CN116595214A - Component non-contact automatic shape correction system based on image processing - Google Patents
Component non-contact automatic shape correction system based on image processing Download PDFInfo
- Publication number
- CN116595214A CN116595214A CN202310861360.XA CN202310861360A CN116595214A CN 116595214 A CN116595214 A CN 116595214A CN 202310861360 A CN202310861360 A CN 202310861360A CN 116595214 A CN116595214 A CN 116595214A
- Authority
- CN
- China
- Prior art keywords
- scanning
- module
- difference
- point
- dimensional
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012937 correction Methods 0.000 title claims abstract description 42
- 238000012545 processing Methods 0.000 title claims abstract description 29
- 230000007547 defect Effects 0.000 claims abstract description 42
- 238000001514 detection method Methods 0.000 claims abstract description 35
- 238000010276 construction Methods 0.000 claims description 32
- 238000011156 evaluation Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000009471 action Effects 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 6
- 238000009877 rendering Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 4
- 238000000034 method Methods 0.000 description 9
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 230000008521 reorganization Effects 0.000 description 2
- 241001025261 Neoraja caerulea Species 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The application discloses a non-contact automatic shape correcting system for parts based on image processing, which relates to the technical field of shape correcting devices and comprises a scanning and positioning module, a workpiece placing module, a blue light scanning module, a scanning and checking module, a model building module, a workpiece database, a defect detecting module and a shape correcting device. The non-contact automatic shape correction system for the parts based on image processing establishes the three-dimensional point cloud of the parts to be detected through blue light scanning, compares the established three-dimensional point cloud with the data of the standard parts, thereby definitely acquiring the difference between the parts and the standard parts, transmitting the difference of detection data to an automatic shape correction device, further reducing and eliminating the difference through on-machine shape correction, and has the effects of high shape correction efficiency and reliable shape correction result data.
Description
Technical Field
The application belongs to the technical field of machine vision, and particularly relates to a non-contact automatic shape correction system for parts based on image processing.
Background
In the production process of parts, the quality of the parts is required to be checked, and the higher precision is obviously difficult to achieve by simply relying on manual quality check. However, the dimension of the parts will have accumulated deviation during the manufacturing process, which will affect the dimension precision of the finished product after processing and the usability of the final product, so that the dimension precision of the parts must be strictly controlled, and all the parts must be inspected to be qualified for production and use.
Blue light scanning is a high-precision dimension measurement method, and can scan an object into a three-dimensional model, and a series of dimension measurements are performed on the basis of the three-dimensional model. The method comprises the steps of projecting a blue light grating on the surface of an object, shooting a distorted grating image by using a high-precision camera to realize scanning measurement of the three-dimensional contour of the surface of the object, and then obtaining a three-dimensional data model of the object through processing. Although the automatic non-contact correction of the parts based on blue light scanning is a more accurate detection mode, the automatic non-contact correction system of the parts based on blue light detection in the related art has simpler structure, simple parameter comparison is performed after the parts are scanned by the blue light detection, so that the detection of the parts is considered to be completed.
Disclosure of Invention
The application aims to provide a non-contact automatic shape correcting system for parts based on image processing, so as to improve the accuracy and reliability of the non-contact automatic shape correction of the parts.
In order to achieve the above purpose, the present application discloses the following technical solutions:
the device comprises a scanning positioning module, a workpiece placement module, a blue light scanning module, a scanning abnormal detection module, a model building module, a workpiece database, a defect detection module and a shape correction device;
the scanning positioning module is used for setting positioning identification marks on the parts to be tested, and the number of the positioning identification marks on each part to be tested is at least 3;
the workpiece placement module is used for clamping or jacking the part to be tested;
the blue light scanning module is used for carrying out omnibearing scanning on the part to be tested on the workpiece placement module based on a blue light scanning technology;
the scanning and checking module is used for summarizing the data obtained by scanning of the blue light scanning module and eliminating abrupt points;
the model construction module is used for carrying out three-dimensional point cloud construction on the part to be tested based on the scanning result of the blue light scanning module and the identification result of the image identification module;
the workpiece database is used for storing size parameters and model parameters of standard parts;
the defect detection module is used for calling parameters in the workpiece database, carrying out overlapping comparison on the parameters and parameters of the three-dimensional point cloud constructed by the model construction module, and evaluating defects of the part to be tested based on the overlapping comparison result to obtain an evaluation result;
the shape correcting device is used for receiving the evaluation result transmitted by the defect detection module configuration, applying stress to the blade according to the evaluation result, and performing shape correcting action to complete on-machine shape correction and detection.
