CN117541615B - Bolt loosening detection method of automatic lapping device - Google Patents
Bolt loosening detection method of automatic lapping device Download PDFInfo
- Publication number
- CN117541615B CN117541615B CN202410027350.0A CN202410027350A CN117541615B CN 117541615 B CN117541615 B CN 117541615B CN 202410027350 A CN202410027350 A CN 202410027350A CN 117541615 B CN117541615 B CN 117541615B
- Authority
- CN
- China
- Prior art keywords
- bolt
- degree
- moment
- image
- bolts
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 14
- 230000002159 abnormal effect Effects 0.000 claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000012216 screening Methods 0.000 claims abstract description 6
- 230000005856 abnormality Effects 0.000 claims description 29
- 210000000746 body region Anatomy 0.000 claims description 23
- 238000010606 normalization Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 8
- 230000011218 segmentation Effects 0.000 description 8
- 238000012935 Averaging Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 3
- 230000005641 tunneling Effects 0.000 description 3
- 239000002689 soil Substances 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- VEMKTZHHVJILDY-UHFFFAOYSA-N resmethrin Chemical compound CC1(C)C(C=C(C)C)C1C(=O)OCC1=COC(CC=2C=CC=CC=2)=C1 VEMKTZHHVJILDY-UHFFFAOYSA-N 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/207—Analysis of motion for motion estimation over a hierarchy of resolutions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Abstract
The invention relates to the technical field of image processing, in particular to a bolt loosening detection method of an automatic lapping device, which comprises the following steps: acquiring images of all bolts at all times, acquiring a bolt main body area and a motion blur area in the images of all bolts at all times, acquiring the blur degree of the bolt main body area according to the gray value of the pixel point of the bolt main body area, acquiring the blur degree of the motion blur area according to the gray distribution of the pixel point of the motion blur area, acquiring the comprehensive blur degree of the bolts according to the blur degree of the bolt main body area and the motion blur area, and acquiring the first abnormal degree of each bolt at the current time according to the comprehensive blur degree of each bolt at each time; and obtaining a second abnormal degree of the bolt according to the difference of the first abnormal degrees of different bolts, and further screening the loose bolt. The invention can accurately identify and timely dispose the loose bolts in the working process of the shield machine and the automatic lapping device, thereby reducing the potential safety hazard.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a bolt loosening detection method of an automatic lapping device.
Background
The automatic lapping device refers to an automatic lapping device working in cooperation with a shield tunneling machine, which is a specific and professional tunneling machine designed to adapt to some special geological conditions and provide better tunnel stability and geological protection, and is installed at the rear of the shield tunneling machine to cover the whole construction working face for capturing and treating the debris and soil falling during the tunnel construction. The automatic lapping device is used for preventing the scraps from entering the soil and geology around the tunnel so as to maintain construction safety and environmental protection. So that it is important to check and maintain the automatic lapping device regularly, wherein the bolt loosening condition of the automatic lapping device is one of the important conditions, and the detection of the automatic lapping device is more that whether the tightening force meets the requirements specified by the manufacturer or not through manual visual inspection or torque wrench is measured.
Because the manual detection method is limited by the capacity of a professional and also needs to be checked when the automatic lapping device stops working, the detection efficiency is relatively low, automatic detection of the loosening condition of the bolt can not be realized when the equipment is in operation, the information condition of the loosening of the bolt can not be timely obtained, and the loosening of the bolt can possibly cause corresponding safety problems.
Disclosure of Invention
In order to solve the above problems, the present invention provides a bolt loosening detection method of an automatic lapping device, the method comprising the steps of:
acquiring images of all bolts of the automatic lapping device at all times; acquiring a bolt main body area and a motion blur area in each bolt image at each moment;
For each image of each bolt at each moment, acquiring the blurring degree of the bolt main body area according to the gray value of the pixel point of the bolt main body area in the image; acquiring the blurring degree of the motion blurring region according to the gray level distribution of the pixel points of the motion blurring region in the image; acquiring the comprehensive fuzzy degree of the bolt according to the fuzzy degree of the bolt main body region and the fuzzy degree of the motion fuzzy region in the image;
acquiring a first abnormal degree of each bolt at the current moment according to the comprehensive fuzzy degree of each bolt at each moment; acquiring a second abnormal degree of each bolt at the current moment according to the difference of the first abnormal degrees of different bolts at the current moment; and screening the loose bolts according to the second abnormality degree.
