Workpiece identification and processing control system applied to intelligent factory

Abstract

The invention relates to a workpiece identification and processing control system applied to an intelligent factory, and relates to the technical field of intelligent production, and the workpiece identification and processing control system comprises a shooting identification module, a comparison identification module, an abnormal information processing module, a control module and a system display platform. According to the application, the initial information of the products is compared with the information obtained by shooting, whether the products are stacked or not is judged, the product state is further detected by utilizing the comparison and identification module and the abnormal information processing module, and the control module is controlled by utilizing the processing information obtained by the abnormal information processing module, so that the product state is detected. Therefore, the state of the product is further confirmed, and the product is adjusted through the control module, so that the stacked product is conveniently separated and detected again, and the problem that the data volume in an abnormal database is increased due to abnormal product detection abnormity caused by abnormal states such as stacking is avoided.

Description

Technical Field

[0001] The present invention relates to the field of intelligent production technology, and in particular to a control system for workpiece identification and processing applied to an intelligent factory. Background Art

[0002] The workpiece is identified through the camera, and the corresponding processing program is automatically loaded and the CNC machine tool is controlled to complete the processing. It can be completed in conjunction with a robot, with a higher degree of automation and a faster recognition speed. Compared with the traditional method of manually scanning the code and loading the processing program, it further saves labor costs, reduces unnecessary errors, improves the intelligence of the smart factory, and improves production efficiency.

[0003] In the patent document with application number: 201910040765.0, an intelligent camera recognition system is disclosed, and specifically a method for automatically extracting data information transmitted by a camera through an identification module is disclosed, so that abnormal conditions can be intelligently judged to ensure production efficiency.

[0004] In the above technical solution, the shooting accuracy of the camera can determine the recognition accuracy of the product. When multiple products are stacked together, if the camera cannot shoot clearly, it will affect the recognition of the product, and the product in this state will cause a burden on the system. The system cannot clearly identify the product in this state. When it is added to the exception library, the data in the exception library increases and is invalid, causing the system to appear stuck in subsequent recognition. Summary of the invention

[0005] The purpose of the present invention is to provide a control system for workpiece identification and processing applied to intelligent factories.

[0006] The technical problem solved by the present invention is to solve the problem in the prior art that when multiple products overlap, accurate detection cannot be performed, resulting in an increase in abnormal library data.

[0007] The present invention can be implemented through the following technical solutions: a control system for workpiece identification and processing applied to smart factories, including a shooting and identification module, a comparison and identification module, an abnormal information processing module, a control module and a system display platform. The shooting and identification module is used to obtain the initial information and shooting appearance information of the product, and send the information to the comparison and identification module for processing. The abnormal information processing module obtains the diagnostic information in the comparison and identification module, and controls the production line of the product through the control module. The system display platform is used to monitor and display the product identification and processing process.

[0008] A further technical improvement of the present invention is that the shooting and identification module includes a code scanning device and a camera. The code scanning device is installed on the side of the camera. The code scanning device pre-scans the workpiece to obtain the production batch and grade of the workpiece, and sends the initial data of the workpiece to the system display platform for storage. The camera shoots the workpiece, and the camera performs image recognition to obtain the actual parameters of the workpiece, and sends the actual parameters of the workpiece to the system display platform for storage and display.

[0009] A further technical improvement of the present invention is that the shooting and recognition module also includes a shooting image acquisition unit, an image preliminary analysis unit and an appearance data preliminary comparison unit. The shooting image acquisition unit is used to acquire the workpiece image taken by the camera, pre-process the image, send the pre-processed image to the image preliminary analysis unit for analysis, retrieve the original parameters of the workpiece in the system display platform, compare the original parameters of the workpiece with the workpiece data in the shooting image acquisition unit, and determine the integrity of the workpiece.

[0010] A further technical improvement of the present invention is that: the shooting image acquisition unit acquires the workpiece image taken by the camera, extracts features of the workpiece image, and annotates the workpiece image to obtain an initial annotated image; the image preliminary analysis unit acquires data from the shooting image acquisition unit, and integrates the image according to the workpiece image and the initial annotated image.