In one embodiment, the shape correction device comprises:
a scanning positioning unit configured to capture and identify the positioning identification;
a coordinate establishing unit configured to establish a three-dimensional coordinate system with the identified positioning identification as an origin based on a preset three-dimensional coordinate establishing strategy;
the scanning execution unit is configured to carry out blue light scanning on the part to be tested based on the established three-dimensional coordinate system;
and a shape correction action unit configured to execute shape correction action unit based on the blue light scanning result.
In one embodiment, the scanning execution unit records three-dimensional coordinate values of the scanned points on each part to be tested when performing blue light scanning.
In one embodiment, the scan checking module is configured to converge three-dimensional coordinate values of the scanned points on each part to be tested based on the scan result of the scan executing unit, sequentially arrange the three-dimensional coordinate values according to a scan sequence, then perform the check on the coordinate values of each scanned point, and reject the scanned point when the coordinate values of the scanned points are found to be abnormal; and evaluating according to the scanning result of the scanning execution unit, applying stress to the workpiece according to the evaluation result, and finally realizing on-machine calibration.
In one embodiment, the correcting the coordinate value of each scanned point specifically includes the following steps:
step one: acquiring three-dimensional coordinates (X i ，Y i ，Z i ) Wherein i is a positive integer;
step two: acquiring three-dimensional coordinates (X) of a scanned point i-1 located before the scanned point i in the scanning order i-1 ,Y i-1 ,Z i-1 ) And acquiring three-dimensional coordinates (X) of a point i+1 located before the scanned point i in the scanning order i+1 ,Y i+1 ,Z i+1 )；
Step three: comparing the coordinate value of the three-dimensional coordinate of the scanned point i-1 and the coordinate value of the three-dimensional coordinate of the scanned point i+1 with the corresponding coordinate value of the three-dimensional coordinate of the scanned point iThe calculation formula for calculating the difference P between each coordinate value and the difference on the X axis is as follows: i X i-1 -X i I and X i+1 -X i The calculation formula of the difference degree on the Y axis is as follows: y is% i-1 -Y i I and Y i+1 -Y i The calculation formula of the difference degree on the Z axis is as follows: z i-1 -Z i I and Z i+1 -Z i I, obtain PX respectively i-1 、PY i-1 、PZ i-1 、PX i+1 、PY i+1 And PZ i+1 ；
Step four: the obtained difference P is compared with a preset difference threshold Q, which refers to the allowable difference between two coordinate values, respectively, and it is understood that when the difference between the two coordinate values is larger, the larger the distance between the two points is indicated, and in a non-fracture type structure (two separated structures), such a far point cannot appear on the same plane. When the difference degree P corresponding to the scanned point i-1 or the difference degree P corresponding to the scanned point i+1 is smaller than the difference threshold value Q, the scanned point i is stored as an effective point, and when at least one of the difference degrees P corresponding to the scanned point i-1 is larger than the difference threshold value Q and at least one of the difference degrees P corresponding to the scanned point i+1 is larger than the difference threshold value Q, the scanned point i is discarded as an ineffective point;
step five: and (3) transmitting the result evaluated in the step four to a shape correcting device, wherein the shape correcting device applies stress in a specific direction to the three-dimensional coordinate of the scanning point i, and finally, the standard difference between the scanning point i and the workpiece database reaches a qualified state, so that the machine-machine dialogue and execution between the detection module and the shape correcting device are completed.
In one embodiment, PX i-1 、PY i-1 、PZ i-1 、PX i+1 、PY i+1 And PZ i+1 When only one of the scanned points i is larger than the difference threshold value Q, replacing the coordinate value corresponding to the difference degree P of the scanned point i larger than the difference threshold value Q with the coordinate value corresponding to the scanned point i-1 or the scanned point i+1.
In one embodiment, the defect detection module includes:
the data retrieval unit is configured to match and retrieve parameters in the workpiece database and parameters of the three-dimensional point cloud constructed by the model construction module;
the parameter superposition unit is configured to conduct superposition comparison on parameters in the workpiece database and parameters of the three-dimensional point cloud constructed by the model construction module, and the parameters comprise image parameters and dimension parameters;
and a defect evaluation unit configured to perform component defect evaluation based on the superposition comparison result of the parameter superposition unit.
