CN116046883A - Crane steel wire rope magnetic leakage-vision multi-mode fusion detection device and method - Google Patents
Crane steel wire rope magnetic leakage-vision multi-mode fusion detection device and method Download PDFInfo
- Publication number
- CN116046883A CN116046883A CN202310345805.9A CN202310345805A CN116046883A CN 116046883 A CN116046883 A CN 116046883A CN 202310345805 A CN202310345805 A CN 202310345805A CN 116046883 A CN116046883 A CN 116046883A
- Authority
- CN
- China
- Prior art keywords
- wire rope
- steel wire
- defect
- magnetic flux
- detection device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
- G01N27/72—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables
- G01N27/82—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws
- G01N27/83—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws by investigating stray magnetic fields
- G01N27/84—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws by investigating stray magnetic fields by applying magnetic powder or magnetic ink
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—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
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30136—Metal
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Engineering & Computer Science (AREA)
- Investigating Or Analyzing Materials By The Use Of Magnetic Means (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Quality & Reliability (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Signal Processing (AREA)
- Mathematical Physics (AREA)
- Electrochemistry (AREA)
Abstract
The invention discloses a crane wire rope magnetic flux leakage-vision multi-mode fusion detection device and a method, wherein the detection device comprises an annular magnetic flux leakage flaw detection device, three miniature industrial cameras and a portable computer, on the basis of qualitatively detecting the defects of a wire rope by adopting the annular magnetic flux leakage flaw detection device, a control module of the portable computer is used for sending out instructions to control the miniature industrial cameras to photograph the wire rope, and the wire rope surface defect detection classification and quantitative identification method based on regional suggestion network and image segmentation are used for realizing wire breakage, rust, abrasion, diameter shrinkage and malformation defect detection classification and wire breakage quantity identification, improving the damage detection rate and accuracy of the wire rope and realizing intelligent and precise detection of the whole wire rope without blind areas; meanwhile, the safety state comprehensive evaluation method based on the accumulated and quantized damage and the residual strength of the steel wire rope is utilized to realize the accurate evaluation of the safety state of the steel wire rope.
Description
Technical Field
The invention belongs to the technical field of nondestructive testing of steel wire ropes, and particularly relates to a magnetic leakage-vision multi-mode fusion detection device and method for a steel wire rope of a crane.
Background
At present, the detection method of the steel wire rope of the crane mainly comprises a manual visual method, an electromagnetic detection method, a machine visual detection method, an eddy current detection method and the like. Electromagnetic detection is difficult to accurately distinguish and identify different types of damage such as corrosion and abrasion, when the corrosion and abrasion conditions are severe, broken wire damage is difficult to accurately detect, visual detection and quantitative analysis cannot be performed on broken wires and broken wire distribution in detail, detection omission and false detection are easy to occur under complex working conditions and strong noise interference, detection blind areas exist on the steel wire ropes at stress bending positions such as reels, pulleys, rope clamps, wedges and joints, and the problem that the GB/T5972-2016 steel wire rope maintenance, inspection and scrapping conditions of hoisting machinery cannot be completely detected: it can be seen that the wire breaks, the diameter of the steel wire rope is reduced, the strand breaks, rust, deformity, heat/arc damage and the like.
The visual detection method has the advantages of being capable of intuitively grasping the surface damage condition of the steel wire rope, finding tiny damage in time and finding a root, avoiding damage evolution or further damage (such as periodic rope biting of a roller and pulley abrasion), being affected by shaking and surface oil stains to a certain extent, being incapable of detecting the internal defects of the steel wire rope, and being mainly matched with manual analysis on the basis of the acquisition of the image information of the steel wire rope, and lacking intelligent analysis processing and assessment. In summary, the single nondestructive testing method for the steel wire rope in the prior art has the problems of missing or false detection, inaccuracy and comprehensiveness, low efficiency and the like.
Disclosure of Invention
The invention aims to provide a magnetic flux leakage-vision multi-mode fusion detection device and method for a steel wire rope of a crane, which solve the problems of missed detection or false detection, inaccuracy, complete and low efficiency and the like of a single nondestructive detection method for the steel wire rope in the prior art.
In order to solve the problems, the invention is realized by the following technical scheme:
the crane wire rope magnetic leakage-vision multi-mode fusion detection device comprises a portable computer, an annular magnetic leakage flaw detection device and three miniature industrial cameras; the annular magnetic flux leakage flaw detection device comprises a body, a multi-stage annular magnetic flux leakage detection assembly and a multi-loop permanent magnet excitation assembly, wherein the multi-stage annular magnetic flux leakage detection assembly and the multi-loop permanent magnet excitation assembly are arranged in an inner cavity of the body; the end face of the body is annular, and the miniature industrial camera is fixedly arranged at the front end of the body; the multistage annular magnetic flux leakage detection assembly, the multi-loop permanent magnet excitation assembly and the miniature industrial camera are electrically connected with the portable computer.
According to the invention, by arranging the annular magnetic flux leakage flaw detection device and the three miniature industrial cameras, on the basis of qualitatively detecting defects through the annular magnetic flux leakage flaw detection device, classification identification of broken wires, rust, abrasion, diameter shrinkage and deformity defects and determination of damage degree are realized through visual detection; in addition, the device can be directly held by hands to shoot and identify defects of the stress bending parts of the steel wire rope which cannot be detected by electromagnetic methods such as a winding drum, a pulley, a rope clamp, a wedge block and a joint, so that the detection of the whole rope without blind areas is realized, the damage detection rate and the accuracy rate of the steel wire rope are improved, and the intelligent and precise visual detection of the steel wire rope is realized. Meanwhile, based on quantitative accumulated damage on the surface and the inside of the steel wire rope, accurate assessment of the residual strength and the safety state of the steel wire rope is realized, potential safety hazards of the steel wire rope can be found in time, rope breakage accidents are prevented, auxiliary personnel scientifically detect maintenance and make a safe and economical rope replacement decision, the service life of the steel wire rope is scientifically prolonged, and the problem of waste in use caused by traditional periodic rope replacement or rope replacement strategies according to workload is avoided.
Further optimizing, the body is divided into two split units along the plane where the axis is located, and the two split units are detachably connected; the contact surfaces of the two split units are provided with first grooves along the length of the contact surfaces, and when the two split units are assembled, the two first grooves form a first hole for a steel wire rope to pass through.
During detection, the two split units are opened, the end head of the steel wire rope to be detected is clamped in the first groove of one split unit, and then the other split unit is covered, so that the steel wire rope passes through the first hole. Through the split design of the body, the steel wire rope and the annular magnetic leakage flaw detection device are convenient to assemble in an adapting way.