[0011] The further technical improvement of the present invention is that the appearance data preliminary comparison unit is used to obtain the workpiece image, the preliminary annotated image and the workpiece initial data, and to perform a separate comparison based on the data annotation Ban on the workpiece image and the data annotation Bbn on the preliminary annotated image to obtain the workpiece initial data Bcn, and according to the formula The image processing accuracy Cn is obtained. In this formula, n is a positive integer greater than or equal to 1, which is used to represent the changes of each data after image processing. Then, according to the formula The processing accuracy of the workpiece image is obtained, and then whether the workpiece image data can be used in the subsequent detection process is determined based on whether the Δ value is within the standard range. If so, the data is corrected to see if it is abnormal; if not, the image processing algorithm in the image preliminary analysis unit needs to be re-corrected.

[0012] A further technical improvement of the present invention is: according to the formula The deformation value An of the workpiece is obtained, and the value range of An is detected, where n is a positive integer greater than or equal to 1, to determine whether the workpiece has a large deformation. If so, it is determined that the workpiece is abnormal and the data is sent to the comparison and recognition module for further processing. If not, the workpiece is directly transferred to the next processing program.

[0013] A further technical improvement of the present invention is that the comparison and identification module includes an abnormal image processing unit, an abnormal analysis unit and a diagnosis result determination unit. The abnormal image analysis unit is used to obtain a workpiece image and a data annotation Ban on the workpiece image, and simultaneously obtain the workpiece initial data Bcn. The abnormal image processing unit is used to perform preliminary processing on the above data and image, and then the abnormal analysis unit is used to analyze the data. Finally, the diagnosis result determination unit is used to determine the abnormal analysis diagnosis in the abnormal analysis unit, and finally the result is processed in the abnormal information processing module.

[0014] A further technical improvement of the present invention is that the abnormal information processing module includes a response adjustment unit and a direct classification unit. The response adjustment unit is used to obtain the workpieces that can be adjusted in the result diagnosis unit, and after intelligently adjusting the workpieces, re-introducing them into the device for re-detection. The direct classification unit is used to directly classify the workpieces according to the diagnosis results in the result diagnosis unit, and place the classified workpieces separately.

[0015] Compared with the prior art, the present invention has the following beneficial effects:

[0016] 1. The present application uses a shooting and recognition module to directly shoot the appearance of the product. At the same time, the shooting and recognition module can also be used to obtain the initial information of the product. The initial information of the product is compared with the information obtained by shooting to determine whether the product is stacked. At the same time, the comparison and recognition module and the abnormal information processing module are used to further detect the product status. The present application controls the control module by using the processing information obtained by the abnormal information processing module, so as to further confirm the status of the product, and adjust the product through the control module, so as to separate the stacked products and re-test them, so as to avoid product detection abnormalities caused by abnormal conditions such as stacking, which leads to an increase in the amount of data in the abnormal database, and can realize automatic processing of the production line to ensure the stability of the production line.

[0017] 2. The present application can obtain the workpiece image, preliminary annotated image and initial data of the workpiece through the preliminary appearance data comparison unit, so as to obtain the image processing accuracy Cn and the workpiece image processing accuracy Δ, and then judge whether the workpiece image data can be used in the subsequent detection process according to whether the size of the Δ value is within the standard range. If so, the data is corrected to see if it is abnormal; if not, the image processing algorithm in the image preliminary analysis unit needs to be re-corrected. In this process, automatic detection of the image can be realized to ensure accurate automatic comparison and detection of the product. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0019] Figure 1 It is a system principle block diagram of the present invention. DETAILED DESCRIPTION

[0020] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation mode, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0021] See also Figure 1 As shown, a control system for workpiece identification and processing applied to a smart factory is applied to a CNC machine tool. An industrial computer controls a visual camera to take photos of the workpiece on the CNC machine tool for identification. The industrial computer extracts feature values ​​from the photos, and then matches the feature values ​​with the database information in the server. According to the matching results, the corresponding processing program is imported into the CNC system of the CNC machine tool, and then the industrial computer controls the CNC machine tool to start the processing program.