Preferably, the obtaining the blur degree of the bolt main body area according to the gray value of the pixel point of the bolt main body area in the image includes the following specific steps:
wherein, Represents the/>Moment/>The degree of blurring of the bolt body region in the image of the individual bolts; /(I)Represents the/>Moment/>First/>, in bolt body region in image of individual boltsAverage gray values of all pixel points of the row; Represents the/> Moment/>First/>, in bolt body region in image of individual boltsAverage gray values of all pixel points of the row; /(I)Represents the/>Moment/>The number of rows contained in the bolt body area in the image of the individual bolts; /(I)Representing a normalization function; /(I)Is an exponential function with a base of natural constant.
Preferably, the step of obtaining the blur degree of the motion blur area according to the gray level distribution of the pixels of the motion blur area in the image includes the following specific steps:
Regarding a motion blur area in an image of each bolt at each moment, taking each pixel point on the inner boundary of the motion blur area as an inner edge pixel point; acquiring a fuzzy gray sequence of each inner edge pixel point in each extending direction according to gray values of all pixel points in the motion fuzzy region; acquiring gray gradient of the motion blur area in the extending direction according to the blur gray sequence of all the inner edge pixel points in the motion blur area in the same extending direction; taking the maximum value of gray gradient of the motion blur area in all extending directions as the whole gradient degree of the motion blur area;
And acquiring the blurring degree of the motion blurring region in the image of each bolt at each moment according to the overall gradual change degree of the motion blurring region in the image of each bolt at each moment and the gray level distribution of the pixel points in the motion blurring region.
Preferably, the extending direction includes、/>、/>、/>、/>、/>、/>/>Is a direction of (2).
Preferably, the step of obtaining the blurred gray sequence of each inner edge pixel point in each extending direction according to gray values of all pixel points in the motion blurred region includes the following specific steps:
and for each inner edge pixel point, sequentially acquiring gray values of all pixel points positioned in the motion blur area in one extension direction of the inner edge pixel point to form a blur gray sequence in the extension direction of the inner edge pixel point.
Preferably, the step of acquiring the gray gradient of the motion blur area in the extending direction according to the blurred gray sequence in the same extending direction of all the inner edge pixel points in the motion blur area comprises the following specific steps:
wherein, Represents the/>Moment/>The motion blur area in the image of the individual bolts is at the/>Gradation in the extending direction gradually changes; /(I)Represents the/>Moment/>The number of inner edge pixel points in the motion blur area in the image of each bolt; /(I)Represents the/>Moment/>First/>, in motion blur area in image of individual boltsFirst/>, of the inner edge pixelsThe number of gray values contained in the blurred gray sequence in the respective extension directions; /(I)Represents the/>Moment/>First/>, in motion blur area in image of individual boltsFirst/>, of the inner edge pixelsThe first in the blurred gray level sequence in the extending directionGray values; /(I)Represents the/>Moment/>First/>, in motion blur area in image of individual boltsFirst/>, of the inner edge pixelsThe/>, in the blurred gray sequence in the extension directionA gray value.
Preferably, the step of obtaining the blur degree of the motion blur area in the image of each bolt at each moment according to the overall gradual change degree of the motion blur area in the image of each bolt at each moment and the gray distribution of the pixel points in the motion blur area comprises the following specific steps:
wherein, Represents the/>Moment/>The degree of blurring of the motion blur area in the image of the individual bolts; /(I)Represents the/>Moment/>The number of pixels contained in the motion blur area in the image of the individual bolts; /(I)Represents the/>Moment/>First/>, in motion blur area in image of individual boltsGray values of the individual pixels; /(I)Represents the/>Moment/>The gray average value of all pixel points of the bolt main body area in the image of each bolt; /(I)Represents the/>Moment/>The overall gradual change degree of the motion blur area in the image of each bolt; /(I)Representing a normalization function; /(I)Is an exponential function with a base of natural constant.
Preferably, the obtaining the comprehensive blur degree of the bolt according to the blur degree of the bolt main body region and the blur degree of the motion blur region in the image includes the following specific steps:
For each image of each bolt at each instant, the product of the degree of blur of the bolt body region in the image and the degree of blur of the motion blur region in the image is taken as the integrated degree of blur for that bolt at that instant.
Preferably, the step of obtaining the first abnormality degree of each bolt at the current moment according to the comprehensive ambiguity degree of each bolt at each moment comprises the following specific steps:
wherein, Represents the current moment/>A first degree of abnormality of the individual bolts; /(I)Represents the/>Moment/>Comprehensive fuzzy degree of each bolt; /(I)Represents the/>Moment/>Comprehensive fuzzy degree of each bolt; /(I)Indicating the common before the current timeTime of day.
Preferably, the obtaining the second abnormality degree of each bolt at the current moment according to the difference of the first abnormality degrees of different bolts at the current moment includes the following specific steps:
wherein, Represents the current moment/>A second degree of abnormality of the individual bolts; /(I)Represents the current moment/>A first degree of abnormality of the individual bolts; /(I)Represents the current moment/>A first degree of abnormality of the individual bolts; /(I)Representing the number of all bolts; Representing the normalization function.