In one embodiment, the step of performing the overlapping comparison by the parameter overlapping unit specifically includes:
step one: performing model reorganization on the parameters called in the workpiece database, and rendering a first color on the reorganized model;
step two: rendering a second color of the three-dimensional point cloud constructed by the model construction module, wherein the second color is different from the first color and has obvious contrast difference;
step three: comparing the parameters which are called in the workpiece database with the parameters of the three-dimensional point cloud constructed by the model construction module, and finding out at least three completely coincident points to serve as reference points;
step four: overlapping all the datum points, and then overlapping the recombined model and the three-dimensional point cloud constructed by the model construction module;
step five: analyzing the overlapped graph, obtaining the difference of the three-dimensional point cloud constructed by the model construction module based on the recombined model, and sending the difference to the defect evaluation unit.
In one embodiment, the obtaining the difference between the three-dimensional point cloud constructed by the model construction module and the recombined model specifically includes:
and performing image processing on the overlapped image, marking and edge tracing frame selection on the area with only the second color and the first color exposed in the overlapped image, and taking the area selected by the frame as a defect area.
In one embodiment, the defect-evaluating unit is further configured to generate a defect-evaluating report including the defective part position information generated based on the coincidence comparison result.
The application relates to a non-contact automatic shape correcting system for parts based on image processing, which comprises a scanning and positioning module, a workpiece placement module, a blue light scanning module, a scanning and checking module, a model construction module, a workpiece database and a defect detection module, wherein a three-dimensional point cloud of the parts to be detected is established through a blue light scanning surface, and the established three-dimensional point cloud is compared with data of standard parts, so that the difference between the parts and the standard parts is definitely obtained, and the system has the effects of high efficiency and reliability; according to the image processing-based component non-contact automatic shape correction system, the scanned points in the scanned results are processed, so that the scanned results are optimized, the error rate of the three-dimensional point cloud obtained by the scanned results when being compared with the standard component model is reduced, and the accuracy of the component non-contact automatic shape correction results is improved; and (3) carrying out full-shape and size detection analysis on the part to be detected by using a blue light scanner, obtaining the surface data of the part by blue light scanning three-dimensional scanning, carrying out point-to-point comparison with the standard part, determining the defect area on the part, determining the detection result and improving the detection accuracy.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings required for the description of the embodiments or the related art will be briefly described, and it will be apparent to those skilled in the art that other drawings can be obtained according to these drawings without inventive effort.
FIG. 1 is a schematic diagram of an image processing-based component contactless automatic shape correction system in accordance with some embodiments of the present application;
FIG. 2 is a schematic illustration of a shape correction device in some embodiments of the application;
FIG. 3 is a flow chart of a method of performing point-to-point entanglement in some embodiments of the application;
FIG. 4 is a schematic diagram of a defect detection module in some embodiments of the application;
FIG. 5 is a flow chart of a defect detection method according to some embodiments of the application.
Detailed Description
In order to make the technical solution of the present application better understood by those skilled in the art, the technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
FIG. 1 is a schematic diagram of an image processing-based component non-contact automatic shape correction system according to some embodiments of the present application, where the image processing-based component non-contact automatic shape correction system shown in FIG. 1 includes a scan positioning module, a workpiece placement module, a blue-ray scanning module, a scan inspection module, a model building module, a workpiece database, a defect detection module, and a shape correction device.
The shape correcting device comprises:
a scanning positioning unit configured to capture and identify the positioning identification;
a coordinate establishing unit configured to establish a three-dimensional coordinate system with the identified positioning identification as an origin based on a preset three-dimensional coordinate establishing strategy;
the scanning execution unit is configured to carry out blue light scanning on the part to be tested based on the established three-dimensional coordinate system;
and a shape correction action unit configured to execute shape correction action unit based on the blue light scanning result.
The scanning positioning module is mainly used for setting positioning identification marks on the parts to be detected, the number of the positioning identification marks on each part to be detected is at least 3, and the blue light scanning in the application is 3D scanning, so that the setting of the positioning marks is at least 3 points which are not on the same straight line, for example, the number of the positioning marks can be 4 or 6, and the like. The positioning identification mark is arranged to facilitate the determination of the scanned area and the coordinate generation of each scanned point of the scanned area during blue light scanning.
Compared with a conventional white light three-dimensional scanner, the application adopts a blue light scanning detection technology, has strong light interference resistance in blue light scanning, and can perform high-precision scanning under the condition of complex light environment. Meanwhile, the image processing-based component contactless automatic shape correction system establishes the three-dimensional point cloud of the component to be detected through the blue light scanning surface, and compares the established three-dimensional point cloud with the data of the standard component, so that the difference between the component and the standard component is definitely obtained, and the image processing-based component contactless automatic shape correction system has the effects of high efficiency and reliability.
