CN113610827A - Crane construction risk assessment method and device based on artificial intelligence - Google Patents
Crane construction risk assessment method and device based on artificial intelligence Download PDFInfo
- Publication number
- CN113610827A CN113610827A CN202110939407.0A CN202110939407A CN113610827A CN 113610827 A CN113610827 A CN 113610827A CN 202110939407 A CN202110939407 A CN 202110939407A CN 113610827 A CN113610827 A CN 113610827A
- Authority
- CN
- China
- Prior art keywords
- hook
- image
- lifting
- hook head
- risk
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000010276 construction Methods 0.000 title claims abstract description 47
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 28
- 238000012502 risk assessment Methods 0.000 title claims abstract description 27
- 230000008569 process Effects 0.000 claims description 31
- 238000004891 communication Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000007797 corrosion Effects 0.000 claims description 11
- 238000005260 corrosion Methods 0.000 claims description 11
- 238000012847 principal component analysis method Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 3
- 238000011156 evaluation Methods 0.000 abstract 1
- 238000003708 edge detection Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000006378 damage Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 239000002184 metal Substances 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 230000010339 dilation Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009435 building construction Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010297 mechanical methods and process Methods 0.000 description 1
- 230000005226 mechanical processes and functions Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Control And Safety Of Cranes (AREA)
Abstract
The invention relates to the technical field of artificial intelligence and hoisting equipment, and provides a crane construction risk assessment method and device based on artificial intelligence, which comprises the following steps: preliminarily judging whether the anti-falling buckle fails or not according to the image of the lifting hook device; if the lifting hook device fails, acquiring a hook head body image, an anti-falling buckle body image and a lifting rope body image according to the lifting hook device image, further determining a first lifting hook risk characteristic, a second lifting hook risk characteristic and a third lifting hook risk characteristic, and determining the lifting hook construction risk degree according to the three lifting hook risk characteristics. According to the invention, under the condition that the anti-drop buckle is failed in preliminary judgment, three hook risk characteristics are correspondingly determined by considering the danger degree of the drop of the lifting rope from the hook head opening, the deviation degree of the hook head opening direction and the distribution symmetry degree of the lifting rope at the hook head, so that the reliable evaluation of the construction risk degree of the crane is finally realized, and the effectiveness and the accuracy of the detection of the working state of the lifting hook are improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence and hoisting equipment, in particular to a crane construction risk assessment method and device based on artificial intelligence.
Background
Because the chemical industry enterprise is because heavy equipment is more, consequently often need professional engineering equipment to carry out auxiliary work when carrying out various engineering operations. Especially, when a chemical enterprise needs to perform building construction, because the operation environment is complex, the number of work procedures is large, and the number of mechanical equipment used is large, the risk and harm factors are correspondingly large and complicated in the process of construction and production activities.
In the construction process, the dangerous sources are generally divided into two categories, one is dangerous chemicals and pressure vessels, the other is unsafe behaviors of people, unsafe states of mechanical processes and adverse environmental conditions, and most dangerous and harmful factors belong to the latter.
The tower crane is a hoisting machine capable of realizing omnibearing transportation of heavy objects, and widely appears in engineering operation scenes. However, the device has a great number of potential safety hazards in the using process, so that the device needs to be checked frequently, but once the device is built, the device generally needs to be operated in an overhead environment for a long time, so that manual detection is difficult to achieve.
Wherein, the lifting hook is as the part that tower crane used most frequently in the operation, though its opening part is provided with the anticreep buckle, nevertheless in tower crane work progress, still can take place the anticreep buckle often and can not be totally with the inside edge complete closure of lifting hook class anticreep buckle malfunctioning phenomenon, this just can lead to the wire rope unhook and then causes serious accident. And because the lifting hook is usually high in position and has a sight blind area, the construction risk state of the lifting hook is difficult to detect reliably through human eyes. Therefore, in the process of high-altitude construction of the tower crane, the safety state of the lifting hook needs to be effectively detected in a high-altitude environment.
Disclosure of Invention
The invention aims to provide a crane construction risk assessment method and device based on artificial intelligence, which are used for solving the problem that the working state of a lifting hook cannot be effectively detected in the prior art.
In order to solve the technical problem, the technical scheme adopted by the invention is as follows:
the invention provides a crane construction risk assessment method based on artificial intelligence, which comprises the following steps:
acquiring an image of a lifting hook device, and preprocessing the image of the lifting hook device;
preliminarily judging whether the anti-falling buckle fails or not according to the preprocessed lifting hook device image;
if the anti-drop buckle is judged to be invalid preliminarily, acquiring a hook head body image, an anti-drop buckle body image and a lifting rope body image according to the preprocessed lifting hook device image;
determining a first lifting hook risk characteristic according to the hook head body image, the anti-falling buckle body image and the lifting rope body image, wherein the first lifting hook risk characteristic is used for representing the danger degree of the lifting rope falling from the hook head opening;
determining a second hook risk characteristic according to the hook head body image and the anti-falling buckle body image, wherein the second hook risk characteristic is used for representing the deviation degree of the opening direction of the hook head;
determining a third hook risk characteristic according to the hook head body image and the lifting rope body image, wherein the third hook risk characteristic is used for representing the distribution symmetry degree of the lifting rope at the hook head;
and determining the construction risk degree of the lifting hook according to the first lifting hook risk characteristic, the second lifting hook risk characteristic and the third lifting hook risk characteristic.
Further, the step of determining a first hook risk characteristic comprises:
determining the shortest distance between the anti-falling buckle and the inner contour of the hook head body according to the hook head body image and the anti-falling buckle body image;
determining the diameter of the lifting rope according to the lifting rope body image;
and calculating a first lifting hook risk characteristic according to the shortest distance between the anti-falling buckle and the inner profile of the hook head body and the diameter of the lifting rope.
