CN114998214A - Sampling speed control method and system for cable defect detection - Google Patents
Sampling speed control method and system for cable defect detection Download PDFInfo
- Publication number
- CN114998214A CN114998214A CN202210474680.5A CN202210474680A CN114998214A CN 114998214 A CN114998214 A CN 114998214A CN 202210474680 A CN202210474680 A CN 202210474680A CN 114998214 A CN114998214 A CN 114998214A
- Authority
- CN
- China
- Prior art keywords
- model
- cable
- image
- sampling
- real
- 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
- 238000005070 sampling Methods 0.000 title claims abstract description 93
- 230000007547 defect Effects 0.000 title claims abstract description 56
- 238000001514 detection method Methods 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000003746 surface roughness Effects 0.000 claims abstract description 22
- 238000004364 calculation method Methods 0.000 claims abstract description 19
- 239000012535 impurity Substances 0.000 claims abstract description 15
- 230000000052 comparative effect Effects 0.000 claims abstract description 9
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 238000004220 aggregation Methods 0.000 claims description 3
- 230000002776 aggregation Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000003064 k means clustering Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000003709 image segmentation Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000036632 reaction speed Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- 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
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
- G06T2207/20112—Image segmentation details
- G06T2207/20152—Watershed segmentation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a sampling speed control method for cable defect detection, which comprises the following steps: s1: acquiring a cable defect calculation factor, wherein the cable defect calculation factor comprises: surface roughness, internal impurities, comparative deviation degree of the outline and the standard and deviation degree of image gray scale and standard gray scale; s2: establishing a positive correlation control function of quality and detection speed, correcting an ideal value of the control function based on a detection value, and calculating a real-time sampling interval; s3: the real-time sampling interval is converted to a sensor sampling interval. The beneficial effects of the invention are: the sampling speed of the cable sensor can be controlled.
Description
Technical Field
The invention relates to the technical field of cable defect detection, in particular to a sampling speed control method and a sampling speed control system for cable defect detection.
Background
At present, communication cables and power cables are important for information transmission and power supply, and with the lapse of time, the cables are corroded and aged by the influence of factors such as external environment, climate, external force and the like, line characteristics are changed, faults such as line short circuit, circuit breaking and the like can occur, and system communication power supply is abnormal.
In the conventional art: the positioning of abnormal points of the cable is difficult to realize, the cable model cannot be visually checked, and the actual condition of the cable is inconvenient to accurately master.
For example, a "cable detection method" disclosed in chinese patent literature, the publication number of which: CN110986852A, filing date thereof: in 2019, 12 months and 05 days, the cable detection method is simple and easy to master in operation, clear in result and easy to distinguish, can comprehensively detect the quality of the cable and improve the use safety of the cable, but has the problem that the sampling speed of a cable sensor cannot be controlled.
Disclosure of Invention
Aiming at the defect that the sampling speed of a cable sensor cannot be controlled in the prior art, the invention provides a sampling speed control method and a sampling speed control system for detecting the defects of a cable, which can control the sampling speed of the cable sensor.
The technical scheme is that the sampling speed control method for the cable defect detection comprises the following steps:
s1: obtaining a cable defect calculation factor, wherein the cable defect calculation factor comprises: surface roughness, internal impurities, comparative deviation degree of the outline and the standard and deviation degree of image gray scale and standard gray scale;
s2: establishing a positive correlation control function of quality and detection speed, correcting an ideal value of the control function based on a detection value, and calculating a real-time sampling interval;
s3: the real-time sampling interval is converted to a sensor sampling interval.
In the scheme, a positive correlation control function of quality and detection speed is established, a real-time sampling interval is calculated according to the surface roughness, the internal impurities, the comparison deviation degree of the outline and the standard and the ideal value of the correction control function of the image gray scale and the standard gray scale deviation degree, and the real-time sampling interval is converted into a sensor sampling interval, so that the cable defect detection sampling speed is controlled.
