A workpiece repairing method and system based on data analysis

Abstract

The application discloses a kind of based on data analysis's workpiece repair method and system, the method includes: step S1. repair robot is obtained point cloud dataset by visual sensor scanning, point cloud dataset and the deflection angle information of visual sensor are sent to intelligent manufacturing cloud platform;Step S2. data separation module divides point cloud dataset into background layer point cloud dataset and foreground layer point cloud dataset;Step S3. relationship construction module obtains the adjacent point dataset of each workpiece scanning point;Step S4. defect analysis module analysis obtains the position information of damaged workpiece breakage area, breakage depth and breakage area;Step S5. grade evaluation module evaluates the damage grade of corresponding damaged workpiece;Step S6. decision execution module executes corresponding workpiece repair strategy according to the damage grade of damaged workpiece.The application can reduce the work burden of operator, reduce labor cost, improve the detection and repair efficiency of damaged workpiece.

Description

TECHNICAL FIELD

[0001] The present application relates to workpiece repair, in particular to a workpiece repair method and system based on data analysis. BACKGROUND

[0002] With the development of information and communication technology, big data is no longer just a concept, but gradually integrated into all aspects of people's production and life, and society presents a trend of Internet of Things.

[0003] Today, digital technology has developed to the point where computer algorithms are becoming more complex, stable and scientific, and the way data is generated, transmitted and processed has undergone tremendous changes, deeply affecting people's way of life. The basic technology of big data is based on cloud computing to store, manage, mine and analyze data, and the core technology includes data collection, machine learning, data preprocessing, database, etc.

[0004] Manufacturing is the main pillar of the national economy. As a new manufacturing method, remanufacturing also plays an increasingly important role in manufacturing. Remanufacturing is an industry that implements high-tech repair and modification of waste products. It targets damaged or scrap parts, and based on performance failure, life assessment and other analyses, it designs for remanufacturing, uses a series of related advanced manufacturing technologies to make remanufactured products meet or exceed new products. Remanufacturing is an extension of the manufacturing industry chain, upgrading the full life cycle of equipment from an open-loop system of "research-use-scrap" to a closed-loop system of "research-use-scrap-reproduction".

[0005] With the progress of remanufacturing technology, manufacturing enterprises began to remanufacture key parts of engineering machinery and equipment approaching the end of their life, thereby extending the life of the equipment and continuing to realize its use value, to some extent reducing resource waste.

[0006] Currently, the traditional design mode does not consider the subsequent remanufacturing of equipment parts, making it difficult to determine the remanufacturing time of equipment parts, i.e. the damage state of each part during operation is difficult to determine in real time, and the time cost of manual detection of equipment parts damage is too high, with low efficiency. If the damaged parts of the equipment cannot be detected and repaired in time, it will accelerate the wear and tear of the equipment parts, affecting the production progress and quality of the product. SUMMARY

[0007] The present application aims to overcome the shortcomings of the prior art and provide a workpiece repair method and system based on data analysis, so that the repair robot can more intelligently perform workpiece repair work, reduce the work burden of the operator, reduce labor costs, and improve the detection and repair efficiency of defective workpieces.

[0008] The object of the application is achieved by the technical solutions: a workpiece repair method based on data analysis, comprising the following steps:

[0009] Step S1. The repair robot scans the defective workpiece in the target area through the visual sensor to obtain a point cloud data set, and sends the point cloud data set and the deflection angle information of the visual sensor to the intelligent manufacturing cloud platform;

[0010] Step S2. In the intelligent manufacturing cloud platform, the data separation module divides all workpiece scanning points by depth level to segment the point cloud data set into background layer point cloud data set and foreground layer point cloud data set;

[0011] Step S3. In the intelligent manufacturing cloud platform, the relationship building module removes the discrete workpiece scanning points deviating from the curvature exceeding the surface curvature threshold as noise points from the foreground layer point cloud data set to obtain a smooth point cloud data set, and then obtains the adjacent point data set of each workpiece scanning point in the three-dimensional space according to the scanning angle information of the visual sensor;