Further preferably, guide wheels are arranged at two ends of each split unit, and second grooves are formed in the guide wheels along the circumferential direction; when the two split units are assembled, two second grooves at the same end form a guide hole for a steel wire rope to pass through; through setting up the leading wheel, the wire rope of being convenient for passes through annular magnetic leakage flaw detection device smoothly, prevents to block.
Further preferably, the three micro industrial cameras are uniformly arranged circumferentially around the axis where the first hole is located, and the shooting angle of each micro industrial camera is greater than or equal to 120 degrees. Through setting up three miniature industrial cameras, ensure to gather 360 no dead angle images of wire rope, improve and detect the precision.
Further optimizing, still include the support, annular magnetic leakage flaw detection device sets up on the support, and this support is scalable support. The height of the support is adjusted according to the requirement, so that the adaptability is improved.
Further optimizing, and setting the distance between the annular magnetic flux leakage flaw detection device and the miniature industrial camera as L; setting the time t for the annular magnetic leakage flaw detector to collect the magnetic field signal data of the steel wire rope and transmit the magnetic field signal data to the portable computer for receiving, and judging the defect of the steel wire rope by the portable computer 1 The time from judging that the steel wire rope has defects to sending out photographing instructions is t 2 By adjusting the speed of forward movement of the traction wire rope to V, l=v is satisfied*(t 1 + t 2 ) The defect position of the steel wire rope can be accurately shot by the miniature industrial camera.
According to the distance between the annular magnetic flux leakage flaw detector and the miniature industrial camera, the moving speed of the steel wire rope is regulated by the traction device, and the time t from judging the magnetic flux leakage phenomenon of the section of steel wire rope to sending out a photographing instruction by the portable computer is regulated 2 When guaranteeing that wire rope's damage position removes miniature industrial camera, miniature industrial camera just in time is triggered, shoots it, realizes accurately shooting wire rope defect position, improves detection accuracy.
The intelligent detection and evaluation method for damage of the hoisting machinery steel wire rope based on the crane steel wire rope magnetic leakage-vision multi-mode fusion detection device specifically comprises the following steps:
step 3, after the portable computer receives the image, the image data is processed by loading a steel wire rope surface defect detection classification and quantitative identification algorithm module based on the regional suggestion network and image segmentation, and whether the surface of the section of steel wire rope has defects is judged:
if the surface defect type is one or more of wire breakage, rust, abrasion, diameter shrinkage and deformity, and quantitatively identifying the defect by analysis;
if not, judging that the defect is positioned in the section of the steel wire rope, marking the section of the steel wire rope at the moment, and then manually disassembling the section of the steel wire rope to further determine whether the defect is in the interior;
step 4, judging whether the steel wire rope reaches the scrapping standard according to the detection result in the step 3:
if yes, scrapping;
if not, the portable computer analyzes and calculates the defects of the steel wire rope by loading a safety state comprehensive evaluation algorithm module based on the accumulated and quantized damage and the residual strength of the steel wire rope, and obtains the residual strength and the static safety coefficient of the steel wire rope, thereby realizing accurate evaluation of the safety state of the steel wire rope.
In the step 3, the image data is processed by loading a steel wire rope surface defect detection classification and quantitative identification algorithm module based on the regional suggestion network and image segmentation, and the method specifically comprises the following steps:
step 3.1, constructing a fault detection and classification algorithm based on a Faster R-CNN area suggestion network through layering design of a multi-scale fault detector on the basis of qualitatively detecting the damage type in the step 2, and realizing specific classification and detection of the surface fault of the steel wire rope through two groups of classification layers and regression layers, wherein the detailed steps of the algorithm are as follows:
step 3.1.1, a large number of steel wire rope surface defect images are stored in a database of a portable computer and used as a training set, and the training set images are input into a deep neural network algorithm model for training to obtain a trained model; and then inputting the steel wire rope image shot by the camera into a trained model, and performing VGG16 convolution operation to obtain an original characteristic diagram.
Step 3.1.2, transmitting the original feature map into a region generation network RPN, extracting a region with the probability of defect target exceeding a set value, and detecting whether the surface of the steel wire rope has defects or not, wherein the method specifically comprises the following steps: carrying out convolution again on the basis of the original feature map obtained in the step 3.1.1 to generate 256 feature maps, then respectively carrying out classification and regression, and outputting a probability value of predicting a defect target or background belonging to the steel wire rope by a classification layer; the regression layer outputs the position of the defect target area of the steel wire rope in the image, and 3 parameters of the defect target frame are given: the position information of the point of the upper left corner of the target frame, the length and the height of the target frame. And determining the position of the defect target frame through the position information of the point of the upper left corner of the target frame. The size of the defect target is determined by the length and height of the target frame.
Step 3.1.3, the pooling layer converts the input features with different sizes into output features with fixed length, the 256 feature maps obtained by the convolution layer of the last layer are downsampled into the networks with the size of 7 multiplied by 7, the maximum pooling processing is carried out on each network, and the features with different sizes are changed into feature vectors with the fixed length of 7 multiplied by 7.
And 3.1.4, classifying, identifying and accurately positioning the defects of the steel wire rope by utilizing a prediction network after the pooling layer, and determining that the defects on the section of the steel wire rope belong to one or more of wire breakage, corrosion, abrasion, diameter shrinkage or deformity, wherein a plurality of defects possibly exist on the same detection section of the steel wire rope, so that the defects possibly comprise a plurality of defect types. The classification layer outputs the defect type and the probability value belonging to the defect type, the regression layer outputs the accurate position of each defect area in the image, and the position information of the point of the left upper corner of each defect target frame and the length and the height of the defect target frame are given; and marking the position and size information of each defect in the image by using the target frame, and marking the defect type and the probability value belonging to the defect type in the upper left corner area of the target frame of the defect area.
Step 3.2, quantitatively calculating the damage degree of the steel wire rope according to the determined defect type:
if the defect is determined to be broken, a broken area is segmented by a threshold segmentation method according to the detected broken defect area, vertical gray projection or horizontal projection is carried out on a threshold segmentation graph, then a starting point and an ending point of projection are taken as segmentation points, broken areas are segmented, and the number of the broken areas is counted by a target counting algorithm to obtain the number of the broken areas.
The fracture area is segmented by a threshold segmentation method, specifically: firstly, drawing a gray level histogram of a target area of a broken wire and a broken mouth, then performing smoothing treatment, taking an image gray level minimum value as a threshold value, and dividing according to the threshold value to obtain a broken mouth threshold value division diagram.
If the defect is determined to be one or more of rust, abrasion, shrinkage or deformity, determining the metal cross-sectional area reduction of the steel wire rope by using the change of the axial total magnetic flux of the steel wire rope under the saturation magnetization measured in the step 2 to determine the damage degree.