The workpiece placement module is mainly used for clamping or jacking the to-be-tested part, and can be any one of the related technologies, such as a clamp for clamping opposite sides or a placement platform with larger volume, and in the use process, the workpiece placement module has a 360-degree rotation function on the to-be-tested part, and the purpose is to ensure that the blue light scanning module can perform omnibearing scanning on the to-be-tested part so as to accurately acquire the three-dimensional point cloud of the to-be-tested part.
In some embodiments, the clamping points of the opposite clamping fixture in the application are positioning identification points of the parts. When the number of the clamping points, namely the positioning identification points is at least 4, the workpiece placement module can rotate 360 degrees along 2 intersecting planes of the parts to be tested respectively, and the two intersecting planes are preferably orthogonal planes. The trajectories of the parts during rotation form the warp and weft lines. In some embodiments, the fixture has a measurement function, and the measured data can be used for verification.
In some embodiments, the number of clamping points for the part may be at least 6, in which case the workpiece placement module is capable of 360 ° rotation of the part to be tested along 3 intersecting planes, respectively.
Fig. 2 is a schematic diagram of a blue light scanning module according to some embodiments of the application.
As shown in fig. 2, the blue light scanning module is mainly used for performing omnibearing scanning on the part to be tested based on a blue light scanning technology. In some embodiments, the blue light scanning module comprises:
a scanning positioning unit for capturing and identifying the positioning identification mark;
the coordinate establishing unit is used for establishing a three-dimensional coordinate system by taking the identified positioning identification mark as an origin based on a preset three-dimensional coordinate establishing strategy;
and the scanning execution unit is used for carrying out blue light scanning on the part to be tested based on the established three-dimensional coordinate system.
When the scanning execution unit performs blue light scanning, three-dimensional coordinate values of scanned points on each part to be detected are recorded.
The scanning and abnormal checking module is mainly used for summarizing and eliminating abrupt points of data obtained by scanning of the blue light scanning module, and aims to optimize a scanning result by processing scanned points in the scanning result, so that the error rate of the three-dimensional point cloud obtained by the scanning result when being compared with a standard part model is reduced, and the accuracy of the non-contact automatic correction result of parts is further improved.
The scanning and abnormal checking module is configured to converge three-dimensional coordinate values of scanned points on each part to be detected based on a scanning result of the scanning execution unit, sequentially arrange the three-dimensional coordinate values according to a scanning sequence, then perform the checking on the coordinate values of each scanned point, and reject the scanned point when the coordinate values of the scanned point are found to be abnormal.
FIG. 3 is a flow chart of a method of performing point-to-point entanglement in some embodiments of the application.
As shown in fig. 3, the performing the correction on the coordinate value of each scanned point specifically includes the following steps:
step one: acquiring three-dimensional coordinates (X i ，Y i ，Z i ) The method comprises the steps of carrying out a first treatment on the surface of the Wherein i is a positive integer;
step two: acquiring three-dimensional coordinates (X) of a scanned point i-1 located before the scanned point i in the scanning order i-1 ,Y i-1 ,Z i-1 ) And acquiring three-dimensional coordinates (X) of a point i+1 located before the scanned point i in the scanning order i+1 ,Y i+1 ,Z i+1 )；
Step three: comparing the coordinate value in the three-dimensional coordinate of the scanned point i-1 and the coordinate value in the three-dimensional coordinate of the scanned point i+1 with the coordinate value in the three-dimensional coordinate of the scanned point i, and calculating the difference degree P between each coordinate value, wherein the calculation formula of the difference degree on the X axis is as follows: i X i-1 -X i I and X i+1 -X i The calculation formula of the difference degree on the Y axis is as follows: y is% i-1 -Y i I and Y i+1 -Y i The calculation formula of the difference degree on the Z axis is as follows: z i-1 -Z i I and Z i+1 -Z i I, obtain PX respectively i-1 、PY i-1 、PZ i-1 、PX i+1 、PY i+1 And PZ i+1 ；
As another calculation method of the difference degree, the difference degree P between each coordinate value is calculated, and the calculation formula of the difference degree on the X axis is: |curl (X) i-1 )-curl(X i ) |and |Curl (X) i+1 )-curl(X i ) The calculation formula of the difference degree on the Y axis is as follows: |crul (Y) i-1 )-crul(Y i ) I and |crul (Y) i+1 )-crul(Y i ) The calculation formula of the difference degree on the Z axis is as follows: |crul (Z) i-1 )-crul(Z i ) I and |crul (Z) i+1 )-crul(Z i ) I, obtain PX respectively i-1 、PY i-1 、PZ i-1 、PX i+1 、PY i+1 And PZ i+1 The method comprises the steps of carrying out a first treatment on the surface of the Wherein, the curl identifies the curl;