[0022] A control system for workpiece identification and processing applied to smart factories comprises a shooting and identification module, a comparison and identification module, an abnormal information processing module, a control module and a system display platform, wherein the shooting and identification module is installed on a numerically controlled machine tool, and the shooting and identification module is used to directly shoot the product and perform preliminary identification. If the identification fails, the result obtained by the shooting and identification module is packaged and sent to the comparison and identification module for further fine identification, and the abnormal result of the identification is sent to the abnormal information processing module for abnormal processing, and the control module is started by the response method obtained by the abnormal information processing module, and the mechanical equipment on the numerically controlled machine tool is controlled by the control module to respond; the above processes are all displayed on the system display platform.

[0023] As a further embodiment of the present application, the shooting and identification module uses a camera for direct shooting, wherein the camera is arranged on a CNC machine tool, wherein the shooting and identification module includes a code scanning device, which is installed on the side of the camera, and the code scanning device pre-scans the workpiece to determine the production batch and grade of the workpiece, and then obtains the initial data of the workpiece, and uploads the initial data to the system display platform of the system for storage;

[0024] The shooting and identifying module also includes a camera, which is used to directly shoot the workpiece, obtain the actual parameters of the workpiece through the camera, and send the parameters to the system display platform for storage and display.

[0025] Furthermore, the shooting and recognition module includes a shooting image acquisition unit, an image preliminary analysis unit and an appearance data preliminary comparison unit, that is, the shooting image acquisition unit is used to acquire the workpiece image captured by the camera and pre-process the workpiece image, and then send the workpiece image to the image preliminary analysis unit for analysis, and finally obtain the initial data of the workpiece through the system display platform, and compare the initial data of the workpiece through the appearance data preliminary comparison unit, so as to determine the integrity of the workpiece.

[0026] Specifically, the image acquisition unit acquires the workpiece image captured by the camera, extracts features from the image, acquires feature points, integrates the feature points, and annotates the workpiece image with standard parameters of the workpiece and error values ​​of the workpiece compared to the standard parameters, and classifies the workpiece according to the annotation type to obtain several groups of basic data about the workpiece, thereby obtaining an initial annotated image;

[0027] Further, the image preliminary analysis unit obtains the data of the shooting image acquisition unit and performs a detailed analysis on the image, that is, firstly obtains the workpiece image and the initial annotated image, and further processes the workpiece image and the initial annotated image. The specific processing process is as follows:

[0028] First, the workpiece image is placed in the system processing platform, and then the preliminary annotation image is overlapped on the workpiece image, and the information on the preliminary annotation image is hidden. This information is initial information and has a certain degree of accuracy. When further processing the image, if it is directly processed, it is easy to increase the error of the information, so it is necessary to save the information and hide the information at the same time, so as to facilitate the image correction of the preliminary annotation image and the workpiece image at the same time, so as to ensure the accuracy of the image. That is, the pixel points of both the preliminary annotation image and the workpiece image are determined, and the pixel points in the preliminary annotation image and the workpiece image are matched and determined, and then the pixel points on the workpiece image are extracted, the workpiece image is preprocessed, and the pixel edge is compensated to obtain a more accurate workpiece image, and the processed workpiece image and the preliminary annotation image are matched, and the workpiece image after processing is annotated, so as to obtain the annotated workpiece image and the processed preliminary annotation image that is initially annotated.