Further optimizing, the step 4 is to analyze and calculate the damage defect of the steel wire rope, obtain the residual strength and the static safety coefficient of the steel wire rope, realize the accurate assessment of the safety state of the steel wire rope, and specifically comprise the following steps:
step 4.1, calculating the residual strength of the steel wire rope according to the following method:
1) For the axial loss LF caused by the broken wire defect, namely the discontinuity of the steel wire rope in the axial direction, the broken wire condition in the failure length range is used as a judgment standard to calculate the residual strength of the steel wire rope, as shown in formulas (1) - (4);
S t =N*S 1 (1)
S w =M*S 1 (2)
Q LF =P(1-m) (4)
(1) In the formula (4) above, the formula (I),S t is the sum of the fracture areas within the failure length range of the steel wire rope;Nis the number of broken ends or broken wires;S 1 for each wire cross-sectional area;S w is the sum of the cross sectional areas of all steel wires of the steel wire rope;Mthe number of all steel wires of the steel wire rope is equal to that of all steel wires of the steel wire rope;mpercent metal cross-sectional area loss due to wire breakage;Pthe breaking force of the steel wire rope is measured through experiments;Q LF to take into account the residual intensity under LF type damage conditions. The failure length of the steel wire ropes twisted in different directions is inconsistent, the failure length of the steel wire ropes twisted in the same direction is 6 times of the twisting distance, and the failure length of the steel wire ropes twisted in different directions is 2.9 times of the twisting distance.
2) For loss of the cross-sectional area LMA of the steel wire rope caused by abrasion, radial shrinkage, deformity or rust, the residual strength of the steel wire rope is calculated according to the following formula:
Q LMA =PB -n (5)
in the method, in the process of the invention,Q LMA to take into account the residual strength under LMA type injury conditions,Pis the breaking force of the steel wire rope,Bis the ratio of the baseline amplitude of the detection signal obtained by the multi-stage annular magnetic flux leakage detection assembly to the baseline amplitude of the detection signal of the new steel wire rope with the same model,nis a characteristic parameter value.
3) For both LF-type and LMA-type damages considered, the remaining strength of the wire rope is calculated as follows:
Q S =Q LMA -P*m (6)
in the method, in the process of the invention, Q S to comprehensively consider the residual intensities under LF-type and LMA-type injury conditions.
And 4.2, calculating the static safety coefficient of the steel wire rope according to the residual strength of the steel wire rope calculated in the step 4.1 by the following formula:
in the method, in the process of the invention,Ris the static safety coefficient of the steel wire rope;
Qfor the remaining strength of the wire rope, when only LF-type damage is considered,Q=Q LF the method comprises the steps of carrying out a first treatment on the surface of the When only LMA type lesions are considered,Q= Q LMA the method comprises the steps of carrying out a first treatment on the surface of the When considering both LF type and LMA type lesions,Q=Q S ;
G max is provided for the steel wire ropeThe fixed maximum static load, i.e. the weight limit value of the steel wire rope.
Compared with the prior art, the invention has the beneficial effects that:
according to the intelligent detection and evaluation method for damage of the hoisting machinery steel wire rope, disclosed by the invention, on the basis of qualitative detection of the defect of the steel wire rope by magnetic leakage, the blind area-free detection classification and the lay length broken wire number identification of the whole rope with defects of broken wire, rust, abrasion, diameter shrinkage and deformity are realized by visual detection, so that the damage detection rate and the accuracy rate of the steel wire rope are improved, and intelligent and precise visual detection of the steel wire rope is realized; meanwhile, the residual strength and the safety state of the steel wire rope are accurately evaluated based on quantitative accumulated damages on the surface and the inside of the steel wire rope, potential safety hazards of the steel wire rope can be timely found, rope breakage accidents are prevented, auxiliary personnel scientifically detect maintenance and make a safe and economical rope replacement decision, the service life of the steel wire rope is scientifically prolonged, and the problem of waste in use caused by traditional periodic rope replacement or rope replacement strategies according to workload is avoided.
Drawings
FIG. 1 is a schematic diagram of a magnetic flux leakage-vision multi-mode fusion detection device for a steel wire rope of a crane;
FIG. 2 is a schematic diagram of the structure of the ring-shaped magnetic leakage flaw detection device after being opened;
FIG. 3 is a schematic view of the placement of three miniature industrial cameras;
FIG. 4 is a schematic diagram of a crane wire rope magnetic flux leakage-vision multi-mode fusion detection device;
FIG. 5 is a schematic diagram of a wire rope magnetic flux leakage detection device;
FIG. 6 is a flow chart of an intelligent detection and evaluation method for damage of a hoisting machinery steel wire rope fusing magnetic flux leakage and vision;
FIG. 7 is a schematic flow chart of a fault detection and classification algorithm of the Faster R-CNN regional advice network;
FIG. 8 is a schematic diagram of a Faster R-CNN network pooling layer;
FIG. 9 is a graph of the wire breakage detection result of a wire rope;
FIG. 10 is a graph of the result of another wire rope breakage detection;
FIG. 11 is a graph of wire deformity detection results;
FIG. 12 is a graph of the result of the wire rope wear detection;
FIG. 13 is a graph of the results of steel wire rope wear and corrosion detection;
FIG. 14 is a detected wire rope break image;
FIG. 15 is a broken wire target frame area extracted from the artwork;
FIG. 16 is a graph of threshold segmentation of a wire rope break area;
FIG. 17 is a gray histogram and a smoothed graph of a wire rope break target region;
fig. 18 is a view of wire breakage and fracture segmentation of a wire rope based on a vertical projection method;
fig. 19 is a diagram showing statistics of the number of wire rope breaks based on a target counting method.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
Embodiment one:
as shown in fig. 1-3, the crane wire rope magnetic flux leakage-vision multi-mode fusion detection device comprises a bracket 8, a portable computer 11, an annular magnetic flux leakage flaw detection device 3 and three miniature industrial cameras 2, wherein the annular magnetic flux leakage flaw detection device 3 and the three miniature industrial cameras 2 are arranged on the bracket 8.
The annular magnetic leakage flaw detection device comprises a body, a multi-stage annular magnetic leakage detection assembly 5 and a multi-loop permanent magnet excitation assembly 6, wherein the multi-stage annular magnetic leakage detection assembly 5 and the multi-loop permanent magnet excitation assembly 6 are arranged in the inner cavity of the body; the terminal surface of body is the ring form, and three miniature industrial cameras are fixed to be set up in the front end of body.
The multistage annular magnetic flux leakage detection assembly 5, the multi-loop permanent magnet excitation assembly 6 and the miniature industrial camera 2 are electrically connected with the portable computer 11 through leads 10.
In this embodiment, as shown in fig. 2, the body is divided into two split units 4 along a plane where an axis thereof is located, and the two split units are detachably connected by a hinge 12; the contact surfaces of the two split units are provided with first grooves 9 along the length of the contact surfaces, and when the two split units are assembled, the two first grooves jointly form a first hole for the steel wire rope 1 to pass through. Two ends of each split unit are provided with guide wheels 7, and second grooves are formed in the guide wheels along the circumferential direction; after the two split units are assembled, two second grooves at the same end form a guide hole for a steel wire rope to pass through, and the guide hole and the first hole are coaxially arranged.