[0012] Step S4. In the intelligent manufacturing cloud platform, the defect analysis module reconstructs the model according to the adjacent point data set of each workpiece scanning point, the three-dimensional coordinates and depth value of each workpiece scanning point to obtain a three-dimensional workpiece model of the target detection defective workpiece, and compares the three-dimensional workpiece model with the standard workpiece model to obtain the position information, damage depth and damage area of the damaged area of the defective workpiece;

[0013] Step S5. In the intelligent manufacturing cloud platform, the grade evaluation module evaluates the damage degree of the defective workpiece according to the damage depth and damage area of the defective workpiece to obtain the damage grade of the corresponding defective workpiece, and the damage grade includes slight damage, moderate damage and severe damage;

[0014] Further, the product of the damage area and the damage depth of the defective workpiece is used as an evaluation index of the damage degree, and a first threshold and a second threshold (wherein the first threshold is less than the second threshold) are set for evaluating the damage grade; when the evaluation index is less than or equal to the first threshold, the damage grade is considered to be slight damage; when the evaluation index is greater than the first threshold and less than or equal to the second threshold, the damage grade is considered to be moderate damage; when the evaluation index is greater than the second threshold, the damage grade is considered to be severe damage.

[0015] Step S6. The decision execution module executes the corresponding workpiece repair strategy according to the damage grade of the defective workpiece.

[0016] A workpiece repair system based on data analysis, comprising a management terminal, a repair robot and an intelligent manufacturing cloud platform; the intelligent manufacturing cloud platform is communicatively connected with the management terminal and the repair robot;

[0017] The intelligent manufacturing cloud platform comprises a data separation module, a relationship construction module, a defect analysis module, a grade evaluation module and a decision execution module;

[0018] The data separation module is used for dividing all workpiece scanning points according to the depth information of each workpiece scanning point in the point cloud data set and the standard structure information of the defective workpiece detected by target detection, so as to divide the point cloud data set into a background layer point cloud data set and a foreground layer point cloud data set;

[0019] The relationship construction module is used for constructing a neighboring curved surface with each workpiece scanning point as a center point according to the three-dimensional coordinates of each workpiece scanning point in the foreground layer point cloud data set in a three-dimensional space, and obtaining the deviation curvature of each discrete workpiece scanning point according to the curved surface curvature of all neighboring curved surfaces, so as to remove the discrete workpiece scanning point with the deviation curvature exceeding a curved surface curvature threshold from the foreground layer point cloud data set as a noise point to obtain a smooth point cloud data set, and then obtaining the adjacent point data set of each workpiece scanning point in the three-dimensional space according to the scanning visual angle information of the visual sensor;

[0020] The defect analysis module is used for reconstructing a three-dimensional workpiece model of the defective workpiece detected by target detection according to the adjacent point data set of each workpiece scanning point, the three-dimensional coordinates and the depth value of each workpiece scanning point, and comparing the three-dimensional workpiece model with a standard workpiece model to obtain the position information, the damage depth and the damage area of the damaged area of the defective workpiece;

[0021] The grade evaluation module is used for evaluating the damage degree of the defective workpiece according to the damage depth and the damage area of the defective workpiece to obtain the damage grade of the corresponding defective workpiece, wherein the damage grade comprises slight damage, moderate damage and severe damage;

[0022] The decision execution module is used for executing a corresponding workpiece repair strategy according to the damage grade of the defective workpiece.

[0023] The present application has the advantages that the present application can detect the damage of the workpiece surface in time by comparing the three-dimensional workpiece model formed by scanning with the standard workpiece model to identify the position information, the damage depth and the damage area of the damaged area of the workpiece, evaluate the damage degree of the workpiece according to the damage area and the damage depth of the damaged area of the workpiece, and adopt a corresponding repair strategy, so that the repair robot can perform the workpiece repair work more intelligently, reduce the work burden of the workers, reduce the labor cost, and improve the detection and repair efficiency of the defective workpiece. BRIEF DESCRIPTION OF DRAWINGS

[0024] Figure 1 The present application has the advantages that the present application can detect the damage of the workpiece surface in time by comparing the three-dimensional workpiece model formed by scanning with the standard workpiece model to identify the position information, the damage depth and the damage area of the damaged area of the workpiece, evaluate the damage degree of the workpiece according to the damage area and the damage depth of the damaged area of the workpiece, and adopt a corresponding repair strategy, so that the repair robot can perform the workpiece repair work more intelligently, reduce the work burden of the workers, reduce the labor cost, and improve the detection and repair efficiency of the defective workpiece.