[0029] When the appearance data preliminary comparison unit is working, it first obtains the annotated workpiece image and the processed preliminary annotated image, and then performs a unified comparison process on the preliminary annotated image and the workpiece image, as well as the initial workpiece data in the system display platform, to determine the integrity of the workpiece and the accuracy of image processing;

[0030] Specifically, the appearance data preliminary comparison unit obtains the workpiece image, the preliminary annotated image and the workpiece initial data, performs a separate comparison based on the data annotation Ban on the workpiece image and the data annotation Bbn on the preliminary annotated image, and obtains the workpiece initial data Bcn, according to the formula The image processing accuracy Cn is obtained. In this formula, n is a positive integer greater than or equal to 1, which is used to represent the changes of each data after image processing. Then, according to the formula The processing accuracy of the workpiece image is obtained, and then whether the workpiece image data can be used in the subsequent detection process is determined according to whether the size of the Δ value is within the standard range. If so, the data is corrected to see if it is abnormal; if not, the image processing algorithm in the image preliminary analysis unit needs to be re-corrected to ensure the accuracy of the workpiece data and facilitate the determination and capture of the workpiece status.

[0031] If in this application, the values ​​of the data annotation Ban on the workpiece image and the data annotation Bbn on the preliminary annotation image are abnormal, the values ​​of the data annotation Ban on the workpiece image and the data annotation Bbn on the preliminary annotation image are compared with the initial data Bcn of the workpiece, that is, according to the formula The deformation value An of the workpiece is obtained, that is, the value range of An is detected, where n is a positive integer greater than or equal to 1, to determine whether the workpiece has a large deformation. If so, it is determined that the workpiece is abnormal and the data is sent to the comparison and recognition module for further processing. If not, the workpiece is directly transferred to the next processing program.

[0032] As a further embodiment of the present application, the comparison and identification module is used to perform further identification processing on the workpiece when the deformation value of the workpiece is large, rather than simply sending the abnormal situation of the workpiece to the fault library for direct comparison.

[0033] Specifically, the comparison and identification module includes an abnormal image processing unit, an abnormal analysis unit and a diagnosis result determination unit, wherein the abnormal image analysis unit is used to obtain the workpiece image, and the data annotation Ban on the workpiece image, and at the same time obtain the workpiece initial data Bcn, and use the abnormal image processing unit to perform preliminary processing on the above data and image, and then use the abnormal analysis unit to analyze the data, and finally use the diagnosis result determination unit to determine the abnormal analysis diagnosis in the abnormal analysis unit, and finally process the result in the abnormal information processing module.

[0034] Specifically, the abnormal image processing unit first obtains the workpiece image and processes the workpiece image again. The processing process is as follows: the workpiece image is placed on the system display platform, the abnormal image processing unit adjusts the brightness of the workpiece image, and obtains the color distribution range under different brightness, depicts the position and shape of the workpiece according to different color distributions, and then simulates the placement of the workpiece to simulate whether the workpiece is overlapped or damaged, and after the simulation, the simulation graphic results are sent to the abnormal analysis unit for abnormal analysis;

[0035] In the above process, in order to simulate the placement of the workpiece, the simulation method adopted in the present application is as follows: first, the color distribution range under different brightness on the workpiece image is obtained, and then the lines of the color distribution range are outlined to obtain the line drawing of the workpiece, the initial data of the workpiece is obtained, and the three-dimensional model of the workpiece is obtained, and then the views of the workpiece at various angles are obtained, and the views of various angles are compared with the line drawing of the workpiece to determine whether there are similar angle diagrams. If so, the workpiece is simulated and shaped, and the parameters on the workpiece are marked on the three-dimensional model, and the values ​​of certain parts of the workpiece are changed, so that the workpiece can be intuitively judged. The areas and deformation conditions on the surface are determined, and the simulated three-dimensional image is then sent to the abnormality analysis unit for further abnormality analysis; if there is no similar angle image, it is necessary to simulate and analyze the photographed line image of the workpiece, obtain the initial data of the workpiece, obtain the three-dimensional model of the workpiece, and simulate the three-dimensional models of the two workpieces, simulate their overlapping positions, and match them according to the various angle views and photographed line images of the overlapping positions to determine whether there are similar three-dimensional models. If so, the similar model is sent to the abnormality analysis unit for analysis. If not, the photographed line image of the workpiece and the product code of the workpiece are sent to the abnormality analysis unit for analysis.

[0036] When the abnormal analysis unit is in use, it first obtains data from the abnormal image processing unit, classifies the data from the abnormal image processing unit, then further processes the data from the abnormal image processing unit, and after processing, sends the cause analysis to the diagnosis result determination unit, which is determined by the diagnosis result determination unit.