Preferably, in step S1, the obtaining of the cable defect calculation factor includes the steps of:
s11: acquiring image data, eliminating noise by adopting Gaussian filtering, mean filtering or median filtering, and enhancing the color, brightness and contrast of an image by utilizing histogram equalization and gamma conversion;
s12: the image processing is to decompose the image into a plurality of independent areas which are respectively used for detecting the surface roughness, the comparison deviation degree of the contour and the standard and the deviation degree of the image gray scale and the standard gray scale, and the adopted methods are a segmentation method based on a threshold value, a segmentation method based on the area and a segmentation method based on the morphological watershed;
s13: extracting features, wherein the image features comprise geometric features, shape features, color features, texture features and gray features, the geometric features are extracted by counting defect boundaries and the number of internal pixels, the shape features are extracted from contours and shape regions, the geometric features and the shape features are used for analyzing the comparison deviation degree of the contours and a standard, the color features are extracted and matched by methods such as color histograms, color aggregation vectors, color matrixes and the like, the texture features are used for extracting texture structures by utilizing the moments of the histograms of the images, the color features and the texture features are used for analyzing surface roughness, the gray features are extracted from gray histogram information of the images, and the gray features are used for analyzing the deviation degree of image gray and the standard gray;
s14: and comparing the image with the model to judge the image defects, and outputting defect values through a BP neural network, a support vector machine and a K-means clustering algorithm.
In the scheme, the acquired image is compared with the model, the image characteristics are extracted, the defects of the acquired image are distinguished, the defect value is output through an algorithm, and the precision of the defect value is improved.
Preferably, in step S14, the step of comparing the image with the model to determine the image defect is as follows:
s141: setting 5 comparison models, and sequencing according to the absolute value of 0-5;
s142: the 360-degree angle of the collected image is divided into 45-degree intervals which are respectively expressed by integers of 1-8;
s143: rounding down two different angles of the image by taking 45 degrees as an interval, expressing the angles by integers, and calculating the absolute value of the difference between the integers;
s144: and comparing the comparison model according to the difference absolute value to judge the image defects.
In the scheme, two different angles of the image are rounded downwards by taking 45 degrees as an interval, the difference absolute value between the integers is calculated and expressed by the integers, the difference absolute value is compared with the comparison model, the image defects are judged, the computer identification and calculation are facilitated, the calculated amount is reduced, and the reaction speed is improved.
Preferably, in step S2, the real-time quality parameter, the positive correlation control function, and the real-time sampling interval are calculated by the following formula:
T i ＝F(Q i )；
T r ＝F(Q r ,σ)；
Q r ＝Q i (aC s +bD i +cD p +dD q )σ；
F(Q i )＝mQ i +n,m＞0；
wherein F is a positive correlation control function of the detection quality and the detection speed, and T is i For the sampling interval, σ is the distribution parameter, T r For a real-time sampling interval, Q r For real-time quality parameters, Q i As a quality parameter, C s To surface roughness, D i To an internal impurity content, D p For comparative deviation of the profile from the standard, D q The degree of deviation of the gray scale of each part of the image from the standard gray scale, m is a positive correlation constant, n is a compensation constant, lambda is a proportionality coefficient, and a, b, c and d are respectively an influence constant of surface roughness, an influence constant of internal impurity content, an influence constant of the comparison deviation of the profile from the standard and an influence constant of the deviation of the gray scale of the image from the standard gray scale.
In the scheme, a positive correlation control function of quality and detection speed is established, a real-time sampling interval is calculated according to the surface roughness, the internal impurities, the comparative deviation degree of the profile and the standard and the ideal value of the correction control function of the image gray scale and the standard gray scale deviation degree, and the real-time sampling interval is converted into a sensor sampling interval, so that the sampling speed of the detection of the cable defects is controlled.
Preferably, in step S3, the sensor sampling start time and the sampling interval are made the same in accordance with the sensor sampling interval corresponding to the real-time sampling interval synchronization.
In the scheme, the sampling start time and the sampling interval of the sensor are the same, so that data acquisition is facilitated.
Preferably, a sampling speed control system for cable defect detection comprises: the computer and the server are connected by adopting a medium not lower than a gigabit Ethernet, and the server is connected with the database.
Preferably, the server comprises a sensor, a physical parameter extraction device and a 3D modeling system, the sensor is used for collecting cable real-time data, the physical parameter extraction device is used for extracting cable physical information, and the 3D modeling system constructs a cable 3D model according to the extracted cable real-time data and the extracted cable physical information.
In this scheme, the sensor is used for gathering cable real-time data, and physical parameter extraction element is used for extracting cable physical information, and 3D modeling system constructs the cable 3D model according to the cable real-time data and the cable physical information that extract, looks up the cable 3D model directly perceived, reduces operator's work load.