The technical scheme of the invention has the beneficial effects that: the method comprises the steps of acquiring images of bolts at each moment, acquiring a bolt main body area and a motion blur area in the images of the bolts at each moment, acquiring the blur degree of the bolt main body area according to the gray value of a pixel point of the bolt main body area, acquiring the blur degree of the motion blur area according to the gray distribution of the pixel point of the motion blur area, acquiring the comprehensive blur degree of the bolts according to the blur degree of the bolt main body area and the motion blur area, and acquiring the first abnormal degree of each bolt at the current moment according to the comprehensive blur degree of each bolt at each moment; and obtaining a second abnormal degree of the bolt according to the difference of the first abnormal degrees of different bolts, and further screening the loose bolt. The invention can accurately identify and timely dispose the loose bolts in the working process of the shield machine and the automatic lapping device, thereby reducing the potential safety hazard.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of steps of a bolt loosening detection method of an automatic lapping device of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects of a bolt loosening detection method of an automatic lapping device according to the invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the bolt loosening detection method of the automatic lapping device provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for detecting loosening of bolts of an automatic lapping device according to an embodiment of the invention is shown, the method includes the following steps:
S001, acquiring images of all bolts of the automatic lapping device at all times, and acquiring bolt main body areas and motion blur areas in the images of all bolts at all times.
The method comprises the steps that a miniature high-definition camera is fixed at the same position angle of each bolt of an automatic lapping device, when the automatic lapping device starts to work, images of the first moment of each bolt are collected through the miniature high-definition camera, and each time is collected every five minutes. It should be noted that, in this embodiment, only five minutes are taken as an example for describing the acquisition interval of the image of the bolt, and the embodiment is not limited to the specific one, and in other embodiments, the operator may set the acquisition interval according to the actual implementation situation.
Because miniature high definition digtal camera is fixed in the same position angle department of each bolt of automatic lapping device for the bolt is located the image center of shooing, and vertical distribution in the image, the nut is in the top of screw thread on the bolt. Therefore, the obtained images of the bolts at all times can be ensured to be at the same angle, and the subsequent motion blur analysis is convenient for the images of each bolt at each time.
For each acquired image of each bolt at each moment, acquiring a bolt main body area and a motion blur area in the image through a semantic segmentation network, wherein the semantic segmentation network comprises the following specific contents:
the structure of the semantic segmentation network is a full convolution neural network FCN, the input of the semantic segmentation network is a bolt image, the output of the semantic segmentation network is a bolt main body area and a motion blur area in the bolt image, a training set of the semantic segmentation network is a bolt image data set, category information in the bolt image is artificially marked, wherein the category of background pixels is 0, the bolt main body area is 1, the motion blur area is 2, and a loss function of the semantic segmentation network is cross entropy loss.
Inputting the image of each bolt at each moment into a trained semantic segmentation network to obtain a bolt main body area and a motion blur area in the image of each bolt at each moment.
Thus, the acquisition of the bolt image is realized, and the bolt main body area and the motion blur area in the bolt image are acquired.
S002, acquiring the blurring degree of the bolt main body area according to the gray value of the pixel point of the bolt main body area in the image of each bolt at each moment.
When the bolt works with the automatic lapping device, the bolt images at all times shot by the camera can generate motion blur at different degrees due to different loosening degrees of the bolt. The tightness of the bolt is determined by the nut and the threaded portion, so that the embodiment uses the corresponding motion blur of the threaded portion as the blur degree of the bolt, the threaded arrangement of the threaded portion is generally uniformly distributed, the arrangement is compact and dense, and the gray value in the image is smoother due to the generated motion blur, so that some subtle details and textures are lost. Meanwhile, in a region where the vibration causes the contour to be extended, an averaging effect of the gray value may be caused due to a change in the pixel position, and the gray value may show a gradual trend along the direction in which the vibration trajectory is extended. Therefore, the embodiment analyzes the blurring degree of the bolt main body region according to the gray scale change condition of the pixel points in the bolt main body region in the bolt image.
Specifically, the blur degree of the bolt main body region in the image of each bolt at each moment is acquired:
wherein, Represents the/>Moment/>The degree of blurring of the bolt body region in the image of the individual bolts; /(I)Represents the/>Moment/>First/>, in bolt body region in image of individual boltsAverage gray values of all pixel points of the row; Represents the/> Moment/>First/>, in bolt body region in image of individual boltsAverage gray values of all pixel points of the row; /(I)Represents the/>Moment/>The number of rows contained in the bolt body area in the image of the individual bolts; /(I)Representing a normalization function; /(I)Is an exponential function with a natural constant as a base; since the bolts are positioned at the center of the shot image and vertically distributed in the image, the nuts on the bolts are above the threads, each row in the bolt main body area represents one thread, different ravines of the threads are periodically arranged in the vertical direction from the nuts to the threads, the average gray values of adjacent rows are different under normal conditions, the ratio between the average gray values of the adjacent rows is larger than 1, when the motion blur is generated, the ravines of the threads are less obvious, the average gray values of the adjacent rows tend to be consistent, the ratio between the average gray values of the adjacent rows is close to 1, and therefore when/>The smaller the thread ravines in the bolt body region, the more blurred the bolt body region.