Further, the calculation formula of the first hook risk characteristic is as follows:
wherein: i 11For the first hook risk feature, D is the shortest distance between the anti-release buckle and the inside profile of the hook head body, and D is the diameter of the lifting rope.
Further, the step of determining a second hook risk characteristic comprises:
determining the principal component direction of the hook head body internal contour image by using a principal component analysis method according to the hook head body image;
determining the principal component direction of the anti-falling buckle by using a principal component analysis method according to the anti-falling buckle body image;
calculating an included angle between the principal component direction of the internal profile image of the hook head body and the principal component direction of the anti-falling buckle;
and calculating the risk characteristic of the second lifting hook according to the calculated included angle of the two principal component directions and the included angle of the two principal component directions when the lifting hook is stable and vertical.
Further, the calculation formula of the second hook risk characteristic is as follows:
I2＝1-e-Δθ
wherein, I2For the second hook risk feature, Δ θ is the angle of departure, Δ θ ═ θ1-θ0|，θ1To calculate the angle between the two principal component directions, θ0The included angle between the two main component directions when the lifting hook is stably vertical.
Further, the step of determining a third hook risk characteristic comprises:
determining the principal component direction of the whole hook body by using a principal component analysis method according to the hook body image;
determining all lifting rope pixel points positioned on two sides of a straight line of the main component direction according to the lifting rope body image and the straight line of the main component direction of the whole hook head body;
calculating the number of all lifting rope pixel points on the first side of the straight line in the principal component direction and the average value of the distances from all the lifting rope pixel points to the straight line in the principal component direction;
calculating the number of all lifting rope pixel points positioned on the second side of the straight line in the principal component direction and the average value of the distances from all lifting rope pixel points to the straight line in the principal component direction;
and calculating the third hook risk characteristic according to the calculated number of the pixel points of the two lifting ropes and the average value of the two corresponding distances.
Further, the calculation formula of the third hook risk characteristic is as follows:
wherein, I3For the third hook risk feature, Δ d is the absolute value of the difference between the mean of the two distances, Δ d ═ d1-d2|，d1D is the average value of the distances from all lifting rope pixel points positioned on the first side of the straight line positioned in the principal component direction to the straight line positioned in the principal component direction2The mean value of the distances from all lifting rope pixel points positioned on the second side of the straight line in the principal component direction to the straight line in the principal component direction is obtained, delta n is the absolute value of the difference value of the number of the two lifting rope pixel points, and delta n is | n ═ n1-n2|，n1The number of pixel points, n, of all lifting ropes on the first side of the straight line with the main component direction2The number of all sling pixel points located on the second side of the straight line where the principal component direction is located.
Further, the calculation formula of the construction risk degree of the lifting hook is as follows:
Z＝α1I1+α2I2+α3I3
wherein Z is the construction risk degree of the lifting hook, I1、I2、I3Respectively a first hook risk characteristic, a second hook risk characteristic, a third hook risk characteristic, a1、α2、α3Are respectively i1、i2、i3And (4) corresponding weight values.
Further, according to the hook gear image after the preliminary treatment, the step of acquireing gib head body image, anticreep buckle body image and lifting rope body image includes:
carrying out corrosion operation on the whole preprocessed image of the lifting hook device until a hook head in the lifting hook device is firstly separated from a connecting piece on the upper part of the hook head, so as to obtain a corroded hook head area image, wherein the corroded hook head area image comprises a hook head body but does not comprise an anti-falling buckle and a lifting rope;
dividing the whole image of the hook device according to the position of the hook head in the hook device and the connecting piece at the upper part of the hook head when the hook head is firstly divided, so as to obtain an original hook head area image;
expanding the corroded hook head area image until the original size of the hook head body is recovered to obtain a hook head body image;
determining a hook body in the original hook region image according to the positions of all pixel points of the hook body in the hook body image;
carrying out convex hull analysis on the determined hook head body in the original hook head region image, and calculating the mass center of the convex hull;
judging whether a connected domain where the centroid of the convex hull is located is a closed background region, if not, performing expansion operation on the original hook head region image until the connected domain where the centroid of the convex hull of the expanded hook head body is located is the closed background region;
in the expanded original hook head area image, obtaining an expanded anti-falling buckle body image according to a communication domain which is enclosed into a closed background area and the expanded hook head body;
corroding the expanded anti-drop buckle body image to finally obtain an anti-drop buckle body image;
and obtaining a lifting rope body image according to the original hook head region image, the hook head body image and the anti-falling buckle body image.
The invention also provides an artificial intelligence based crane construction risk assessment device which comprises a processor and a memory, wherein the processor is used for processing the instructions stored in the memory so as to realize the artificial intelligence based crane construction risk assessment method.
The invention has the following beneficial effects: through the image that acquires the hook assembly of high altitude construction in-process, and under the condition that preliminary judgement anticreep buckle became invalid, acquire gib head body image according to the hook assembly image, anticreep buckle body image and lifting rope body image, and can follow the dangerous degree that the gib head opening drops from the lifting rope respectively, the skew degree of gib head opening direction and the lifting rope reliably aassessment to the construction risk degree of crane in the three aspect of the distribution symmetry degree of gib head department, the validity and the accuracy that have improved the detection of lifting hook operating condition.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a crane construction risk assessment method based on artificial intelligence according to the present invention;
fig. 2 is a schematic view of an image of a hook assembly taken in accordance with the present invention.
Detailed Description
In order to further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the method and apparatus for crane construction risk assessment based on artificial intelligence according to the present invention with reference to the accompanying drawings and preferred embodiments shows the following detailed descriptions.