step four: the obtained difference P is compared with a preset difference threshold Q, which refers to the allowable difference between two coordinate values, respectively, and it is understood that when the difference between the two coordinate values is larger, the larger the distance between the two points is indicated, and in a non-fracture type structure (two separated structures), such a far point cannot appear on the same plane. When the difference degree P corresponding to the scanned point i-1 or the difference degree P corresponding to the scanned point i+1 is smaller than the difference threshold value Q, the scanned point i is stored as an effective point, and when at least one of the difference degrees P corresponding to the scanned point i-1 is larger than the difference threshold value Q and at least one of the difference degrees P corresponding to the scanned point i+1 is larger than the difference threshold value Q, the scanned point i is discarded as an ineffective point;
step five: and (3) transmitting the result evaluated in the step four to a shape correcting device, wherein the shape correcting device applies stress in a specific direction to the three-dimensional coordinate of the scanning point i, and finally, the standard difference between the scanning point i and the workpiece database reaches a qualified state, so that the machine-machine dialogue and execution between the detection module and the shape correcting device are completed.
Further, when PX i-1 、PY i-1 、PZ i-1 、PX i+1 、PY i+1 And PZ i+1 When only one of the scanned points i is larger than the difference threshold value Q, replacing the coordinate value corresponding to the difference degree P of the scanned point i larger than the difference threshold value Q with the coordinate value corresponding to the scanned point i-1 or the scanned point i+1. The difference threshold Q can be flexibly set according to requirements, for example, the relative value of the common difference threshold Q relative to the whole size of the part is less than 0.01% -0.05%.
The model construction module is mainly used for carrying out three-dimensional point cloud construction on the part to be tested based on the scanning result of the blue light scanning module and the identification result of the image identification module, and the three-dimensional construction mode, principle and specific related algorithm can be improved based on the modeling mode in the related technology.
The workpiece database stores dimension parameters and model parameters of standard parts, wherein the dimension parameters comprise the length, the width, the height, the depth of a notch, the curvature of an arc, the included angle between surfaces and the like of the parts, and the model parameters refer to three-dimensional point clouds of the standard parts.
FIG. 4 is a schematic diagram of a defect detection module in some embodiments of the application.
As shown in fig. 4, the defect detection module is mainly configured to retrieve parameters in the workpiece database, perform a duplication comparison with parameters of the three-dimensional point cloud constructed by the model construction module, and evaluate defects of the part to be tested based on a result of the duplication comparison. In some embodiments, the defect detection module comprises:
the data retrieval unit is configured to match and retrieve parameters in the workpiece database and parameters of the three-dimensional point cloud constructed by the model construction module;
the parameter superposition unit is configured to conduct superposition comparison on parameters in the workpiece database and parameters of the three-dimensional point cloud constructed by the model construction module, and the parameters comprise image parameters and dimension parameters;
and a defect evaluation unit configured to perform component defect evaluation based on the superposition comparison result of the parameter superposition unit.
FIG. 5 is a flow chart of a defect detection method according to some embodiments of the application.
As shown in fig. 5, further, the step of performing the overlapping comparison by the parameter overlapping unit specifically includes:
step one: performing model reorganization on the parameters called in the workpiece database, and rendering a first color on the reorganized model;
step two: rendering a second color of the three-dimensional point cloud constructed by the model construction module, wherein the second color is different from the first color and has obvious contrast difference;
step three: comparing the parameters which are called in the workpiece database with the parameters of the three-dimensional point cloud constructed by the model construction module, and finding out at least 3 completely coincident points to serve as reference points; the at least 3 full overlap points are not collinear.
Step four: overlapping all the datum points, and then overlapping the recombined model and the three-dimensional point cloud constructed by the model construction module;
step five: analyzing the overlapped graph, obtaining the difference of the three-dimensional point cloud constructed by the model construction module based on the recombined model, and sending the difference to the defect evaluation unit.
