CN111292293A - Intelligent manipulator fault detection method and system - Google Patents
Intelligent manipulator fault detection method and system Download PDFInfo
- Publication number
- CN111292293A CN111292293A CN202010061242.7A CN202010061242A CN111292293A CN 111292293 A CN111292293 A CN 111292293A CN 202010061242 A CN202010061242 A CN 202010061242A CN 111292293 A CN111292293 A CN 111292293A
- Authority
- CN
- China
- Prior art keywords
- image
- punching
- images
- feature
- circle
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to an intelligent manipulator fault detection method and system, which comprises the following steps: step 201, numbering N for each punching module in sequence according to the circulation direction of the production lineiI is 1-n, and n is the total number of the punching modules; step 202, obtaining N in sequence according to the sequence of i from small to bigiA punched image P ofiAs a first image, preprocessing the first image to obtain a second image for detection; step 203, extracting feature points of the second image, judging whether the feature points are located in a feature circle, if so, judging that a punching module corresponding to the second image has a fault, and if not, continuing the detection of a next-stage punching module; and step 204, displaying the punching module with the fault, and controlling an alarm device to be started. The punching modules where the mechanical arm is located can be numbered in sequence, and punching detection is carried out on the punching modules according to the numbering sequence, so that the checking time of a large number of workers is undoubtedly reduced, and the ordered operation of a production line is facilitated.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to an intelligent manipulator fault detection method and system.
Background
The industrial automatic punching technology is quite mature nowadays, is mainly applied to home production, and during work, the mechanical arm is controlled through numerical control programming to move a plate to a specific position according to a set path, and the plate is positioned in a photoelectric positioning mode and the like. Once the photoelectric positioning device of the manipulator has a problem, the whole production line is disordered, for example, if the distance controlled by numerical control programming is changed, the originally set punching position has a problem, and at this time, the manipulator needs to be automatically analyzed quickly to determine which manipulator specifically has the photoelectric positioning problem, so that an engineer can conveniently check and repair the manipulator.
The current market does not provide a method for effectively and quickly positioning the mechanical arm with the problem, so that an engineer needs a long time to position the mechanical arm with the problem, the punching is delayed undoubtedly, and unnecessary loss is caused.
Disclosure of Invention
The invention aims to solve the defects of the prior art, and provides an intelligent manipulator fault detection method and system, which can number the punching modules where the manipulator is located in sequence, carry out punching detection on the punching modules according to the numbering sequence, and display the detected punching modules with problems, thereby undoubtedly reducing the time for checking by a large number of workers, accelerating the repair of abnormal manipulators to a certain extent, and being beneficial to the orderly operation of a production line.
In order to achieve the purpose, the invention adopts the following technical scheme:
an intelligent manipulator fault detection system is proposed, comprising:
the system comprises a plurality of image acquisition units, a plurality of image acquisition units and a plurality of image acquisition units, wherein the image acquisition units are arranged at each level of punching modules and used for acquiring punching images of each level of punching modules after punching is completed;
the image preprocessing unit is used for preprocessing the first image to obtain a second image for detection;
a feature point extraction unit for extracting feature points of an input image;
a feature circle construction unit for constructing a feature circle according to NiIs perforated for a plurality of timesThen, successfully obtaining an image, wherein the successful image refers to an image of which the distance between the characteristic point of the image and the characteristic point of the standard construction drawing is smaller than a threshold value M, and extracting the characteristic point of each successful image to obtain a characteristic circle;
a fault judging unit for judging whether the feature point of the second image falls into a corresponding feature circle;
and the display and alarm unit is used for displaying the serial number of the punching module with the fault and giving an alarm.
The invention also provides an intelligent manipulator fault detection method, which comprises the following steps:
step 201, numbering N for each punching module in sequence according to the circulation direction of the production lineiI is 1-n, and n is the total number of the punching modules;
step 202, obtaining N in sequence according to the sequence of i from small to bigiA punched image P ofiAs a first image, preprocessing the first image to obtain a second image for detection;
step 203, extracting feature points of the second image, judging whether the feature points are located in a feature circle, if so, judging that a punching module corresponding to the second image has a fault, and if not, continuing the detection of a next-stage punching module;
and step 204, displaying the punching module with the fault, and controlling an alarm device to be started.
Further, the preprocessing the first image in step 202 to obtain a second image for detection specifically includes the following steps:
301, graying the first image and then carrying out binarization processing to obtain a third image;
step 302, performing contour extraction on the third image through OpenCV to obtain a fourth image;
303, performing noise reduction on the fourth image through wiener filtering to obtain a fifth image;
and step 304, performing image contour defect repairing on the fifth image to obtain a repaired contour image, namely a second image.