Thus, the blurring degree of the bolt main body region in the image of each bolt at each moment is obtained.
S003, obtaining the blurring degree of the motion blurring region according to the gray distribution of the pixel points of the motion blurring region in the image of each bolt at each moment.
In the region where the vibration causes the contour to be extended, an averaging effect of the gradation value may be caused due to the change in the pixel position, and the gradation value may show a tendency to be gradually changed along the direction in which the vibration locus is extended. Therefore, the present embodiment analyzes gradation characteristics of a motion blur region in an image of each bolt at each timing. Since the motion blur area is an extension of the bolt body area, the motion blur area surrounds the bolt body area, i.e. the motion blur area takes the shape of a ring with an inner boundary and an outer boundary.
Specifically, for a motion blur area in an image of each bolt at each moment, each pixel point on the inner boundary of the motion blur area is taken as an inner edge pixel point. Will be、/>、/>、/>、/>、/>、/>、The directions are each taken as an extension direction. And for each inner edge pixel point, sequentially acquiring gray values of all pixel points positioned in the motion blur area in one extension direction of the inner edge pixel point to form a blur gray sequence in the extension direction of the inner edge pixel point.
Acquiring gray gradient of the motion blur area in the extending direction according to the blur gray sequence of all inner edge pixel points in the motion blur area in the same extending direction:
wherein, Represents the/>Moment/>The motion blur area in the image of the individual bolts is at the/>Gradation in the extending direction gradually changes; /(I)Represents the/>Moment/>The number of inner edge pixel points in the motion blur area in the image of each bolt; /(I)Represents the/>Moment/>First/>, in motion blur area in image of individual boltsFirst/>, of the inner edge pixelsThe number of gray values contained in the blurred gray sequence in the respective extension directions; /(I)Represents the/>Moment/>First/>, in motion blur area in image of individual boltsFirst/>, of the inner edge pixelsThe first in the blurred gray level sequence in the extending directionGray values; /(I)Represents the/>Moment/>First/>, in motion blur area in image of individual boltsFirst/>, of the inner edge pixelsThe/>, in the blurred gray sequence in the extension directionGray values; since the bolt has darker color and lighter background color, in the region where the bolt generates motion blur, the gray scale is smaller nearer to the bolt and larger farther from the bolt, so that in the blurred gray scale sequence of the inner edge pixel point in the motion blur region, the gray scale value is smaller nearer to the front and the gray scale value is larger farther to the rear, so that the embodiment will/>When/>, compared with 1The larger the difference of gray values of two adjacent pixel points in the corresponding extending direction is compared with the larger 1, the larger the looseness degree of the bolt is, the larger the blurring degree is, and the stronger the gray gradient in the corresponding extending direction is. When the blurred gray sequence in a certain extending direction of the inner edge pixel point of the motion blurred region is null, the inner edge pixel point does not participate in the calculation of gray gradient in the extending direction of the motion blurred region.
The maximum value of the gradation gradient of the motion blur area in all the extending directions is taken as the overall gradient degree of the motion blur area.
Obtaining the blurring degree of the motion blurring region in the image of each bolt at each moment according to the overall gradual change degree of the motion blurring region in the image of each bolt at each moment and the gray level distribution of the pixel points in the motion blurring region:
wherein, Represents the/>Moment/>The degree of blurring of the motion blur area in the image of the individual bolts; /(I)Represents the/>Moment/>The number of pixels contained in the motion blur area in the image of the individual bolts; /(I)Represents the/>Moment/>First/>, in motion blur area in image of individual boltsGray values of the individual pixels; /(I)Represents the/>Moment/>The gray average value of all pixel points of the bolt main body area in the image of each bolt; /(I)Represents the/>Moment/>The overall gradual change degree of the motion blur area in the image of each bolt; /(I)Representing a normalization function; /(I)Is an exponential function with a natural constant as a base; when/>Moment/>The more the number of pixel points contained in the motion blur area in the image of each bolt, the greater the vibration degree of the bolt at the moment, the greater the range of the motion blur area, and the greater the blur degree of the motion blur area in the image of the bolt; in the region where vibration causes contour extension (i.e., motion blur region), an averaging effect of gray values may be caused due to a change in pixel position, that is, the pixel gray values near the contour may tend to the average gray value of the bolt body region because the position of the contour of the object in the image changes, and when the averaging effect caused by vibration is stronger, an increase in image blur degree is generally caused, so that the effect of the average gray value due to blur is expressed as/>The smaller the corresponding value, the stronger the gray level averaging effect, and the greater the degree of blurring of the motion blur region. Meanwhile, when the overall gradation degree of the motion blur area is larger, the blur degree of the motion blur area is larger.