Preferably, the model display interface displays a preview of the 3D model, pre-processes 3D model thumbnails, real-time data and physical information, the preview 3D model adopts a slice type display mode, an arrow button is arranged for rotating the preview 3D model, the number of the preprocessed 3D model thumbnails is 5, the model thumbnails are clicked, the computer moves the corresponding model thumbnails to the middle of the left or right according to the minimum moving distance, creating a preview 3D model according to the model thumbnails, moving the model thumbnails to the left or right for a plurality of grids, preprocessing the right end or the left end of the 3D model thumbnails to supplement a plurality of new model thumbnails, the real-time data comprises surface roughness, internal impurity content, profile deviation and image grey scale deviation, the physical information comprises an inner diameter, an outer diameter, a layer thickness, a core diameter, a core structure constant and a core structure coefficient.
In the scheme, the arrow buttons are arranged and used for rotating the preview 3D model, the state of the cable is visually checked in multiple dimensions, the generation time of the preview 3D model is shortened by preprocessing the 3D model thumbnail, and the applicability of the system is improved.
Preferably, the account authority comprises a non-operator authority and an operator authority, the non-operator authority refers to the state of the preview 3D model, only displays physical information of the cable, and cannot switch the 3D model, the operator authority refers to the preview 3D model, creates and displays the preview 3D model according to the cable real-time data and the cable physical information, and displays the preprocessed 3D model thumbnail.
In the scheme, the computer permission is divided into non-operator permission and operator permission, and the contents which can be checked by different permissions are different, so that the safety of the system is improved.
Preferably, the sensor control interface displays sensor information, the sensor number, the sensor name, the sampling value and the sampling speed content are not editable, and the content of modifying the sampling speed is editable, which is realized as follows: and inputting a speed value in the input box, after a mouse clicks a region other than the input port, reading the speed value, the number of the corresponding sensor and the name of the sensor by the system, transmitting the speed value to the corresponding sensor through the Ethernet, and modifying the speed value into the sampling speed of the corresponding sensor.
In the scheme, the sampling speed of the remote sensor is modified through the computer, the efficiency is improved, and the applicability of the system is improved.
The beneficial effects of the invention are: the sampling speed of the cable sensor can be controlled.
Drawings
FIG. 1 is a flow chart of a sampling rate control method for cable defect detection according to the present invention.
FIG. 2 is a page view of a model display interface of a sampling rate control system for cable defect detection according to the present invention.
FIG. 3 is a sensor control interface page view of a sampling rate control system for cable defect detection according to the present invention.
Detailed Description
The technical scheme of the invention is further specifically described by the following embodiments and the accompanying drawings.
Example (b): as shown in fig. 1, a sampling speed control method for cable defect detection includes the following steps:
step 1: acquiring a cable defect calculation factor;
step 2: establishing a positive correlation control function of quality and detection speed, correcting an ideal value of the control function based on a detection value, and calculating a real-time sampling interval;
and step 3: the real-time sampling interval is converted to a sensor sampling interval.
In step 1, cable defect calculation factors are obtained, wherein the defect calculation factors comprise: surface roughness, internal impurities, comparative deviation of the profile from the standard, and deviation of the gray level of each part of the image from the standard gray level.
The method for acquiring the surface roughness, the comparative deviation degree of the profile and the standard and the deviation degree of the image gray scale and the standard gray scale by an artificial feature extraction method comprises the following steps:
step 11: collecting image data;
the image processing method comprises image enhancement and image segmentation, and is influenced by factors such as sensor material properties, and the images acquired in an industrial field usually contain noise. And eliminating the noise by adopting image enhancement strategies such as Gaussian filtering, mean filtering or median filtering and the like according to different preferences of the noise energy distribution interval. Histogram equalization, gamma conversion, etc. are used to purposefully enhance certain features of the image, such as color, brightness, contrast, etc.
Step 12: processing an image;
the image processing method is to divide the image into a plurality of independent areas according to the difference of the characteristic attributes by adopting image segmentation, and the independent areas are respectively used for detecting the problems of surface roughness, the comparison deviation degree of the outline and the standard and the deviation degree of the image gray scale and the standard gray scale. After effective segmentation, the characteristics in each similar region in the image are the same or similar, and the characteristics in different regions are obviously different. The image segmentation methods include threshold-based segmentation methods, region-based segmentation methods, and morphological watershed-based segmentation methods.