Further, the denoising processing by wiener filtering in step 303 specifically includes the following steps:
h-wiener 2(J, [ m n ], noise), [ H, noise ] -wiener 2(J, [ m n ]), H-wiener 2(J, [ mn ], noise), where m and n are both 3 by default, noise is the noise in the image, J is the first image, and H is the fifth image.
Further, the operation of repairing the image contour defect of the fifth image in step 304 specifically includes the following steps:
step 501, finding an image endpoint in the fifth image, where the endpoint is found according to the following method:
judging whether the pixel value change times of the 8 fields in the clockwise direction or the anticlockwise direction of any point on the outline in the fifth image is 0 time or 2 times, and if so, judging the point as an end point;
and 502, connecting any two end points with the distance smaller than the threshold value H through a straight line to finish the contour defect repair.
Further, the manner of extracting the feature points of the second image in step 203 is as follows: and scanning the second image, and extracting the outermost point in the vertical direction of the outline of the second image to be used as a characteristic point.
Further, the characteristic circle is constructed by the following specific method:
obtaining NiAnd (3) processing the images which are successfully punched for multiple times, wherein the successful images refer to the images of which the distance between the characteristic points of the images and the characteristic points of the standard construction drawing is smaller than a threshold value M, and extracting the characteristic points of each successful image to obtain a characteristic circle.
Further, the manipulator fault detection method further comprises:
when there is a failure, a log file is generated, which contains,
numbering N of failed punching modulesiThe date the test was completed and the time the test was completed.
The invention can obtain the following beneficial effects when adopting the system and the method:
according to the invention, the punching modules where the mechanical arm is located are numbered in sequence, the punching detection is carried out on the punching modules according to the numbering sequence, and the detected punching modules with problems are displayed, so that the checking time of a large number of workers is undoubtedly reduced, the repair of abnormal mechanical arms is accelerated to a certain extent, and the ordered operation of a production line is facilitated.
Drawings
Fig. 1 is a flow chart of an intelligent manipulator fault detection method according to the present invention.
Detailed Description
The conception, the specific structure and the technical effects of the present invention will be clearly and completely described in conjunction with the embodiments and the accompanying drawings to fully understand the objects, the schemes and the effects of the present invention. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The same reference numbers will be used throughout the drawings to refer to the same or like parts.
Referring to fig. 1, the present invention provides an intelligent manipulator fault detection system, including:
the system comprises a plurality of image acquisition units, a plurality of image acquisition units and a plurality of image acquisition units, wherein the image acquisition units are arranged at each level of punching modules and used for acquiring punching images of each level of punching modules after punching is completed;
the image preprocessing unit is used for preprocessing the first image to obtain a second image for detection;
a feature point extraction unit for extracting feature points of an input image;
a feature circle construction unit for constructing a feature circle according to NiAfter the holes are punched for multiple times, successfully obtaining images, wherein the successful images refer to images of which the distance between the characteristic points of the images and the characteristic points of the standard construction drawing is smaller than a threshold value M, and extracting the characteristic points of each successful image to obtain a characteristic circle;
a fault judging unit for judging whether the feature point of the second image falls into a corresponding feature circle;
and the display and alarm unit is used for displaying the serial number of the punching module with the fault and giving an alarm.
The invention also provides an intelligent manipulator fault detection method, which comprises the following steps:
step 201, numbering N for each punching module in sequence according to the circulation direction of the production lineiI is 1-n, and n is the total number of the punching modules;
step 202, obtaining N in sequence according to the sequence of i from small to bigiA punched image P ofiAs a first image, preprocessing the first image to obtain a second image for detection;
step 203, extracting feature points of the second image, judging whether the feature points are located in a feature circle, if so, judging that a punching module corresponding to the second image has a fault, and if not, continuing the detection of a next-stage punching module;
and step 204, displaying the punching module with the fault, and controlling an alarm device to be started.
As a preferred embodiment of the present invention, the preprocessing the first image in the step 202 to obtain the second image for detection specifically includes the following steps:
301, graying the first image and then carrying out binarization processing to obtain a third image;
step 302, performing contour extraction on the third image through OpenCV to obtain a fourth image;
303, performing noise reduction on the fourth image through wiener filtering to obtain a fifth image;
and step 304, performing image contour defect repairing on the fifth image to obtain a repaired contour image, namely a second image.
As a preferred embodiment of the present invention, the noise reduction processing by wiener filtering in step 303 specifically includes the following steps:
h-wiener 2(J, [ m n ], noise), [ H, noise ] -wiener 2(J, [ m n ]), H-wiener 2(J, [ mn ], noise), where m and n are both 3 by default, noise is the noise in the image, J is the first image, and H is the fifth image.