Thus, the blurring degree of the motion blurring region in the image of each bolt at each moment is obtained.
S004, acquiring the comprehensive fuzzy degree of the bolts according to the fuzzy degree of the bolt main body area and the fuzzy degree of the motion fuzzy area, and acquiring the first abnormal degree of each bolt at the current moment according to the comprehensive fuzzy degree of each bolt at each moment.
Acquiring the comprehensive fuzzy degree of each bolt at each moment according to the fuzzy degree of the main bolt region and the fuzzy degree of the motion fuzzy region in the image of each bolt at each moment:
wherein, Represents the/>Moment/>Comprehensive fuzzy degree of each bolt; /(I)Represents the/>Moment/>The degree of blurring of the bolt body region in the image of the individual bolts; /(I)Represents the/>Moment/>The degree of blurring of the motion blur region in the image of the individual bolts, when/>The larger the description of the first/>Moment/>The greater the degree of overall ambiguity of the individual bolts, the greater the likelihood that the corresponding bolt loosening event will occur.
Thus, the comprehensive fuzzy degree of each bolt at each moment is obtained.
It should be noted that, when an image of a bolt at a first moment is captured, the shield machine starts to start, and vibration is not generated yet, so that the motion blur degree of the bolt at the first moment is smaller, therefore, the embodiment compares the comprehensive blur degree of the bolt at each moment with the comprehensive blur degree of the bolt at the first moment, and analyzes the loosening condition of the bolt according to the change condition of the comprehensive blur degree of the bolt at different moments. The bolt loosening is an integral process, and the larger the comprehensive fuzzy degree at a certain moment in the loosening process is, the larger the loosening possibility of the bolt is, and the larger the reference value of the loosening condition of the bolt at the current moment is, so that the embodiment obtains the weight at each moment according to the comprehensive fuzzy degree of the bolt at each moment, and obtains the first abnormal degree of the bolt at the current moment according to the difference between the comprehensive fuzzy degree of the bolt at different moments and the comprehensive fuzzy degree of the bolt at the first moment so as to reflect the loosening condition of the bolt to a certain extent.
Specifically, according to the difference between the comprehensive fuzzy degree of each bolt at each moment and the comprehensive fuzzy degree of each bolt at the first moment, a first abnormal degree of each bolt at the current moment is obtained:
wherein, Represents the current moment/>A first degree of abnormality of the individual bolts; /(I)Represents the/>Moment/>Comprehensive fuzzy degree of each bolt; /(I)Represents the/>Moment/>Comprehensive fuzzy degree of each bolt; /(I)Indicating the common before the current timeThe time is the same; /(I)Represents the/>Moment/>The ratio of the integrated blur degree of each bolt to the sum of the integrated blur degrees of the ith bolt at all times is used as the/>Weights for each moment. The first abnormal degree of the ith bolt at the current moment is determined through the comprehensive fuzzy degree difference between each moment and the first moment and the weight corresponding to each moment, when the comprehensive fuzzy degree of the bolt at a certain moment is larger, the weight is larger, at the moment, the difference between the comprehensive fuzzy degree of the bolt at the corresponding moment and the comprehensive fuzzy degree of the bolt at the first moment is more concerned, the more the difference is, the more looseness is likely to be generated for the bolt, and at the moment, the more abnormal is caused for the bolt. Conversely, the smaller the difference, the less likely the bolt will come loose, and the smaller the first degree of abnormality of the bolt.
Thus, the first abnormal degree of each bolt at the current moment is obtained.
S005, obtaining second abnormal degrees of each bolt at the current moment according to differences of first abnormal degrees of different bolts at the current moment, and screening loose bolts according to the second abnormal degrees.
The automatic lapping device is connected behind the shield machine, so that the shield machine works to drive bolts of the automatic lapping device to vibrate. The working states of the shield machine are different at different moments, so that the vibration degrees of the bolts for automatic lapping are different, when the vibration degrees are different, the generated motion blur is also different, if the loosening state of the bolts is directly identified according to the first abnormal degree of a single bolt, the different vibration degrees at different moments can influence the identification result. At the same moment, the vibration degree of the bolts with the same loosening degree brought by the shield machine is the same, so that the loosening degree of each bolt is determined according to the difference of the first abnormal degrees of the different bolts at the current moment.
