CN113963216A - Steel wire rope defect identification method, device, equipment and medium - Google Patents
Steel wire rope defect identification method, device, equipment and medium Download PDFInfo
- Publication number
- CN113963216A CN113963216A CN202111325438.3A CN202111325438A CN113963216A CN 113963216 A CN113963216 A CN 113963216A CN 202111325438 A CN202111325438 A CN 202111325438A CN 113963216 A CN113963216 A CN 113963216A
- Authority
- CN
- China
- Prior art keywords
- defect
- wire rope
- target
- image
- steel wire
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 246
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 142
- 239000010959 steel Substances 0.000 title claims abstract description 142
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000007781 pre-processing Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims description 43
- 230000003321 amplification Effects 0.000 claims description 15
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 11
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000003708 edge detection Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 11
- 238000013135 deep learning Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000007797 corrosion Effects 0.000 description 3
- 238000005260 corrosion Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000005299 abrasion Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000009941 weaving Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003739 neck Anatomy 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000036319 strand breaking Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/60—Rotation of whole images or parts thereof
-
- 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
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a method for identifying defects of a steel wire rope, which comprises the following steps: and carrying out image preprocessing on the target steel wire rope image to obtain a preprocessed image. And downloading the latest target defect model from the knowledge base, identifying the defects of the preprocessed image by using the target defect model in combination with a deep learning technology, and uploading the detection result to a data platform once the defects are found, so that the effects of improving the detection efficiency of the defects of the steel wire rope, reducing the misjudgment risk and saving the labor cost are achieved. In addition, a wire rope defect identification device, a computer device and a storage medium are also provided.
Description
Technical Field
The invention relates to the technical field of overhead transmission lines, in particular to a method, a device, equipment and a medium for identifying defects of a steel wire rope.
Background
The anti-twist steel wire rope is a main machine tool in tension paying-off construction, is also called as a woven anti-twist steel wire rope, and is also called as a non-twist steel wire rope or a non-rotating steel wire rope. The steel wire rope is formed by symmetrically weaving a group of left-twisted round strand steel wire ropes and a group of right-twisted round strand steel wire ropes (crossed spiral tracks), wherein the number of the left-twisted strands is equal to that of the right-twisted strands, and two groups of spiral moments are balanced due to opposite directions, so that the steel wire ropes have the characteristic of no rotation when stressed, and the steel wire rope is applied to equipment such as a traction mechanism, a winding mechanism, a paying-off tackle and the like.
However, in the long-term use process, the steel wire rope is worn by surface friction with various devices and tools, and also deformed and damaged by load impact and overload in the traction operation process, and the problems of rusting, twisting, strand breaking and the like are caused by the influence of the external environment. For the above reasons, the wire rope will inevitably be defective. However, any defect can cause the steel wire rope to run and even break, which causes serious safety accidents.
Therefore, in addition to regular maintenance, before tension stringing construction, the weaving quality and appearance quality of the anti-twisting steel wire rope are often checked by appearance inspection methods such as hand feeling and visual inspection, and once defects are found by inspectors, the inspectors need to report and maintain in time. However, this method relies mainly on the experience of the person to make the judgment, and is likely to cause erroneous judgment due to fatigue under long-term observation. This approach also requires a significant amount of human resources.
Disclosure of Invention
In view of the above, it is desirable to provide a method, an apparatus, a device and a medium for identifying a defect of a wire rope, which avoid manual field inspection.
A method of wire rope defect identification, the method comprising:
acquiring a target steel wire rope image, and performing image preprocessing on the target steel wire rope image to acquire a preprocessed image;
and downloading a target defect model from a knowledge base, and performing defect identification on the preprocessed image according to the target defect model so as to identify and obtain the target defect of the steel wire rope in the target steel wire rope image.
In one embodiment, before the downloading the target defect model from the knowledge base, the method further includes:
constructing an image defect library, wherein the image defect library comprises steel wire rope defect images and defect labels matched with the steel wire rope defect images;
performing amplification pretreatment on the steel wire rope defect image, wherein the amplification pretreatment comprises at least one of image blurring, angle rotation, contrast adjustment and channel switching, and acquiring the treated amplified steel wire rope defect image and a matched defect label;
inputting the amplified steel wire rope defect image and the matched defect label into a training defect model for iterative training until the training defect model is determined to be converged based on a training output result of the training defect model and the defect label, and obtaining a trained target defect model.
