiece coordinate system. The planning module 406 is used to plan the target trajectory corresponding to the workpiece to be processed based on the target workpiece model and the target process corresponding to the workpiece to be processed when no reference trajectory file is found. Then, it generates a target trajectory file based on the target workpiece coordinate system and the target trajectory, and stores the target trajectory file and the target workpiece model in a preset storage location. The process processing module 408 is used to perform target process processing on the workpiece to be processed using the target trajectory.

[0068] The specific methods of execution of each unit in the above device embodiments have been described in detail in the embodiments related to the method, and will not be elaborated further here.

[0069] According to another aspect of the present invention, an electronic device for implementing the above-described process automation method based on digital control is also provided. This electronic device may be as follows: Figure 5 The terminal device or server shown. This embodiment uses this electronic device as an example for illustration. Figure 5 As shown, the electronic device includes: at least one processor 504; and a memory 502 communicatively connected to at least one processor 504; wherein the memory 502 stores a computer program that can be executed by at least one processor 504, the computer program being executed by at least one processor 504 to cause at least one processor 504 to perform the steps in any of the above embodiments of the process automation method based on digital control.

[0070] Optionally, in this embodiment, the aforementioned electronic device may be located in at least one of a plurality of network devices in a computer network.

[0071] Optionally, in this embodiment, the processor can be configured to execute the various steps in the above-described digital control-based process automation method via a computer program.

[0072] Alternatively, as those skilled in the art will understand, Figure 5 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones (such as Android phones, iOS phones, etc.), tablets, PDAs, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 5 This does not limit the structure of the aforementioned electronic devices. For example, the electronic device may also include components that are more... Figure 5The more or fewer components shown (such as network interfaces, etc.), or having the same Figure 5 The different configurations shown.

[0073] The memory 502 can be used to store software programs and modules. The processor 504 executes various functional applications and data processing by running the software programs and modules stored in the memory 502, thereby realizing the aforementioned process automation method based on digital control. The memory 502 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 502 may further include memory remotely located relative to the processor 504, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Specifically, the memory 502 may be used, but is not limited to, to store various models and data involved in this application. As an example, such as Figure 5 As shown, the memory 502 may include, but is not limited to, the acquisition module 402, search module 404, planning module 406, and process processing module 408 from the aforementioned process automation system. Furthermore, it may include, but is not limited to, other module units from the aforementioned process automation device, which will not be elaborated upon in this example.

[0074] Optionally, the transmission device 506 described above is used to receive or send data via a network. Specific examples of the network described above may include wired networks and wireless networks. In one example, the transmission device 506 includes a Network Interface Controller (NIC), which can be connected to other network devices and a router via a network cable to communicate with the Internet or a local area network. In another example, the transmission device 506 is a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0075] In addition, the above-mentioned electronic device also includes a display 508 and a connection bus 510 for connecting the various module components in the above-mentioned electronic device.

[0076] In other embodiments, the aforementioned terminal device or server can be a node in a distributed system, wherein the distributed system can be a blockchain system, which is a distributed system formed by connecting multiple nodes through network communication. The nodes can form a peer-to-peer (P2P) network, using any type of computing device.

[0077] According to one aspect of this application, a computer program product is provided, comprising a computer program / instructions containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit, it performs various functions provided in embodiments of this application.

[0078] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0079] According to one aspect of this application, a computer-readable storage medium is provided, from which a processor of a computer device reads computer instructions and executes the computer instructions, causing the computer device to perform the aforementioned process automation method based on digital control.

[0080] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the above-described process automation method based on digital control.

[0081] Those skilled in the art will understand that all or part of the processes in the above method embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory (FM), hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0082] If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0083] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0084] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units described above is only a logical functional division, and other division methods may be used in actual implementation. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.

[0085] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0086] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0087] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A process automation method based on digitized management and control, characterized by, The method comprises the following steps: obtaining a target workpiece model and a target workpiece type corresponding to a workpiece to be processed, and determining a target workpiece coordinate system corresponding to the target workpiece model, the target workpiece coordinate system being used to indicate a coordinate system of the workpiece to be processed; finding a reference trajectory file corresponding to the target workpiece type from a preset storage location, and converting a reference trajectory indicated by the reference trajectory file into a target trajectory corresponding to the target workpiece based on the target workpiece coordinate system when the reference trajectory file is found; when the reference trajectory file is not found, planning a target trajectory corresponding to the workpiece to be processed according to the target workpiece model and a target process corresponding to the workpiece to be processed, generating a target trajectory file based on the target workpiece coordinate system and the target trajectory, and storing the target trajectory file and the target workpiece type in the preset storage location; processing the workpiece to be processed by using the target trajectory.