The method comprises the following steps:
the embodiment provides a crane construction risk assessment method based on artificial intelligence, which can be used for carrying out safety risk assessment on a lifting hook device of a tower crane in the process of high-altitude operation, so that workers can conveniently master the working condition of the lifting hook in real time, and the occurrence of damage accidents caused by unhooking is prevented.
Specifically, a flow chart corresponding to the crane construction risk assessment method based on artificial intelligence is shown in fig. 1, and the method comprises the following steps:
(1) and acquiring an image of the lifting hook device, and preprocessing the image of the lifting hook device.
Wherein, because need evaluate the unhook risk condition of the hook assembly of the tower machine of operation in high altitude, consequently this embodiment uses unmanned aerial vehicle to carry the camera and gathers the image of hook position department, obtains hook assembly image. The camera here is an industrial RGB camera, and the image of the hook device taken is shown in fig. 2.
Because the hook device is made of metal products, the formed image is susceptible to corrosion spots and illumination, in the embodiment, Gaussian filtering is used for the collected hook device image to remove the interference of image summary noise, so that the image is smoother, then the image enhancement technology is used for enhancing the internal attribute information of the image, and the influence of factors such as image noise and illumination is reduced and eliminated.
Among numerous image enhancement algorithms, the Retinex image enhancement algorithm has a good image enhancement effect, the incident coefficient of incident light on the metal surface of the hook (which means the influence of the material of the metal surface on the incident light) directly determines the dynamic range which can be reached by the pixels of the image of the hook device under the long-term irradiation of external sunlight, and the Retinex algorithm adopts a method for reducing the incident light coefficient, so that the influence of the incident light on the image can be reduced and eliminated, and the enhancement of the intrinsic attribute of the image is realized. That is to say, by processing the acquired images of the hook device by adopting a Retinex image enhancement algorithm, the distortion condition of the images caused by the influence of the material of the metal surface on the illumination can be eliminated, so that the processed images can truly reflect the hook device.
In addition, since the specific implementation processes of the gaussian filtering and the Retinex image enhancement algorithm both belong to the prior art, the specific processes thereof are not described in detail in this embodiment.
(2) And preliminarily judging whether the anti-falling buckle fails or not according to the preprocessed lifting hook device image.
In the image of the lifting hook device, the first end of the anti-falling buckle is fixedly connected with the first end of the hook head body, and the second end of the anti-falling buckle is movably connected with the second end of the hook head body. The second end of the hook head body is used as an opening of the hook head body, under the normal condition, the anti-falling buckle (the second end) and the opening are completely closed, and when the anti-falling buckle (the second end) and the opening are not completely closed, the anti-falling buckle is proved to be invalid.
Based on hook assembly's this kind of structure basis, whether anti-disengaging buckle is closed completely with gib head body opening part in according to hook assembly image, can tentatively judge whether the anti-disengaging buckle is inefficacy. When the anti-falling buckle in the image of the lifting hook device is completely closed with the opening of the hook head body, the anti-falling buckle is not failed, and at the moment, no risk exists in the construction process; and when anticreep buckle and gib head body opening part are not totally closed in the hook assembly image, when anticreep buckle and gib head body opening part exist certain opening in the hook assembly image promptly, explain that the work progress has the risk, need assess this risk to report to the police when the risk degree is higher, and in time inform the staff to carry out subsequent processing, prevent the emergence of harm accident.
In this embodiment, whether the anti-disengaging buckle and the hook head body opening part are completely closed in the image of the lifting hook device is judged, whether the anti-disengaging buckle and the hook head body in the image of the lifting hook device enclose a closed background communication domain is judged, when the closed background communication domain is enclosed, the anti-disengaging buckle and the hook head body opening part in the image of the lifting hook device are completely closed, otherwise, the anti-disengaging buckle and the hook head body opening part in the image of the lifting hook device are not completely closed.
(3) If the anti-falling buckle is judged to be invalid preliminarily, acquiring a hook head body image, an anti-falling buckle body image and a lifting rope body image according to the preprocessed lifting hook device image.
Wherein, judging under the circumstances that the anticreep buckle became invalid, need carry out further analysis to the hook assembly picture after the preliminary treatment, need acquire gib head body image, anticreep buckle body image and lifting rope body image according to the hook assembly image after the preliminary treatment promptly, carry out accurate aassessment to construction risk severity, concrete step is as follows:
(3-1) carrying out corrosion operation on the whole preprocessed image of the lifting hook device until a hook head in the lifting hook device is firstly separated from a connecting piece on the upper part of the hook head, so that a corroded hook head region image is obtained, wherein the corroded hook head region image comprises a hook head body but does not comprise an anti-falling buckle and a lifting rope.
The pre-processed image of the whole lifting hook device is subjected to successive corrosion operation until the lifting hook device is firstly split into two connected domains, so that the pixel connection position of the hook head and the upper connecting piece can be determined.
And then obtaining the principal component direction of the whole hook device by using a principal component analysis method, and then making a normal line of the principal component direction at the connection position of the corresponding pixels, which are separated by the hook device for the first time, wherein the normal line in the corroded image of the whole hook device below the normal line is an image of a hook head area. Since the specific implementation process using the principal component analysis algorithm belongs to the prior art, the specific process will not be described in detail in this embodiment.
In addition, in this embodiment, in the original whole image of the hook device, the maximum thickness of the hook body is the largest, the second time the anti-drop buckle is performed, the lifting rope (diameter) is the smallest, and the thickness of the hook at the joint of the whole hook device is greater than the maximum thickness of the anti-drop buckle, so that after the first time the hook device is gradually corroded and separated, the obtained corroded hook region image only contains the hook body, but does not contain the anti-drop buckle and the lifting rope, and thus, the corroded hook region image is expanded in the later period to restore the original image size, and then the pixel points only containing the hook body can be obtained.