As shown in fig. 3, the three micro industrial cameras 2 are uniformly arranged circumferentially around the axis of the first hole, and the shooting angle of each micro industrial camera is 120 ° or more. Through setting up three miniature industrial cameras, ensure to gather 360 no dead angle images of wire rope, improve and detect the precision.
The support 8 is a telescopic support, the height of which is adjusted according to the requirement, and the adaptability is improved.
In other embodiments, the body may be of unitary construction, such as being generally cylindrical.
In this embodiment, the distance between the annular leakage flux detection component and the miniature industrial camera in the annular leakage flux inspection apparatus is measuredL0.15m; the annular magnetic leakage flaw detector collects magnetic field signal data of the steel wire rope and transmits the magnetic field signal data to the portable computer for receiving, and the portable computer judges the time when the magnetic leakage phenomenon exists in the steel wire ropet 1 Setting the time from judging the magnetic leakage phenomenon of the steel wire rope to sending out a photographing instruction by the portable computer to 0.1st 2 For 0.05s by adjusting the speed of forward movement of the traction wire ropeVIs 1m/sThen satisfyL=V*(t 1 + t 2 ) The defect position of the steel wire rope can be accurately shot by the miniature industrial camera.
Embodiment two:
as shown in fig. 6, the intelligent detection and evaluation method for damage of the hoisting machinery steel wire rope based on the crane steel wire rope magnetic leakage-vision multi-mode fusion detection device specifically comprises the following steps:
And 2, after receiving magnetic field signal data, the portable computer qualitatively detects whether the section of steel wire rope has defects causing magnetic flux leakage and magnetic flux change by loading a LMA (loss of metallic crosssectionalarea) and LF (local flaw) -based steel wire rope multi-scale damage magnetic flux detection algorithm module, and when detecting that the section of steel wire rope has defects, the control module of the portable computer sends out an instruction to control the miniature industrial camera to photograph the section of steel wire rope and transmit a photographed image to the portable computer, as shown in fig. 4.
Step 3, after the portable computer receives the image, the image data is processed by loading a steel wire rope surface defect detection classification and quantitative identification algorithm module based on the regional suggestion network and image segmentation, and whether the surface of the section of steel wire rope has defects is judged:
if the surface defect type is one or more of wire breakage, rust, abrasion, shrinkage and deformity, and quantitatively identifying the defect by analysis;
if not, judging that the defect is positioned in the section of the steel wire rope, marking the section of the steel wire rope at the moment, and then manually disassembling the section of the steel wire rope to further determine whether the defect is in the interior;
step 4, judging whether the steel wire rope reaches the scrapping standard according to the detection result in the step 3:
if yes, scrapping;
if not, the portable computer analyzes and calculates the defects of the steel wire rope by loading a safety state comprehensive evaluation algorithm module based on the accumulated and quantized damage and the residual strength of the steel wire rope, and obtains the residual strength and the static safety coefficient of the steel wire rope, thereby realizing accurate evaluation of the safety state of the steel wire rope. The scrapping standard of the steel wire rope is the prior art and is not repeated.
In this embodiment, in the step 2, the method for detecting multi-scale damage and leakage of magnetic flux of the wire rope based on LMA and LF specifically includes the following steps:
(1) The annular magnetic leakage flaw detection device consisting of the multi-loop permanent magnet excitation assembly and the multi-stage annular magnetic leakage detection assembly (namely the Hall array sensor) is designed, as shown in fig. 5, a closed excitation magnetic circuit is formed by adopting a permanent magnet and a magnetic yoke made of industrial pure iron, and the excitation uniformity is improved by adopting a multi-loop excitation mode, so that the saturated excitation of the steel wire rope is realized. When the steel wire rope moves 0.65-mm relatively, the encoder sends a synchronous pulse to the acquisition unit, the data acquisition unit acquires data of 30 Hall channels, and the acquisition of magnetic flux leakage data of the steel wire rope is completed along with the steel wire rope passing through the excitation assembly.
(2) And detecting the axial total magnetic flux in the steel wire rope and magnetic leakage caused by discontinuity in the steel wire rope, such as wire breakage, rust pit, deformation and the like, so as to perform qualitative detection on the defects of the steel wire rope.
Local damage LF refers to discontinuity in a steel wire rope, such as broken wire, a broken wire etching pit, deeper steel wire abrasion or degradation of local physical states of other steel wire ropes, and the like, can cause local leakage magnetic fields of the steel wire rope, finally cause waveform fluctuation and mutation of LF signals, and realize qualitative detection of defects such as broken wire, abrasion, corrosion and the like through LF curve comparison analysis. The metal cross-sectional area loss LMA is determined by comparing the detection point with a datum point on the steel wire rope, which symbolizes the maximum metal cross-sectional area, and when the crane works normally, the steel wire rope at the safety ring is not used, the cross-sectional area of the steel wire rope at the safety ring close to the fixed end of the winding drum is taken as the initial cross-sectional area, and the LMA curve is subjected to comparative analysis, so that the metal cross-sectional area loss amount identification of the steel wire rope is realized.
In this embodiment, in the step 3, the image data is processed by loading a classification and quantitative recognition algorithm module for detecting the surface defects of the steel wire rope based on the area suggestion network and the image segmentation, which specifically includes the following steps:
step 3.1, constructing a fault detection and classification algorithm based on a Faster R-CNN area suggestion network through a multi-scale fault detector layering design on the basis of qualitatively detecting the damage type in the step 2, and realizing specific classification and detection of the surface faults of the steel wire rope through two groups of classification layers and regression layers as shown in fig. 7, wherein the detailed steps of the algorithm are as follows:
step 3.1.1, a large number of steel wire rope surface defect images are stored in a database of a portable computer and used as a training set, and the training set images are input into a deep neural network algorithm model for training to obtain a trained model; and then inputting the steel wire rope image shot by the camera into a trained model, and performing VGG16 convolution operation to obtain an original characteristic diagram.
Step 3.1.2, transmitting the original feature map into a region generation network RPN, extracting a region with the probability of defect target exceeding a set value, and detecting whether the surface of the steel wire rope has defects or not, wherein the method specifically comprises the following steps: carrying out convolution again on the basis of the original feature map obtained in the step 3.1.1 to generate 256 feature maps, then respectively carrying out classification and regression, and outputting a probability value of predicting a defect target or background belonging to the steel wire rope by a classification layer; the regression layer outputs the position of the defect target area of the steel wire rope in the image, and 3 parameters of a defect position target frame are given: the position information of the point of the upper left corner of the target frame, the length and the height of the target frame.
Step 3.1.3, the pooling layer converts the input features with different sizes into output features with fixed length, as shown in fig. 8, downsampling 256 feature graphs obtained by the convolution layer of the last layer into networks with the size of 7×7, performing maximum pooling treatment on each network, changing the features with different sizes into feature vectors with uniform sizes, ensuring that each window with different sizes has the same dimension, forming the feature graphs with fixed sizes, and facilitating full-connection operation.
And 3.1.4, classifying, identifying and accurately positioning the defects of the steel wire rope by utilizing a prediction network after the pooling layer, and determining which one or more defects belong to wire breakage, corrosion, abrasion, diameter shrinkage or deformity on the section of the steel wire rope. The classifying layer outputs the defect type and the probability value belonging to the defect of the type, the regression layer outputs the accurate position of each defect area in the image, gives the position information of the point of the left upper corner of each defect target frame, the length and the height of the target frame, marks the position and the size information of each defect in the image by using the target frame, and marks the defect type and the probability value belonging to the defect of the type at the defect area target frame.
If the image detection method does not detect the surface defects of the steel wire rope, the defects such as wire breakage, corrosion and the like of the steel wire rope are generated in the steel wire rope, and at the moment, the steel wire rope structure at the position needs to be disassembled manually to verify whether the internal defects exist. The partial detection results of the fault detection and classification algorithm of the fast R-CNN area suggestion network are shown in fig. 9-13, wherein fig. 9 and 10 are graphs of broken wire detection results, fig. 11 is a graph of malformation detection results, and fig. 12 and 13 are graphs of abrasion detection results. Wherein, the number at the target frame in the figure is the probability of predicting the defects, such as the probability of the defects being broken wires is 0.98 in fig. 10, and the probability of the defects being worn is 0.92 in fig. 12. In the present embodiment, the threshold value is set to 0.8, and when the probability of a defect by deep learning is greater than the set threshold value, it is determined to be the defect.
For the steel wire rope stress bending parts which cannot be detected by electromagnetic methods such as reels, pulleys, rope clamps, wedges and joints, a detector can directly hold detection equipment to shoot and identify defects, so that the detection of the whole rope without blind areas is realized, and images are shown in figures 11-13.
Step 3.2, quantitatively calculating the damage degree according to the determined defect type:
if the defect is determined to be broken, a broken area is segmented by a threshold segmentation method according to the detected broken defect area, vertical gray projection or horizontal projection is carried out on a threshold segmentation graph, then a starting point and an ending point of projection are taken as segmentation points, broken areas are segmented, and the number of the broken areas is counted by a target counting algorithm to obtain the number of the broken areas.
The fracture area is segmented by a threshold segmentation method, specifically: firstly, drawing a gray level histogram of a target area of a broken wire and a broken mouth, then performing smoothing treatment, taking an image gray level minimum value as a threshold value, and dividing according to the threshold value to obtain a broken mouth threshold value division diagram. If the defect is determined to be one or more of rust, abrasion, shrinkage or deformity, determining the metal cross-sectional area reduction of the steel wire rope by utilizing the change of the axial total magnetic flux of the steel wire rope under the saturation magnetization measured in the step 2 to determine the damage degree. The loss LMA of the metal cross-sectional area of the steel wire rope is measured by comparing the detection point with a datum point of the maximum metal cross-sectional area symbolized on the steel wire rope, the steel wire rope at the safety ring is not used in the normal operation of the crane, the cross-sectional area of the steel wire rope close to the safety ring at the fixed end of the winding drum is taken as the initial cross-sectional area, and the LMA curve is subjected to comparative analysis, so that the loss amount identification of the metal cross-sectional area of the steel wire rope is realized.
For example, fig. 14 shows a detected wire rope broken image, and fig. 15 shows a broken target frame area extracted from an original drawing. The gray level histogram of the target region of the wire breakage is drawn, as shown in fig. 17, and then the smoothing process is performed, and as can be seen from the gray level smoothing graph, there is a minimum value between gray levels 0 to 100, the minimum value is taken as a threshold value, and the threshold value segmentation map shown in fig. 16 is obtained after the threshold value segmentation. And then, carrying out vertical projection on the threshold segmentation graph, taking the starting point and the ending point of projection as segmentation points to segment the fracture, as shown in fig. 18, and adopting a target counting algorithm to realize the statistics of the number of the fracture, so as to obtain the number of the broken wires as 3, as shown in fig. 19.
In this embodiment, in the step 4, the method for comprehensively evaluating the safety state based on the accumulated and quantized damage and the residual strength of the steel wire rope is specifically as follows: and establishing a corresponding model of metal sectional area loss and residual strength, obtaining the sum of the unbroken steel wire strength of the steel wire rope, namely the residual strength, and judging the static safety coefficient according to the sum.
Step 4.1, calculating the residual strength of the steel wire rope according to the following method:
1) The residual strength of the wire rope is calculated by taking the broken wire condition in the failure length range as a judgment standard for the axial loss caused by the local defect LF (local flaw) of broken wire, namely the discontinuity in the axial direction of the wire rope, as shown in formulas (1) - (4).
S t =N*S 1 (1)
S w =M*S 1 (2)
Q LF =P(1-m) (4)
(1) In the formula (4) above, the formula (I),S t is the sum of the fracture areas within the failure length range of the steel wire rope,Nfor the number of breaks or broken filaments,S 1 for each steel wire cross-sectional area,S w is the sum of the cross-sectional areas of all steel wires of the steel wire rope,Mfor all the number of steel wires of the steel wire rope,mas a percentage of metal cross-sectional area loss due to wire breakage,Pis the breaking force of the steel wire rope,Q LF to take into account the residual intensity under LF type damage conditions. The failure length of the steel wire ropes twisted in different directions is inconsistent, the failure length of the steel wire ropes twisted in the same direction is 6 times of the twisting distance, and the failure length of the steel wire ropes twisted in different directions is 2.9 times of the twisting distance.
2) For the loss LMA (loss of metallic crosssectionalarea) of metal cross-sectional area caused by abrasion, radial shrinkage, rust and the like, the residual strength can not be directly determined according to the linear relation between the magnetic leakage signal and the residual strength due to the twisting structure of the steel wire rope, and the residual strength of the steel wire rope is calculated according to the following formula
Q LMA =PB -n (5)
In the method, in the process of the invention,Q LMA to take into account the residual strength under LMA type injury conditions,Pb is the ratio of the baseline amplitude of the detection signal obtained by the detection of the annular magnetic flux leakage flaw detection device to the baseline amplitude of the detection signal of the new steel wire rope with the same model,nanalyzing a large number of steel wire rope twisting conditions and using conditions as characteristic parameter values, wherein the characteristic parameter values are used for steel wire ropes for vertical lifting of a cranenTaking 0.05.
3) For the case of considering both LF type and LMA type damage, the residual strength of the steel wire rope is calculated as follows
Q S =Q LMA -P*m (6)
In the method, in the process of the invention, Q S to comprehensively consider the residual intensities under LF-type and LMA-type injury conditions.
The metal cross-sectional area loss of the steel wire rope twisted in the same direction is detected through magnetic leakage and visual detection, the residual strength of the steel wire rope is calculated according to formulas (1) - (6), and the tensile test of the steel wire rope is carried out in a mechanical laboratory to obtain the breaking strength, as shown in table 1. It can be seen that the remaining total strength of the steel wire rope is calculated to be smaller than or close to the breaking strength of the test through the loss of the metal sectional area, and the method for calculating the remaining total strength by utilizing the loss of the metal sectional area is safe and feasible.
Table 1 analysis and calculation of wire rope strength
And 4.2, calculating the static safety coefficient of the steel wire rope according to the residual strength of the steel wire rope calculated in the step 4.1 by the following formula:
in the method, in the process of the invention, Ris the static safety coefficient of the steel wire rope;Qis the residual strength of the steel wire rope; g max The maximum static load set for the wire rope, i.e. the weight limit value of the wire rope.
For example, according to the index of a 28mm six-strand seven-wire rope, the minimum breaking force is 414kN in the case of galvanization and 466kN in the case of no galvanization. The residual strength of the steel wire rope is 288.33kN according to the formulas (1) - (6), and the static safety coefficient is 8.24 under the condition that the maximum tension born by the steel wire rope under the limited running condition is 35kN, so that the residual strength is reduced, the safety coefficient is reduced and the degradation trend is serious with the increase of the service time.
It should be understood that the detailed description and specific examples, while indicating the invention, are intended for purposes of illustration only and are not intended to limit the invention; any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. The magnetic flux leakage-vision multi-mode fusion detection device for the crane steel wire rope is characterized by comprising an annular magnetic flux leakage flaw detection device, three miniature industrial cameras and a portable computer;
the annular magnetic flux leakage flaw detection device comprises a body, a multi-stage annular magnetic flux leakage detection assembly and a multi-loop permanent magnet excitation assembly, wherein the multi-stage annular magnetic flux leakage detection assembly and the multi-loop permanent magnet excitation assembly are arranged in an inner cavity of the body; the end face of the body is annular, and the miniature industrial camera is fixedly arranged at the front end of the body;
the multistage annular magnetic flux leakage detection assembly, the multi-loop permanent magnet excitation assembly and the miniature industrial camera are electrically connected with the portable computer.
2. The crane wire rope magnetic flux leakage-vision multi-mode fusion detection device according to claim 1, wherein the body is divided into two split units along a plane where an axis of the body is located, and the two split units are detachably connected;
the contact surfaces of the two split units are provided with first grooves along the length direction, and when the two split units are assembled, the two first grooves jointly form a first hole for a steel wire rope to pass through.
3. The magnetic flux leakage-vision multi-mode fusion detection device for the steel wire rope of the crane according to claim 2, wherein guide wheels are arranged at two ends of each split unit, and second grooves are formed in the guide wheels along the circumferential direction; when the two split units are assembled, the second grooves on the two guide wheels positioned at the same end form a guide hole for the steel wire rope to pass through.
4. The crane wire rope magnetic flux leakage-vision multi-mode fusion detection device according to claim 3, wherein three micro industrial cameras are uniformly arranged circumferentially around the axis where the first hole is located, and the shooting angle of each micro industrial camera is greater than or equal to 120 °.
5. The crane wire rope magnetic flux leakage-vision multi-mode fusion detection device according to claim 1, further comprising a support, wherein the annular magnetic flux leakage flaw detection device is arranged on the support, and the support is a telescopic support.
6. The crane wire rope magnetic flux leakage-vision multi-mode fusion detection device according to claim 1, wherein the distance from the annular magnetic flux leakage flaw detection device to the miniature industrial camera is set to be L; setting the time t for the annular magnetic leakage flaw detector to collect the magnetic field signal data of the steel wire rope and transmit the magnetic field signal data to the portable computer for receiving, and judging the defect of the steel wire rope by the portable computer 1 The time from judging that the steel wire rope has defects to sending out photographing instructions is t 2 By adjusting the speed of forward movement of the traction wire rope to V, l=v (t 1 + t 2 )。
7. The intelligent detection and evaluation method for damage of the hoisting machinery steel wire rope based on the magnetic leakage and vision fusion is characterized by specifically comprising the following steps of:
step 1, starting an annular magnetic leakage flaw detection device, and pulling one end of a steel wire rope to pass through a first hole of the annular magnetic leakage flaw detection device at a set speed and continuously moving forwards; when the corresponding section of the steel wire rope passes through the first hole of the annular magnetic leakage flaw detection device, the saturated excitation of the section of the steel wire rope is realized through the multi-loop permanent magnet excitation assembly, then the magnetic field signal data of the steel wire rope is collected through the multi-stage annular magnetic leakage detection assembly, and the magnetic field signal data is transmitted to the portable computer in real time;
step 2, after the portable computer receives magnetic field signal data, qualitatively detecting whether the section of steel wire rope has defects causing magnetic flux leakage and magnetic flux change by loading a steel wire rope multi-scale damage magnetic flux leakage detection algorithm module based on LMA and LF, and when detecting that the section of steel wire rope has defects, sending an instruction by a control module of the portable computer to control a miniature industrial camera to photograph the section of steel wire rope and transmitting a photographed image to the portable computer;
step 3, after the portable computer receives the image, the image data is processed by loading a steel wire rope surface defect detection classification and quantitative identification algorithm module based on the regional suggestion network and image segmentation, and whether the surface of the section of steel wire rope has defects is judged:
if the surface defect type is one or more of wire breakage, rust, abrasion, shrinkage and deformity, and quantitatively identifying the defect by analysis;
if not, judging that the defect is positioned in the section of the steel wire rope, marking the section of the steel wire rope at the moment, and then manually disassembling the section of the steel wire rope to further determine whether the defect is in the interior;
step 4, judging whether the steel wire rope reaches the scrapping standard according to the detection result in the step 3:
if yes, scrapping;
if not, the portable computer analyzes and calculates the defects of the steel wire rope by loading a safety state comprehensive evaluation algorithm module based on the accumulated and quantized damage and the residual strength of the steel wire rope, and obtains the residual strength and the static safety coefficient of the steel wire rope, thereby realizing accurate evaluation of the safety state of the steel wire rope.
8. The intelligent detection and evaluation method for damage to the hoisting machinery steel wire rope by fusing magnetic flux leakage and vision according to claim 7, wherein in the step 3, the image data is processed by loading a steel wire rope surface defect detection classification and quantitative identification algorithm module based on a region suggestion network and image segmentation, and the method specifically comprises the following steps:
step 3.1, constructing a fault detection and classification algorithm based on a Faster R-CNN area suggestion network through layering design of a multi-scale fault detector on the basis of qualitatively detecting the damage type in the step 2, and realizing specific classification and detection of the surface fault of the steel wire rope through two groups of classification layers and regression layers, wherein the detailed steps of the algorithm are as follows:
step 3.1.1, a large number of steel wire rope surface defect images are stored in a database of a portable computer and used as a training set, and the training set images are input into a deep neural network algorithm model for training to obtain a trained model; then inputting the steel wire rope image shot by the camera into a trained model, and performing VGG16 convolution operation to obtain an original feature map;
step 3.1.2, transmitting the original feature map into a region generation network RPN, extracting a region with the probability of defect target exceeding a set value, and detecting whether the surface of the steel wire rope has defects or not, wherein the method specifically comprises the following steps: carrying out convolution again on the basis of the original feature map obtained in the step 3.1.1 to generate 256 feature maps, then respectively carrying out classification and regression, and outputting a probability value of predicting a defect target or background belonging to the steel wire rope by a classification layer; the regression layer outputs the position of the defect target area of the steel wire rope in the image, and 3 parameters of a defect position target frame are given: the position information of the point of the left upper corner of the target frame, the length and the height of the target frame;
step 3.1.3, the pooling layer converts the input features with different sizes into output features with fixed length, the 256 feature graphs obtained by the last layer of convolution layer are downsampled into the networks with the size of 7 multiplied by 7, the maximum pooling treatment is carried out on each network, and the features with different sizes are changed into feature vectors with the fixed length of 7 multiplied by 7;
step 3.1.4, classifying, identifying and accurately positioning the defects of the steel wire rope by utilizing a prediction network after a pooling layer, outputting the types of the defects and probability values of the defects in the types by a classification layer, outputting the accurate positions of the defect areas in an image by a regression layer, giving out the position information of points of the left upper corners of the defect target frames, the length and the height of the defect target frames, marking the position and the size information of the defects in the image by the target frames, and marking the types of the defects and the probability values of the defects in the types in the left upper corners of the defect area target frames;
step 3.2, quantitatively calculating the damage degree of the steel wire rope according to the determined defect type:
if the defect is determined to be broken, a broken area is segmented by a threshold segmentation method according to the detected broken defect area, vertical gray projection or horizontal projection is carried out on a threshold segmentation graph, then a starting point and an ending point of projection are taken as segmentation points, broken areas are segmented, and the number of the broken areas is counted by a target counting algorithm to obtain the number of the broken wires;
if the defect is determined to be one or more of rust, abrasion, shrinkage or deformity, determining the metal cross-sectional area reduction of the steel wire rope by using the change of the axial total magnetic flux of the steel wire rope under the saturation magnetization measured in the step 2 to determine the damage degree.
9. The intelligent detection and evaluation method for damage of the hoisting machinery steel wire rope fusing magnetic flux leakage and vision according to claim 8, wherein the step 4 is characterized by analyzing and calculating defects of the steel wire rope, obtaining residual strength and static safety coefficient of the steel wire, and realizing accurate evaluation of the safety state of the steel wire rope, and specifically comprises the following steps:
step 4.1, calculating the residual strength of the steel wire rope according to the following method:
1) For the axial loss LF caused by the broken wire defect, namely the discontinuity of the steel wire rope in the axial direction, the broken wire condition in the failure length range is used as a judgment standard to calculate the residual strength of the steel wire rope, as shown in formulas (1) - (4);
S t =N*S 1 (1)
S w =M*S 1 (2)
Q LF =P(1-m) (4)
(1) In the formula (4) above, the formula (I),S t is broken within the failure length range of the steel wire ropeThe sum of the mouth areas is used to determine,Nfor the number of breaks or broken filaments,S 1 for each steel wire cross-sectional area,S w is the sum of the cross-sectional areas of all steel wires of the steel wire rope,Mfor all the number of steel wires of the steel wire rope,mas a percentage of metal cross-sectional area loss due to wire breakage,Pis the breaking force of the steel wire rope,Q LF to take into account the residual strength under LF type damage conditions;
for different twisted steel wire ropes, the failure length is inconsistent, the failure length of the same-direction twisted steel wire rope is 6 times of the twisting distance, and the failure length of the different-direction twisted steel wire rope is 2.9 times of the twisting distance;
2) For the loss of the cross-sectional area LMA of the steel wire rope caused by abrasion, radial shrinkage, deformity or rust, the residual strength of the steel wire rope is calculated according to the following formula:
Q LMA =PB -n (5)
in the method, in the process of the invention,Q LMA to take into account the residual strength under LMA type injury conditions,Pb is the ratio of the baseline amplitude of the detection signal obtained by the detection of the annular magnetic flux leakage flaw detection device to the baseline amplitude of the detection signal of the new steel wire rope with the same model,nis a characteristic parameter value;
3) For both LF-type and LMA-type damages considered, the remaining strength of the wire rope is calculated as follows:
Q S =Q LMA -P*m (6)
in the method, in the process of the invention, Q S to comprehensively consider the residual strength under the LF type and LMA type damage conditions;
and 4.2, calculating the static safety coefficient of the steel wire rope according to the residual strength of the steel wire rope calculated in the step 4.1 by the following formula:
in the method, in the process of the invention,Ris the static safety coefficient of the steel wire rope;QIs the residual strength of the steel wire rope;G max the maximum static load set for the wire rope, i.e. the weight limit value of the wire rope.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310345805.9A CN116046883B (en) | 2023-04-03 | 2023-04-03 | Crane steel wire rope magnetic leakage-vision multi-mode fusion detection device and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310345805.9A CN116046883B (en) | 2023-04-03 | 2023-04-03 | Crane steel wire rope magnetic leakage-vision multi-mode fusion detection device and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116046883A true CN116046883A (en) | 2023-05-02 |