[0025] Figure 2 Fig. 1 is a schematic diagram of the system principle of the present application. DETAILED DESCRIPTION

[0026] The technical solutions of the present application will be described in further detail below with reference to the accompanying drawings, but the protection scope of the present application is not limited to the following description.

[0027] As shown in Fig. 1, in the embodiment of the present application, the data analysis-based workpiece repairing method of the present application comprises the following steps: Figure 1

[0028] S1, the repairing robot, in response to a workpiece detection request sent by the management terminal, scans the defective workpiece in the target area through the vision sensor of its peripheral device to obtain a point cloud data set of several geometric structure surfaces of the target detected defective workpiece, and sends the point cloud data set and the deflection angle information of the vision sensor to the intelligent manufacturing cloud platform.

[0029] Optionally, the workpiece detection request comprises a robot identifier, a target detection area and workpiece list information; the workpiece list information comprises the workpiece number, workpiece name, workpiece model, standard structure information and standard workpiece model of each workpiece to be checked.

[0030] Optionally, the robot identifier is used for uniquely identifying the robot; the deflection angle information is used for indicating the changing angle of the vision sensor in the process of scanning each geometric structure surface of the defective workpiece.

[0031] Optionally, the standard structure information is used for representing the initial structure information of the defective workpiece, i.e. the shape structure in the non-defective state; the standard workpiece model is a three-dimensional structure model of the defective workpiece in the non-defective state.

[0032] Optionally, the point cloud data set comprises several workpiece scanning points of each geometric structure surface of the defective workpiece.

[0033] Optionally, the vision sensor comprises a camera and a laser, and the laser is used for emitting a specific pattern of structured light to the surface of an object.

[0034] The specific pattern comprises a point structured light pattern, a line structured light pattern, a multi-line structured light pattern and a grid structured light pattern.

[0035] S2, the data separation module of the intelligent manufacturing cloud platform performs depth-level division on all workpiece scanning points according to the depth information of each workpiece scanning point in the point cloud data set and the standard structure information of the target detected defective workpiece to segment the point cloud data set into a background layer point cloud data set and a foreground layer point cloud data set.

[0036] ​Optionally, the depth information is used to represent a relative distance between an object surface corresponding to each workpiece scanning point in an actual scene and a laser of the visual sensor.

[0037] In particular, the data separation module performs depth-level division on all workpiece scanning points according to depth information of each workpiece scanning point in the point cloud dataset and standard structure information of the defective workpiece detected by the target detection, so as to divide the point cloud dataset into a background layer point cloud dataset and a foreground layer point cloud dataset.

[0038] The data separation module analyzes a spatial size range of the defective workpiece according to the standard structure information of the defective workpiece, and divides all workpiece scanning points in the point cloud dataset into depth regions in corresponding depth ranges according to the spatial size range and the depth information of each workpiece scanning point in the point cloud dataset.

[0039] The data separation module performs depth statistics on depth values of workpiece scanning points in each depth region according to the depth information of the workpiece scanning points, so as to take a depth region with the most workpiece scanning points as a main depth region, wherein the depth values are used to represent relative distances between corresponding workpiece scanning points and the visual sensor.

[0040] The data analysis module obtains depth values of all workpiece scanning points in adjacent depth regions smaller than the main depth region to obtain minimum depth values of the adjacent depth regions, and then divides the point cloud dataset into the background layer point cloud dataset and the foreground layer point cloud dataset according to maximum and minimum depth values of the main depth region and the adjacent depth regions, wherein the adjacent depth regions are a previous depth region and a next depth region adjacent to the main depth region in front and back.

[0041] Optionally, the spatial size range is a spatial volume size of the corresponding defective workpiece in the actual scene.