Further, the obtaining the three-dimensional point cloud constructed by the model construction module based on the difference of the recombined model specifically includes:
the method comprises the steps of performing image processing on the overlapped image, marking and edge tracing and framing the area with only the second color and the first color exposed in the overlapped image, taking the area selected by the frame as a defect area, and performing corresponding adjustment or modification on the defect area in a corresponding manufacturing process or in a mold in the subsequent treatment process by staff, so that the production efficiency and the product qualification rate are improved.
In this embodiment, the defect evaluation unit is further configured to generate a defect evaluation report including the part position information with the defect generated based on the coincidence comparison result.
The application relates to a non-contact automatic shape correcting system for parts based on image processing, which comprises a scanning positioning module, a workpiece placing module, a blue light scanning module, a scanning checking module, a model building module, a workpiece database, a defect detecting module and a shape correcting device, wherein a three-dimensional point cloud of the parts to be detected is built through a blue light scanning surface, and the built three-dimensional point cloud is compared with data of standard parts, so that differences between the parts and the standard parts are definitely obtained, and the system has the effects of high efficiency and reliability. In addition, the application utilizes the blue light scanner to carry out full-shape and size detection analysis on the parts to be detected, thus obtaining complete measurement and inspection report, improving the quality of the parts and optimizing the manufacturing process of the parts; meanwhile, the surface data of the parts are obtained through blue light scanning three-dimensional scanning, point-to-point comparison is carried out on the surface data and the standard parts, defect areas on the parts are clear, detection results are clear, and detection accuracy is improved. Meanwhile, the scanned points in the scanning result are processed, so that the scanning result is optimized, the error rate of the three-dimensional point cloud obtained by the scanning result when being compared with the standard part model is reduced, and the accuracy of the non-contact automatic shape correction result of the parts is improved.
Those of ordinary skill in the art will appreciate that all or a portion of the steps of implementing the above embodiments may be implemented by hardware, or may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, where the computer readable storage medium may be a read-only memory, a magnetic disk or optical disk, etc. disposed in a network switch.
In the embodiments provided in the present application, it should be understood that the disclosed system configuration and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
Finally, it should be noted that: the foregoing description is only illustrative of the preferred embodiments of the present application, and although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described, or equivalents may be substituted for elements thereof, and any modifications, equivalents, improvements or changes may be made without departing from the spirit and principles of the present application.
Claims (10)
1. An image processing-based component contactless automatic shape correction system, comprising:
the device comprises a scanning positioning module, a workpiece placement module, a blue light scanning module, a scanning abnormal detection module, a model building module, a workpiece database, a defect detection module and a shape correction device;
the scanning positioning module is used for setting positioning identification marks on the parts to be tested, and the number of the positioning identification marks on each part to be tested is at least 3;
the workpiece placement module is used for clamping or jacking the part to be tested;
the blue light scanning module is used for carrying out omnibearing scanning on the part to be tested on the workpiece placement module based on a blue light scanning technology;
the scanning and checking module is used for summarizing the data obtained by scanning of the blue light scanning module and eliminating abrupt points;
the model construction module is used for carrying out three-dimensional point cloud construction on the part to be tested based on the scanning result of the blue light scanning module and the identification result of the image identification module;
the workpiece database is used for storing size parameters and model parameters of standard parts;
the defect detection module is used for calling parameters in the workpiece database, carrying out overlapping comparison on the parameters and parameters of the three-dimensional point cloud constructed by the model construction module, and evaluating defects of the part to be tested based on the overlapping comparison result to obtain an evaluation result;
the shape correcting device is used for receiving the evaluation result transmitted by the defect detection module configuration, applying stress to the blade according to the evaluation result, and performing shape correcting action to complete on-machine shape correction and detection.
2. The image processing-based component contactless automatic shape correction system according to claim 1, wherein the shape correction device includes:
a scanning positioning unit configured to capture and identify the positioning identification;
a coordinate establishing unit configured to establish a three-dimensional coordinate system with the identified positioning identification as an origin based on a preset three-dimensional coordinate establishing strategy;
the scanning execution unit is configured to carry out blue light scanning on the part to be tested based on the established three-dimensional coordinate system;
and a shape correction action unit configured to execute shape correction action unit based on the blue light scanning result.
3. The system according to claim 2, wherein the scanning execution unit records three-dimensional coordinate values of scanned points on each part to be measured when performing blue light scanning.
4. The image processing-based component contactless automatic shape correction system according to claim 3, wherein the scanning and checking module is configured to converge three-dimensional coordinate values of scanned points on each component to be detected and sequentially arrange the three-dimensional coordinate values according to a scanning order based on a scanning result of the scanning execution unit, and then to perform a checking on the coordinate values of each scanned point, and to reject the scanned point when the coordinate values of the scanned point are found to be abnormal;
and evaluating according to the scanning result of the scanning execution unit, applying stress to the workpiece according to the evaluation result, and finally realizing on-machine calibration.