Specifically, a second abnormality degree of each bolt at the current moment is obtained according to the first abnormality degree of each bolt at the current moment:
wherein, Represents the current moment/>A second degree of abnormality of the bolts for reflecting the current time of the first/>Loosening degree of the bolts; /(I)Represents the current moment/>A first degree of abnormality of the individual bolts; /(I)Represents the current moment/>A first degree of abnormality of the individual bolts; /(I)Representing the number of all bolts; /(I)Representing a normalization function; if the current moment is the/>The greater the first degree of abnormality of a bolt compared to the first degree of abnormality of other bolts, the current/>The more likely the bolts will come loose, at this point/>The greater the second degree of abnormality of the individual bolts; if the current moment is the/>The smaller the first degree of abnormality of a bolt is compared with the first degree of abnormality of other bolts, the current/>The less likely the individual bolts will come loose, at this point/>The smaller the second degree of abnormality of the individual bolts.
Thus, the second abnormality degree of each bolt at the current time is obtained.
Presetting an abnormal threshold valueIn particular, without limitation, e.g./>The enforcer may set the anomaly threshold according to the actual implementation. If the second abnormality degree of the bolt at the current moment is larger than the abnormality threshold value, the bolt is considered to be loose, and relevant personnel are informed of overhauling the bolt at the moment.
Through the steps, bolt loosening detection of the automatic lapping device is completed.
According to the embodiment of the invention, through collecting images of bolts at all times, acquiring a bolt main body area and a motion blur area in the images of the bolts at all times, acquiring the blur degree of the bolt main body area according to the gray value of the pixel point of the bolt main body area, acquiring the blur degree of the motion blur area according to the gray distribution of the pixel point of the motion blur area, acquiring the comprehensive blur degree of the bolts according to the blur degree of the bolt main body area and the motion blur area, and acquiring the first abnormal degree of each bolt at the current time according to the comprehensive blur degree of each bolt at each time; and obtaining a second abnormal degree of the bolt according to the difference of the first abnormal degrees of different bolts, and further screening the loose bolt. The invention can accurately identify and timely dispose the loose bolts in the working process of the shield machine and the automatic lapping device, thereby reducing the potential safety hazard.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (4)
1. The bolt loosening detection method of the automatic lapping device is characterized by comprising the following steps of:
acquiring images of all bolts of the automatic lapping device at all times; acquiring a bolt main body area and a motion blur area in each bolt image at each moment;
For each image of each bolt at each moment, acquiring the blurring degree of the bolt main body area according to the gray value of the pixel point of the bolt main body area in the image; acquiring the blurring degree of the motion blurring region according to the gray level distribution of the pixel points of the motion blurring region in the image; acquiring the comprehensive fuzzy degree of the bolt according to the fuzzy degree of the bolt main body region and the fuzzy degree of the motion fuzzy region in the image;
acquiring a first abnormal degree of each bolt at the current moment according to the comprehensive fuzzy degree of each bolt at each moment; acquiring a second abnormal degree of each bolt at the current moment according to the difference of the first abnormal degrees of different bolts at the current moment; screening loose bolts according to the second abnormality degree;
The method for acquiring the fuzzy degree of the bolt main body region according to the gray value of the pixel point of the bolt main body region in the image comprises the following specific steps:
wherein, Represents the/>Moment/>The degree of blurring of the bolt body region in the image of the individual bolts; /(I)Represents the/>Moment/>First/>, in bolt body region in image of individual boltsAverage gray values of all pixel points of the row; /(I)Represents the/>Moment/>First/>, in bolt body region in image of individual boltsAverage gray values of all pixel points of the row; /(I)Represents the/>Moment/>The number of rows contained in the bolt body area in the image of the individual bolts; /(I)Representing a normalization function; /(I)Is an exponential function with a natural constant as a base;
The method for obtaining the blurring degree of the motion blurring region according to the gray level distribution of the pixel points of the motion blurring region in the image comprises the following specific steps:
Regarding a motion blur area in an image of each bolt at each moment, taking each pixel point on the inner boundary of the motion blur area as an inner edge pixel point; acquiring a fuzzy gray sequence of each inner edge pixel point in each extending direction according to gray values of all pixel points in the motion fuzzy region; acquiring gray gradient of the motion blur area in the extending direction according to the blur gray sequence of all the inner edge pixel points in the motion blur area in the same extending direction; taking the maximum value of gray gradient of the motion blur area in all extending directions as the whole gradient degree of the motion blur area;