In one embodiment, the defect signature includes at least one of broken filaments, staggered wires, poor splicing of the cord sleeve, loose strands, uneven pitch, loose strands, wavy, lantern, kinked, poor oiling, surface damage, wear distortion, mechanical wear, diameter thinning, corrosion.
In one embodiment, after the identifying the target defect of the wire rope in the target wire rope image, the method further includes:
inputting the target steel wire rope image and the target defect into the target defect model for iterative training so as to adjust the hyper-parameters in the convolutional neural network.
In one embodiment, the method further comprises:
and classifying the target steel wire rope image according to the target defects, and displaying the target steel wire rope image by taking the same category as a division.
In one embodiment, after the identifying the target defect of the wire rope in the target wire rope image, the method further includes:
and acquiring a preset alarm level standard, determining an alarm level according to the target defect and the alarm level standard, and sending an alarm prompt of the alarm level.
In one embodiment, the preprocessing includes at least one of grayscale processing, gaussian blur, on-off operations, and edge detection.
A wire rope defect identification device, the device comprising:
the preprocessing module is used for acquiring a target steel wire rope image, and carrying out image preprocessing on the target steel wire rope image to acquire a preprocessed image;
and the model identification module is used for downloading a target defect model from a knowledge base and identifying the defects of the preprocessed image according to the target defect model so as to identify and obtain the target defects of the steel wire ropes in the target steel wire rope image.
A computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of:
acquiring a target steel wire rope image, and performing image preprocessing on the target steel wire rope image to acquire a preprocessed image;
and downloading a target defect model from a knowledge base, and performing defect identification on the preprocessed image according to the target defect model so as to identify and obtain the target defect of the steel wire rope in the target steel wire rope image.
A wire rope defect identification apparatus comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of:
acquiring a target steel wire rope image, and performing image preprocessing on the target steel wire rope image to acquire a preprocessed image;
and downloading a target defect model from a knowledge base, and performing defect identification on the preprocessed image according to the target defect model so as to identify and obtain the target defect of the steel wire rope in the target steel wire rope image.
The invention provides a method, a device, equipment and a medium for identifying a steel wire rope defect, which are used for preprocessing an image of a target steel wire rope to obtain a preprocessed image. And downloading the latest target defect model from the knowledge base, identifying the defects of the preprocessed image by using the target defect model in combination with a deep learning technology, and uploading the detection result to a data platform once the defects are found, so that the effects of improving the detection efficiency of the defects of the steel wire rope, reducing the misjudgment risk and saving the labor cost are achieved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in 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 for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Wherein:
FIG. 1 is a schematic flow chart of a method for identifying defects of a steel wire rope in one embodiment;
FIG. 2 is a schematic diagram of a display platform in one embodiment;
FIG. 3 is a schematic structural diagram of a wire rope defect identifying device in one embodiment;
fig. 4 is a block diagram of a steel wire rope defect identifying device in one embodiment.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, fig. 1 is a schematic flow chart of a method for identifying a defect of a steel wire rope in an embodiment, where the method for identifying a defect of a steel wire rope in this embodiment includes the steps of:
and 102, acquiring a target steel wire rope image, and performing image preprocessing on the target steel wire rope image to acquire a preprocessed image.
And in a steel wire rope detection field, controlling a camera to align the straightened steel wire rope to be detected which advances at a constant speed, and shooting the steel wire rope to be detected to obtain a target steel wire rope image. And carrying out image preprocessing on the target steel wire rope image to obtain a preprocessed image which is required by the next link and has clear details. The preprocessing in this embodiment includes at least one of gradation processing, gaussian blur, opening and closing operations, and edge detection.
There are various algorithms for gray processing, and one of them can be selected according to the requirement. Illustratively, a component method is adopted, the brightness of three components in a colorful target steel wire rope image is respectively used as the gray values of three gray images, and one gray image is selected according to application requirements. And adopting a maximum value method, and taking the maximum value of the three-component brightness in the colorful target steel wire rope image as the gray value of the processed gray image. And (4) averaging the three-component brightness in the colorful target steel wire rope image by adopting an average value method to serve as the gray value of the processed gray image. And performing weighted average on the three components by using different weights according to importance and other indexes by using a weighted average method, and taking the weighted values as the gray value of the processed gray image.