5. The system for automatically calibrating a component based on image processing without contact according to claim 4, wherein said correcting the coordinate value of each scanned point comprises the steps of:
step one: acquiring three-dimensional coordinates (X i ，Y i ，Z i ) Wherein i is a positive integer;
step two: acquiring three-dimensional coordinates (X) of a scanned point i-1 located before the scanned point i in the scanning order i-1 ,Y i-1 ,Z i-1 ) And acquiring three-dimensional coordinates (X) of a point i+1 located before the scanned point i in the scanning order i+1 ,Y i+1 ,Z i+1 )；
Step three: comparing the coordinate value in the three-dimensional coordinate of the scanned point i-1 and the coordinate value in the three-dimensional coordinate of the scanned point i+1 with the coordinate value in the three-dimensional coordinate of the scanned point i, and calculating the difference degree P between each coordinate value, wherein the calculation formula of the difference degree on the X axis is as follows: i X i-1 -X i I and X i+1 -X i The calculation formula of the difference degree on the Y axis is as follows: y is% i-1 -Y i I and Y i+1 -Y i The calculation formula of the difference degree on the Z axis is as follows: z i-1 -Z i I and Z i+1 -Z i I, obtain PX respectively i-1 、PY i-1 、PZ i-1 、PX i+1 、PY i+1 And PZ i+1 ；
Step four: comparing the acquired difference degree P with a preset difference threshold Q respectively, wherein the difference threshold Q refers to a difference value which can be allowed between two coordinate values; when the difference degree P corresponding to the scanned point i-1 or the difference degree P corresponding to the scanned point i+1 is smaller than the difference threshold Q, the scanned point i is taken as an effective point to be stored; when at least one of the difference degrees P corresponding to the scanned point i-1 is larger than a difference threshold Q and at least one of the difference degrees P corresponding to the scanned point i+1 is larger than the difference threshold Q, discarding the scanned point i as an invalid point;
step five: and (3) transmitting the result evaluated in the step four to a shape correcting device, wherein the shape correcting device applies stress in a specific direction to the three-dimensional coordinate of the scanning point i, and finally, the standard difference between the scanning point i and the workpiece database reaches a qualified state, so that the machine-machine dialogue and execution between the detection module and the shape correcting device are completed.
6. The image processing-based component contactless automatic shape correction system according to claim 5, wherein when PX i-1 、PY i-1 、PZ i-1 、PX i+1 、PY i+1 And PZ i+1 When only one of the scanned points i is larger than the difference threshold value Q, replacing the coordinate value corresponding to the difference degree P of the scanned point i larger than the difference threshold value Q with the coordinate value corresponding to the scanned point i-1 or the scanned point i+1.
7. The image processing-based component contactless automatic shape correction system according to claim 1, wherein the defect detection module includes:
the data retrieval unit is configured to match and retrieve parameters in the workpiece database and three-dimensional point cloud parameters constructed by the model construction module;
the parameter superposition unit is configured to conduct superposition comparison on parameters in the workpiece database and parameters of the three-dimensional point cloud constructed by the model construction module, and the parameters comprise image parameters and dimension parameters;
and a defect evaluation unit configured to perform component defect evaluation based on the superposition comparison result of the parameter superposition unit.
8. The image processing-based component contactless automatic shape correction system according to claim 7, wherein the step of the parameter registration unit performing the registration alignment specifically includes:
step one: rendering a first color on the model called in the workpiece database;
step two: rendering a second color of the three-dimensional point cloud constructed by the model construction module, wherein the second color is different from the first color and has obvious contrast difference;
step three: comparing the parameters called in the workpiece database with the parameters of the three-dimensional model constructed by the model construction module, and finding out at least six completely coincident points to serve as reference points;
step four: overlapping all the datum points, and then overlapping the recombined model and the three-dimensional point cloud constructed by the model construction module;
step five: analyzing the overlapped graph, obtaining the difference of the three-dimensional point cloud constructed by the model construction module based on the recombined model, and sending the difference to the defect evaluation unit.
9. The system for automatically calibrating a component based on image processing without contact according to claim 8, wherein the obtaining the three-dimensional point cloud constructed by the model construction module based on the difference of the workpiece database model specifically comprises:
and performing image processing on the overlapped image, marking and edge tracing frame selection on the area with only the second color and the first color exposed in the overlapped image, and taking the area selected by the frame as a defect area.