[0042] S3, the relationship construction module constructs a neighboring surface with each workpiece scanning point as a center point according to three-dimensional coordinates of each workpiece scanning point in the foreground layer point cloud dataset in a three-dimensional space, obtains a deviation curvature of each discrete workpiece scanning point according to surface curvatures of all neighboring surfaces, removes a discrete workpiece scanning point with a deviation curvature exceeding a surface curvature threshold from the foreground layer point cloud dataset as a noise point to obtain a smoothed point cloud dataset, and obtains a neighboring point dataset of each workpiece scanning point in the smoothed point cloud dataset in the three-dimensional space according to scanning angle information of the visual sensor.

[0043] Optionally, the surface curvature threshold is a numerical value preset by the system to determine whether the workpiece scanning point falls on the neighboring surface; the scanning angle information is angle information when the visual sensor scans a corresponding geometric structure surface in the defective workpiece; and the discrete workpiece scanning point is a workpiece scanning point not falling on the neighboring surface.

[0044] In particular, the relationship building module constructs the adjacent surface with each workpiece scanning point as the center point according to the three-dimensional coordinates of each workpiece scanning point in the foreground layer point cloud data set, including:

[0045] The relationship building module extracts a plurality of workpiece scanning points within a preset distance from the corresponding workpiece scanning point according to the three-dimensional coordinates of each workpiece scanning point to obtain a neighbor point set of the target analyzed workpiece scanning point.

[0046] The relationship building module constructs the adjacent surface with the target analyzed workpiece scanning point as the center point according to the three-dimensional coordinates of each workpiece scanning point in the neighbor point set and the normal vector between each workpiece scanning point.

[0047] Optionally, the relationship building module constructs the adjacent surface with each workpiece scanning point as the center point according to the three-dimensional coordinates of each workpiece scanning point in the foreground layer point cloud data set, further including:

[0048] The data separation module obtains the translation amount and the angle offset amount of the visual sensor in the scanning process according to the deflection angle information of the visual sensor, and analyzes the roll angle, the pitch angle and the yaw angle of the visual sensor under different scanning angle information according to the translation amount and the angle offset amount of the visual sensor in the scanning process.

[0049] The data analysis module constructs the rotation matrix and the translation transformation vector of the point cloud data set when performing spatial conversion according to the roll angle, the pitch angle and the yaw angle of the visual sensor, and normalizes the workpiece scanning points of each geometric structure surface of the defective workpiece to the world coordinate system to obtain the three-dimensional coordinates of each workpiece scanning point in the three-dimensional space according to the rotation matrix and the translation transformation vector.

[0050] Optionally, the neighbor point set is composed of a plurality of workpiece scanning points within a preset distance from the corresponding workpiece scanning point, and the preset distance is set by the system according to the size capable of reflecting the local minimum details of the defective workpiece.

[0051] In particular, the relationship building module obtains the adjacent point data set of each workpiece scanning point in the three-dimensional space in the smoothed point cloud data set according to the scanning angle information of the visual sensor, including:

[0052] The relationship building module projects the workpiece scanning points belonging to the same geometric structure surface of the defective workpiece in the smoothed point cloud data set onto the corresponding two-dimensional view plane to obtain a plurality of workpiece two-dimensional mapping points according to the scanning angle information of the visual sensor.

[0053] The relationship building module establishes a corresponding plane topology structure for each workpiece two-dimensional mapping point according to the distance vectors between all workpiece two-dimensional mapping points on the two-dimensional visual plane to obtain the connection relationship between each workpiece two-dimensional mapping point and adjacent two-dimensional mapping points, and then maps the plane topology structure of each workpiece two-dimensional mapping point from the two-dimensional visual plane to the three-dimensional space to obtain the adjacent point data set of each workpiece scanning point according to the connection relationship between each workpiece two-dimensional mapping point and adjacent two-dimensional mapping points.

[0054] Optionally, the adjacent point data set includes all workpiece scanning points directly connected in various directions corresponding to the workpiece scanning point.

[0055] S4, the defect analysis module reconstructs a model according to the adjacent point data set of each workpiece scanning point, the three-dimensional coordinates and the depth value of each workpiece scanning point to obtain a three-dimensional workpiece model of the target detected defective workpiece, and compares the three-dimensional workpiece model with a standard workpiece model to obtain the position information, the damage depth and the damage area of the damaged area of the defective workpiece.

[0056] Specifically, the defect analysis module compares the three-dimensional workpiece model with the standard workpiece model to obtain the position information, the damage depth and the damage area of the damaged area of the defective workpiece includes:

[0057] The defect analysis module extracts the surface structure feature vector of each geometric structure surface of the three-dimensional workpiece model and the standard structure feature vector of each geometric structure surface of the standard workpiece model, and obtains the position information of the damaged area of the three-dimensional workpiece model according to the distance between each surface structure feature vector and the corresponding standard structure feature vector, and then obtains the damage depth and the damage area of the damaged area according to the position information of the damaged area of the three-dimensional workpiece model.

[0058] S5, the grade evaluation module evaluates the damage degree of the defective workpiece according to the damage depth and the damage area of the defective workpiece to obtain the damage grade of the corresponding defective workpiece, and the damage grade includes slight damage, moderate damage and severe damage.

[0059] S6, the decision execution module executes the corresponding workpiece repair strategy according to the damage grade of the defective workpiece.

[0060] Specifically, the decision execution module executes the corresponding workpiece repair strategy according to the damage grade of the defective workpiece includes:

[0061] When it is determined that the damage grade of the defective workpiece is slight damage, the decision execution module generates a workpiece repair instruction according to the workpiece type of the defective workpiece, the position information of the damaged area and the robot identifier, and sends it to the corresponding repair robot;

[0062] The decision execution module generates an artificial maintenance instruction according to the workpiece type, the position information of the damaged area and the equipment identifier of the damaged workpiece when determining that the damage level of the damaged workpiece is moderate damage, and sends the artificial maintenance instruction to the corresponding management terminal.

[0063] The decision execution module generates a workpiece replacement instruction according to the workpiece type and the robot identifier of the damaged workpiece when determining that the damage level of the damaged workpiece is slight damage, and sends the workpiece replacement instruction to the corresponding repair robot.

[0064] The present application can detect the damage of the workpiece surface in time by quickly scanning and measuring each surface of the workpiece, comparing the three-dimensional workpiece model formed by the scanning with the standard workpiece model, identifying the position information, damage depth and damage area of the damaged area of the workpiece, evaluating the damage degree of the damaged area of the workpiece according to the damage area and damage depth of the damaged area of the workpiece, and adopting the corresponding repair strategy, so that the repair robot can more intelligently perform the workpiece repair work, reduce the work burden of the workers, reduce the labor cost, and improve the detection and repair efficiency of the damaged workpiece.

[0065] Referring to Figure 2 In one embodiment, the workpiece repair system for performing the method of the present application includes a management terminal, a repair robot and an intelligent manufacturing cloud platform. The intelligent manufacturing cloud platform is communicatively connected between the management terminal and the repair robot. The management terminal is a device used by the operator and has computing, storage and communication functions, including a smartphone, a desktop computer and a notebook computer.

[0066] The intelligent manufacturing cloud platform includes a data separation module, a relationship construction module, a defect analysis module, a level evaluation module and a decision execution module.

[0067] The data separation module is used to divide all workpiece scanning points according to the depth information of each workpiece scanning point in the point cloud data set and the standard structure information of the damaged workpiece detected by the target to divide the point cloud data set into a background layer point cloud data set and a foreground layer point cloud data set.

[0068] The relationship construction module is used to construct a neighboring surface with each workpiece scanning point as a center point according to the three-dimensional coordinates of each workpiece scanning point in the foreground layer point cloud data set in the three-dimensional space, and obtain the deviation curvature of each discrete workpiece scanning point according to the surface curvature of all neighboring surfaces, so that the discrete workpiece scanning points with deviation curvature exceeding the surface curvature threshold are removed from the foreground layer point cloud data set as noise points to obtain a smooth point cloud data set, and then obtain the adjacent point data set of each workpiece scanning point in the three-dimensional space in the smooth point cloud data set according to the scanning viewing angle information of the visual sensor.

[0069] The defect analysis module is configured to reconstruct a three-dimensional workpiece model of the target detected defective workpiece according to the neighboring point data set of each workpiece scanning point, the three-dimensional coordinates and the depth value of each workpiece scanning point, and compare the three-dimensional workpiece model with a standard workpiece model to obtain the position information, the damage depth and the damage area of the damaged area of the defective workpiece.

[0070] The grade evaluation module is configured to evaluate the damage degree of the defective workpiece according to the damage depth and the damage area of the defective workpiece to obtain the damage grade of the corresponding defective workpiece, wherein the damage grade includes light damage, moderate damage and severe damage.

[0071] The decision execution module is configured to execute a corresponding workpiece repair strategy according to the damage grade of the defective workpiece.

[0072] The above description shows and describes one preferred embodiment of the present application, but as mentioned above, it should be understood that the present application is not limited to the form disclosed herein, should not be considered as excluding other embodiments, and can be used in various other combinations, modifications and environments, and can be modified within the scope of the inventive concept described herein by the above teaching or related art or knowledge. Any modification and change made by those skilled in the art without departing from the spirit and scope of the present application shall be within the protection scope of the claims of the present application.

Claims

1. A workpiece repair method based on data analysis, characterized in that: Includes the following steps: Step S1. The repair robot scans the damaged workpiece in the target area using a vision sensor to obtain a point cloud dataset, and sends the point cloud dataset and the deflection angle information of the vision sensor to the intelligent manufacturing cloud platform. The point cloud dataset includes several workpiece scanning points on each geometric surface of the damaged workpiece. The deflection angle information is used to indicate the change in angle of the vision sensor during the scanning of various geometric surfaces of the defective workpiece. Step S2. In the intelligent manufacturing cloud platform, the data separation module performs depth-level division on all workpiece scanning points to divide the point cloud dataset into a background layer point cloud dataset and a foreground layer point cloud dataset. Step S3. In the intelligent manufacturing cloud platform, the relationship building module removes discrete workpiece scanning points whose deviation curvature exceeds the surface curvature threshold as noise points from the foreground layer point cloud dataset to obtain a smooth point cloud dataset. Then, based on the scanning perspective information of the vision sensor, it obtains the adjacent point dataset of each workpiece scanning point in the smooth point cloud dataset in three-dimensional space. Step S3 includes: In the intelligent manufacturing cloud platform, the relationship building module constructs a neighboring surface centered on each workpiece scanning point based on the three-dimensional coordinates of each workpiece scanning point in the three-dimensional space in the foreground layer point cloud dataset. The relationship construction module obtains the deviation curvature of each discrete workpiece scanning point based on the curvature of all neighboring surfaces. Discrete workpiece scanning points with deviation curvature exceeding the surface curvature threshold are treated as noise points and removed from the foreground layer point cloud dataset to obtain a smooth point cloud dataset. The surface curvature threshold is a value preset by the system to determine whether a workpiece scanning point falls on a neighboring surface. The discrete workpiece scanning point is the workpiece scanning point that does not fall on a neighboring surface. The relationship building module obtains the adjacent point dataset in three-dimensional space for each workpiece scanning point in the smooth point cloud dataset based on the scanning perspective information of the vision sensor; the scanning perspective information is the angle information when the vision sensor scans the corresponding geometric surface in the defective workpiece; Step S4. In the intelligent manufacturing cloud platform, the defect analysis module reconstructs the model based on the adjacent point dataset of each workpiece scanning point, the three-dimensional coordinates and depth values ​​of each workpiece scanning point to obtain the three-dimensional workpiece model of the target detected defective workpiece, and compares the three-dimensional workpiece model with the standard workpiece model to obtain the location information, damage depth and damage area of ​​the damaged area of ​​the defective workpiece. Step S5. In the intelligent manufacturing cloud platform, the level assessment module assesses the degree of damage of the missing workpiece based on the depth and area of ​​the damage to obtain the corresponding damage level of the missing workpiece. The damage level includes minor damage, moderate damage and severe damage. Step S6. The decision execution module executes the corresponding workpiece repair strategy according to the damage level of the defective workpiece.