Step 13: extracting features;
the method comprises the steps of extracting feature information of defects from an image, wherein the image features comprise geometric features, shape features, color features, texture features and gray level features, the geometric features and the shape features are used for analyzing the comparison deviation degree of a contour and a standard, the geometric features are extracted by counting the number of pixel points at the boundary and inside the defect, the shape features are extracted from the contour and a shape area, the color features and the texture features are used for analyzing surface roughness, the color features are extracted and matched by methods such as a color histogram, a color aggregation vector and a color matrix, the texture features are extracted by utilizing the moment of the histogram of the image, the gray level features are used for analyzing the deviation degree of the gray level of an image and the standard gray level, and the gray level features are extracted from the gray level histogram information of the image.
Step 14: judging a model and identifying a result;
after the characteristics capable of accurately describing the defects are extracted, the defect detection system needs to classify by means of a discrimination model to judge whether the defects exist in the image, common discrimination algorithms include a BP neural network, a support vector machine, a K-means clustering algorithm and the like, and specific defect values are output.
The image matching method based on the contrast model comprises the following steps:
step 141: setting 5 comparison models, sequencing according to the absolute value of 0-5, and comparing the acquired images;
step 142: the collected 360-degree angle of the image is divided into 45-degree intervals which are respectively expressed by integers of 1-8, so that the identification and calculation of a computer are facilitated;
step 143: the angle of the collected image is rounded downwards by taking 45 degrees as an interval, the angle is expressed by integers, and the absolute value of the difference between the integers is calculated, so that the identification and calculation of a computer are facilitated;
step 144: and comparing the comparison model according to the difference absolute value, judging the image defects and reducing the calculated amount.
In step 2, a positive correlation control function of the quality and the detection speed is established, an ideal value of the control function is corrected based on the detection value, and a real-time sampling interval is calculated.
And establishing a positive correlation control function for detecting quality and speed. At the initial stage of detection and starting, all parameters are initialized according to ideal values, and the comprehensive calculation result of the parameters represents the quality parameters of the product. The equipment after initialization is sampled at intervals of a certain span, so that the detection process has higher speed, and the positive correlation control function calculation formula of the detection quality and the detection speed is as follows:
T i ＝F(Q i )；
in the formula, Q i As a quality parameter, T i F is a positive correlation control function of the detection quality and the detection speed for the sampling interval.
After the machine starts the detection process, the ideal value adopted by initialization is gradually corrected by the detection value. Obtaining real-time quality parameters and distribution parameters, and calculating the real-time sampling interval according to the following formula:
T r ＝F(Q r ,σ)；
in the formula, Q r For real-time quality parameters, σ is a distribution parameter, T r And F is a positive correlation control function of the detection quality and the detection speed for a real-time sampling interval.
The real-time quality parameter, the positive correlation control function and the real-time sampling interval calculation formula are as follows:
Q r ＝Q i (aC s +bD i +cD p +dD q )σ；
F(Q i )＝mQ i +n,m＞0；
wherein F is a positive correlation control function of the detection quality and the detection speed, and T is i For the sampling interval, σ is the distribution parameter, T r For a real-time sampling interval, Q r For real-time quality parameters, Q i As a quality parameter, C s To surface roughness, D i To an internal impurity content, D p For comparative deviation of the profile from the standard, D q The image gray scale and standard gray scale deviation degree of each part, m is a positive correlation constant, n is a compensation constant, lambda is a proportionality coefficient, and a, b, c and d are respectively an influence constant of surface roughness, an influence constant of internal impurity content, an influence constant of comparison deviation degree of the profile and the standard and an influence constant of the image gray scale and standard gray scale deviation degree.
In step 3, the real-time sampling interval is converted into a sensor sampling interval. And according to the sampling interval of the sensor synchronously corresponding to the real-time sampling interval, the sampling start time of the sensor is the same as the sampling interval, the effectiveness of data sampling is improved, and the abnormal probability of the data is reduced.
A sampling speed control system for cable defect detection comprises a computer, a server and a database, wherein the computer and the server are connected by adopting a medium not lower than a gigabit Ethernet, the server is connected with the database, and the database is a local database or a cloud database.
The server comprises a sensor, a physical parameter extraction device and a 3D modeling system, the sensor is used for collecting cable real-time data, the physical parameter extraction device is used for extracting cable physical information, the 3D modeling system constructs a cable 3D model according to the extracted cable real-time data and the extracted cable physical information, and the cable 3D information is displayed in real time. The computer is responsible for model display interfaces of various physical parameters and instant computation of the 3D model.