CN116046883B CN116046883B (en) | 2023-06-09 |
Family
ID=86131685
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310345805.9A Active CN116046883B (en) | 2023-04-03 | 2023-04-03 | Crane steel wire rope magnetic leakage-vision multi-mode fusion detection device and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116046883B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117197150A (en) * | 2023-11-08 | 2023-12-08 | 山东新沙单轨运输装备有限公司 | Method and system for controlling stability of monorail crane based on artificial intelligence |
CN117237357A (en) * | 2023-11-15 | 2023-12-15 | 上海杰臻电气技术有限公司 | Machine vision-based steel wire rope online monitoring system and method |
CN118150588A (en) * | 2024-05-13 | 2024-06-07 | 浙江省三建建设集团有限公司 | Workpiece damage detection device and detection method thereof |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002005896A (en) * | 2000-06-26 | 2002-01-09 | Toshiba Elevator Co Ltd | Apparatus for detecting flaw of wire rope |
CN204405562U (en) * | 2015-01-14 | 2015-06-17 | 兖州煤业股份有限公司 | Strong magnetic-online nondestructive inspection system of image associating wire rope |
KR20170121686A (en) * | 2017-03-30 | 2017-11-02 | 한국수자원공사 | Cleaning and Damage Monitering Method of Wire Rope of Moving Type with Camera and Magnetic Sensor |
CN108706310A (en) * | 2018-05-31 | 2018-10-26 | 武汉理工大学 | Steel cable core conveying belt integration on-line monitoring system |
CN108776171A (en) * | 2018-09-12 | 2018-11-09 | 中国计量大学 | Steel wire rope nondestructive inspection sensing device based on multiloop excitation and image analysis |
CN208334270U (en) * | 2018-07-03 | 2019-01-04 | 北京巨辰检测服务有限公司 | Steel wire rope damage detection apparatus |
CN109212016A (en) * | 2018-10-18 | 2019-01-15 | 青岛理工大学 | Separable steel wire rope flaw detection device and method based on magnetic concentration effect |
CN109682824A (en) * | 2018-12-28 | 2019-04-26 | 河南科技大学 | Nondestructive test method of wire rope and its device based on image co-registration |
CN111862083A (en) * | 2020-07-31 | 2020-10-30 | 中国矿业大学 | Comprehensive monitoring system and method for steel wire rope state based on vision-electromagnetic detection |
CN214122103U (en) * | 2020-12-14 | 2021-09-03 | 青岛理工大学 | Steel wire rope flaw detection instrument based on magnetic leakage detection and optical detection |
-
2023
- 2023-04-03 CN CN202310345805.9A patent/CN116046883B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002005896A (en) * | 2000-06-26 | 2002-01-09 | Toshiba Elevator Co Ltd | Apparatus for detecting flaw of wire rope |
CN204405562U (en) * | 2015-01-14 | 2015-06-17 | 兖州煤业股份有限公司 | Strong magnetic-online nondestructive inspection system of image associating wire rope |
KR20170121686A (en) * | 2017-03-30 | 2017-11-02 | 한국수자원공사 | Cleaning and Damage Monitering Method of Wire Rope of Moving Type with Camera and Magnetic Sensor |
CN108706310A (en) * | 2018-05-31 | 2018-10-26 | 武汉理工大学 | Steel cable core conveying belt integration on-line monitoring system |
CN208334270U (en) * | 2018-07-03 | 2019-01-04 | 北京巨辰检测服务有限公司 | Steel wire rope damage detection apparatus |
CN108776171A (en) * | 2018-09-12 | 2018-11-09 | 中国计量大学 | Steel wire rope nondestructive inspection sensing device based on multiloop excitation and image analysis |
CN109212016A (en) * | 2018-10-18 | 2019-01-15 | 青岛理工大学 | Separable steel wire rope flaw detection device and method based on magnetic concentration effect |
CN109682824A (en) * | 2018-12-28 | 2019-04-26 | 河南科技大学 | Nondestructive test method of wire rope and its device based on image co-registration |
CN111862083A (en) * | 2020-07-31 | 2020-10-30 | 中国矿业大学 | Comprehensive monitoring system and method for steel wire rope state based on vision-electromagnetic detection |
CN214122103U (en) * | 2020-12-14 | 2021-09-03 | 青岛理工大学 | Steel wire rope flaw detection instrument based on magnetic leakage detection and optical detection |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117197150A (en) * | 2023-11-08 | 2023-12-08 | 山东新沙单轨运输装备有限公司 | Method and system for controlling stability of monorail crane based on artificial intelligence |
CN117197150B (en) * | 2023-11-08 | 2024-02-02 | 山东新沙单轨运输装备有限公司 | Method and system for controlling stability of monorail crane based on artificial intelligence |
CN117237357A (en) * | 2023-11-15 | 2023-12-15 | 上海杰臻电气技术有限公司 | Machine vision-based steel wire rope online monitoring system and method |
CN117237357B (en) * | 2023-11-15 | 2024-01-30 | 上海杰臻电气技术有限公司 | Machine vision-based steel wire rope online monitoring system and method |
CN118150588A (en) * | 2024-05-13 | 2024-06-07 | 浙江省三建建设集团有限公司 | Workpiece damage detection device and detection method thereof |
Also Published As
Publication number | Publication date |
---|---|
CN116046883B (en) | 2023-06-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116046883B (en) | Crane steel wire rope magnetic leakage-vision multi-mode fusion detection device and method | |
CN111862083B (en) | Visual-electromagnetic detection-based steel wire rope state comprehensive monitoring system and method | |
CA2737897C (en) | System and method for testing ropes | |
CN103476697B (en) | For identifying the equipment of the state of scrapping of the fibrecord used in weight-lifting equipment | |
JP6329304B1 (en) | Rope inspection equipment | |
CN103279765A (en) | Steel wire rope surface damage detection method based on image matching | |
CN111678979B (en) | Wire rope eddy current thermal imaging defect detection method and device | |
CN110653271B (en) | Automatic grading device and grading method for roll surface quality of hot-rolled strip steel coiling pinch roll | |
CN114119595A (en) | GMAW welding quality on-line monitoring and evaluating method based on integrated deep learning | |
CN110526118B (en) | Bridge crane mechanical steel wire rope detection device and detection method | |
JPH11325844A (en) | Diagnosis method of wire rope | |
CN106815831B (en) | Method and device for detecting abrasion of steel wire rope | |
CN111855794A (en) | Steel wire rope flaw detection system and flaw detection method thereof | |
CN114371215A (en) | Method and apparatus for monitoring integrity of a wireline apparatus | |
CN116086677B (en) | Multi-wire rope tension balance monitoring method and system and electronic equipment | |
CN212255191U (en) | Eddy current thermal imaging defect detection device for steel wire rope | |
CN113567540A (en) | Steel wire rope nondestructive testing equipment, system and method | |
CN112037205A (en) | Crane crack detection method based on deep learning | |
CN116256368A (en) | Elevator composite steel belt scrapping judging method based on internal and external defect detection | |
CN107328852B (en) | Steel wire detection method of vehicle-mounted steel wire rope operation equipment | |
CN114380166A (en) | Dynamic quantitative evaluation device and method for elevator steel belt damage | |
JP7143690B2 (en) | Magnetic material inspection system, magnetic material inspection apparatus, and magnetic material inspection method | |
CN115330776B (en) | Method for detecting abrasion degree of steel wire rope | |
CN115221748A (en) | Method for predicting stress of steel wire in hoisting steel wire rope based on three-dimensional image recognition | |
CN116883503A (en) | Visual identification and detection method for tail rope winding AI of vertical shaft hoist |
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 |