As a preferred embodiment of the present invention, the operation of performing image contour defect repairing on the fifth image in step 304 specifically includes the following steps:
step 501, finding an image endpoint in the fifth image, where the endpoint is found according to the following method:
judging whether the pixel value change times of the 8 fields in the clockwise direction or the anticlockwise direction of any point on the outline in the fifth image is 0 time or 2 times, and if so, judging the point as an end point;
and 502, connecting any two end points with the distance smaller than the threshold value H through a straight line to finish the contour defect repair. The threshold H should satisfy a distance greater than the distance between two adjacent end points but less than the minimum distance between two non-adjacent end points, and when this condition is satisfied, the threshold H may be set artificially.
In a preferred embodiment of the present invention, the feature point extraction of the second image in step 203 is performed by: and scanning the second image, and extracting the outermost point in the vertical direction of the outline of the second image to be used as a characteristic point.
As a preferred embodiment of the present invention, the characteristic circle is constructed by:
obtaining NiAnd (3) processing the images which are successful after the holes are punched for enough times, wherein the successful images refer to the images of which the distance between the characteristic points of the images and the characteristic points of the standard construction drawing is less than a threshold value M, and extracting the characteristic points of each successful image to obtain a characteristic circle.
When the obtained image which is punched successfully is enough for multiple times, all the images which meet the condition that the distance between the characteristic point and the characteristic point of the standard construction drawing is smaller than a threshold value M can be obtained, the threshold value M can be set manually and generally set as a reasonable error, and thus a characteristic circle which takes the characteristic point of the standard construction drawing as the center of a circle and the threshold value M as the radius can be obtained.
As a preferred embodiment of the present invention, the robot failure detection method further includes:
when there is a failure, a log file is generated, which contains,
numbering N of failed punching modulesiThe date the test was completed and the time the test was completed.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium and can implement the steps of the above-described method embodiments when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, etc. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media which may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
While the present invention has been described in considerable detail and with particular reference to a few illustrative embodiments thereof, it is not intended to be limited to any such details or embodiments or any particular embodiments, but it is to be construed as effectively covering the intended scope of the invention by providing a broad, potential interpretation of such claims in view of the prior art with reference to the appended claims. Furthermore, the foregoing describes the invention in terms of embodiments foreseen by the inventor for which an enabling description was available, notwithstanding that insubstantial modifications of the invention, not presently foreseen, may nonetheless represent equivalent modifications thereto.
The above description is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiment, and the present invention shall fall within the protection scope of the present invention as long as the technical effects of the present invention are achieved by the same means. The invention is capable of other modifications and variations in its technical solution and/or its implementation, within the scope of protection of the invention.
Claims (8)
1. An intelligent manipulator fault detection system, comprising:
the system comprises a plurality of image acquisition units, a plurality of image acquisition units and a plurality of image acquisition units, wherein the image acquisition units are arranged at each level of punching modules and used for acquiring punching images of each level of punching modules after punching is completed;
the image preprocessing unit is used for preprocessing the first image to obtain a second image for detection;
a feature point extraction unit for extracting feature points of an input image;
a feature circle construction unit for constructing a feature circle according to NiAfter the holes are punched for multiple times, successfully obtaining images, wherein the successful images refer to images of which the distance between the characteristic points of the images and the characteristic points of the standard construction drawing is smaller than a threshold value M, and extracting the characteristic points of each successful image to obtain a characteristic circle;
a fault judging unit for judging whether the feature point of the second image falls into a corresponding feature circle;
and the display and alarm unit is used for displaying the serial number of the punching module with the fault and giving an alarm.
2. An intelligent manipulator fault detection method is characterized by comprising the following steps:
step 201, numbering N for each punching module in sequence according to the circulation direction of the production lineiI is 1-n, and n is the total number of the punching modules;
step 202, obtaining N in sequence according to the sequence of i from small to bigiA punched image P ofiAs a first image, preprocessing the first image to obtain a second image for detection;
step 203, extracting feature points of the second image, judging whether the feature points are located in a feature circle, if so, judging that a punching module corresponding to the second image has a fault, and if not, continuing the detection of a next-stage punching module;
and step 204, displaying the punching module with the fault, and controlling an alarm device to be started.
3. The method according to claim 2, wherein the preprocessing the first image to obtain the second image for detection in step 202 specifically includes the following steps:
301, graying the first image and then carrying out binarization processing to obtain a third image;
step 302, performing contour extraction on the third image through OpenCV to obtain a fourth image;
303, performing noise reduction on the fourth image through wiener filtering to obtain a fifth image;
and step 304, performing image contour defect repairing on the fifth image to obtain a repaired contour image, namely a second image.
4. The method according to claim 3, wherein the noise reduction processing by wiener filtering in step 303 specifically includes the following steps:
h-wiener 2(J, [ m n ], noise), [ H, noise ] -wiener 2(J, [ m n ]), H-wiener 2(J, [ m n ], noise), where m and n both have a default value of 3, noise is the noise in the image, J is the first image, and H is the fifth image.