acquiring the blurring degree of the motion blurring region in the image of each bolt at each moment according to the overall gradual change degree of the motion blurring region in the image of each bolt at each moment and the gray level distribution of pixel points in the motion blurring region;
The step of obtaining the blur degree of the motion blur area in the image of each bolt at each moment according to the overall gradual change degree of the motion blur area in the image of each bolt at each moment and the gray level distribution of the pixel points in the motion blur area comprises the following specific steps:
wherein, Represents the/>Moment/>The degree of blurring of the motion blur area in the image of the individual bolts; /(I)Represents the/>Moment/>The number of pixels contained in the motion blur area in the image of the individual bolts; /(I)Represents the/>Moment/>First/>, in motion blur area in image of individual boltsGray values of the individual pixels; /(I)Represents the/>Moment/>The gray average value of all pixel points of the bolt main body area in the image of each bolt; /(I)Represents the/>Moment/>The overall gradual change degree of the motion blur area in the image of each bolt; /(I)Representing a normalization function; /(I)Is an exponential function with a natural constant as a base;
the method for obtaining the comprehensive fuzzy degree of the bolt according to the fuzzy degree of the bolt main body area and the fuzzy degree of the motion fuzzy area in the image comprises the following specific steps:
For each image of each bolt at each moment, taking the product of the blur degree of the bolt main body area in the image and the blur degree of the motion blur area in the image as the comprehensive blur degree of the bolt at the moment;
The method for acquiring the first abnormal degree of each bolt at the current moment according to the comprehensive fuzzy degree of each bolt at each moment comprises the following specific steps:
wherein, Represents the current moment/>A first degree of abnormality of the individual bolts; /(I)Represents the/>Moment/>Comprehensive fuzzy degree of each bolt; /(I)Represents the/>Moment/>Comprehensive fuzzy degree of each bolt; /(I)Representing the common/>, before the current timeThe time is the same;
The second abnormal degree of each bolt at the current moment is obtained according to the difference of the first abnormal degrees of different bolts at the current moment, and the method comprises the following specific steps:
wherein, Represents the current moment/>A second degree of abnormality of the individual bolts; /(I)Represents the current moment/>A first degree of abnormality of the individual bolts; /(I)Represents the current moment/>A first degree of abnormality of the individual bolts; /(I)Representing the number of all bolts; /(I)Representing the normalization function.
2. The method for detecting loosening of bolts of an automatic lapping device according to claim 1, wherein the extending direction includes、/>、/>、/>、/>、/>、/>/>Is a direction of (2).
3. The method for detecting loosening of bolts of an automatic lapping device according to claim 1, wherein the step of obtaining the blurred gray sequence of each inner edge pixel point in each extending direction according to gray values of all pixel points in the motion blurred region comprises the following specific steps:
and for each inner edge pixel point, sequentially acquiring gray values of all pixel points positioned in the motion blur area in one extension direction of the inner edge pixel point to form a blur gray sequence in the extension direction of the inner edge pixel point.
4. The method for detecting loosening of bolts of an automatic lapping device according to claim 1, wherein the step of acquiring gradation gradient of the motion blur area in the extending direction according to a blur gradation sequence in the same extending direction of all inner edge pixels in the motion blur area comprises the following specific steps:
wherein, Represents the/>Moment/>The motion blur area in the image of the individual bolts is at the/>Gradation in the extending direction gradually changes; /(I)Represents the/>Moment/>The number of inner edge pixel points in the motion blur area in the image of each bolt; Represents the/> Moment/>First/>, in motion blur area in image of individual boltsFirst/>, of the inner edge pixelsThe number of gray values contained in the blurred gray sequence in the respective extension directions; /(I)Represents the/>Moment/>First/>, in motion blur area in image of individual boltsFirst/>, of the inner edge pixelsThe first in the blurred gray level sequence in the extending directionGray values; /(I)Represents the/>Moment/>First/>, in motion blur area in image of individual boltsFirst/>, of the inner edge pixelsThe/>, in the blurred gray sequence in the extension directionA gray value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410027350.0A CN117541615B (en) | 2024-01-09 | 2024-01-09 | Bolt loosening detection method of automatic lapping device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410027350.0A CN117541615B (en) | 2024-01-09 | 2024-01-09 | Bolt loosening detection method of automatic lapping device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117541615A CN117541615A (en) | 2024-02-09 |
