CN117911415A - Automatic equipment supervision system and method based on machine vision - Google Patents
Automatic equipment supervision system and method based on machine vision Download PDFInfo
- Publication number
- CN117911415A CN117911415A CN202410316387.5A CN202410316387A CN117911415A CN 117911415 A CN117911415 A CN 117911415A CN 202410316387 A CN202410316387 A CN 202410316387A CN 117911415 A CN117911415 A CN 117911415A
- Authority
- CN
- China
- Prior art keywords
- image
- workpiece
- cutter
- marking
- industrial equipment
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012423 maintenance Methods 0.000 claims abstract description 30
- 238000012216 screening Methods 0.000 claims abstract description 6
- 238000013441 quality evaluation Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 238000007689 inspection Methods 0.000 claims description 3
- 230000008439 repair process Effects 0.000 claims description 3
- 239000003550 marker Substances 0.000 claims 2
- 238000005516 engineering process Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004382 visual function Effects 0.000 description 1
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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of equipment automation supervision, in particular to an equipment automation supervision system and method based on machine vision, comprising the steps of constructing an equipment supervision cloud platform and calculating the marking similarity between a workpiece image and a standard workpiece image; based on the marking similarity between the workpiece image and the standard workpiece image, performing quality evaluation on the workpiece to which the workpiece image belongs, acquiring a time point when the industrial equipment stops running from a historical tool maintenance record, and screening the marking time period of the industrial equipment according to the length of the distance between the marking time period and the time point to obtain a characteristic marking time period; extracting image features of the feature cutter images to obtain cutter feature image data of industrial equipment; the method comprises the steps of evaluating the use state of a cutter in industrial equipment, marking the cutter in the industrial equipment, and sending a cutter maintenance prompt to prompt staff when the cutter is marked, so as to automatically monitor the industrial equipment.
Description
Technical Field
The invention relates to the technical field of equipment automation supervision, in particular to an equipment automation supervision system and method based on machine vision.
Background
The machine vision is a technology for simulating human visual functions by using equipment such as a computer, a camera and the like, images and videos can be captured by a camera sensor, and the captured images and video contents are analyzed by a computer algorithm, so that the identification and understanding of objects, scenes and actions are realized, and the machine vision can be used for the automatic supervision of the equipment, mainly because the machine vision has the following advantages of 1 and instantaneity, the machine vision technology can continuously and automatically monitor the equipment for 24 hours, is not limited by human resources, and can rapidly and timely detect the running state and abnormal conditions of the equipment; 2. the identification accuracy, the machine vision technology can accurately identify and analyze the state of equipment through images or equipment, so that the inaccuracy of manual monitoring is reduced, and the supervision accuracy and reliability are improved; 3. the automatic supervision, machine vision technology can be integrated with other automatic equipment and systems, thereby realizing the automatic supervision and control of the equipment, greatly reducing the requirement of manual intervention and improving the degree of the automatic supervision of the equipment.
Most of the existing equipment is required to use a cutter when processing a workpiece, the cutter is damaged or the required precision requirement of a product cannot be met, the processing condition of the equipment on the workpiece can be influenced, so that the quality of the equipment is influenced, but because the precision requirements of different workpieces on the cutter in the equipment are different, if the cutter images in the historical maintenance record of the cutter are analyzed, the cutter can be damaged early in maintenance, and the condition of the cutter in the equipment cannot be predicted, so that the equipment is inaccurately monitored in an automatic manner, and the normal operation of the equipment is influenced.
Disclosure of Invention
The invention aims to provide an equipment automation supervision system and method based on machine vision, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: an equipment automation supervision method based on machine vision, the method comprises the following steps:
Step S100: constructing an equipment supervision cloud platform, shooting a workpiece processed by industrial equipment by using an industrial camera to obtain a workpiece image, acquiring a workpiece image database stored in the equipment supervision cloud platform in advance, extracting a plurality of standard workpiece images of the workpiece from the workpiece image database, and calculating the marking similarity between the workpiece images and the standard workpiece images;
Step S200: based on the marking similarity between the workpiece image and the standard workpiece image, performing quality evaluation on the workpiece to which the workpiece image belongs to obtain a marked workpiece, acquiring a time period in which the industrial equipment is used for processing the marked workpiece, marking the time period as a marked time period, acquiring a historical tool maintenance record of the industrial equipment, acquiring a time point when the industrial equipment stops running from the historical tool maintenance record, and screening the marked time period of the industrial equipment according to the distance between the marked time period and the time point to obtain a characteristic marked time period;
Step S300: shooting a cutter image of a cutter in the industrial equipment by an industrial camera in a characteristic marking period, marking the cutter image as a characteristic cutter image, and extracting image characteristics of the characteristic cutter image to obtain cutter characteristic image data of the industrial equipment;
Step S400: and acquiring a cutter image of the industrial equipment in the current period, evaluating the use state of the cutter in the industrial equipment according to the cutter characteristic image data of the industrial equipment, marking the cutter in the industrial equipment, and sending a cutter maintenance prompt to prompt staff when the cutter is marked, so as to automatically monitor the industrial equipment.
Further, step S100 includes:
Step S101: constructing an equipment supervision cloud platform, acquiring a workpiece image shot by an industrial camera, adjusting the image size of the workpiece image to the image size of a standard image, carrying out gray conversion on the workpiece image and the standard workpiece image, and carrying out noise removal on the workpiece image after gray conversion by using a Gaussian filter;
step S1O2: the gray value of each pixel point in the workpiece image and the standard workpiece image is obtained, the pixel size of a local block in the workpiece image is set, the workpiece image is aligned with the standard workpiece image, the workpiece image and the marked workpiece image are respectively split into a plurality of local blocks, the local blocks in the workpiece image and the marked workpiece image are respectively in one-to-one correspondence, and the marked brightness similarity value of each local block in the workpiece image and the standard workpiece image is calculated, wherein the marked brightness value of the (a) th local block in the workpiece image and the standard workpiece image is calculated :
;
Wherein,The average value of gray values of an a-th local block in the workpiece image; /(I)The average value of gray values of an a-th local block in the workpiece image; /(I)For a preset mark brightness factor,/>Is a positive number;
Step S103: calculating the mark contrast value of each partial block in the workpiece image and the standard workpiece image, wherein the mark contrast value of the a-th partial block in the workpiece image and the standard workpiece image :
;
Wherein,The variance of gray values in an a-th local block in the workpiece image; /(I)The variance of gray values in an a-th local block in the standard workpiece image is obtained; /(I)For a preset mark contrast factor,/>Is a positive number;
Step S104: calculating the marking structure value of each local block in the workpiece image and the standard workpiece image, wherein the marking structure value of the a-th local block in the workpiece image and the standard workpiece image :
;
Wherein,Covariance of gray values between the workpiece image and the standard workpiece image; /(I)For a preset mark structural factor,/>Is a positive number;
step S105: calculating the mark similarity between the workpiece image and the standard workpiece image, wherein the mark similarity between the workpiece image g and the standard workpiece image k :
;
Wherein,For the marked brightness value of the ith partial block in the workpiece image g and standard workpiece image k,/>The mark contrast value of the ith local block in the workpiece image g and the standard workpiece image k; /(I)Marking structure values of the ith local block in the workpiece image g and the standard workpiece image k; j is the total number of partial blocks in the workpiece image g.
Further, step S200 includes:
Step S201: obtaining the mark similarity between the workpiece image and each standard workpiece image in a workpiece image database, obtaining the maximum value of the mark similarity, setting a mark similarity threshold, judging that the quality of the workpiece to which the workpiece image belongs is qualified when the maximum value of the mark similarity is more than or equal to the mark similarity threshold, and marking the workpiece to which the workpiece image belongs as a mark workpiece when the maximum value of the mark similarity is less than the mark similarity threshold;
Step S202: when the industrial equipment processes the marked workpiece, the time period of the industrial equipment is recorded as the marking time period of the industrial equipment, the historical tool maintenance record of the industrial equipment is obtained, and the time point when the industrial equipment stops running when the industrial equipment is checked is extracted from the historical tool maintenance record ;
Step S203: calculating a marking distance of a historical tool repair record and a marking periodWherein, the method comprises the steps of, wherein,When a certain marking period is equal to the marking distance/>, the marking time is recorded for the industrial equipment to finish processing the workpieceMarking a certain marking period, and when the adjacent period of the marked other marking period is not the marking period, marking the other marking period as a characteristic marking period;
The characteristic marking time period is acquired in the step, and the image selection of the tool is important, so that the time point when the industrial equipment stops running is firstly extracted from the historical tool maintenance record when the industrial equipment is checked, the time point when the industrial equipment stops running is acquired according to the distance between the marking time period in the industrial equipment and the time point when the industrial equipment stops running, the time point when the tool in the industrial equipment is firstly failed is acquired according to the distance between the marking time period and the time point when the industrial equipment stops running, the time point is recorded as the characteristic marking time period, the tool image of the characteristic marking time period is acquired, the acquired tool image is ensured to be the image of the tool in the industrial equipment, and the analysis accuracy of the tool in the industrial equipment is improved.
Further, step S300 includes:
Step S301: when industrial equipment processes a workpiece, an industrial camera is used for shooting a cutter for processing the workpiece in the industrial equipment to obtain a cutter image, and the cutter image of the industrial equipment shot by the industrial camera in a characteristic marking period is recorded as a characteristic cutter image;
Step S302: acquiring the workpiece model of a workpiece processed by industrial equipment, collecting characteristic cutter images shot by an industrial camera when the workpiece with the same workpiece model is processed by the industrial equipment to obtain a characteristic cutter image set, acquiring cutter images of cutters in the industrial equipment when the workpiece with the same workpiece model is not processed by the industrial equipment in a marking period, and randomly selecting a plurality of cutter images from the cutter images to collect to obtain a comparison cutter image set;
Step S303: calculating the mark similarity between each cutter image in the characteristic cutter image and the contrast cutter image set, taking the mark similarity average value as the mark similarity average value between the characteristic cutter image and the contrast cutter image set, setting a mark similarity average value threshold value, and marking a certain characteristic cutter image as a target characteristic cutter image when the mark similarity average value between a certain characteristic cutter image and the contrast cutter image set is larger than the mark similarity average value threshold value;
Step S304: collecting target feature cutter images to obtain a target feature cutter image set, adjusting the image size of each target feature cutter image in the target feature cutter image set, performing gray level conversion, dividing the target feature cutter images into a plurality of pixel areas with the same pixel size, and calculating feature difference values among each feature cutter image in the target feature cutter image set, wherein the target feature cutter image s and the target feature cutter image w are calculated Characteristic difference value of individual pixel region/>:
;
Wherein,For the/>, in the target feature tool image sA gray value of a z-th pixel point in the pixel area; For the/>, in the target feature tool image w A gray value of a z-th pixel point in the pixel area; n is the/>, in the target feature tool image s and the target feature tool image wThe total number of pixel points in the pixel areas;
step S305: calculating variances of feature differences of all pixel areas in the target feature tool image set, obtaining pixel areas with maximum variances, obtaining key pixel areas in the target feature tool image set of all workpiece types, and collecting to obtain tool feature image data of industrial equipment.
Further, step S400 includes:
Step S401: shooting a cutter of industrial equipment in a current period by using an industrial camera to obtain a cutter image of the industrial equipment in the current period, and obtaining the model of a workpiece processed by the industrial equipment in the current period;
step S402: extracting from cutter characteristic image data of industrial equipment, calculating the mark similarity between a cutter image and each target characteristic cutter image in the target characteristic cutter image set, and acquiring the mark similarity maximum value, judging that cutters in the industrial equipment are damaged in the current period when the mark similarity maximum value in the current period is larger than a preset threshold value, marking the damaged cutters, acquiring the areas of key pixel areas in the target characteristic image set on the marked cutters, checking preferentially, sending cutter maintenance prompts to prompt staff, and performing automatic supervision on the industrial equipment.
In order to better realize the method, the device automatic supervision system is also provided, and comprises a marking similarity module, a characteristic marking period module, a cutter characteristic image data module and an automatic supervision module;
the marking similarity module is used for calculating the marking similarity between the workpiece image and the standard workpiece image;
The characteristic marking time period module is used for screening the marking time period of the industrial equipment according to the duration of the distance between the marking time period and the time point to obtain a characteristic marking time period;
the cutter characteristic image data module is used for extracting image characteristics of the characteristic cutter image to obtain cutter characteristic image data of industrial equipment;
And the automatic supervision module is used for evaluating the use state of the cutters in the industrial equipment, marking the cutters in the industrial equipment, and sending a cutter maintenance prompt to prompt staff when the cutters are marked, so as to carry out automatic supervision on the industrial equipment.
Further, the marking similarity module comprises a local block unit and a marking similarity unit;
The local block unit is used for aligning the workpiece image with the standard workpiece image and dividing the workpiece image and the marked workpiece image into a plurality of local blocks respectively;
and the mark similarity unit is used for calculating the mark similarity of the workpiece image and the standard workpiece image.
Further, the characteristic marking time period module comprises a marking workpiece unit and a characteristic marking time period unit;
the marking workpiece unit is used for acquiring marking similarity between the workpiece image and each standard workpiece image in the workpiece image database, and marking the workpiece to which the workpiece image belongs as a marking workpiece when the maximum value of the marking similarity is smaller than the marking similarity threshold;
and a characteristic marking period unit for marking a certain marking period, and marking another marking period as a characteristic marking period when the adjacent period of the marked other marking period is not the marking period.
Further, the cutter characteristic image data module comprises a characteristic difference value unit and a cutter characteristic image data unit;
The characteristic difference value unit is used for calculating characteristic difference values among the characteristic cutter images in the target characteristic cutter image set;
and the cutter characteristic image data unit is used for acquiring and collecting key pixel areas in the target characteristic cutter image set of each workpiece model to obtain cutter characteristic image data of industrial equipment.
Further, the automatic supervision module comprises an automatic supervision unit;
The automatic supervision unit is used for judging the damage condition of the cutters in the industrial equipment in the current period, marking the damaged cutters, acquiring the areas of the key pixel areas in the target characteristic image set on the marked cutters, carrying out priority inspection, sending a cutter maintenance prompt to prompt staff, and carrying out automatic supervision on the industrial equipment.
Compared with the prior art, the invention has the following beneficial effects: the invention realizes the automatic supervision of the industrial equipment, and for the industrial equipment, even when the same type of industrial equipment processes workpieces with different types, the requirements for the cutters in the industrial equipment are different, so the invention solves the problem, and the judgment of the cutter condition in the industrial equipment is related to the actual processed workpieces of the industrial equipment, so that the judgment of the cutters is more accurate.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of a method of the present invention for a machine vision based automated supervisory system and method for equipment;
Fig. 2 is a schematic block diagram of an automated machine vision-based system and method for monitoring and controlling a machine.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, the present invention provides the following technical solutions: an equipment automation supervision method based on machine vision, the method comprises the following steps:
Step S100: constructing an equipment supervision cloud platform, shooting a workpiece processed by industrial equipment by using an industrial camera to obtain a workpiece image, acquiring a workpiece image database stored in the equipment supervision cloud platform in advance, extracting a plurality of standard workpiece images of the workpiece from the workpiece image database, and calculating the marking similarity between the workpiece images and the standard workpiece images;
wherein, step S100 includes:
Step S101: constructing an equipment supervision cloud platform, acquiring a workpiece image shot by an industrial camera, adjusting the image size of the workpiece image to the image size of a standard image, carrying out gray conversion on the workpiece image and the standard workpiece image, and carrying out noise removal on the workpiece image after gray conversion by using a Gaussian filter;
step S1O2: the gray value of each pixel point in the workpiece image and the standard workpiece image is obtained, the pixel size of a local block in the workpiece image is set, the workpiece image is aligned with the standard workpiece image, the workpiece image and the marked workpiece image are respectively split into a plurality of local blocks, the local blocks in the workpiece image and the marked workpiece image are respectively in one-to-one correspondence, and the marked brightness similarity value of each local block in the workpiece image and the standard workpiece image is calculated, wherein the marked brightness value of the (a) th local block in the workpiece image and the standard workpiece image is calculated :
;
Wherein,The average value of gray values of an a-th local block in the workpiece image; /(I)The average value of gray values of an a-th local block in the workpiece image; /(I)For a preset mark brightness factor,/>Is a positive number;
Step S103: calculating the mark contrast value of each partial block in the workpiece image and the standard workpiece image, wherein the mark contrast value of the a-th partial block in the workpiece image and the standard workpiece image :
;
Wherein,The variance of gray values in an a-th local block in the workpiece image; /(I)The variance of gray values in an a-th local block in the standard workpiece image is obtained; /(I)For a preset mark contrast factor,/>Is a positive number;
Step S104: calculating the marking structure value of each local block in the workpiece image and the standard workpiece image, wherein the marking structure value of the a-th local block in the workpiece image and the standard workpiece image :
;
Wherein,Covariance of gray values between the workpiece image and the standard workpiece image; /(I)For a preset mark structural factor,/>Is a positive number;
step S105: calculating the mark similarity between the workpiece image and the standard workpiece image, wherein the mark similarity between the workpiece image g and the standard workpiece image k :
;
Wherein,For the marked brightness value of the ith partial block in the workpiece image g and standard workpiece image k,/>The mark contrast value of the ith local block in the workpiece image g and the standard workpiece image k; /(I)Marking structure values of the ith local block in the workpiece image g and the standard workpiece image k; j is the total number of local blocks in the workpiece image g;
for example, j is 2; marking brightness value of 1 st partial block in workpiece image g and standard workpiece image k 0.4; Mark contrast value/>, of 1 st partial block in workpiece image g and standard workpiece image k0.5; Mark contrast value/>, of 1 st partial block in workpiece image g and standard workpiece image k0.6; Marking brightness value/>, of 2 nd partial block in workpiece image g and standard workpiece image k0.7; Mark contrast value/>, of 2 nd partial block in workpiece image g and standard workpiece image k0.8; Mark contrast value/>, of 2 nd partial block in workpiece image g and standard workpiece image k0.9; Calculating the mark similarity/>, between the workpiece image g and the standard workpiece image k=0.624;
Step S200: based on the marking similarity between the workpiece image and the standard workpiece image, performing quality evaluation on the workpiece to which the workpiece image belongs to obtain a marked workpiece, acquiring a time period in which the industrial equipment is used for processing the marked workpiece, marking the time period as a marked time period, acquiring a historical tool maintenance record of the industrial equipment, acquiring a time point when the industrial equipment stops running from the historical tool maintenance record, and screening the marked time period of the industrial equipment according to the distance between the marked time period and the time point to obtain a characteristic marked time period;
Wherein, step S200 includes:
Step S201: obtaining the mark similarity between the workpiece image and each standard workpiece image in a workpiece image database, obtaining the maximum value of the mark similarity, setting a mark similarity threshold, judging that the quality of the workpiece to which the workpiece image belongs is qualified when the maximum value of the mark similarity is more than or equal to the mark similarity threshold, and marking the workpiece to which the workpiece image belongs as a mark workpiece when the maximum value of the mark similarity is less than the mark similarity threshold;
Step S202: when the industrial equipment processes the marked workpiece, the time period of the industrial equipment is recorded as the marking time period of the industrial equipment, the historical tool maintenance record of the industrial equipment is obtained, and the time point when the industrial equipment stops running when the industrial equipment is checked is extracted from the historical tool maintenance record ;
Step S203: calculating a marking distance of a historical tool repair record and a marking periodWherein/>When a certain marking period is equal to the marking distance/>, the marking time is recorded for the industrial equipment to finish processing the workpieceMarking a certain marking period, and when the adjacent period of the marked other marking period is not the marking period, marking the other marking period as a characteristic marking period;
Step S300: shooting a cutter image of a cutter in the industrial equipment by an industrial camera in a characteristic marking period, marking the cutter image as a characteristic cutter image, and extracting image characteristics of the characteristic cutter image to obtain cutter characteristic image data of the industrial equipment;
Wherein, step S300 includes:
Step S301: when industrial equipment processes a workpiece, an industrial camera is used for shooting a cutter for processing the workpiece in the industrial equipment to obtain a cutter image, and the cutter image of the industrial equipment shot by the industrial camera in a characteristic marking period is recorded as a characteristic cutter image;
Step S302: acquiring the workpiece model of a workpiece processed by industrial equipment, collecting characteristic cutter images shot by an industrial camera when the workpiece with the same workpiece model is processed by the industrial equipment to obtain a characteristic cutter image set, acquiring cutter images of cutters in the industrial equipment when the workpiece with the same workpiece model is not processed by the industrial equipment in a marking period, and randomly selecting a plurality of cutter images from the cutter images to collect to obtain a comparison cutter image set;
Step S303: calculating the mark similarity between each cutter image in the characteristic cutter image and the contrast cutter image set, taking the mark similarity average value as the mark similarity average value between the characteristic cutter image and the contrast cutter image set, setting a mark similarity average value threshold value, and marking a certain characteristic cutter image as a target characteristic cutter image when the mark similarity average value between a certain characteristic cutter image and the contrast cutter image set is larger than the mark similarity average value threshold value;
Step S304: collecting target feature cutter images to obtain a target feature cutter image set, adjusting the image size of each target feature cutter image in the target feature cutter image set, performing gray level conversion, dividing the target feature cutter images into a plurality of pixel areas with the same pixel size, and calculating feature difference values among each feature cutter image in the target feature cutter image set, wherein the target feature cutter image s and the target feature cutter image w are calculated Characteristic difference value of individual pixel region/>:
;
Wherein,For the/>, in the target feature tool image sA gray value of a z-th pixel point in the pixel area; For the/>, in the target feature tool image w A gray value of a z-th pixel point in the pixel area; n is the/>, in the target feature tool image s and the target feature tool image wThe total number of pixel points in the pixel areas;
Step S305: calculating variances of feature differences of all pixel areas in the target feature tool image set, obtaining pixel areas with maximum variances, obtaining key pixel areas in the target feature tool image set of all workpiece types, and collecting to obtain tool feature image data of industrial equipment;
Step S400: acquiring a cutter image of industrial equipment in a current period, evaluating the use state of cutters in the industrial equipment according to cutter characteristic image data of the industrial equipment, marking the cutters in the industrial equipment, and sending a cutter maintenance prompt to prompt staff when the cutters are marked, so as to automatically monitor the industrial equipment;
Wherein, step S400 includes:
Step S401: shooting a cutter of industrial equipment in a current period by using an industrial camera to obtain a cutter image of the industrial equipment in the current period, and obtaining the model of a workpiece processed by the industrial equipment in the current period;
Step S402: extracting from cutter characteristic image data of industrial equipment, calculating the mark similarity between a cutter image and each target characteristic cutter image in the target characteristic cutter image set, and acquiring the mark similarity maximum value, judging that cutters in the industrial equipment are damaged in the current period when the mark similarity maximum value in the current period is larger than a preset threshold value, marking the damaged cutters, acquiring the areas of key pixel areas in the target characteristic image set on the marked cutters, checking preferentially, sending cutter maintenance prompts to prompt staff, and performing automatic supervision on the industrial equipment;
In order to better realize the method, the device automatic supervision system is also provided, and comprises a marking similarity module, a characteristic marking period module, a cutter characteristic image data module and an automatic supervision module;
the marking similarity module is used for calculating the marking similarity between the workpiece image and the standard workpiece image;
The characteristic marking time period module is used for screening the marking time period of the industrial equipment according to the duration of the distance between the marking time period and the time point to obtain a characteristic marking time period;
the cutter characteristic image data module is used for extracting image characteristics of the characteristic cutter image to obtain cutter characteristic image data of industrial equipment;
The automatic supervision module is used for evaluating the use state of the cutters in the industrial equipment, marking the cutters in the industrial equipment, and sending a cutter maintenance prompt to prompt staff when the cutters are marked so as to carry out automatic supervision on the industrial equipment;
The marking similarity module comprises a local block unit and a marking similarity unit;
The local block unit is used for aligning the workpiece image with the standard workpiece image and dividing the workpiece image and the marked workpiece image into a plurality of local blocks respectively;
the marking similarity unit is used for calculating the marking similarity of the workpiece image and the standard workpiece image;
the characteristic marking time period module comprises a marking workpiece unit and a characteristic marking time period unit;
the marking workpiece unit is used for acquiring marking similarity between the workpiece image and each standard workpiece image in the workpiece image database, and marking the workpiece to which the workpiece image belongs as a marking workpiece when the maximum value of the marking similarity is smaller than the marking similarity threshold;
a characteristic marking period unit configured to mark a certain marking period, and when an adjacent period of another marked marking period is not a marking period, mark the other marking period as a characteristic marking period;
the cutter characteristic image data module comprises a characteristic difference value unit and a cutter characteristic image data unit;
The characteristic difference value unit is used for calculating characteristic difference values among the characteristic cutter images in the target characteristic cutter image set;
The cutter characteristic image data unit is used for acquiring and collecting key pixel areas in the target characteristic cutter image set of each workpiece model to obtain cutter characteristic image data of industrial equipment;
The automatic supervision module comprises an automatic supervision unit;
The automatic supervision unit is used for judging the damage condition of the cutters in the industrial equipment in the current period, marking the damaged cutters, acquiring the areas of the key pixel areas in the target characteristic image set on the marked cutters, carrying out priority inspection, sending a cutter maintenance prompt to prompt staff, and carrying out automatic supervision on the industrial equipment.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A machine vision-based method of automated supervision of a device, the method comprising:
Step S100: constructing an equipment supervision cloud platform, shooting a workpiece processed by industrial equipment by using an industrial camera to obtain a workpiece image, acquiring a workpiece image database stored in the equipment supervision cloud platform in advance, extracting a plurality of standard workpiece images of the workpiece from the workpiece image database, and calculating the marking similarity between the workpiece images and the standard workpiece images;
Step S200: based on the marking similarity between the workpiece image and the standard workpiece image, carrying out quality evaluation on the workpiece to which the workpiece image belongs to obtain a marked workpiece, obtaining a time period in which the industrial equipment is used for processing the marked workpiece, marking the time period as a marked time period, extracting a time point when the industrial equipment stops running from the obtained historical tool maintenance record of the industrial equipment, calculating the marking distance between the historical tool maintenance record and the marked time period in a historical period, marking the marked time period in the historical period according to the marking distance, and marking the marked time period as a characteristic marked time period when the adjacent time period of the marked another marked time period is not the marked time period;
Step S300: shooting a cutter image of a cutter in the industrial equipment by an industrial camera in a characteristic marking period, marking the cutter image as a characteristic cutter image, and extracting image characteristics of the characteristic cutter image to obtain cutter characteristic image data of the industrial equipment;
Step S400: and acquiring a cutter image of the industrial equipment in the current period, evaluating the use state of the cutter in the industrial equipment according to the cutter characteristic image data of the industrial equipment, marking the cutter in the industrial equipment, and sending a cutter maintenance prompt to prompt staff when the cutter is marked, so as to automatically monitor the industrial equipment.
2. The machine vision-based equipment automation supervision method according to claim 1, wherein the step S100 includes:
Step S101: constructing an equipment supervision cloud platform, acquiring a workpiece image shot by an industrial camera, adjusting the image size of the workpiece image to the image size of a standard image, carrying out gray conversion on the workpiece image and the standard workpiece image, and carrying out noise removal on the workpiece image after gray conversion by using a Gaussian filter;
step S102: the method comprises the steps of obtaining gray values of pixel points in a workpiece image and a standard workpiece image, setting pixel sizes of local blocks in the workpiece image, aligning the workpiece image with the standard workpiece image, dividing the workpiece image and a marked workpiece image into a plurality of local blocks, respectively, wherein the local blocks in the workpiece image and the marked workpiece image are in one-to-one correspondence, and calculating marked brightness similarity values of the local blocks in the workpiece image and the standard workpiece image, wherein marked brightness values L a of an a-th local block in the workpiece image and the standard workpiece image are calculated:
;
wherein, The average value of gray values of an a-th local block in the workpiece image; /(I)The average value of gray values of an a-th local block in the workpiece image; /(I)For a preset mark brightness factor,/>Is a positive number;
Step S103: calculating the mark contrast value of each partial block in the workpiece image and the standard workpiece image, wherein the mark contrast value Y a of the a-th partial block in the workpiece image and the standard workpiece image:
;
wherein, The variance of gray values in an a-th local block in the workpiece image; /(I)The variance of gray values in an a-th local block in the standard workpiece image is obtained; /(I)For a preset mark contrast factor,/>Is a positive number;
Step S104: calculating the marking structure value of each local block in the workpiece image and the standard workpiece image, wherein the marking structure value X a of the a-th local block in the workpiece image and the standard workpiece image is as follows:
;
wherein, Covariance of gray values between the workpiece image and the standard workpiece image; /(I)For a preset mark structural factor,/>Is a positive number;
Step S105: calculating the mark similarity between the workpiece image and the standard workpiece image, wherein the mark similarity P g,k between the workpiece image g and the standard workpiece image k is as follows:
;
wherein, For the marked brightness value of the ith partial block in the workpiece image g and standard workpiece image k,/>The mark contrast value of the ith local block in the workpiece image g and the standard workpiece image k; /(I)Marking structure values of the ith local block in the workpiece image g and the standard workpiece image k; j is the total number of partial blocks in the workpiece image g.
3. The machine vision based equipment automation supervision method according to claim 2, wherein the step S200 includes:
Step S201: obtaining the mark similarity between the workpiece image and each standard workpiece image in a workpiece image database, obtaining the maximum value of the mark similarity, setting a mark similarity threshold, judging that the quality of the workpiece to which the workpiece image belongs is qualified when the maximum value of the mark similarity is more than or equal to the mark similarity threshold, and marking the workpiece to which the workpiece image belongs as a mark workpiece when the maximum value of the mark similarity is less than the mark similarity threshold;
Step S202: when the industrial equipment processes the marked workpiece, the time period of the industrial equipment is recorded as the marking time period of the industrial equipment, the historical tool maintenance record of the industrial equipment is obtained, and the time point when the industrial equipment stops running when the industrial equipment is checked is extracted from the historical tool maintenance record ;
Step S203: calculating a marking distance of a historical tool repair record and a marking periodWherein/>When a certain marking period in the history period is at a marking distance/>, from the history tool maintenance record, for the point of time when the industrial equipment finishes processing the workpiece in the marking period in the history periodAnd marking the certain marking time period, and marking the other marked marking time period as a characteristic marking time period when the adjacent time period of the other marked marking time period is not the marking time period.
4. A machine vision based equipment automation supervision method according to claim 3, wherein the step S300 comprises:
Step S301: when industrial equipment processes a workpiece, an industrial camera is used for shooting a cutter for processing the workpiece in the industrial equipment to obtain a cutter image, and the cutter image of the industrial equipment shot by the industrial camera in a characteristic marking period is recorded as a characteristic cutter image;
Step S302: acquiring the workpiece model of a workpiece processed by industrial equipment, collecting characteristic cutter images shot by an industrial camera when the workpiece with the same workpiece model is processed by the industrial equipment to obtain a characteristic cutter image set, acquiring cutter images of cutters in the industrial equipment when the workpiece with the same workpiece model is not processed by the industrial equipment in a marking period, and randomly selecting a plurality of cutter images from the cutter images to collect to obtain a comparison cutter image set;
Step S303: calculating the mark similarity between each cutter image in the characteristic cutter image and the contrast cutter image set, taking the mark similarity average value as the mark similarity average value between the characteristic cutter image and the contrast cutter image set, setting a mark similarity average value threshold value, and marking a certain characteristic cutter image as a target characteristic cutter image when the mark similarity average value between the certain characteristic cutter image and the contrast cutter image set is larger than the mark similarity average value threshold value;
Step S304: collecting target feature cutter images to obtain a target feature cutter image set, adjusting the image size of each target feature cutter image in the target feature cutter image set, performing gray level conversion, dividing the target feature cutter images into a plurality of pixel areas with the same pixel size, and calculating feature difference values among each feature cutter image in the target feature cutter image set, wherein the target feature cutter image s and the target feature cutter image w are calculated Characteristic difference M γ s,w for each pixel region:
;
wherein, For the/>, in the target feature tool image sA gray value of a z-th pixel point in the pixel area; /(I)For the/>, in the target feature tool image wA gray value of a z-th pixel point in the pixel area; n is the/>, in the target feature tool image s and the target feature tool image wThe total number of pixel points in the pixel areas;
Step S305: calculating variances of feature differences of all pixel areas in the target feature tool image set, acquiring pixel areas with maximum variances, acquiring key pixel areas in the target feature tool image set of all workpiece types, and collecting to obtain tool feature image data of industrial equipment.
5. The machine vision based equipment automation supervision method according to claim 4, wherein the step S400 includes:
Step S401: shooting a cutter of industrial equipment in a current period by using an industrial camera to obtain a cutter image of the industrial equipment in the current period, and obtaining the model of a workpiece processed by the industrial equipment in the current period;
Step S402: extracting from cutter characteristic image data of industrial equipment, calculating the mark similarity between a cutter image and each target characteristic cutter image in the target characteristic cutter image set, and acquiring the mark similarity maximum value, judging that cutters in the industrial equipment are damaged in the current period when the mark similarity maximum value is larger than a preset threshold value in the current period, marking the damaged cutters, acquiring the areas of key pixel areas in the target characteristic cutter image set on the marked cutters, checking preferentially, sending cutter maintenance prompts to prompt staff, and performing automatic supervision on the industrial equipment.
6. An equipment automation supervision system applying the equipment automation supervision method based on machine vision as set forth in any one of claims 4-5, wherein the equipment automation supervision system includes a marker similarity module, a feature marker period module, a cutter feature image data module, and an automation supervision module;
the marking similarity module is used for calculating the marking similarity between the workpiece image and the standard workpiece image;
the characteristic marking time period module is used for screening the marking time period of the industrial equipment according to the distance duration between the marking time period and the time point to obtain the characteristic marking time period;
The cutter characteristic image data module is used for extracting image characteristics of the characteristic cutter image to obtain cutter characteristic image data of industrial equipment;
the automatic supervision module is used for evaluating the use state of the cutters in the industrial equipment, marking the cutters in the industrial equipment, and sending a cutter maintenance prompt to prompt staff when the cutters are marked so as to carry out automatic supervision on the industrial equipment.
7. The device automated supervisory system according to claim 6, wherein the tag similarity module comprises a local block unit, a tag similarity unit;
The local block unit is used for aligning the workpiece image with the standard workpiece image and dividing the workpiece image and the marked workpiece image into a plurality of local blocks respectively;
The marking similarity unit is used for calculating the marking similarity of the workpiece image and the standard workpiece image.
8. The device automated supervisory system of claim 6, wherein the signature period module comprises a signature workpiece unit, a signature period unit;
The marking workpiece unit is used for acquiring the marking similarity between the workpiece image and each standard workpiece image in the workpiece image database, and marking the workpiece to which the workpiece image belongs as a marking workpiece when the maximum value of the marking similarity is smaller than a marking similarity threshold;
The characteristic marking time period unit is used for marking the certain marking time period, and when the adjacent time period of the marked other marking time period is not the marking time period, the other marking time period is marked as the characteristic marking time period.
9. The equipment automated supervisory system according to claim 6, wherein the tool feature image data module comprises a feature difference unit, a tool feature image data unit;
The characteristic difference unit is used for calculating characteristic differences among all characteristic cutter images in the target characteristic cutter image set;
the cutter characteristic image data unit is used for acquiring and collecting key pixel areas in the target characteristic cutter image set of each workpiece model to obtain cutter characteristic image data of industrial equipment.
10. The device automated supervisory system of claim 6, wherein the automated supervisory module comprises an automated supervisory unit;
The automatic supervision unit is used for judging the damage condition of the cutters in the industrial equipment in the current period, marking the damaged cutters, acquiring the areas of the key pixel areas in the target characteristic cutter image set on the marked cutters, carrying out priority inspection, sending cutter maintenance prompts to prompt staff, and carrying out automatic supervision on the industrial equipment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410316387.5A CN117911415B (en) | 2024-03-20 | 2024-03-20 | Automatic equipment supervision system and method based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410316387.5A CN117911415B (en) | 2024-03-20 | 2024-03-20 | Automatic equipment supervision system and method based on machine vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117911415A true CN117911415A (en) | 2024-04-19 |
CN117911415B CN117911415B (en) | 2024-05-24 |
Family
ID=90686233
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410316387.5A Active CN117911415B (en) | 2024-03-20 | 2024-03-20 | Automatic equipment supervision system and method based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117911415B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108527004A (en) * | 2018-03-29 | 2018-09-14 | 蚌埠市金洋机床有限责任公司 | A kind of cutting tool for CNC machine breakage detection system |
CN113076935A (en) * | 2021-04-29 | 2021-07-06 | 平安国际智慧城市科技股份有限公司 | Supervision method based on image recognition, related equipment and storage medium |
US20210319250A1 (en) * | 2020-04-09 | 2021-10-14 | Sensetime International Pte. Ltd. | Matching method and apparatus, electronic device, computer-readable storage medium, and computer program |
CN113608482A (en) * | 2021-08-13 | 2021-11-05 | 重庆允成互联网科技有限公司 | Intelligent monitoring method, system and management system for precision machining tool |
EP4009038A1 (en) * | 2019-09-10 | 2022-06-08 | Siemens Energy Global GmbH & Co. KG | Method and device for detecting mechanical equipment parts |
US20230063002A1 (en) * | 2021-08-25 | 2023-03-02 | Genpact Luxembourg S.à r.l. II | Dimension estimation using duplicate instance identification in a multiview and multiscale system |
JP2023046777A (en) * | 2021-09-24 | 2023-04-05 | Assest株式会社 | Equipment maintenance inspection system |
CN117520785A (en) * | 2023-12-21 | 2024-02-06 | 工品行(苏州)数字科技有限公司 | Industrial intelligent decision support system and method based on big data analysis |
-
2024
- 2024-03-20 CN CN202410316387.5A patent/CN117911415B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108527004A (en) * | 2018-03-29 | 2018-09-14 | 蚌埠市金洋机床有限责任公司 | A kind of cutting tool for CNC machine breakage detection system |
EP4009038A1 (en) * | 2019-09-10 | 2022-06-08 | Siemens Energy Global GmbH & Co. KG | Method and device for detecting mechanical equipment parts |
US20210319250A1 (en) * | 2020-04-09 | 2021-10-14 | Sensetime International Pte. Ltd. | Matching method and apparatus, electronic device, computer-readable storage medium, and computer program |
CN113076935A (en) * | 2021-04-29 | 2021-07-06 | 平安国际智慧城市科技股份有限公司 | Supervision method based on image recognition, related equipment and storage medium |
CN113608482A (en) * | 2021-08-13 | 2021-11-05 | 重庆允成互联网科技有限公司 | Intelligent monitoring method, system and management system for precision machining tool |
US20230063002A1 (en) * | 2021-08-25 | 2023-03-02 | Genpact Luxembourg S.à r.l. II | Dimension estimation using duplicate instance identification in a multiview and multiscale system |
JP2023046777A (en) * | 2021-09-24 | 2023-04-05 | Assest株式会社 | Equipment maintenance inspection system |
CN117520785A (en) * | 2023-12-21 | 2024-02-06 | 工品行(苏州)数字科技有限公司 | Industrial intelligent decision support system and method based on big data analysis |
Non-Patent Citations (2)
Title |
---|
HAICHENG YU ET AL.: "An Improved Tool Wear Monitoring Method Using Local Image and Fractal Dimension of Workpiece", pages 1 - 11, Retrieved from the Internet <URL:https://doi.org/10.1155/2021/9913581> * |
济南孚芯通: "基于工件表面图像的刀具磨损状态监测", pages 1 - 79, Retrieved from the Internet <URL:https://www.docin.com/p-1545589628.html> * |
Also Published As
Publication number | Publication date |
---|---|
CN117911415B (en) | 2024-05-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115293463B (en) | Glass lens processing supervision method and system based on cutting quality prediction | |
CN116428984A (en) | Hardware mould stamping processing intelligent detection system | |
CN113269042B (en) | Intelligent traffic management method and system based on driving vehicle violation identification | |
CN116308300B (en) | Power equipment state monitoring evaluation and command method and system | |
US11682112B2 (en) | Inspection device and machine learning method | |
CN112985515B (en) | Method and system for detecting assembly qualification of product fastener and storage medium | |
CN117314921B (en) | RFID-based starting point detection and treatment method for track inspection equipment | |
CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
CN117911415B (en) | Automatic equipment supervision system and method based on machine vision | |
CN117664480A (en) | Bridge health monitoring system and method | |
CN116344378B (en) | Intelligent detection system for photovoltaic panel production and detection method thereof | |
CN115587978B (en) | Floor leather laminating embossing on-line measuring system based on degree of depth study | |
CN114192583B (en) | Scada platform-based strip steel rolling process quality monitoring method and system | |
CN108181315B (en) | Image processing-based biscuit damage detection device and detection method | |
CN114463293A (en) | Steel structure quality wireless detection and analysis method and system based on image processing technology | |
CN116088454B (en) | Intelligent manufacturing management system based on data fusion | |
CN118275451B (en) | Printed circuit board defect detection system and method based on visual detection | |
CN116630316B (en) | Belt fatigue detection alarm method and alarm system based on video analysis | |
CN117607019B (en) | Intelligent detection method and detection system for electric power fitting surface | |
CN118101899A (en) | Intelligent analysis management method and system for security monitoring storage information | |
CN114969468A (en) | Semiconductor FDC data classification method, apparatus and computer readable storage medium | |
CN118275451A (en) | Printed circuit board defect detection system and method based on visual detection | |
CN118261889A (en) | Unmanned aerial vehicle image-based power line defect data processing method and system | |
CN117875556A (en) | High-accuracy AI pipeline defect degree quantitative analysis system and method | |
CN113379073A (en) | Defective product statistical management method and system |
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 |