Gaussian blur uses normal distribution (Gaussian function) to calculate a fuzzy template, and the template and a target steel wire rope image are used for convolution operation, so that the aim of blurring the target steel wire rope image is fulfilled. Wherein the normal distribution equation under the N-dimensional space is as follows:
the opening and closing operation consists of an opening operation and a closing operation, is a combined operation of corrosion and expansion, and is positioned as follows:
opening operation:
closing operation:
the opening operation uses the structuring element B to open the set A, which includes eroding A with B and then expanding the result with B to smooth the image contour, break narrower necks and eliminate thin protrusions. The closing operation expands a with B and then corrodes the result with B, which, contrary to the opening operation, closes narrow discontinuities and elongated gullies, eliminates small holes and fills cracks in the contour.
The edge detection operators that can be used in this step include sobel, Roberts, Prewitt, Laplace, etc., and the edge detection operators are used to detect pixels with step changes in the gray levels of the surrounding pixels, and the set of these pixels is the edge of the image. Taking the detection process of the sobel operator as an example, each point in the target steel wire rope image is subjected to two convolution by the sobel operator: one for detecting vertical edges and one for detecting horizontal edges, and then taking the maximum of the last two convolutions as the output of each point, i.e. the gray level of each point after detection. Then, the gray level change of each pixel in a certain field is inspected by utilizing the gray level of all the points, and finally, the edge is detected by utilizing the change rule of the first-order or second-order directional derivative adjacent to the edge, namely, the edge detection algorithm.
And 104, downloading a target defect model from the knowledge base, and identifying the defects of the preprocessed image according to the target defect model so as to identify and obtain the target defects of the steel wire ropes in the target steel wire rope image.
In this embodiment, after the industrial personal computer for defect recognition is started, the industrial personal computer downloads the latest target defect model from the knowledge base, and inputs the preprocessed image acquired by the camera into the defect model for comparison and recognition. And when any preset target defect is identified and found, performing acousto-optic alarm. And simultaneously, transmitting the target steel wire rope image containing the target defects back to the image defect library of the knowledge base so as to train and update the target defect model.
In order to identify the defects, a target defect model needs to be built in advance before the step is executed. Firstly, an image defect library is constructed, wherein the image defect library comprises steel wire rope defect images and defect labels matched with the steel wire rope defect images. The steel wire rope defect image comprises a history image of the defects detected in advance, a defect image simulated by a computer and the like. Due to numerous defects of the steel wire rope, the arranged defect label should meet the requirements of characteristic wire breakage, steel wire staggering, poor splicing of a rope sleeve, strand loosening, uneven pitch, strand loosening, wave shape, lantern shape, twisting, poor oiling, surface damage, abrasion deformation, mechanical abrasion, diameter thinning and corrosion as far as possible. In addition, in order to enable the number of samples of the steel wire rope defect image to meet the training requirement, amplification pretreatment is carried out on the steel wire rope defect image, the amplification pretreatment comprises at least one of image blurring, angle rotation, contrast adjustment and channel switching, and the treated amplified steel wire rope defect image and the matched defect label are obtained. And finally inputting the amplified steel wire rope defect image and the matched defect label into a training defect model for iterative training until the training defect model is determined to be converged based on a training output result of the training defect model and the defect label, so as to obtain a trained target defect model. In order to avoid the excessive number of iterative training, a convergence condition needs to be set, for example, the difference of loss functions of two iterations is set to be smaller than a threshold value to control the number of iterations, and a maximum number of iterations is also limited for insurance.
After the target defect is identified and obtained, inputting the target steel wire rope image and the target defect into a target defect model for iterative training, adjusting hyper-parameters (such as learning rate and network layer number) in a convolutional neural network, and simultaneously adding a regularization term behind a cost function to prevent the model from being over-fitted so as to obtain the latest target defect model.
Further, in this embodiment, alarm reminders with different alarm levels may be set, for example, a yellow light alarm for a low risk level, a red light alarm for a general risk level, and an acousto-optic alarm for a high risk level. And calling a preset alarm level standard from the cloud or the local, determining the alarm level by combining the target defect, and sending an alarm prompt of the corresponding alarm level to prompt maintenance personnel to make corresponding response.
According to the steel wire rope defect identification method, the target steel wire rope image is subjected to image preprocessing, and a preprocessed image is obtained. And downloading the latest target defect model from the knowledge base, identifying the defects of the preprocessed image by using the target defect model in combination with a deep learning technology, and uploading the detection result to a data platform once the defects are found, so that the effects of improving the detection efficiency of the defects of the steel wire rope, reducing the misjudgment risk and saving the labor cost are achieved.