As shown in FIG. 2, the model display interface displays a preview of the 3D model, pre-processing 3D model thumbnails, real-time data, and physical information. The preview 3D model adopts a slice type display mode, the data calculation amount is reduced, the computer burden is reduced, arrow buttons are respectively arranged on the upper side, the lower side, the left side and the right side of the preview 3D model and used for turning the preview 3D model, and for example, the preview 3D model is rotated from right to left through the left arrow button. The method comprises the steps that a preprocessed 3D model thumbnail is located right below a previewed 3D model, 5 model thumbnails are total, a middle model thumbnail is a thumbnail of the previewed 3D model, the model thumbnail is clicked, a computer moves the corresponding model thumbnail to the middle leftwards or rightwards according to the minimum moving distance, the 3D model is created according to the model thumbnail and is displayed at the previewed 3D model, the model thumbnail moves leftwards for one or two frames, one or two new model thumbnails are supplemented to the right end of the preprocessed 3D model thumbnail, one or two new model thumbnails are supplemented to the right end of the model thumbnail, and one or two new model thumbnails are supplemented to the left end of the preprocessed 3D model thumbnail. The real-time data comprises surface roughness, internal impurity content, profile deviation and image gray level deviation, and the physical information comprises inner diameter, outer diameter, layer thickness, core diameter, core structure constant and core structure coefficient.
As shown in fig. 3, the sensor control interface displays sensor information including sensor number, sensor name, sampling value, sampling speed, and modified sampling speed, sorted in the sensor number order. The sensor number, the sensor name, the sampling value and the sampling speed content are not editable, and the content of modifying the sampling speed is editable, and the implementation mode is as follows: and inputting a speed value in the input box, after clicking a non-input port area by a mouse, reading the speed value, the corresponding sensor number and the sensor name by the system, transmitting the speed value to the corresponding sensor through the Ethernet, and modifying the speed value into the sampling speed of the corresponding sensor. The specified sensor is precisely searched for by the sensor number or the sensor name.
The computer sets two account authorities, which are respectively: non-operator authority and operator authority.
The non-operator authority refers to the state of the preview 3D model, the system only displays the physical information of the cable, and the 3D model cannot be switched.
An operator has authority to look up the state of the previewed 3D model, instantly generates and displays the 3D model according to real-time data and physical information of the cable, and simultaneously informs a server to preview the front and rear positions near the vacancy to display the thumbnail of the preprocessed 3D model, and a local database or a cloud database stores the calculation result of the 3D model.
Claims (10)
1. A sampling speed control method for cable defect detection is characterized by comprising the following steps:
s1: obtaining a cable defect calculation factor, wherein the cable defect calculation factor comprises: surface roughness, internal impurities, comparative deviation degree of the outline and the standard and deviation degree of image gray scale and standard gray scale;
s2: establishing a positive correlation control function of quality and detection speed, correcting an ideal value of the control function based on a detection value, and calculating a real-time sampling interval;
s3: the real-time sampling interval is converted to a sensor sampling interval.
2. The sampling speed control method for cable defect detection according to claim 1, wherein the step S1 of obtaining the cable defect calculation factor comprises the following steps:
s11: acquiring image data, eliminating noise by adopting Gaussian filtering, mean filtering or median filtering, and enhancing the color, brightness and contrast of an image by utilizing histogram equalization and gamma conversion;
s12: the image processing is to decompose the image into a plurality of independent areas which are respectively used for detecting the surface roughness, the comparison deviation degree of the contour and the standard and the deviation degree of the image gray scale and the standard gray scale, and the adopted methods are a segmentation method based on a threshold value, a segmentation method based on the area and a segmentation method based on the morphological watershed;
s13: extracting features, wherein the image features comprise geometric features, shape features, color features, texture features and gray features, the geometric features are extracted by counting defect boundaries and the number of internal pixels, the shape features are extracted from contours and shape regions, the geometric features and the shape features are used for analyzing the comparison deviation degree of the contours and the standard, the color features are extracted and matched by methods such as color histograms, color aggregation vectors, color matrixes and the like, the texture features are used for extracting texture structures by utilizing the moments of the histograms of the images, the color features and the texture features are used for analyzing surface roughness, the gray features are extracted from gray histogram information of the images, and the gray features are used for analyzing the deviation degree of image gray and the standard gray;
s14: and comparing the image with the model to judge the image defects, and outputting defect values through a BP neural network, a support vector machine and a K-means clustering algorithm.