[0037] Specifically, when the abnormality analysis unit obtains a similar simulated three-dimensional image, it further analyzes the simulated three-dimensional image, that is, it further analyzes the deformation area and deformation conditions marked in the simulated three-dimensional image, that is, it simulates the deformation area and deformation conditions marked in the simulated three-dimensional image, determines the external force conditions that cause the deformation, and determines the shape of the external force according to the external force conditions, whether it is the deformation caused by scratching or collision, so as to classify the cause of the deformation, and send the cause of the deformation to the result diagnosis unit for confirmation;

[0038] When the abnormal image processing unit determines that the two workpieces overlap, the abnormal analysis unit obtains the photographed line drawing and the simulated three-dimensional image, wherein a view angle image in the simulated three-dimensional image similar to the photographed line drawing is obtained, that is, the view angle image is compared with the photographed line drawing to determine the difference between them, and the difference is marked in the simulated three-dimensional image, and the difference is simulated to determine whether there is deformation on the workpiece. If there is, the area where the deformation may occur is marked on the side of the simulated three-dimensional image, and the information is sent to the result diagnosis unit for confirmation;

[0039] When the abnormal image processing unit is unable to judge the state of the workpiece, the photographed line drawing of the workpiece is directly sent to the result diagnosis unit for diagnosis.

[0040] Furthermore, when the result diagnosis unit diagnoses the result of deformation of a single simulated three-dimensional image, the result is directly stored in the initial information of the workpiece, and the initial information of the workpiece and the current abnormal information are classified and stored, and the result diagnosis unit sends it to the abnormal information processing module for abnormal information processing;

[0041] When the result diagnosis unit diagnoses the simulated three-dimensional images of the two overlapping workpieces, it determines whether the two overlapping workpieces are deformed. If so, it records it in the initial information of the workpieces, and stores the initial information of the workpieces and the current abnormal information in a classified manner. The abnormal information records whether the workpieces are fitted and whether deformation occurs between the workpieces. The result diagnosis unit sends the information to the abnormal information processing module for abnormal information processing.

[0042] When the result diagnosis unit diagnoses an abnormal workpiece with no matching information, the initial information and current abnormal information of the workpiece are classified and stored, and the abnormal classification information is directly marked on the workpiece. Subsequently, the workpiece is directly marked under the action of the result diagnosis unit.

[0043] As a further embodiment of the present application, the abnormal information processing module includes a response adjustment unit and a direct classification unit, wherein the response adjustment unit is used to obtain the workpieces that can be adjusted in the result diagnosis unit, and after intelligently adjusting the workpieces, re-introduce them into the device for re-detection, while the direct classification unit is used to directly classify the workpieces according to the diagnosis results in the result diagnosis unit, and place the classified workpieces separately to facilitate the tracing of abnormal workpieces and the elimination of abnormal workpieces.

[0044] Specifically, the response adjustment unit is used to send a control signal to make the control module work, that is, to use the control module to adjust the workpiece. That is, when there is no deformation of the workpiece and only a stacking state is produced, the control module is used to control the mechanical equipment to separate the stacked workpieces, and the separated workpieces are re-tested by the equipment. During the detection process, the original data on the stacking state is encapsulated, and the separated workpieces are re-tested individually, and the detection results are sent to the system display platform for re-processing.

[0045] In the present application, the control module is implemented using a separation device, wherein the separation device uses a suction cup to adsorb and clamp the two workpieces, and then uses a separation power mechanism to realize the separation function of the workpieces so that the two workpieces are separated, so that the electrostatic adsorption force between the workpieces can be gradually overcome, and then the two workpieces are separated respectively, and the two workpieces are placed back to the initial point of the system for re-inspection.