Furthermore, in the daily monitoring process, the display platform of the industrial personal computer can browse the image defect library so that monitoring personnel can know the current and historical defects of the steel wire rope in real time. Referring to fig. 2, fig. 2 is a schematic diagram of an embodiment of a display platform, in which the left side of the display platform shows the classification of defects in common use and the right side shows images in the form of a photo album. And when the defect classification is clicked, displaying the defect image of the type. When the unclassified nodes are clicked, newly uploaded and unclassified defect images are discharged and displayed in reverse order according to uploading time, and the unclassified images can be manually judged and marked. And classifying the target steel wire rope image which is newly transmitted back to the knowledge base according to the target defect, and displaying the target steel wire rope image by taking the same category as the classification.
In one embodiment, as shown in fig. 3, a steel wire rope defect identifying device is provided, which includes:
the preprocessing module 302 is configured to obtain a target steel wire rope image, perform image preprocessing on the target steel wire rope image, and obtain a preprocessed image;
and the model identification module 304 is used for downloading the target defect model from the knowledge base and identifying the defects of the preprocessed image according to the target defect model so as to identify and obtain the target defects of the steel wire ropes in the target steel wire rope image.
The steel wire rope defect identification device carries out image preprocessing on the target steel wire rope image to obtain a preprocessed image. And downloading the latest target defect model from the knowledge base, identifying the defects of the preprocessed image by using the target defect model in combination with a deep learning technology, and uploading the detection result to a data platform once the defects are found, so that the effects of improving the detection efficiency of the defects of the steel wire rope, reducing the misjudgment risk and saving the labor cost are achieved.
In one embodiment, the wire rope defect identifying apparatus further includes: the model training module is used for constructing an image defect library, and the image defect library comprises steel wire rope defect images and defect labels matched with the steel wire rope defect images; carrying out amplification pretreatment on the steel wire rope defect image, wherein the amplification pretreatment comprises at least one of image blurring, angle rotation, contrast adjustment and channel switching, and obtaining the treated amplification steel wire rope defect image and a matched defect label; inputting the amplified steel wire rope defect image and the matched defect label into a training defect model for iterative training until the training defect model is determined to be converged based on a training output result of the training defect model and the defect label, and obtaining a target defect model after training.
In one embodiment, the wire rope defect identifying apparatus further includes: and the model training module is also specifically used for inputting the target steel wire rope image and the target defect into the target defect model for iterative training so as to adjust the hyper-parameters in the convolutional neural network.
In one embodiment, the wire rope defect identifying apparatus further includes: and the display module is used for classifying the target steel wire rope image according to the target defect and displaying the target steel wire rope image by taking the same category as the classification.
In one embodiment, the wire rope defect identifying apparatus further includes: and the alarm module is used for acquiring a preset alarm level standard, determining an alarm level according to the target defect and the alarm level standard and sending an alarm prompt of the alarm level.
Fig. 4 shows an internal structure diagram of the wire rope defect identifying apparatus in one embodiment. As shown in fig. 4, the wire rope defect identifying apparatus includes a processor, a memory, and a network interface connected through a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The nonvolatile storage medium of the steel wire rope defect identification device stores an operating system and also stores a computer program, and when the computer program is executed by a processor, the processor can realize the steel wire rope defect identification method. The internal memory may also have a computer program stored therein, which when executed by the processor, causes the processor to perform the method for identifying a wire rope defect. It will be understood by those skilled in the art that the configuration shown in fig. 4 is a block diagram of only a portion of the configuration relevant to the present application and does not constitute a limitation of the wire rope defect identifying apparatus to which the present application is applied, and that a particular wire rope defect identifying apparatus may include more or fewer components than those shown in the drawings, or may combine certain components, or have a different arrangement of components.
A wire rope defect identification apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the following steps when executing the computer program: acquiring a target steel wire rope image, and performing image preprocessing on the target steel wire rope image to acquire a preprocessed image; and downloading a target defect model from the knowledge base, and performing defect identification on the preprocessed image according to the target defect model so as to identify and obtain the target defect of the steel wire rope in the target steel wire rope image.
In one embodiment, before downloading the target defect model from the knowledge base, the method further comprises: constructing an image defect library, wherein the image defect library comprises steel wire rope defect images and defect labels matched with the steel wire rope defect images; carrying out amplification pretreatment on the steel wire rope defect image, wherein the amplification pretreatment comprises at least one of image blurring, angle rotation, contrast adjustment and channel switching, and obtaining the treated amplification steel wire rope defect image and a matched defect label; inputting the amplified steel wire rope defect image and the matched defect label into a training defect model for iterative training until the training defect model is determined to be converged based on a training output result of the training defect model and the defect label, and obtaining a target defect model after training.
In one embodiment, after identifying the target defect of the wire rope in the target wire rope image, the method further comprises: and inputting the target steel wire rope image and the target defect into a target defect model for iterative training so as to adjust the hyper-parameters in the convolutional neural network.
In one embodiment, the method further comprises: and classifying the target steel wire rope image according to the target defect, and displaying the target steel wire rope image by taking the same category as the classification.
In one embodiment, after identifying the target defect of the wire rope in the target wire rope image, the method further comprises: and acquiring a preset alarm level standard, determining an alarm level according to the target defect and the alarm level standard, and sending an alarm prompt of the alarm level.
A computer-readable storage medium storing a computer program which, when executed by a processor, performs the steps of: acquiring a target steel wire rope image, and performing image preprocessing on the target steel wire rope image to acquire a preprocessed image; and downloading a target defect model from the knowledge base, and performing defect identification on the preprocessed image according to the target defect model so as to identify and obtain the target defect of the steel wire rope in the target steel wire rope image.
In one embodiment, before downloading the target defect model from the knowledge base, the method further comprises: constructing an image defect library, wherein the image defect library comprises steel wire rope defect images and defect labels matched with the steel wire rope defect images; carrying out amplification pretreatment on the steel wire rope defect image, wherein the amplification pretreatment comprises at least one of image blurring, angle rotation, contrast adjustment and channel switching, and obtaining the treated amplification steel wire rope defect image and a matched defect label; inputting the amplified steel wire rope defect image and the matched defect label into a training defect model for iterative training until the training defect model is determined to be converged based on a training output result of the training defect model and the defect label, and obtaining a target defect model after training.
In one embodiment, after identifying the target defect of the wire rope in the target wire rope image, the method further comprises: and inputting the target steel wire rope image and the target defect into a target defect model for iterative training so as to adjust the hyper-parameters in the convolutional neural network.
In one embodiment, the method further comprises: and classifying the target steel wire rope image according to the target defect, and displaying the target steel wire rope image by taking the same category as the classification.
In one embodiment, after identifying the target defect of the wire rope in the target wire rope image, the method further comprises: and acquiring a preset alarm level standard, determining an alarm level according to the target defect and the alarm level standard, and sending an alarm prompt of the alarm level.
It should be noted that the method, the apparatus, the device and the computer-readable storage medium for identifying a defect of a steel wire rope belong to a general inventive concept, and the contents in the embodiments of the method, the apparatus, the device and the computer-readable storage medium for identifying a defect of a steel wire rope are applicable to each other.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of identifying defects in a steel cord, the method comprising:
acquiring a target steel wire rope image, and performing image preprocessing on the target steel wire rope image to acquire a preprocessed image;
and downloading a target defect model from a knowledge base, and performing defect identification on the preprocessed image according to the target defect model so as to identify and obtain the target defect of the steel wire rope in the target steel wire rope image.
2. The method of claim 1, further comprising, prior to said downloading the target defect model from the knowledge base:
constructing an image defect library, wherein the image defect library comprises steel wire rope defect images and defect labels matched with the steel wire rope defect images;
performing amplification pretreatment on the steel wire rope defect image, wherein the amplification pretreatment comprises at least one of image blurring, angle rotation, contrast adjustment and channel switching, and acquiring the treated amplified steel wire rope defect image and a matched defect label;
inputting the amplified steel wire rope defect image and the matched defect label into a training defect model for iterative training until the training defect model is determined to be converged based on a training output result of the training defect model and the defect label, and obtaining a trained target defect model.
3. The method of claim 2, wherein the defect labels comprise at least one of broken wires, staggered wires, poor splicing of rope sleeves, loose strands, uneven pitch, loose strands, wavy, lantern, kinking, poor oiling, surface damage, wear deformation, mechanical wear, diameter reduction, rust.
4. The method of claim 2, further comprising, after said identifying a target flaw of a wire rope in the target wire rope image:
inputting the target steel wire rope image and the target defect into the target defect model for iterative training so as to adjust the hyper-parameters in the convolutional neural network.
5. The method of claim 2, further comprising:
and classifying the target steel wire rope image according to the target defects, and displaying the target steel wire rope image by taking the same category as a division.