3. The sampling speed control method for cable defect detection according to claim 2, wherein in step S14, the step of comparing the image with the model to determine the image defect is as follows:
s141: setting 5 comparison models, and sequencing according to the absolute value of 0-5;
s142: the 360-degree angle of the collected image is divided into 45-degree intervals which are respectively expressed by integers of 1-8;
s143: rounding down two different angles of the image by taking 45 degrees as an interval, expressing the angles by integers, and calculating the absolute value of the difference between the integers;
s144: and comparing the comparison model according to the difference absolute value to judge the image defects.
4. The sampling speed control method for cable defect detection according to claim 1, wherein in step S2, the real-time quality parameter, the positive correlation control function and the real-time sampling interval are calculated according to the following formula:
T i ＝F(Q i )；
T r ＝F(Q r ,σ)；
Q r ＝Q i (aC s +bD i +cD p +dD q )σ；
F(Q i )＝mQ i +n,m＞0；
wherein F is a positive correlation control function of the detection quality and the detection speed, and T is i For the sampling interval, σ is the distribution parameter, T r For a real-time sampling interval, Q r For real-time quality parameters, Q i As a quality parameter, C s To surface roughness, D i As internal impurity content, D p For comparative deviation of the profile from the standard, D q The degree of deviation of the gray scale of each part of the image from the standard gray scale, m is a positive correlation constant, n is a compensation constant, lambda is a proportionality coefficient, and a, b, c and d are respectively an influence constant of surface roughness, an influence constant of internal impurity content, an influence constant of the comparison deviation of the profile from the standard and an influence constant of the deviation of the gray scale of the image from the standard gray scale.
5. The method as claimed in claim 1, wherein in step S3, the sampling start time and the sampling interval are the same according to the real-time sampling interval and the corresponding sensor sampling interval.
6. A sampling speed control system for cable defect detection, which is suitable for the sampling speed control method for cable defect detection according to any one of claims 1 to 5, and comprises: the computer and the server are connected by adopting a medium not lower than a gigabit Ethernet, and the server is connected with the database.
7. The sampling speed control system for cable defect detection according to claim 6, wherein the server comprises a sensor, a physical parameter extraction device and a 3D modeling system, the sensor is used for collecting cable real-time data, the physical parameter extraction device is used for extracting cable physical information, and the 3D modeling system constructs a cable 3D model according to the extracted cable real-time data and the extracted cable physical information.
8. The sampling speed control system for cable defect detection according to claim 6 or 7, wherein the model display interface displays a preview 3D model, pre-process 3D model thumbnails, real-time data and physical information, the preview 3D model adopts a slice display mode, arrow buttons are arranged for rotating the preview 3D model, the number of the pre-process 3D model thumbnails is 5, the model thumbnails are clicked, the computer moves the corresponding model thumbnails to the right or left according to the minimum moving distance to the middle, the preview 3D model is created according to the model thumbnails, the model thumbnails move to the right or left for a plurality of grids, the right or left end of the pre-process 3D model thumbnails is supplemented with a plurality of new model thumbnails, the real-time data comprises surface roughness, internal impurity content, contour deviation and image gray deviation, the physical information comprises an inner diameter, an outer diameter, a layer thickness, a core diameter, a core structure constant and a core structure coefficient.
9. The system as claimed in claim 8, wherein the account authority includes a non-operator authority and an operator authority, the non-operator authority refers to preview the state of the 3D model, only displays physical information of the cable, and does not switch the 3D model, the operator authority refers to preview the 3D model, creates a preview 3D model according to cable real-time data and cable physical information, and displays, displays a preprocessed 3D model thumbnail.
10. The system of claim 6, wherein the sensor control interface displays sensor information, sensor number, sensor name, sampling value and sampling rate content are not editable, and the modified sampling rate content is editable, and is implemented as follows: and inputting a speed value in the input box, after clicking a non-input port area by a mouse, reading the speed value, the corresponding sensor number and the sensor name by the system, transmitting the speed value to the corresponding sensor through the Ethernet, and modifying the speed value into the sampling speed of the corresponding sensor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210474680.5A CN114998214A (en) | 2022-04-29 | 2022-04-29 | Sampling speed control method and system for cable defect detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210474680.5A CN114998214A (en) | 2022-04-29 | 2022-04-29 | Sampling speed control method and system for cable defect detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114998214A true CN114998214A (en) | 2022-09-02 |
Family
ID=83026064
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210474680.5A Pending CN114998214A (en) | 2022-04-29 | 2022-04-29 | Sampling speed control method and system for cable defect detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114998214A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115796668A (en) * | 2022-11-28 | 2023-03-14 | 广东新亚光电缆股份有限公司 | Signal quality management system of control cable |
| CN116721108A (en) * | 2023-08-11 | 2023-09-08 | 山东奥晶生物科技有限公司 | Stevioside product impurity detection method based on machine vision |
| CN116912234A (en) * | 2023-09-06 | 2023-10-20 | 青岛理研电线电缆有限公司 | Cable stranded wire quality detection method based on image features |
-
2022
- 2022-04-29 CN CN202210474680.5A patent/CN114998214A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115796668A (en) * | 2022-11-28 | 2023-03-14 | 广东新亚光电缆股份有限公司 | Signal quality management system of control cable |
| CN115796668B (en) * | 2022-11-28 | 2023-09-19 | 广东新亚光电缆股份有限公司 | Signal quality management system of control cable |
| CN116721108A (en) * | 2023-08-11 | 2023-09-08 | 山东奥晶生物科技有限公司 | Stevioside product impurity detection method based on machine vision |
| CN116721108B (en) * | 2023-08-11 | 2023-11-03 | 山东奥晶生物科技有限公司 | Stevioside product impurity detection method based on machine vision |
| CN116912234A (en) * | 2023-09-06 | 2023-10-20 | 青岛理研电线电缆有限公司 | Cable stranded wire quality detection method based on image features |
| CN116912234B (en) * | 2023-09-06 | 2023-11-28 | 青岛理研电线电缆有限公司 | Cable stranded wire quality detection method based on image features |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114998214A (en) | Sampling speed control method and system for cable defect detection | |
| CN110070570B (en) | Obstacle detection system and method based on depth information | |
| CN111582294B (en) | Method for constructing convolutional neural network model for surface defect detection and application thereof | |
| CN106651872B (en) | Pavement crack identification method and system based on Prewitt operator | |
| CN107194937B (en) | Traditional Chinese medicine tongue picture image segmentation method in open environment | |
| CN110120042B (en) | Crop image pest and disease damage area extraction method based on SLIC super-pixel and automatic threshold segmentation | |
| CN110400322B (en) | Fruit point cloud segmentation method based on color and three-dimensional geometric information | |
| CN108181316B (en) | Bamboo strip defect detection method based on machine vision | |
| CN113324864B (en) | Pantograph carbon slide plate abrasion detection method based on deep learning target detection | |
| CN112907519A (en) | Metal curved surface defect analysis system and method based on deep learning | |
| CN110110618B (en) | SAR target detection method based on PCA and global contrast | |
| CN110598030A (en) | Oracle bone rubbing classification method based on local CNN framework | |
| CN111667475B (en) | Machine vision-based Chinese date grading detection method | |
| CN112132166A (en) | Intelligent analysis method, system and device for digital cytopathology image | |
| CN114331986A (en) | Dam crack identification and measurement method based on unmanned aerial vehicle vision | |
| CN108596176B (en) | Method and device for identifying diatom types of extracted diatom areas | |
| CN111105398A (en) | Transmission line component crack detection method based on visible light image data | |
| CN110866547B (en) | Automatic classification system and method for traditional Chinese medicine decoction pieces based on multiple features and random forests | |
| CN110232703B (en) | Moving object recognition device and method based on color and texture information | |
| CN114998103A (en) | Point cloud cultural relic fragment three-dimensional virtual splicing method based on twin network | |
| CN114120218A (en) | River course floater monitoring method based on edge calculation | |
| CN116740044B (en) | Copper pipe milling surface processing method and system based on visual detection and control | |
| CN113723314A (en) | Sugarcane stem node identification method based on YOLOv3 algorithm | |
| JP5403180B1 (en) | Image evaluation method, image evaluation apparatus, and image evaluation program | |
| CN117330582A (en) | Polymer PE film surface crystal point detecting system |
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 |