2. The method of claim 1, wherein, The method comprises the following steps: based on a trigger operation of process processing, identifying position information of a plurality of workpieces on a processing production line at a current timestamp; determining a workpiece to be processed according to a plurality of position information; obtaining a target workpiece model and a target workpiece type corresponding to the workpiece to be processed from a preset storage location, wherein the preset storage location stores a plurality of types of workpiece models, processing trajectory files, workpiece types and real workpiece models constructed during processing.

3. The method of claim 1, wherein, The method comprises the following steps: extracting a plurality of feature points from the target workpiece model based on a feature point determination rule; determining the target workpiece coordinate system based on a plurality of feature points and a preset coordinate system establishment rule.

4. The method of claim 1, wherein, Before obtaining a target workpiece model and a target workpiece type corresponding to a workpiece to be processed, the method further comprises the following steps: obtaining a plurality of first shooting images of a plurality of first workpieces on a processing production line shot by a shooting device in a first shooting time period, and determining a first image type corresponding to each first shooting image, each first shooting image corresponding to a shooting angle; preprocessing a plurality of point cloud data by using a first image type corresponding to each first shooting image, respectively; performing point cloud clustering on a plurality of point cloud data to obtain different point cloud clustering results; performing different post-processing operations on a plurality of point cloud data according to different point cloud clustering results, and determining the workpiece model from the operation results.

5. The method of claim 4, wherein, The method comprises the following steps: integrating point cloud data belonging to the same workpiece indicated by the point cloud clustering result to obtain a plurality of reference workpiece models; performing workpiece type identification on each workpiece to be processed by using an identification mode corresponding to a processing process of a plurality of workpieces on the processing production line, to obtain a reference workpiece type corresponding to each workpiece; According to each of the reference workpiece model, the model integrity of each of the reference workpiece model is obtained by model integrity matching based on each of the standard workpiece model. The post-processing operation is performed according to the model integrity.

6. The method of claim 5, wherein, The post-processing operation is performed according to the model integrity, including: In the case that the model integrity is greater than or equal to a preset integrity, the reference workpiece model and the reference workpiece model corresponding to the reference workpiece model are stored in a preset storage location. In the case that the model integrity is less than the preset integrity, a plurality of second shooting images of a plurality of second workpieces on the machining production line shot by the camera device in a second shooting time period and a plurality of third shooting images of a plurality of third workpieces on the machining production line shot by the camera device in a third shooting time period are obtained, wherein the second shooting time period is a neighboring time period before the first shooting time period, and the third shooting time period is a neighboring time period after the first shooting time period. The second shooting images and the third shooting images are image-processed in the same image processing manner as the first shooting image to obtain different second point cloud clustering results, wherein the image processing includes preprocessing and point cloud clustering. The reference workpiece model with the model integrity less than the preset integrity is matched and spliced according to the second point cloud clustering results to obtain a spliced model, and the spliced model and the workpiece model corresponding to the spliced model are stored in the preset storage location.

7. The method of claim 6, wherein, The reference workpiece model with the model integrity less than the preset integrity is matched and spliced according to the second point cloud clustering results, including: The point cloud data of the second point cloud clustering results indicating the same workpiece is integrated to obtain a plurality of first reference workpiece models; According to the position information of each of the first reference workpiece model on the machining production line, a second reference workpiece model corresponding to the reference workpiece model with the model integrity less than the preset integrity is determined; The second reference workpiece model is matched and spliced with the reference workpiece model with the model integrity less than the preset integrity to obtain the spliced model.

8. A process automation system based on digitized management and control, characterized by, The system includes: An acquisition module is configured to acquire a target workpiece model and a target workpiece type corresponding to a workpiece to be processed, and determine a target workpiece coordinate system corresponding to the target workpiece model, the target workpiece coordinate system being used to indicate a coordinate system of the workpiece to be processed; A search module is configured to search for a reference trajectory file corresponding to the target workpiece type from a preset storage location, and convert a reference trajectory indicated by the reference trajectory file into a target trajectory corresponding to the target workpiece based on the target workpiece coordinate system in the case that the reference trajectory file is searched. The planning module is configured to, in a case where the reference trajectory file is not found, plan a target trajectory corresponding to the to-be-processed workpiece according to the target workpiece model and a target process corresponding to the to-be-processed workpiece, generate a target trajectory file based on the target workpiece coordinate system and the target trajectory, and store the target trajectory file and the target workpiece model in the preset storage position. The process processing module is configured to perform target process processing on the to-be-processed workpiece by using the target trajectory.

9. A computer readable storage medium, characterized in that, The computer readable storage medium stores computer instructions, and the computer instructions are used to make the computer execute the process automation method based on digital management and control according to any one of claims 1-7.

10. An electronic device, comprising: The electronic device comprises at least one processor and a memory connected with the at least one processor in communication; the memory stores a computer program executable by the at least one processor; the computer program is executed by the at least one processor to make the at least one processor execute the process automation method based on digital management and control according to any one of claims 1-7.

Images