And (3-2) dividing the whole image of the hook device according to the position of the hook head in the hook device and the connecting piece at the upper part of the hook head when the hook head is firstly divided, so as to obtain the original hook head area image.
And (3) according to the pixel connection position of the hook head and the connecting piece at the upper part of the hook head in the image of the hook device in the step (3-1), making a normal line of a principal component direction passing through the pixel connection position in the original hook device, and obtaining an original hook head area image which is positioned below the normal line in the original hook device. For subsequent convenience in processing, the obtained original hook area image is subjected to background segmentation extraction, a background area in the original hook area image is determined, and the pixel gray value of the background area is set to be 255, that is, the background area is set to be white, so that a final original hook area image is obtained. Since the specific implementation process of performing background segmentation and extraction on an image belongs to the prior art, the specific process of the embodiment is not described in detail.
And (3-3) performing expansion operation on the corroded hook head area image until the original size of the hook head body is recovered, and obtaining the hook head body image.
And (3) according to the characteristics of the corroded hook head area image obtained in the step (3-1), namely the hook head area image comprises the hook head body but does not comprise the anti-falling buckle and the lifting rope, so that the corroded hook head area image is expanded to the original image size. And similarly performing background segmentation and extraction on the hook head area image restored to the original image size, determining a background area in the hook head area image, and setting the background area to be white to obtain a hook head body image. Since the specific implementation process of performing the dilation operation on the image to restore the image to the original size belongs to the prior art, the specific process of the embodiment will not be described in detail.
And (3-4) determining the hook body in the original hook area image according to the positions of all pixel points of the hook body in the hook body image.
And (3-5) carrying out convex hull analysis on the determined hook head body in the original hook head region image, and calculating the mass center of the convex hull. And judging whether the connected domain where the centroid of the convex hull is located is a closed background region, if not, performing successive expansion operation on the original hook head region image until the connected domain where the centroid of the convex hull of the expanded hook head body is located is the closed background region.
The method comprises the steps that a hook body, an anti-falling buckle and a lifting rope are contained in an original hook area image, and under the condition that the position of the hook body is known at present, in order to determine a pixel connected domain of the anti-falling buckle, a convex hull analysis is carried out on the determined hook body in the original hook area image, and the mass center of the convex hull is calculated. Since the specific implementation process of convex hull analysis belongs to the prior art, the specific process is not described in detail in this embodiment. Judging whether a connected domain where the centroid of the convex hull is located is a closed background region, if the connected domain is not the closed background region, verifying that the front judgment that the anti-drop buckle is accurate, performing expansion operation on an original hook head region image, performing convex hull analysis on the expanded hook head body again after the expansion operation is finished once, calculating the centroid of the convex hull, judging whether the connected domain where the centroid of the convex hull is located is the closed background region, and if the connected domain is not the closed background region, performing expansion operation again on the basis of the front expansion until the connected domain where the centroid of the convex hull of the expanded hook head body is located is the closed background region.
And (3-6) in the expanded original hook head area image, obtaining an expanded anti-falling buckle body image according to the communication domain which is enclosed into the closed background area and the expanded hook head body.
In the expanded original hook head area image, the communication domain which encloses the closed background area is composed of the expanded hook head body and the anti-falling buckle, so that the expanded anti-falling buckle body image can be determined under the condition that the expanded hook head body is known.
And (3-7) carrying out corrosion operation on the expanded anti-drop buckle body image to finally obtain the anti-drop buckle body image.
And carrying out corresponding corrosion operation on the obtained expanded anti-drop buckle body image to restore the image to the original size, so that the anti-drop buckle body image can be obtained at the moment.
And (3-8) obtaining a lifting rope body image according to the original hook head region image, the hook head body image and the anti-falling buckle body image.
Wherein, because in original gib head region image, contain gib head body, anticreep buckle and lifting rope, then, under the condition of known gib head body image and anticreep buckle body image, just can acquire lifting rope body image.
It should be noted that, in the specific process of obtaining the hook body image, the anti-release buckle body image, and the lifting rope body image according to the preprocessed lifting hook device image in the above steps (3-1) - (3-8), it is applicable to a situation that the thickness of the hook at the connection point of the whole lifting hook device is greater than that of the anti-release buckle and the lifting rope, that is, the image of the area of the hook corroded in step (3-1) only includes the hook body, but does not include the anti-release buckle and the lifting rope. However, in the conventional hook device, in order to improve the anti-slip reliability of the lifting rope, the anti-slip buckle may be provided to be relatively thick, and the thickness of the hook head at the joint of the entire hook device may be larger than the lifting rope and smaller than the anti-slip buckle, that is, the hook head region image after passing through the corrosion in (3-1) includes the hook head body and the anti-slip buckle, but does not include the lifting rope. At this time, as another embodiment, the hook body image, the anti-release buckle body image, and the lifting rope body image are acquired according to the preprocessed lifting hook device image, and the method may be implemented by:
(3-11) carrying out corrosion operation on the whole preprocessed image of the lifting hook device until a hook head in the lifting hook device is firstly separated from a connecting piece on the upper part of the hook head, so that a corroded hook head area image is obtained, wherein the corroded hook head area image comprises a hook head body and an anti-falling buckle but does not comprise a lifting rope.
The specific process of performing the etching operation on the preprocessed whole image of the hook device to obtain the etched image of the hook head region refers to the step (3-1), and the specific process is not described in detail here.
The difference between the step (3-11) and the step (3-1) is only that, in the original whole image of the hook device, the maximum thickness of the hook body is the largest, the anti-drop buckle is the next, and the lifting rope (diameter) is the smallest, and the thickness of the hook at the joint of the whole hook device is smaller than the maximum thickness of the anti-drop buckle, so that after the hook device is successively corroded and is firstly and basically separated, the obtained corroded hook head region image contains the hook body and the anti-drop buckle but does not contain the lifting rope, and then the corroded hook head region image is expanded in the later period to restore the original image size, and the pixel point position containing the hook body and the anti-drop buckle can be obtained.
And (3-12) dividing the whole image of the hook device according to the position of the hook head in the hook device and the connecting piece at the upper part of the hook head when the hook head is firstly divided, so as to obtain an original hook head area image, namely a hook area image containing the lifting rope.
Wherein, the specific process of obtaining the original hook head area image can refer to the above step (3-2), and the detailed process thereof will not be described in detail here.
And (3-13) performing expansion operation on the corroded hook head area image until the original size of the hook head body is restored, and obtaining the hook head area image without the lifting rope.
And (3) according to the characteristics of the corroded hook head area image obtained in the step (3-11), namely the hook head area image comprises the hook head body and the anti-falling buckle but does not comprise the lifting rope, so that the corroded hook head area image is expanded to the original image size, and the hook head area image without the lifting rope can be obtained. Since the specific implementation process of performing the dilation operation on the image to restore the image to the original size belongs to the prior art, the specific process of the embodiment will not be described in detail.
In addition, the accurate and effective hook head area image is obtained by morphological operation through the steps (3-11) - (3-13), so that the problem that the hook head area is very difficult to identify and separate based on simple color clustering or information such as edge contour and the like because the hook head and the anti-falling buckle are contained in the hook device image and the connected lifting rope exists is solved.
And (3-14) obtaining an image of a lifting rope body according to the image of the lifting hook area containing the lifting rope and the image of the hook head area without the lifting rope.
And (3) subtracting the hook area image finally obtained in the step (3-12) and containing the lifting rope from the hook area image without the lifting rope obtained in the step (3-13), so that a lifting rope communication domain at the hook position in the original image, namely a lifting rope body image, can be obtained.
And (3-15) continuing expansion operation on the hook head area image without the lifting rope obtained in the step (3-13) until the anti-falling buckle in the hook head area image is closed to the opening of the hook head body, so as to obtain the expanded hook area image and a closed background communication domain surrounded by the anti-falling buckle and the hook head body.
And similarly performing background segmentation and extraction on the hook head area image without the lifting rope, determining a background area in the image, and setting the background area to be white. Because the anticreep buckle became invalid this moment, and also when the anticreep buckle did not have complete closure with gib head body opening part, the anticreep buckle can't form complete closed background region with the gib head body, consequently set up white gib head regional image that does not contain the lifting rope to the background region and continue to expand, then stop the inflation operation when the lifting hook region detects confined background region for the first time, just can obtain the closed background connected domain that anticreep buckle and gib head body enclose this moment to subsequent analysis detects.
And (3-16) respectively carrying out edge detection on the expanded lifting hook area image and a closed background communication area surrounded by the anti-falling buckle and the hook head body, and subtracting the two edge detection results to obtain the edges of the lifting hook body and the anti-falling buckle part.
Wherein, canny edge detection is carried out on the closed background connected domain obtained in the step (3-15), and canny edge detection is also carried out on the obtained hook area image after expansion. Since the specific implementation process of edge detection on an image belongs to the prior art, the embodiment will not describe the specific process in detail.
After the edge detection is finished, subtracting the result graphs of the two times of edge detection to obtain the edges of the hook body and the anti-falling buckle part, wherein the part of the edges refers to all edges left after the edges of the closed background communication area are removed from all edges of the hook body and the anti-falling buckle in the expanded hook area image.
And (3-17) obtaining an expanded hook head body image according to a closed background communication domain surrounded by the hook body, the anti-falling buckle part edge, the anti-falling buckle and the hook head body and the expanded hook head region image.
The inner edge and the outer edge of the lifting hook body can be approximately seen as concentric circles, so that in order to determine the expanded hook head body image, pixel traversal is performed on the lifting hook body and the anti-falling buckle part edge outline, namely pixel points at the first time division position of the lifting hook device in the part edge outline are used as initial pixel points, the slope between the current pixel point and the next adjacent pixel point is calculated along a single direction, then the current pixel points are used as vertical lines of the required current pixel point slope, and intersection points of the vertical lines when the corresponding edges of the first time background connected domain (including the closed background connected domain and the background connected domain except the closed background connected domain) and the expanded whole lifting hook area image are intersected are reserved. And then judging whether the intersection point is positioned in a closing area of the hook head or on an outer edge contour of the hook head, wherein the closing area of the hook head refers to a hook head edge pixel area corresponding to a closed background communication area, and the outer edge contour of the hook head refers to other edge areas except the hook head edge pixel area corresponding to the closed background communication area in the hook head.
And stopping traversing when the obtained intersection points are detected to be positioned on the hook head outer edge contour for the first time, taking the current intersection points as stop points, and taking the obtained intersection point set as the hook inner edge contour. And (4) according to the hook body, the edge of the anti-falling buckle part and the profile of the inner edge of the hook obtained in the step (3-16), a communication domain formed from a pixel point at the upper and lower junction of the hook to the stop point position, namely an expanded hook body image can be obtained.
And (3-18) obtaining an expanded anti-drop buckle body image according to the expanded hook area image and the expanded hook body image.
And (4) subtracting the expanded hook area image obtained in the step (3-16) from the expanded hook body image to obtain an expanded anti-drop buckle body image.
And (3-19) respectively carrying out corrosion operation on the expanded hook body image and the expanded anti-falling buckle body image to obtain a final actual hook body image and an actual anti-falling buckle body image.
And respectively carrying out corresponding corrosion operation on the obtained expanded hook body image and the expanded anti-falling buckle body image to restore the original sizes of the hook body image and the expanded anti-falling buckle body image, so that the hook body image and the anti-falling buckle body image can be obtained at the moment.
(4) According to gib head body image, anticreep buckle body image and lifting rope body image, confirm first lifting hook risk characteristic, first lifting hook risk characteristic is used for the dangerous degree that the characterization lifting rope can follow the gib head opening and drop.
Wherein, when the anticreep buckle can not normally be worked, often can't effectively laminate the inboard edge of gib head in order to form effectual closure, when the goods takes place to rock in the transfer process and the landing can take place, consequently this embodiment at first constructs first lifting hook risk characteristic I according to the distance between anticreep buckle and the inside profile of gib head body1The specific process is as follows:
(4-1) determining the shortest distance between the anti-falling buckle and the inner contour of the hook head body according to the hook head body image and the anti-falling buckle body image.
Wherein, when calculating the shortest distance between anticreep buckle and the inside profile of gib head body, to the second end of gib head body, namely with the non-fixed link of anticreep buckle as the starting point, traverse along the inside edge extending direction of gib head, and only need traverse to the midpoint department of the inside edge of gib head body can, the reason lies in reducing the error that the inside half pixel of gib head body brought and reducing the calculated amount, thereby obtain the shortest distance D between anticreep buckle and the inside profile of gib head body.
And (4-2) determining the diameter of the lifting rope according to the lifting rope body image.
In the corresponding lifting rope body image, due to imaging reasons, a plurality of lifting ropes may be located in the same communication domain, so that only the portion with the smallest width value of the communication domain is selected in the embodiment, and the diameter d of the corresponding lifting rope is obtained through calculation.
(4-3) comparing the shortest distance D between the anti-falling buckle and the inner contour of the hook head body with the diameter D of the lifting rope, and calculating a first lifting hook risk characteristic I1When D is greater than or equal to D, then I11 is ═ 1; otherwise, the calculation formula of the first hook risk characteristic is as follows:
wherein, I1For the first hook risk feature, D is the shortest distance between the anti-release buckle and the inside profile of the hook head body, and D is the diameter of the lifting rope.
(5) And determining a second lifting hook risk characteristic according to the hook head body image and the anti-falling buckle body image, wherein the second lifting hook risk characteristic is used for representing the deviation degree of the opening direction of the hook head.
Wherein, when gib head body opening direction skew normal value, the lifting rope easily appears sliding, and then probably the goods is uneven and the accident that falls that causes appears, therefore this embodiment is established and is constructed second lifting hook risk characteristic I2The specific process is as follows:
and (5-1) determining the principal component direction of the hook body internal contour image by using a principal component analysis method according to the hook body image, and determining the principal component direction of the anti-falling buckle by using the principal component analysis method according to the anti-falling buckle body image.
(5-2) calculating an included angle theta between the principal component direction of the hook head body internal contour image and the principal component direction of the anti-falling buckle1And the angle value of the standard principal component direction corresponding to the stable and vertical lifting hook is set as theta0And the deviation angle between the two is delta theta ═ theta1-θ0If the second hook risk characteristic is calculated as follows:
I2＝1-e-Δθ
wherein, I2For the second hook risk feature, Δ θ is the angle of departure, Δ θ ═ θ1-θ0|，θ1To calculate the angle between the two principal component directions, θ0The included angle between the two main component directions when the lifting hook is stably vertical.
It should be noted that the included angle Δ θ is introduced to evaluate the deviation direction of the hook body opening, so θ is used herein1、θ0And Δ θ is simply the magnitude of the angle and does not include a unit.
(6) And determining a third lifting hook risk characteristic according to the hook head body image and the lifting rope body image, wherein the third lifting hook risk characteristic is used for representing the distribution symmetry degree of the lifting rope at the hook head.
Wherein, in crane work engineering, the position distribution of lifting rope on the gib head body whether symmetry also can influence the equilibrium of goods to produce great potential safety hazard, consequently the third lifting hook risk characteristic I is built to this embodiment3The specific process is as follows:
(6-1) determining the principal component direction of the whole hook body by using a principal component analysis method according to the hook body image, and determining all lifting rope pixel points positioned on two sides of the line where the principal component direction is positioned according to the lifting rope body image and the line where the principal component direction of the whole hook body is positioned.
The main component direction of the whole hook head body is the main component direction of the whole hook device. For example, when the entire hook assembly is in a vertically stable state, the principal component direction of the entire hook head body is a vertical direction passing through the geometric center of the hook assembly.
(6-2) calculating the number n of pixel points of all lifting ropes on the first side of the straight line with the main component direction1And the mean value d of the distances from all the lifting rope pixel points to the straight line in the principal component direction1. Meanwhile, the number n of pixel points of all lifting ropes on the second side of the straight line with the principal component direction is calculated2And the mean value d of the distances from all the lifting rope pixel points to the straight line in the principal component direction2。
(6-3) calculating the number n of pixel points of all the lifting ropes according to the calculated number1,n2And the mean d of the corresponding two distances1,d2Then, the calculation formula of the third hook risk characteristic is:
wherein, I3For the third hook risk feature, Δ d is the absolute value of the difference between the mean of the two distances, Δ d ═ d1-d2|，d1D is the average value of the distances from all lifting rope pixel points positioned on the first side of the straight line positioned in the principal component direction to the straight line positioned in the principal component direction2The mean value of the distances from all lifting rope pixel points positioned on the second side of the straight line in the principal component direction to the straight line in the principal component direction is obtained, delta n is the absolute value of the difference value of the number of the two lifting rope pixel points, and delta n is | n ═ n1-n2|，n1The number of pixel points, n, of all lifting ropes on the first side of the straight line with the main component direction2The number of all sling pixel points located on the second side of the straight line where the principal component direction is located.
It should be noted that the deviating angles Δ d, Δ n are introduced here to evaluate the position distribution equilibrium of the lifting rope on the hook body, and therefore d here1、d2、n1、n2Δ d, Δ n are merely the size of the distance or number and do not include units.
(7) According to first lifting hook risk characteristic, second lifting hook risk characteristic and third lifting hook risk characteristic, confirm the lifting hook construction risk degree of the whole lifting hook safety risk of reaction, the computational formula that corresponds is:
Z＝α1I1+α2I2+α3I3
wherein Z is the construction risk degree of the lifting hook, I1、I2、I3Respectively a first hook risk characteristic, a second hook risk characteristic, a third hook risk characteristic, a1、α2、α3Are respectively I1、I2、I3Corresponding weight value, α1＝α2＝α3＝1/3。
(8) Whether the lifting hook construction risk degree is larger than a lifting hook construction risk degree threshold value epsilon is 0.5 or not is judged, when the lifting hook construction risk degree Z is detected to exceed the threshold value epsilon, early warning needs to be immediately carried out, and in time, workers are informed to carry out follow-up processing, so that the occurrence of damage accidents is prevented.
The embodiment of the device is as follows:
the embodiment provides an artificial intelligence based crane construction risk assessment device which comprises a processor and a memory, wherein the processor is used for processing instructions stored in the memory so as to realize the artificial intelligence based crane construction risk assessment method in the above method embodiment. Since the crane construction risk assessment method based on artificial intelligence is described in detail in the above method embodiments, the description is omitted here.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A crane construction risk assessment method based on artificial intelligence is characterized by comprising the following steps:
acquiring an image of a lifting hook device, and preprocessing the image of the lifting hook device;
preliminarily judging whether the anti-falling buckle fails or not according to the preprocessed lifting hook device image;
if the anti-drop buckle is judged to be invalid preliminarily, acquiring a hook head body image, an anti-drop buckle body image and a lifting rope body image according to the preprocessed lifting hook device image;
determining a first lifting hook risk characteristic according to the hook head body image, the anti-falling buckle body image and the lifting rope body image, wherein the first lifting hook risk characteristic is used for representing the danger degree of the lifting rope falling from the hook head opening;
determining a second hook risk characteristic according to the hook head body image and the anti-falling buckle body image, wherein the second hook risk characteristic is used for representing the deviation degree of the opening direction of the hook head;
determining a third hook risk characteristic according to the hook head body image and the lifting rope body image, wherein the third hook risk characteristic is used for representing the distribution symmetry degree of the lifting rope at the hook head;
and determining the construction risk degree of the lifting hook according to the first lifting hook risk characteristic, the second lifting hook risk characteristic and the third lifting hook risk characteristic.
2. The artificial intelligence based crane construction risk assessment method according to claim 1, wherein said step of determining a first hook risk feature comprises:
determining the shortest distance between the anti-falling buckle and the inner contour of the hook head body according to the hook head body image and the anti-falling buckle body image;
determining the diameter of the lifting rope according to the lifting rope body image;
and calculating a first lifting hook risk characteristic according to the shortest distance between the anti-falling buckle and the inner profile of the hook head body and the diameter of the lifting rope.
3. The artificial intelligence based crane construction risk assessment method according to claim 2, wherein the calculation formula of the first hook risk characteristic is as follows:
wherein, I1For the first hook risk feature, D is the shortest distance between the anti-release buckle and the inside profile of the hook head body, and D is the diameter of the lifting rope.
4. The artificial intelligence based crane construction risk assessment method according to any one of claims 1-3, wherein said step of determining a second hook risk characteristic comprises:
determining the principal component direction of the hook head body internal contour image by using a principal component analysis method according to the hook head body image;
determining the principal component direction of the anti-falling buckle by using a principal component analysis method according to the anti-falling buckle body image;
calculating an included angle between the principal component direction of the internal profile image of the hook head body and the principal component direction of the anti-falling buckle;
and calculating the risk characteristic of the second lifting hook according to the calculated included angle of the two principal component directions and the included angle of the two principal component directions when the lifting hook is stable and vertical.
5. The artificial intelligence based crane construction risk assessment method according to claim 4, wherein the calculation formula of the second hook risk characteristic is as follows:
I2＝1-e-Δθ
wherein, I2For the second hook risk feature, Δ θ is the angle of departure, Δ θ ═ θ1-θ0|，θ1To calculate the angle between the two principal component directions, θ0For the stability of the lifting hookThe included angle of the two main component directions when vertical.
6. The artificial intelligence based crane construction risk assessment method according to any one of claims 1-3, wherein said step of determining a third hook risk characteristic comprises:
determining the principal component direction of the whole hook body by using a principal component analysis method according to the hook body image;
determining all lifting rope pixel points positioned on two sides of a straight line of the main component direction according to the lifting rope body image and the straight line of the main component direction of the whole hook head body;
calculating the number of all lifting rope pixel points on the first side of the straight line in the principal component direction and the average value of the distances from all the lifting rope pixel points to the straight line in the principal component direction;
calculating the number of all lifting rope pixel points positioned on the second side of the straight line in the principal component direction and the average value of the distances from all lifting rope pixel points to the straight line in the principal component direction;
and calculating the third hook risk characteristic according to the calculated number of the pixel points of the two lifting ropes and the average value of the two corresponding distances.
7. The artificial intelligence based crane construction risk assessment method according to claim 6, wherein the calculation formula of the third hook risk characteristic is as follows:
wherein, I3For the third hook risk feature, Δ d is the absolute value of the difference between the mean of the two distances, Δ d ═ d1-d2|，d1D is the average value of the distances from all lifting rope pixel points positioned on the first side of the straight line positioned in the principal component direction to the straight line positioned in the principal component direction2All lifting rope pixel points on the second side of the straight line with the principal component direction reaching the main componentThe mean value of the distance of the straight line in the principal component direction, Δ n is the absolute value of the difference between the numbers of the pixel points of all the lifting ropes, and Δ n is | n1-n2|，n1The number of pixel points, n, of all lifting ropes on the first side of the straight line with the main component direction2The number of all sling pixel points located on the second side of the straight line where the principal component direction is located.
8. The artificial intelligence based crane construction risk assessment method according to claim 1, wherein the calculation formula of the hook construction risk degree is as follows:
Z＝α1I1+α2I2+α3I3
wherein Z is the construction risk degree of the lifting hook, I1、I2、I3Respectively a first hook risk characteristic, a second hook risk characteristic, a third hook risk characteristic, a1、α2、α3Are respectively I1、I2、I3And (4) corresponding weight values.
9. The artificial intelligence based crane construction risk assessment method according to any one of claims 1-8, wherein the step of obtaining a hook body image, an anti-drop buckle body image and a lifting rope body image according to the preprocessed lifting hook device image comprises:
carrying out corrosion operation on the whole preprocessed image of the lifting hook device until a hook head in the lifting hook device is firstly separated from a connecting piece on the upper part of the hook head, so as to obtain a corroded hook head area image, wherein the corroded hook head area image comprises a hook head body but does not comprise an anti-falling buckle and a lifting rope;
dividing the whole image of the hook device according to the position of the hook head in the hook device and the connecting piece at the upper part of the hook head when the hook head is firstly divided, so as to obtain an original hook head area image;
expanding the corroded hook head area image until the original size of the hook head body is recovered to obtain a hook head body image;
determining a hook body in the original hook region image according to the positions of all pixel points of the hook body in the hook body image;
carrying out convex hull analysis on the determined hook head body in the original hook head region image, and calculating the mass center of the convex hull;
judging whether a connected domain where the centroid of the convex hull is located is a closed background region, if not, performing expansion operation on the original hook head region image until the connected domain where the centroid of the convex hull of the expanded hook head body is located is the closed background region;
in the expanded original hook head area image, obtaining an expanded anti-falling buckle body image according to a communication domain which is enclosed into a closed background area and the expanded hook head body;
corroding the expanded anti-drop buckle body image to finally obtain an anti-drop buckle body image;
and obtaining a lifting rope body image according to the original hook head region image, the hook head body image and the anti-falling buckle body image.
10. An artificial intelligence based crane construction risk assessment apparatus comprising a processor and a memory, the processor being configured to process instructions stored in the memory to implement the artificial intelligence based crane construction risk assessment method of any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110939407.0A CN113610827A (en) | 2021-08-16 | 2021-08-16 | Crane construction risk assessment method and device based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110939407.0A CN113610827A (en) | 2021-08-16 | 2021-08-16 | Crane construction risk assessment method and device based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113610827A true CN113610827A (en) | 2021-11-05 |
Family
ID=78308718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110939407.0A Withdrawn CN113610827A (en) | 2021-08-16 | 2021-08-16 | Crane construction risk assessment method and device based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610827A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117474321A (en) * | 2023-10-30 | 2024-01-30 | 郑州宝冶钢结构有限公司 | BIM model-based construction site risk intelligent identification method and system |
-
2021
- 2021-08-16 CN CN202110939407.0A patent/CN113610827A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117474321A (en) * | 2023-10-30 | 2024-01-30 | 郑州宝冶钢结构有限公司 | BIM model-based construction site risk intelligent identification method and system |
| CN117474321B (en) * | 2023-10-30 | 2024-04-19 | 郑州宝冶钢结构有限公司 | BIM model-based construction site risk intelligent identification method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114842017B (en) | HDMI cable surface quality detection method and system | |
| CN107764839B (en) | Machine vision-based steel wire rope surface defect online detection method and device | |
| KR20180029973A (en) | Systems and methods for automatically inspecting surfaces | |
| CN111832415B (en) | Truck safety intelligent protection system for container hoisting operation | |
| CN113610827A (en) | Crane construction risk assessment method and device based on artificial intelligence | |
| CN117474321B (en) | BIM model-based construction site risk intelligent identification method and system | |
| CN103149222A (en) | Flaw detection device in real-time imaging of ray | |
| CN111080601A (en) | Method for identifying fault image of pull ring grinding shaft of derailment brake device of railway wagon | |
| CN111832571B (en) | Automatic detection method for truck brake beam strut fault | |
| CN113184707A (en) | Method and system for preventing lifting of container truck based on laser vision fusion and deep learning | |
| CN111506011A (en) | Construction safety monitoring method and device | |
| CN112197715A (en) | Elevator brake wheel and brake shoe gap detection method based on image recognition | |
| CN107200274A (en) | A kind of anti-container truck based on machine vision is lifted method | |
| CN113139943B (en) | Method and system for detecting appearance defects of open circular ring workpiece and computer storage medium | |
| CN112418323B (en) | Railway wagon coupler knuckle pin fault detection method based on image processing | |
| CN113179389A (en) | System and method for identifying crane jib of power transmission line dangerous vehicle | |
| CN116958069A (en) | Visual detection system and method for welding seam of steel structure | |
| CN113239832B (en) | Hidden danger intelligent identification method and system based on image identification | |
| CN112883789B (en) | Bowling prevention method and system based on laser vision fusion and deep learning | |
| KR101846259B1 (en) | System for inspecting sealer spread using machine vision technique | |
| WO2024119359A1 (en) | Online state inspection system for hoisting rope of elevator, and inspection method therefor | |
| CN112184800A (en) | Container truck hanger detection method and system | |
| CN113537159B (en) | Crane risk data identification method based on artificial intelligence | |
| RU2775954C1 (en) | Method for automated cargo capture by a crane | |
| CN118004900B (en) | Portal crane security protection system based on visual monitoring |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20211105 |