10. The image processing-based component contactless automatic shape correction system according to any one of claims 7 to 9, wherein the defect evaluation unit is further configured to generate a defect evaluation report including the component position information with defects generated based on the coincidence comparison result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310861360.XA CN116595214A (en) | 2023-07-14 | 2023-07-14 | Component non-contact automatic shape correction system based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310861360.XA CN116595214A (en) | 2023-07-14 | 2023-07-14 | Component non-contact automatic shape correction system based on image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116595214A true CN116595214A (en) | 2023-08-15 |
Family
ID=87590287
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310861360.XA Pending CN116595214A (en) | 2023-07-14 | 2023-07-14 | Component non-contact automatic shape correction system based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116595214A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109580630A (en) * | 2018-11-10 | 2019-04-05 | 东莞理工学院 | A kind of visible detection method of component of machine defect |
| CN112304954A (en) * | 2020-10-20 | 2021-02-02 | 西安工程大学 | Part surface defect detection method based on line laser scanning and machine vision |
| CN112326673A (en) * | 2020-11-13 | 2021-02-05 | 南京航空航天大学 | Injection molding surface defect detection method and device based on machine vision |
| WO2021208230A1 (en) * | 2020-04-15 | 2021-10-21 | 上海工程技术大学 | Intelligent assembly control system |
| CN114136972A (en) * | 2021-10-25 | 2022-03-04 | 上汽大众汽车有限公司 | Blue light scanning part integrated detection tool and part quality evaluation method |
-
2023
- 2023-07-14 CN CN202310861360.XA patent/CN116595214A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109580630A (en) * | 2018-11-10 | 2019-04-05 | 东莞理工学院 | A kind of visible detection method of component of machine defect |
| WO2021208230A1 (en) * | 2020-04-15 | 2021-10-21 | 上海工程技术大学 | Intelligent assembly control system |
| CN112304954A (en) * | 2020-10-20 | 2021-02-02 | 西安工程大学 | Part surface defect detection method based on line laser scanning and machine vision |
| CN112326673A (en) * | 2020-11-13 | 2021-02-05 | 南京航空航天大学 | Injection molding surface defect detection method and device based on machine vision |
| CN114136972A (en) * | 2021-10-25 | 2022-03-04 | 上汽大众汽车有限公司 | Blue light scanning part integrated detection tool and part quality evaluation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7015473B2 (en) | Method and apparatus for internal feature reconstruction | |
| US8526705B2 (en) | Driven scanning alignment for complex shapes | |
| CN108332708B (en) | Automatic detection system and detection method for laser level meter | |
| US20150269723A1 (en) | Stereo vision measurement system and method | |
| US20090033947A1 (en) | Method for repeatable optical determination of object geometry dimensions and deviations | |
| CN115077425B (en) | Product detection equipment and method based on structured light three-dimensional vision | |
| CN110966956A (en) | Binocular vision-based three-dimensional detection device and method | |
| CN115731165B (en) | Detection system and method for on-line size spot inspection of lithium battery | |
| CN112884743A (en) | Detection method and device, detection equipment and storage medium | |
| JP3696336B2 (en) | How to calibrate the camera | |
| CN117649404A (en) | Medicine packaging box quality detection method and system based on image data analysis | |
| CN111738971A (en) | Circuit board stereo scanning detection method based on line laser binocular stereo vision | |
| CN116563391B (en) | Automatic laser structure calibration method based on machine vision | |
| CN116595214A (en) | Component non-contact automatic shape correction system based on image processing | |
| TWI823780B (en) | A method and system for detecting wafer edge topography | |
| CN117252465A (en) | BIM technology-based intelligent acceptance method for decoration and fitment engineering | |
| CN114966238B (en) | Automatic detection and alignment method for antenna phase center | |
| CN109040724B (en) | Light spot distortion detection method and device of structured light projector and readable storage medium | |
| CN114392940B (en) | Pin detection method and device for special-shaped component | |
| TW201317587A (en) | Dimension measuring device and method thereof | |
| CN114638795A (en) | Multi-structure light measurement unit online measurement method and system | |
| CN108534707A (en) | Industry manufacture component scale scanning detection method | |
| CN114061480B (en) | Method for detecting appearance of workpiece | |
| JP7007525B1 (en) | Borescope inspection method and equipment | |
| JP2023543310A (en) | Semantic segmentation to be inspected |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |