CN110111303A - A kind of large-scale carrier strip tearing intelligent fault detection method based on dynamic image - Google Patents
A kind of large-scale carrier strip tearing intelligent fault detection method based on dynamic image Download PDFInfo
- Publication number
- CN110111303A CN110111303A CN201910268327.XA CN201910268327A CN110111303A CN 110111303 A CN110111303 A CN 110111303A CN 201910268327 A CN201910268327 A CN 201910268327A CN 110111303 A CN110111303 A CN 110111303A
- Authority
- CN
- China
- Prior art keywords
- image
- belt
- tearing
- carrier strip
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000009434 installation Methods 0.000 claims abstract description 13
- 239000000284 extract Substances 0.000 claims abstract description 4
- 230000009466 transformation Effects 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000003709 image segmentation Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 239000003086 colorant Substances 0.000 claims description 3
- 230000001788 irregular Effects 0.000 claims description 3
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 210000001367 artery Anatomy 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 238000004080 punching Methods 0.000 claims 1
- 210000003462 vein Anatomy 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 description 7
- 239000003245 coal Substances 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000012535 impurity Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 229920002379 silicone rubber Polymers 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003760 hair shine Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The present invention relates to a kind of, and the large-scale carrier strip based on dynamic image tears intelligent fault detection method, comprising: step 1 is directed to large-scale carrier strip transportation system, determines the installation site of intelligent high-speed industrial camera；Step 2 pre-processes the belt operation image of camera acquisition；Step 3 is split belt tearing image；Step 4 extracts belt tearing image features；Step 5, the connected domain area for calculating belt tearing image, fault level division is carried out according to the belt tearing area of industry spot, obtains the threshold value of belt tearing, and, whenCorresponding to the practical tearing area of carrier strip is, it is determined as secondary failure；WhenThe corresponding practical tearing area of carrier strip is greater than, it is determined as level fault.Determine the tearing area and tearing fault level of belt.Compared with prior art, the present invention has many advantages, such as detection accuracy height, strong real-time, is not necessarily to manual intervention.
Description
Technical field
The present invention relates to automatic industrial manufacturing line large size carrier strip device intelligence detection fields, more particularly, to one kind
Large-scale carrier strip based on dynamic image tears intelligent fault detection method.
Background technique
Carrier strip is widely used in industrial circles such as coal production, metallurgy, by often adulterating in institute's transported material
Various sharp impurity, and these impurity can cause to damage to belt.Gently it will cause belt torn edges, Steel cord be broken, it is heavy then
It will cause belt transverse breakage, the even longitudinal tear of long range, seriously reduce the service life of carrier strip.
It is all based on the touch switch detection method of mechanical conductive silicon rubber item greatly to the tearing detection of belt at present,
On the one hand the position of detection physical equipment installation is fixed, tear the physical unit of detection after a period of operation can because collision,
It wears and damages, the accuracy decline of detection, stability is poor.On the other hand, when touching conductive silicon rubber by foreign matter, detection
Switch makes movement, and the detection accuracy for issuing tearing signal is low, and physical unit involves great expense, cannot be in real time to the tear face of belt
Product carries out quantitative detection.Therefore, the research of belt tearing fault detection method problem is very valuable and urgently to be resolved.
Machine vision technique has non-contact, and detection speed is fast, and detection accuracy is high, the objective reliable advantage of testing result,
Matching suitable intelligent measurement algorithm can rapidly and accurately detect whether carrier strip occurs to tear failure.Machine vision is very
More detection fields have application, and also having still most of using precedent in belt tearing detection field is to belt longitudinal tear
Situation is studied, and belt imaging system is designed, and the number of the discontinuity point in detection image is former to discriminate whether to occur to tear
Hinder (such as patent CN105293002A).Method used by this detection means is coarse, detection accuracy is low, and imaging system design
Complexity, the detection computation complexity for carrying out processing and moving object failure to dynamic image is higher, and time-consuming, is difficult to meet industry
Fault in production news speed detection, the target quickly excluded, especially in coal production line, carrier strip extremely closes the transport of coal mine
It is important, how to realize fast and accurately whether carrier strip occurs to tear the phase that fault detection is production technician's many years
Expect.
Summary of the invention
The object of the invention is to provide a kind of based on dynamic image to overcome the problems of the above-mentioned prior art
Large-scale carrier strip tear intelligent fault detection method, it is fast that this method detects speed than existing methods, and detection accuracy is high, does not have to
The advantages that manual intervention.
In order to achieve the above objectives, insight of the invention is that
This method is installed to the station to be detected on coal mine material transportation production line using high-speed industrial smart camera, utilizes
Special light source illuminates the hypodermis zone face of belt station to be measured, carrier strip operation image information is acquired, to the image information of acquisition
Carry out online processing in real time.Key of the invention is the fast algorithm detected to belt tearing failure, to belt surface figure
As the intelligent measurement algorithm handled includes belt tearing image preprocessing, belt tearing image segmentation, belt tearing image
Characteristic parameter extraction and tearing connected domain areal calculation etc..The high-speed industrial smart camera in ray image processing system to institute
Fault message is exported after stating belt surface image procossing, host computer interface is transferred to and carries out Dynamically Announce.The high-speed industrial intelligence
Energy camera is monochromatic or colored planar array scanning high-speed industrial camera, and the high-speed industrial can be attached to existing coal according to smart camera
Mineral material transport production line is attached on the dedicated assembly line of belt failure detection, and installation site is can be to belt edge and belt
The workshop section position that frame image is conveniently taken pictures.The special light source is annular LED light source, is provided for the high-speed industrial smart camera
Illumination.The high-speed industrial intelligently shines the surface that machine is located at the special light source, the camera lens of the high-speed industrial smart camera
It finds a view by the way that the annular of the special light source is intermediate.The host computer interface includes industrial computer and belt tearing malfunction monitoring
Software.
According to above-mentioned design, the present invention adopts the following technical scheme:
A kind of large-scale carrier strip tearing intelligent fault detection method based on dynamic image, for obtaining carrier strip fortune
The tearing area and fault level of belt in autocontrol system, the method the following steps are included:
Step 1 is directed to large-scale carrier strip operating system, determines the installation site of high-speed industrial camera, and acquire belt
Face image；
Step 2 pre-processes the carrier strip face image of acquisition, by image gray processing and image denoising；
Pretreated belt tearing image is split by step 3, and fracture image is further analyzed and handled；
Step 4 extracts the characteristic parameter in belt tearing face；
Step 5, the area S for calculating belt tearing determine the tearing area and tearing fault level of belt.
The step 1 specifically includes the following steps:
Step 1.1 tracks large-scale carrier strip operating status, records related data, analyzes large-scale carrier strip
The station to be detected of suitable high-speed industrial camera installation is nearby found in the position easily torn in the position；
Step 1.2, installation high-speed industrial camera, adjust the focal length of camera, find the best mirror of camera shooting carrier strip
Head parameter setting, and acquire strap surface image.
The step 2 specifically includes the following steps:
Step 2.1, the image acquired for the camera are pre-processed, and the image of rgb format is converted to grayscale image
Picture；
After step 2.2, identification belt crack, gradation conversion, image grayscale conversion formula are carried out to strap surface image are as follows:
H (i, j)=0.1250R (i, j)+0.7154G (i, j)+0.0721B (i, j)
In above formula: h (i, j) is the gray value of the i-th row jth column in gray level image；R (i, j), G (i, j), B (i, j) is respectively
For the component value of 3 kinds of basic colors of red, green, blue in original carrier strip color image；
Step 2.3 protrudes strap surface image crack using " linear gradation transformation ", if I is belt image slices before converting
Element, I ' are " linear gradation transformation " treated belt image pixel, and set convert before belt image gray scale value model
It encloses for [Imin,Imax], the gray value value range of " linear gradation transformation " treated belt image is [fmin,fmax], specifically
Tuning function are as follows:
Step 2.4 is handled carrier strip image using median filtering algorithm, filters out the noise of image, is eliminated outer
The interference of boundary's pulse, the output description of median filtering are as follows:
The step 3 specifically includes the following steps:
Step 3.1 is split belt crack image using thresholding method, determines image segmentation threshold；Using most
Big Ostu method calculates threshold value, and the gray scale of belt crack image is divided into C grade, the pixel that gray value is c
Number is n, then has total number of pixels N=n0+n1+…+nc, ratio shared by each pixel value is Pi=ni/N；If strap surface image
Segmentation threshold be ξ, divided by the set of pixels of bound pair image of ξ, be divided into C0And C1Two major classes, then C0=0,1,2 ...,
ξ }, C1=ξ+1, ξ+2 ..., C-1 }；
Step 3.2 calculates belt crack image gray average, carrier strip face image overall intensity mean value are as follows:
P (c) is ratio shared by each pixel in formula.
The step 4 specifically includes the following steps:
The characteristic parameter extraction of step 4.1, belt tearing image, the calculating of picture break-up linear degree: linear calculating
When fracture length, the skeleton of linear fractures is first extracted, after skeletal extraction, linear fractures are refined as single pixel wide, it is then right
The number of white pixel is counted, and the linear fractures length indicated by pixel number is calculated, further according to smart camera
Resolution ratio demarcates real image, the linear fractures length that each pixel number indicates in image is calculated, then by i and meter
The pixel number of calculating, which is multiplied, finds out the physical length in crack, the i.e. physical length of linear fractures are as follows:
L=num (white pixel point number) × i (conversion coefficient)
Step 4.2, the mean breadth for calculating strap surface picture break-up: assuming that each pixel in the image of belt crack
The real area size represented is S*, number of pixels shared by crack is B, then the gross area in belt crack is A=S*× B, is split
After stitching the gross area and tearing length, then its crack mean breadth is W=A/L.
The step 5 specifically includes the following steps:
Step 5.1 calculates irregular belt flaw area, obtains in the image of crack in white pixel point ordinate most
Greatly, minimum value is respectively ymax,ymin, maximum, the minimum value of the abscissa in white pixel point are respectively xmax,xmin, then deliver
The area of belt tearing are as follows:
S=(ymax-ymin)×(xmax-xmin)
Step 5.2 carries out fault level division according to the belt tearing area of industry spot, obtains belt tearing area
Threshold value S1、S2, and S1<S2, wherein S1<S≤S2The corresponding practical tearing area of carrier strip is S3~S4, it is determined as secondary failure；When
S>S2The corresponding practical tearing area of carrier strip is greater than S4, it is determined as level fault, so that it is determined that the tearing area of belt and tearing
Fault level.
Compared with prior art, the invention has the following advantages that
1, it is easily achieved, does not need manual intervention, real time automatic detection failure.
2, belt tearing fault detection speed is fast and precision is high.
3, the real-time diagnosis of belt tearing On-line Fault, fault message interface Dynamically Announce can be achieved.
4, tearing fault diagnosis can be carried out to large-scale carrier strip operating system, find failure in time, deliver skin to repair
Band provides reference.
Detailed description of the invention
Fig. 1 is the flow chart of the method for the present invention；
Fig. 2 is the smart camera installation site and large size carrier strip schematic diagram of the embodiment of the present invention；
Fig. 3 is that the large-scale carrier strip of the embodiment of the present invention tears figure；
Fig. 4 is that the large-scale carrier strip of the embodiment of the present invention tears fault diagnosis interface.
Specific embodiment
Technical scheme in the embodiment of the invention is clearly and completely described with reference to the accompanying drawing.
As shown in Figure 1, the large-scale carrier strip based on dynamic image tears intelligent fault detection method, for being delivered
The tearing area and fault level of belt in belt movement control system, the method the following steps are included:
Step 1 is directed to large-scale carrier strip operating system, determines the installation site of high-speed industrial camera, and acquire belt
Face image；Specific steps are as follows:
Step 1.1 tracks large-scale carrier strip operating status, records related data, and large-scale fortune is found after analysis
The position that belt is easily torn is carried, nearby finds the station to be detected of suitable camera installation in the position；
Step 1.2, as shown in Fig. 2, determine in three whole L meters of large-scale carrier strip tail, weight, head station intelligence
The installation site of energy camera, adjusts the focal length of camera, finds the optimum lens of smart camera shooting carrier strip.
Step 2 pre-processes the carrier strip face image of acquisition, by image gray processing and image denoising；Specific step
Suddenly are as follows:
Step 2.1, for camera acquisition image carry out pretreatment be that the image of rgb format is converted into gray level image；
Start to carry out gradation conversion, image grayscale conversion formula to strap surface image after step 2.2, identification belt crack
Are as follows:
H (i, j)=0.1250R (i, j)+0.7154G (i, j)+0.0721B (i, j)
In above formula: h (i, j) is the gray value of the i-th row jth column in gray level image；R (i, j), G (i, j), B (i, j) is respectively
For the component value of 3 kinds of basic colors of red, green, blue in original carrier strip color image.
Step 2.3 is easy to be stained by sports belt noise, coal mine material when shooting carrier strip image
The influence of external factor causes belt crack image the gray areas of partial invalidity or part nothing occur after completing transformation
The image of effect.In order to improve the tearing detection effect of strap surface, need to handle these invalid images and gray areas,
Form sharpness of border, apparent image is distinguished in crack.Using " linear gradation transformation " prominent strap surface image crack, if I is to become
Alternatively preceding belt image pixel, I ' are " linear gradation transformation " treated belt image pixel, and set convert before belt
The gray scale value range of image is [Imin,Imax], the gray value value range of " linear gradation transformation " treated belt image
For [fmin,fmax], specific Tuning function are as follows:
Step 2.4 is handled carrier strip image using median filtering algorithm, can efficiently filter out making an uproar for image
Sound eliminates the interference of extraneous pulse, and the output of median filtering can be described as:
Pretreated belt tearing image is split by step 3, and fracture image is further analyzed and handled；Tool
Steps are as follows for body:
Step 3.1 is split belt crack image using thresholding method, determines image segmentation threshold.Using most
Big Ostu method calculates threshold value, and the gray scale of belt crack image is divided into C grade, the pixel that gray value is c
Number is n, then has total number of pixels N=n0+n1+…+nc, ratio shared by each pixel value is Pi=ni/N.If strap surface image
Segmentation threshold be ξ, divided by the set of pixels of bound pair image of ξ, be divided into C0And C1Two major classes, then C0=0,1,2 ...,
ξ }, C1=ξ+1, ξ+2 ..., C-1 }；
Step 3.2 calculates belt crack image gray average.Carrier strip face image overall intensity mean value are as follows:
P (c) is ratio shared by each pixel in formula.
Step 4 extracts the characteristic parameter in belt tearing face, such as the length computation of belt tearing, the average width in crack
The calculating etc. of degree；Specific step is as follows:
The characteristic parameter extraction of step 4.1, belt tearing image.The calculating of picture break-up linear degree.In the present embodiment,
The tearing image of large-scale carrier strip is as shown in Figure 3.When calculating linear fractures length, the skeleton of linear fractures is first extracted,
After skeletal extraction, linear fractures are refined as single pixel wide, then the number of white pixel is counted, is calculated by pixel
The linear fractures length that point number indicates is demarcated real image further according to the resolution ratio of smart camera, is calculated in image every
I, is then multiplied with calculated pixel number and finds out the reality in crack by the linear fractures length that a pixel number indicates
Length, the i.e. physical length of linear fractures are as follows:
L=num (white pixel point number) × i (conversion coefficient)
Step 4.2, the mean breadth for calculating strap surface picture break-up.Assuming that each pixel in the image of belt crack
The real area size represented is S*, number of pixels shared by crack is B, then the gross area in belt crack is A=S*×B.It is split
After stitching the gross area and tearing length, then its crack mean breadth is W=A/L.
Step 5, the area S for calculating belt tearing determine the tearing area and tearing fault level of belt；Specific steps are such as
Under:
Step 5.1 calculates irregular belt flaw area, obtains in the image of crack in white pixel point ordinate most
Greatly, minimum value is respectively ymax,ymin, maximum, the minimum value of the abscissa in white pixel point are respectively xmax,xmin, then deliver
The area of belt tearing are as follows:
S=(ymax-ymin)×(xmax-xmin)
Step 5.2 carries out fault level division according to the belt tearing area of industry spot, obtains belt tearing area
Threshold value S1、S2, and S1<S2, wherein S1<S≤S2The corresponding practical tearing area of carrier strip is S3~S4, it is determined as secondary failure；When
S>S2The corresponding practical tearing area of carrier strip is greater than S4, it is determined as level fault, so that it is determined that the tearing area of belt and tearing
Fault level.The present embodiment medium-and-large-sized carrier strip tearing fault diagnosis interface is as shown in Figure 4.
So far, it is completed from step 1 to step 5 and the failure of large-scale carrier strip tearing area and tearing grade is examined
It is disconnected.
Claims (6)
1. a kind of large-scale carrier strip based on dynamic image tears intelligent fault detection method, for obtaining carrier strip movement
The tearing area and fault level of belt in control system, which is characterized in that the method the following steps are included:
Step 1 is directed to large-scale carrier strip operating system, determines the installation site of high-speed industrial camera, and acquire strap surface figure
Picture；
Step 2 pre-processes the carrier strip face image of acquisition, by image gray processing and image denoising；
Pretreated belt tearing image is split by step 3, and fracture image is further analyzed and handled；
Step 4 extracts the characteristic parameter in belt tearing face；
Step 5, the area S for calculating belt tearing determine the tearing area and tearing fault level of belt.
2. the large-scale carrier strip according to claim 1 based on dynamic image tears intelligent fault detection method, special
Sign is, the step 1 specifically includes the following steps:
Step 1.1 tracks large-scale carrier strip operating status, records related data, analyzes large-scale carrier strip and easily sends out
The station to be detected of suitable high-speed industrial camera installation is nearby found in the position of raw tearing in the position；
Step 1.2, installation high-speed industrial camera, adjust the focal length of camera, find the optimum lens ginseng of camera shooting carrier strip
Number setting, and acquire strap surface image.
3. the large-scale carrier strip according to claim 1 based on dynamic image tears intelligent fault detection method, special
Sign is, the step 2 specifically includes the following steps:
Step 2.1, the image acquired for the camera are pre-processed, and the image of rgb format is converted to gray level image；
After step 2.2, identification belt crack, gradation conversion, image grayscale conversion formula are carried out to strap surface image are as follows:
H (i, j)=0.1250R (i, j)+0.7154G (i, j)+0.0721B (i, j)
In above formula: h (i, j) is the gray value of the i-th row jth column in gray level image；R (i, j), G (i, j), B (i, j) are respectively original
The component value of 3 kinds of basic colors of red, green, blue in beginning carrier strip color image；
Step 2.3 protrudes strap surface image crack using " linear gradation transformation ", if I is belt image pixel before converting, I '
For " linear gradation transformation " treated belt image pixel, and set the gray scale value range of belt image before transformation as
[Imin,Imax], the gray value value range of " linear gradation transformation " treated belt image is [fmin,fmax], it is specific to adjust
Function are as follows:
Step 2.4 is handled carrier strip image using median filtering algorithm, filters out the noise of image, eliminates extraneous arteries and veins
The interference of punching, the output description of median filtering are as follows:
4. the large-scale carrier strip according to claim 1 based on dynamic image tears intelligent fault detection method, special
Sign is, the step 3 specifically includes the following steps:
Step 3.1 is split belt crack image using thresholding method, determines image segmentation threshold；Using maximum kind
Between variance method threshold value is calculated, the gray scale of belt crack image is divided into C grade, the number of pixels that gray value is c is
N then has total number of pixels N=n0+n1+…+nc, ratio shared by each pixel value is Pi=ni/N；If point of strap surface image
Cutting threshold value is ξ, is divided by the set of pixels of bound pair image of ξ, is divided into C0And C1Two major classes, then C0={ 0,1,2 ..., ξ }, C1
=ξ+1, ξ+2 ..., C-1 }；
Step 3.2 calculates belt crack image gray average, carrier strip face image overall intensity mean value are as follows:
P (c) is ratio shared by each pixel in formula.
5. the large-scale carrier strip according to claim 1 based on dynamic image tears intelligent fault detection method, special
Sign is, the step 4 specifically includes the following steps:
The calculating of picture break-up linear degree: the characteristic parameter extraction of step 4.1, belt tearing image is calculating linear fractures
When length, the skeleton of linear fractures is first extracted, after skeletal extraction, linear fractures are refined as single pixel wide, then dialogue picture
The number of element is counted, and the linear fractures length indicated by pixel number is calculated, further according to the resolution of smart camera
Rate demarcates real image, and the linear fractures length that each pixel number indicates in image is calculated, and then by i and calculates
Pixel number be multiplied and find out the physical length in crack, i.e. the physical length of linear fractures are as follows:
L=num (white pixel point number) × i (conversion coefficient)
Step 4.2, the mean breadth for calculating strap surface picture break-up: assuming that each pixel in the image of belt crack represents
Real area size be S*, number of pixels shared by crack is B, then the gross area in belt crack is A=S*It is total to obtain crack by × B
After area and tearing length, then its crack mean breadth is W=A/L.
6. the large-scale carrier strip according to claim 1 based on dynamic image tears intelligent fault detection method, special
Sign is, the step 5 specifically includes the following steps:
Step 5.1 calculates irregular belt flaw area, obtains in the image of crack the maximum of ordinate in white pixel point, most
Small value is respectively ymax,ymin, maximum, the minimum value of the abscissa in white pixel point are respectively xmax,xmin, then carrier strip is torn
The area split are as follows:
S=(ymax-ymin)×(xmax-xmin)
Step 5.2 carries out fault level division according to the belt tearing area of industry spot, obtains the threshold value of belt tearing area
S1、S2, and S1<S2, wherein S1<S≤S2The corresponding practical tearing area of carrier strip is S3~S4, it is determined as secondary failure；Work as S > S2
The corresponding practical tearing area of carrier strip is greater than S4, it is determined as level fault, so that it is determined that the tearing area of belt and tearing event
Hinder grade.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910268327.XA CN110111303A (en) | 2019-04-04 | 2019-04-04 | A kind of large-scale carrier strip tearing intelligent fault detection method based on dynamic image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910268327.XA CN110111303A (en) | 2019-04-04 | 2019-04-04 | A kind of large-scale carrier strip tearing intelligent fault detection method based on dynamic image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110111303A true CN110111303A (en) | 2019-08-09 |
Family
ID=67485071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910268327.XA Pending CN110111303A (en) | 2019-04-04 | 2019-04-04 | A kind of large-scale carrier strip tearing intelligent fault detection method based on dynamic image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110111303A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992323A (en) * | 2019-11-26 | 2020-04-10 | 中冶赛迪重庆信息技术有限公司 | Steel strip detection method and device based on image processing and steel clamping detection method |
| CN111223094A (en) * | 2020-03-13 | 2020-06-02 | 中冶长天国际工程有限责任公司 | Method and system for detecting spacing between trolley grates of sintering machine |
| CN111223095A (en) * | 2020-03-13 | 2020-06-02 | 中冶长天国际工程有限责任公司 | Method and system for detecting spacing between trolley grates of sintering machine |
| CN111591715A (en) * | 2020-05-28 | 2020-08-28 | 华中科技大学 | Belt longitudinal tearing detection method and device |
| CN111646146A (en) * | 2020-05-14 | 2020-09-11 | 精英数智科技股份有限公司 | Intelligent belt tearing detection method and device |
| CN111754466A (en) * | 2020-06-08 | 2020-10-09 | 西安电子科技大学 | Intelligent detection method for belt damage condition of conveyor |
| CN113724258A (en) * | 2021-11-02 | 2021-11-30 | 山东中都机器有限公司 | Conveyor belt tearing detection method and system based on image processing |
| CN113998415A (en) * | 2021-11-04 | 2022-02-01 | 凌云光技术股份有限公司 | Machine vision-based longitudinal tear detection method and device for conveying belt |
| CN114002228A (en) * | 2021-11-05 | 2022-02-01 | 华能国际电力股份有限公司上海石洞口第二电厂 | Belt crack detection method based on image recognition |
| CN114348581A (en) * | 2022-01-29 | 2022-04-15 | 山东省科学院激光研究所 | Belt tearing detection method and system |
| CN115159027A (en) * | 2022-07-22 | 2022-10-11 | 山东省科学院激光研究所 | Belt tearing monitoring method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002252764A (en) * | 2001-02-26 | 2002-09-06 | Matsushita Graphic Communication Systems Inc | Image processor and image processing method |
| JP2012002531A (en) * | 2010-06-14 | 2012-01-05 | Taisei Corp | Crack detection method |
| CN103387123A (en) * | 2012-05-09 | 2013-11-13 | 刘晓奇 | Mine adhesive tape tearing intelligent detecting system based on machine vision |
| CN107240079A (en) * | 2017-06-09 | 2017-10-10 | 南京理工大学 | A kind of road surface crack detection method based on image procossing |
-
2019
- 2019-04-04 CN CN201910268327.XA patent/CN110111303A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002252764A (en) * | 2001-02-26 | 2002-09-06 | Matsushita Graphic Communication Systems Inc | Image processor and image processing method |
| JP2012002531A (en) * | 2010-06-14 | 2012-01-05 | Taisei Corp | Crack detection method |
| CN103387123A (en) * | 2012-05-09 | 2013-11-13 | 刘晓奇 | Mine adhesive tape tearing intelligent detecting system based on machine vision |
| CN107240079A (en) * | 2017-06-09 | 2017-10-10 | 南京理工大学 | A kind of road surface crack detection method based on image procossing |
Non-Patent Citations (2)
| Title |
|---|
| 张磊: "基于图像处理的公路路面裂缝检测技术研究", 《机械设计与制造工程》 * |
| 王志星: "输送带纵向撕裂双目视觉在线检测系统研究与设计", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992323B (en) * | 2019-11-26 | 2023-05-12 | 中冶赛迪信息技术(重庆)有限公司 | Steel strip detection method and device based on image processing and steel clamping detection method |
| CN110992323A (en) * | 2019-11-26 | 2020-04-10 | 中冶赛迪重庆信息技术有限公司 | Steel strip detection method and device based on image processing and steel clamping detection method |
| CN111223094A (en) * | 2020-03-13 | 2020-06-02 | 中冶长天国际工程有限责任公司 | Method and system for detecting spacing between trolley grates of sintering machine |
| CN111223095A (en) * | 2020-03-13 | 2020-06-02 | 中冶长天国际工程有限责任公司 | Method and system for detecting spacing between trolley grates of sintering machine |
| CN111223095B (en) * | 2020-03-13 | 2024-03-12 | 中冶长天国际工程有限责任公司 | Trolley grate spacing detection method and system for sintering machine |
| CN111223094B (en) * | 2020-03-13 | 2024-03-12 | 中冶长天国际工程有限责任公司 | Trolley grate spacing detection method and system for sintering machine |
| CN111646146B (en) * | 2020-05-14 | 2021-03-02 | 精英数智科技股份有限公司 | Intelligent belt tearing detection method and device |
| CN111646146A (en) * | 2020-05-14 | 2020-09-11 | 精英数智科技股份有限公司 | Intelligent belt tearing detection method and device |
| CN111591715A (en) * | 2020-05-28 | 2020-08-28 | 华中科技大学 | Belt longitudinal tearing detection method and device |
| CN111754466A (en) * | 2020-06-08 | 2020-10-09 | 西安电子科技大学 | Intelligent detection method for belt damage condition of conveyor |
| CN111754466B (en) * | 2020-06-08 | 2023-07-28 | 西安电子科技大学 | Intelligent detection method for damage condition of conveyor belt |
| CN113724258A (en) * | 2021-11-02 | 2021-11-30 | 山东中都机器有限公司 | Conveyor belt tearing detection method and system based on image processing |
| CN113724258B (en) * | 2021-11-02 | 2022-02-08 | 山东中都机器有限公司 | Conveyor belt tearing detection method and system based on image processing |
| CN113998415A (en) * | 2021-11-04 | 2022-02-01 | 凌云光技术股份有限公司 | Machine vision-based longitudinal tear detection method and device for conveying belt |
| CN114002228A (en) * | 2021-11-05 | 2022-02-01 | 华能国际电力股份有限公司上海石洞口第二电厂 | Belt crack detection method based on image recognition |
| CN114348581A (en) * | 2022-01-29 | 2022-04-15 | 山东省科学院激光研究所 | Belt tearing detection method and system |
| CN114348581B (en) * | 2022-01-29 | 2024-04-12 | 山东省科学院激光研究所 | Belt tearing detection method and system |
| CN115159027A (en) * | 2022-07-22 | 2022-10-11 | 山东省科学院激光研究所 | Belt tearing monitoring method |
| CN115159027B (en) * | 2022-07-22 | 2024-03-22 | 山东省科学院激光研究所 | Belt tearing monitoring method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110111303A (en) | A kind of large-scale carrier strip tearing intelligent fault detection method based on dynamic image | |
| CN102495069B (en) | Method for detecting defects of chain belts of zipper on basis of digital image processing | |
| CN109490316B (en) | Surface defect detection algorithm based on machine vision | |
| Yang et al. | On-line conveyor belts inspection based on machine vision | |
| CN104914111B (en) | A kind of steel strip surface defect online intelligent recognition detecting system and its detection method | |
| CN101893580B (en) | Digital image based detection method of surface flaw of steel rail | |
| CN106093066A (en) | A kind of magnetic tile surface defect detection method based on the machine vision attention mechanism improved | |
| CN104608799A (en) | Information fusion technology based train wheel set tread damage online detection and recognition method | |
| CN106018422B (en) | Based on matched special-shaped stamping parts profile defects vision detection system and method | |
| CN110009618A (en) | A kind of Axle Surface quality determining method and device | |
| CN104574389A (en) | Battery piece chromatism selection control method based on color machine vision | |
| CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
| CN109506628A (en) | Object distance measuring method under a kind of truck environment based on deep learning | |
| CN112067618A (en) | Product quality defect acquisition and analysis system based on imaging | |
| CN104008368A (en) | Fire recognition method based on maximum entropy threshold segmentation | |
| CN110096980A (en) | Character machining identifying system | |
| CN104677908A (en) | Blanking fracture surface quality detection system based on machine vision and blanking fracture surface quality detection method based on machine vision | |
| CN111539927B (en) | Detection method of automobile plastic assembly fastening buckle missing detection device | |
| CN107967681A (en) | Defect inspection method is hindered in a kind of elevator compensation chain punching based on machine vision | |
| CN108305259A (en) | A kind of abrasive type automatic identifying method of multi-texturing Fusion Features | |
| CN111487192A (en) | Machine vision surface defect detection device and method based on artificial intelligence | |
| Cheng et al. | Image segmentation technology and its application in digital image processing | |
| CN103729856A (en) | Method for cloth defect detection by utilizing S transformation signal extraction | |
| CN105069778A (en) | Industrial product surface defect detection method constructed based on target characteristic saliency map | |
| CN105414206A (en) | Online rapid positioning method for cold-rolled strip steel edge |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190809 |