2. The workpiece repair method based on data analysis according to claim 1, characterized in that: Step S1 includes: The repair robot responds to the workpiece inspection request sent by the management terminal, scans the defective workpiece in the target area through its peripheral vision sensor, obtains a point cloud dataset of several geometric structural surfaces of the defective workpiece, and sends the point cloud dataset and the deflection angle information of the vision sensor to the intelligent manufacturing cloud platform. The workpiece inspection request includes a robot identifier, a target inspection area, and workpiece list information; the workpiece list information includes the workpiece number, workpiece name, workpiece model, standard structure information, and standard workpiece model for each workpiece to be inspected.

3. The workpiece repair method based on data analysis according to claim 2, characterized in that: The robot identifier is used to uniquely identify the robot; The standard structural information is used to characterize the initial structural information of the damaged workpiece, that is, the shape structure in the undamaged state; the standard workpiece model is the three-dimensional structural model of the damaged workpiece in the undamaged state. The visual sensor includes a camera and a laser, the laser being used to emit structured light of a specific pattern onto the surface of an object; the specific patterns include: point structured light pattern, line structured light pattern, multi-line structured light pattern, and grid structured light pattern.

4. The workpiece repair method based on data analysis according to claim 3, characterized in that: Step S2 includes: The data separation module analyzes the standard structural information of the damaged workpiece to obtain the spatial size range of the damaged workpiece, and divides all workpiece scanning points in the point cloud data into depth regions within the corresponding depth range based on the spatial size range and the depth information of each workpiece scanning point in the point cloud data; the spatial size range is the spatial volume occupied by the corresponding damaged workpiece in the actual scene; the depth information is used to characterize the relative distance between the object surface corresponding to each workpiece scanning point in the actual scene and the laser of the vision sensor. The data separation module performs depth statistics on the depth values ​​of the workpiece scanning points in each depth region based on the depth information of the workpiece scanning points, and takes the depth region containing the most workpiece scanning points as the main depth region. The depth value is used to characterize the relative distance between the corresponding workpiece scanning point and the vision sensor. The data analysis module obtains the depth values ​​of all workpiece scanning points in the neighboring depth regions whose depth range is smaller than that of the main depth region to obtain the minimum depth value of the neighboring depth region. Then, based on the maximum depth value of the main depth region and the minimum depth value of the neighboring depth region, the point cloud data is divided into a background layer point cloud dataset and a foreground layer point cloud dataset. The neighboring depth region is the previous depth region and the next depth region that are connected to the depth range of the corresponding main depth region.

5. The workpiece repair method based on data analysis according to claim 4, characterized in that: The relationship construction module constructs a neighboring surface centered on each workpiece scanning point based on the three-dimensional coordinates of each workpiece scanning point in the three-dimensional space of the foreground layer point cloud dataset, including: The relationship building module extracts several workpiece scanning points whose spatial distance from the corresponding workpiece scanning point is within a preset distance based on the three-dimensional coordinates of each workpiece scanning point to obtain the neighboring point set of the target workpiece scanning point; the neighboring point set consists of several workpiece scanning points whose spatial distance from the corresponding workpiece scanning point is within a preset distance, and the preset distance is preset by the system based on the size that can reflect the smallest local details of the defective workpiece; The relation building module constructs a neighboring surface centered on the workpiece scanning point of the target analysis, based on the three-dimensional coordinates of each workpiece scanning point in the neighboring point set and the normal vector between each workpiece scanning point.

6. The workpiece repair method based on data analysis according to claim 5, characterized in that: The relationship building module obtains the adjacent point dataset in three-dimensional space for each workpiece scanning point in the smooth point cloud dataset based on the scanning perspective information of the vision sensor. The dataset includes: The relationship building module projects the workpiece scanning points belonging to the same geometric structure surface of the defective workpiece in the smooth point cloud dataset onto the corresponding two-dimensional view plane based on the scanning perspective information of the vision sensor to obtain several two-dimensional mapping points of the workpiece. The relationship construction module establishes a corresponding planar topology for each workpiece 2D mapping point based on the distance vector between all workpiece 2D mapping points on the 2D view plane to obtain the connection relationship between each workpiece 2D mapping point and its adjacent 2D mapping points. Then, the planar topology of each workpiece 2D mapping point is mapped from the 2D view plane to the 3D space to obtain the adjacency point dataset of each workpiece scanning point based on the connection relationship between each workpiece 2D mapping point and its adjacent 2D mapping points. The adjacency point dataset contains all workpiece scanning points that are directly connected to the corresponding workpiece scanning point in each direction.

7. The workpiece repair method based on data analysis according to claim 6, characterized in that: The step of comparing the three-dimensional workpiece model with the standard workpiece model to obtain the location information, depth of damage, and area of ​​the damaged area of ​​the defective workpiece includes: The defect analysis module extracts the surface structure feature vectors of each geometric surface of the 3D workpiece model and the standard structure feature vectors of each geometric surface of the standard workpiece model. Based on the distance between each surface structure feature vector and the corresponding standard structure feature vector, the module obtains the location information of the damaged area of ​​the 3D workpiece model. Then, based on the location information of the damaged area of ​​the 3D workpiece model, the module obtains the damage depth and damage area of ​​the damaged area.

8. The workpiece repair method based on data analysis according to claim 7, characterized in that: Step S6 includes: When the decision execution module determines that the damage level of the missing workpiece is minor, it generates a workpiece repair instruction based on the workpiece type, the location information of the damaged area, and the robot identifier, and sends it to the corresponding repair robot. When the decision execution module determines that the damage level of the missing workpiece is moderate, it generates a manual maintenance instruction based on the workpiece type, the location information of the damaged area, and the equipment identifier, and sends it to the corresponding management terminal. When the decision execution module determines that the damage level of the defective workpiece is minor, it generates a workpiece replacement instruction based on the workpiece type and robot identifier, and sends it to the corresponding repair robot.

9. A workpiece repair system based on data analysis, wherein the workpiece is repaired using the method described in any one of claims 1 to 8, characterized in that: It includes a management terminal, a repair robot, and a smart manufacturing cloud platform; the smart manufacturing cloud platform has communication connections with both the management terminal and the repair robot. The intelligent manufacturing cloud platform includes a data separation module, a relationship building module, a defect analysis module, a level assessment module, and a decision execution module; The data separation module is used to perform depth-level division of all workpiece scanning points according to the depth information of each workpiece scanning point in the point cloud dataset and the standard structural information of the defective workpiece detected by the target, so as to divide the point cloud dataset into a background layer point cloud dataset and a foreground layer point cloud dataset. The relationship construction module is used to construct a neighboring surface centered on each workpiece scanning point based on the three-dimensional coordinates of each workpiece scanning point in the three-dimensional space in the foreground layer point cloud dataset, and to obtain the deviation curvature of each discrete workpiece scanning point based on the curvature of all neighboring surfaces. Discrete workpiece scanning points with deviation curvature exceeding the curvature threshold are treated as noise points and removed from the foreground layer point cloud dataset to obtain a smooth point cloud dataset. Then, the adjacent point dataset of each workpiece scanning point in the three-dimensional space is obtained based on the scanning perspective information of the visual sensor. The defect analysis module is used to reconstruct the model based on the adjacent point dataset of each workpiece scanning point, the three-dimensional coordinates and depth values ​​of each workpiece scanning point to obtain the three-dimensional workpiece model of the target detected defective workpiece, and compare the three-dimensional workpiece model with the standard workpiece model to obtain the location information, damage depth and damage area of ​​the damaged area of ​​the defective workpiece. The grade assessment module is used to assess the degree of damage to the missing workpiece based on the depth and area of ​​the damage to obtain the corresponding damage grade of the missing workpiece. The damage grades include minor damage, moderate damage, and severe damage. The decision execution module is used to execute corresponding workpiece repair strategies based on the damage level of the defective workpiece.

Images