| CN117541615B true CN117541615B (en) | 2024-04-26 |
Family
ID=89788447
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410027350.0A Active CN117541615B (en) | 2024-01-09 | 2024-01-09 | Bolt loosening detection method of automatic lapping device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117541615B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20080102808A (en) * | 2007-05-22 | 2008-11-26 | 삼성전자주식회사 | Liquid crystal display device and control method thereof |
| CN102353527A (en) * | 2011-08-26 | 2012-02-15 | 东南大学 | Method for measuring brightness response characteristic of display screen of notebook computer |
| CN104899834A (en) * | 2015-03-04 | 2015-09-09 | 苏州大学 | Blurred image recognition method and apparatus based on SIFT algorithm |
| CN107451973A (en) * | 2017-07-31 | 2017-12-08 | 西安理工大学 | Motion blur image restoration method based on the extraction of abundant fringe region |
| CN115294137A (en) * | 2022-10-09 | 2022-11-04 | 南通市通州区欢伴纺织品有限公司 | Cloth surface color bleeding defect detection method |
| CN116664451A (en) * | 2023-07-27 | 2023-08-29 | 中铁九局集团第一建设有限公司 | Measurement robot measurement optimization method based on multi-image processing |
| CN117152135A (en) * | 2023-10-30 | 2023-12-01 | 济宁市市政园林养护中心 | Road construction crack defect evaluation and detection method |
-
2024
- 2024-01-09 CN CN202410027350.0A patent/CN117541615B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20080102808A (en) * | 2007-05-22 | 2008-11-26 | 삼성전자주식회사 | Liquid crystal display device and control method thereof |
| CN102353527A (en) * | 2011-08-26 | 2012-02-15 | 东南大学 | Method for measuring brightness response characteristic of display screen of notebook computer |
| CN104899834A (en) * | 2015-03-04 | 2015-09-09 | 苏州大学 | Blurred image recognition method and apparatus based on SIFT algorithm |
| CN107451973A (en) * | 2017-07-31 | 2017-12-08 | 西安理工大学 | Motion blur image restoration method based on the extraction of abundant fringe region |
| CN115294137A (en) * | 2022-10-09 | 2022-11-04 | 南通市通州区欢伴纺织品有限公司 | Cloth surface color bleeding defect detection method |
| CN116664451A (en) * | 2023-07-27 | 2023-08-29 | 中铁九局集团第一建设有限公司 | Measurement robot measurement optimization method based on multi-image processing |
| CN117152135A (en) * | 2023-10-30 | 2023-12-01 | 济宁市市政园林养护中心 | Road construction crack defect evaluation and detection method |
Non-Patent Citations (3)
| Title |
|---|
| Xiaoyu Zhao.Defocused Image Splicing Localization by Distinguishing Multiple Cues between Raw Naturally Blur and Artificial Blur.《Digital Forensics and Watermarking》.全文. * |
| 利用数字图像处理技术检测锥螺纹;宋志刚;《中国优秀硕士学位论文全文数据库》;20041215;全文 * |
| 断层突水温度- 非线性渗流- 应力耦合模型 研究;刘伟韬;《煤矿安全》;20181130;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117541615A (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110310261B (en) | Contact net dropper defect detection model training method and defect detection method | |
| DE69923048T2 (en) | Effective test method for classifying the image quality of an optical sensor using three pixel categories | |
| CN110602484A (en) | Online checking method for shooting quality of power transmission line equipment | |
| CN109030499B (en) | Device and method suitable for continuous online detection of target defects and preventing repeated counting of defect number | |
| CN112686120B (en) | Power transmission line abnormity detection method based on unmanned aerial vehicle aerial image | |
| CN112417955A (en) | Patrol video stream processing method and device | |
| CN110913209B (en) | Camera shielding detection method and device, electronic equipment and monitoring system | |
| CN115936672A (en) | Smart power grid online safety operation and maintenance management method and system | |
| CN110490872A (en) | The foreign matter detecting method and system of process equipment | |
| CN117541615B (en) | Bolt loosening detection method of automatic lapping device | |
| CN115018785A (en) | Hoisting steel wire rope tension detection method based on visual vibration frequency identification | |
| CN114820626A (en) | Intelligent detection method for automobile front part configuration | |
| CN114331997A (en) | Wire defect monitoring method based on image recognition | |
| EP3293672A1 (en) | Particle boundary identification | |
| DE102015205524B4 (en) | Method and device for classifying an object, for example a traffic sign, in an image | |
| CN105335981A (en) | Image-based goods monitoring method | |
| CN115631191A (en) | Coal blockage detection algorithm based on gray level features and edge detection | |
| CN108133479B (en) | Automatic spinning machine drawing-in monitoring method and device | |
| CN115457459A (en) | Machine vision system capable of effectively improving detection efficiency | |
| Xu et al. | Computer assistance image processing spores counting | |
| Yang et al. | Cherry recognition based on color channel transform | |
| CN110827272B (en) | Tire X-ray image defect detection method based on image processing | |
| CN110865084A (en) | Self-learning mode-based harness wire separation detection system and method | |
| EP1998272A2 (en) | Device for determining an object and/or probability of a search object existing in a readout window of a picture, method and computer program | |
| CN109214390B (en) | Fence state detection method and system based on machine vision principle |
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 |