[0046] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A control system for workpiece identification and processing applied to smart factories, characterized by: It includes a shooting and recognition module, a comparison and recognition module, an abnormal information processing module, a control module and a system display platform. The shooting and recognition module is used to obtain the initial information and shooting appearance information of the product, and send the information to the comparison and recognition module for processing. The abnormal information processing module obtains the diagnostic information in the comparison and recognition module, and controls the product production line through the control module. The system display platform is used to monitor and display the product recognition processing process.

2. A control system for workpiece identification and processing applied to a smart factory according to claim 1, characterized in that: The shooting and identification module includes a code scanning device and a camera. The code scanning device is installed on the side of the camera. The code scanning device pre-scans the workpiece to obtain the production batch and grade of the workpiece, and sends the initial data of the workpiece to the system display platform for storage. The camera shoots the workpiece, and the camera performs image recognition to obtain the actual parameters of the workpiece, and sends the actual parameters of the workpiece to the system display platform for storage and display.

3. A control system for workpiece identification and processing applied to a smart factory according to claim 1, characterized in that: The shooting recognition module also includes a shooting image acquisition unit, an image preliminary analysis unit and an appearance data preliminary comparison unit. The shooting image acquisition unit is used to acquire the workpiece image taken by the camera, pre-process the image, send the pre-processed image to the image preliminary analysis unit for analysis, retrieve the original parameters of the workpiece in the system display platform, compare the original parameters of the workpiece with the workpiece data in the shooting image acquisition unit, and determine the integrity of the workpiece.

4. A control system for workpiece identification and processing applied to a smart factory according to claim 3, characterized in that: The captured image acquisition unit acquires the workpiece image captured by the camera, extracts features from the workpiece image, and annotates the workpiece image to obtain an initial annotated image; the image preliminary analysis unit acquires data from the captured image acquisition unit, and integrates the image according to the workpiece image and the initial annotated image.

5. A control system for workpiece identification and processing applied to a smart factory according to claim 4, characterized in that: The appearance data preliminary comparison unit is used to obtain the workpiece image, the preliminary annotated image and the workpiece initial data, and perform a separate comparison based on the data annotation Ban on the workpiece image and the data annotation Bbn on the preliminary annotated image to obtain the workpiece initial data Bcn. The image processing accuracy Cn is obtained. In this formula, n is a positive integer greater than or equal to 1, which is used to represent the changes of each data after image processing. Then, according to the formula The processing accuracy of the workpiece image is obtained, and then the workpiece image data is judged whether it can be used in the subsequent detection process according to whether the Δ value is within the standard range. If so, the data is corrected to see if it is abnormal; If not, the image processing algorithm in the image preliminary analysis unit needs to be revised.

6. A control system for workpiece identification and processing applied to a smart factory according to claim 5, characterized in that: According to the formula The deformation value An of the workpiece is obtained, and the value range of An is detected, where n is a positive integer greater than or equal to 1, to determine whether the workpiece has a large deformation. If so, it is determined that the workpiece is abnormal and the data is sent to the comparison and recognition module for further processing. If not, the workpiece is directly transferred to the next processing program.

7. A control system for workpiece identification and processing applied to a smart factory according to claim 1, characterized in that: The comparison and identification module includes an abnormal image processing unit, an abnormal analysis unit and a diagnosis result determination unit. The abnormal image analysis unit is used to obtain a workpiece image and a data annotation Ban on the workpiece image, and simultaneously obtain the workpiece initial data Bcn. The abnormal image processing unit is used to perform preliminary processing on the above data and image, and then the abnormal analysis unit is used to analyze the data. Finally, the diagnosis result determination unit is used to determine the abnormal analysis diagnosis in the abnormal analysis unit, and finally the result is processed in the abnormal information processing module.

8. The control system for workpiece identification and processing applied to a smart factory according to claim 1, characterized in that: The abnormal information processing module includes a response adjustment unit and a direct classification unit. The response adjustment unit is used to obtain the workpieces that can be adjusted in the result diagnosis unit, and after intelligently adjusting the workpieces, re-introduce them into the equipment for re-detection. The direct classification unit is used to directly classify the workpieces according to the diagnosis results in the result diagnosis unit, and place the classified workpieces separately.

Images