6. The method of claim 5, further comprising, after said identifying a target flaw of a wire rope in the target wire rope image:
and acquiring a preset alarm level standard, determining an alarm level according to the target defect and the alarm level standard, and sending an alarm prompt of the alarm level.
7. The method of claim 1, wherein the preprocessing comprises at least one of grayscale processing, gaussian blur, switching operations, and edge detection.
8. A wire rope defect identification device, the device comprising:
the preprocessing module is used for acquiring a target steel wire rope image, and carrying out image preprocessing on the target steel wire rope image to acquire a preprocessed image;
and the model identification module is used for downloading a target defect model from a knowledge base and identifying the defects of the preprocessed image according to the target defect model so as to identify and obtain the target defects of the steel wire ropes in the target steel wire rope image.
9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 7.
10. A wire rope defect identification device comprising a memory and a processor, characterized in that the memory stores a computer program which, when executed by the processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111325438.3A CN113963216A (en) | 2021-11-10 | 2021-11-10 | Steel wire rope defect identification method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111325438.3A CN113963216A (en) | 2021-11-10 | 2021-11-10 | Steel wire rope defect identification method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113963216A true CN113963216A (en) | 2022-01-21 |
Family
ID=79469811
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111325438.3A Pending CN113963216A (en) | 2021-11-10 | 2021-11-10 | Steel wire rope defect identification method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113963216A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115028095A (en) * | 2022-08-11 | 2022-09-09 | 杭州未名信科科技有限公司 | Intelligent robot for tower crane maintenance and intelligent tower crane |
| CN116152257A (en) * | 2023-04-22 | 2023-05-23 | 拓普思传感器(太仓)有限公司 | Detection information optimization method applied to sensor, server and medium |
-
2021
- 2021-11-10 CN CN202111325438.3A patent/CN113963216A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115028095A (en) * | 2022-08-11 | 2022-09-09 | 杭州未名信科科技有限公司 | Intelligent robot for tower crane maintenance and intelligent tower crane |
| CN116152257A (en) * | 2023-04-22 | 2023-05-23 | 拓普思传感器(太仓)有限公司 | Detection information optimization method applied to sensor, server and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113963216A (en) | Steel wire rope defect identification method, device, equipment and medium | |
| US8718352B2 (en) | System and method for testing ropes | |
| CN111862083B (en) | Visual-electromagnetic detection-based steel wire rope state comprehensive monitoring system and method | |
| US10268913B2 (en) | Equipment damage prediction system using neural networks | |
| CN113592828B (en) | Nondestructive testing method and system based on industrial endoscope | |
| CN108956614A (en) | A kind of pit rope dynamic method for detection fault detection and device based on machine vision | |
| US10783406B1 (en) | Method for detecting structural surface cracks based on image features and bayesian data fusion | |
| CN114235825B (en) | Steel wire rope quality detection method based on computer vision | |
| US20200202508A1 (en) | Image-based maintenance prediction and detection of operating errors | |
| CN111024704A (en) | Automatic defect detection for wire ropes using image processing techniques | |
| CN110889838A (en) | Fabric defect detection method and device | |
| CN111598889B (en) | Identification method and device for inclination fault of equalizing ring and computer equipment | |
| CN114022671B (en) | Intelligent cableway cable position identification method based on residual neural network | |
| JP2020128877A (en) | Linear object abnormality detection device and abnormality detection method | |
| US20200005084A1 (en) | Training method of, and inspection system based on, iterative deep learning system | |
| DE202023105341U1 (en) | Deep learning-based system for detecting corrosion in metallic objects | |
| Falconer et al. | Computer vision and thermal monitoring of HMPE fibre rope condition during CBOS testing | |
| CN112487976B (en) | Monitoring method, device and storage medium based on image recognition | |
| CN118134830A (en) | Cable open surface defect detection method and device | |
| CN113762330A (en) | Method and device for optimizing service configuration in dynamic network | |
| CN115830403B (en) | Automatic defect classification system and method based on deep learning | |
| CN112102302A (en) | Image recognition method and device, electronic equipment and storage medium | |
| CN115797316A (en) | Heavy load rope monitoring method and device, computer equipment and medium | |
| KR20190119211A (en) | Apparatus and method for discrimiating high temperature equipment degradation level using artificial intelligence | |
| KR20210105774A (en) | Method and apparatus for sampling of cloud outsorcing task for inspection by using artificial intelligent |
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 |