5. The method according to claim 3, wherein the step 304 of repairing the image contour defect of the fifth image comprises the following steps:
step 501, finding an image endpoint in the fifth image, where the endpoint is found according to the following method:
judging whether the pixel value change times of the 8 fields in the clockwise direction or the anticlockwise direction of any point on the outline in the fifth image is 0 time or 2 times, and if so, judging the point as an end point;
and 502, connecting any two end points with the distance smaller than the threshold value H through a straight line to finish the contour defect repair.
6. The intelligent manipulator fault detection method according to claim 2, wherein the manner of extracting the feature points of the second image in step 203 is as follows: and scanning the second image, and extracting the outermost point in the vertical direction of the outline of the second image to be used as a characteristic point.
7. The intelligent manipulator fault detection method according to claim 6, wherein the characteristic circle is constructed by the following specific steps:
obtaining NiAnd (3) processing the images which are successful after the holes are punched for enough times, wherein the successful images refer to the images of which the distance between the characteristic points of the images and the characteristic points of the standard construction drawing is less than a threshold value M, and extracting the characteristic points of each successful image to obtain a characteristic circle.
8. The intelligent manipulator fault detection method according to claim 2, further comprising:
when there is a failure, a log file is generated, which contains,
numbering N of failed punching modulesiThe date the test was completed and the time the test was completed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010061242.7A CN111292293B (en) | 2020-01-19 | 2020-01-19 | Intelligent manipulator fault detection method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010061242.7A CN111292293B (en) | 2020-01-19 | 2020-01-19 | Intelligent manipulator fault detection method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111292293A true CN111292293A (en) | 2020-06-16 |
CN111292293B CN111292293B (en) | 2023-04-25 |
Family
ID=71017615
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010061242.7A Active CN111292293B (en) | 2020-01-19 | 2020-01-19 | Intelligent manipulator fault detection method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111292293B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180108120A1 (en) * | 2016-10-17 | 2018-04-19 | Conduent Business Services, Llc | Store shelf imaging system and method |
CN109035249A (en) * | 2018-09-10 | 2018-12-18 | 东北大学 | A kind of parallel global threshold detection method of pipeline fault based on image procossing |
-
2020
- 2020-01-19 CN CN202010061242.7A patent/CN111292293B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180108120A1 (en) * | 2016-10-17 | 2018-04-19 | Conduent Business Services, Llc | Store shelf imaging system and method |
CN109035249A (en) * | 2018-09-10 | 2018-12-18 | 东北大学 | A kind of parallel global threshold detection method of pipeline fault based on image procossing |
Also Published As
Publication number | Publication date |
---|---|
CN111292293B (en) | 2023-04-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021196501A1 (en) | Big data-based fault monitoring method and system for industrial production line | |
CN110987493A (en) | Equipment abnormality detection method and device, storage medium and electronic equipment | |
CN110599484B (en) | Defect detection method, device and storage medium | |
CN111292254B (en) | Method, device, equipment and medium for determining data abnormality in remote sensing image | |
CN112364740A (en) | Unmanned machine room monitoring method and system based on computer vision | |
CN102005051A (en) | Edge detection method and related device | |
CN112669295A (en) | Lithium battery pole piece defect detection method based on secondary threshold segmentation theory | |
CN111221996B (en) | Instrument screen vision detection method and system | |
CN110992323A (en) | Steel strip detection method and device based on image processing and steel clamping detection method | |
CN111292293A (en) | Intelligent manipulator fault detection method and system | |
CN114331997A (en) | Wire defect monitoring method based on image recognition | |
CN108133479B (en) | Automatic spinning machine drawing-in monitoring method and device | |
CN113628232B (en) | Method for eliminating interference points in fitting line, visual identification equipment and storage medium | |
CN115619796A (en) | Method and device for obtaining photovoltaic module template and nonvolatile storage medium | |
CN116309307A (en) | Weld defect detection method and device, readable storage medium and electronic equipment | |
CN115331193A (en) | Parking space identification method, parking space identification system, electronic equipment and storage medium | |
CN113627885A (en) | Power grid power supply abnormity monitoring system and monitoring method thereof | |
CN114399733A (en) | Image detection method, device, equipment and storage medium | |
CN111833317A (en) | Industrial product specification detection method and equipment based on augmented reality | |
CN112185058A (en) | Monitoring alarm method, system, equipment and storage medium | |
CN112907542B (en) | Crystal back defect detection method, storage medium and computer equipment | |
CN114850071B (en) | Detection system and method for injector assembly machine | |
CN117173185B (en) | Method and device for detecting area of rolled plate, storage medium and computer equipment | |
CN116330041B (en) | Fault detection method, device, equipment and medium for numerical control machining transmission device | |
CN116563521B (en) | Detection frame processing method and device for target detection and electronic equipment |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |