CN116953196A - Defect detection and safety state assessment method for steel tee joint - Google Patents

Defect detection and safety state assessment method for steel tee joint Download PDF

Info

Publication number
CN116953196A
CN116953196A CN202311212960.XA CN202311212960A CN116953196A CN 116953196 A CN116953196 A CN 116953196A CN 202311212960 A CN202311212960 A CN 202311212960A CN 116953196 A CN116953196 A CN 116953196A
Authority
CN
China
Prior art keywords
image
defect
steel tee
ultrasonic
branch pipe
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202311212960.XA
Other languages
Chinese (zh)
Other versions
CN116953196B (en
Inventor
黄荣国
王培利
温启佳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Feiting Pipe Manufacture Co ltd
Original Assignee
Shanghai Feiting Pipe Manufacture Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Feiting Pipe Manufacture Co ltd filed Critical Shanghai Feiting Pipe Manufacture Co ltd
Priority to CN202311212960.XA priority Critical patent/CN116953196B/en
Publication of CN116953196A publication Critical patent/CN116953196A/en
Application granted granted Critical
Publication of CN116953196B publication Critical patent/CN116953196B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/20—Metals
    • G01N33/204—Structure thereof, e.g. crystal structure
    • G01N33/2045—Defects
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
    • G01N23/02—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material
    • G01N23/04—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and forming images of the material
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/04—Analysing solids
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/04—Analysing solids
    • G01N29/06—Visualisation of the interior, e.g. acoustic microscopy
    • G01N29/0654—Imaging
    • G01N29/069—Defect imaging, localisation and sizing using, e.g. time of flight diffraction [TOFD], synthetic aperture focusing technique [SAFT], Amplituden-Laufzeit-Ortskurven [ALOK] technique
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
    • G01N29/4409—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by comparison
    • G01N29/4418—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by comparison with a model, e.g. best-fit, regression analysis
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
    • G01N29/4445—Classification of defects
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
    • G01N3/40—Investigating hardness or rebound hardness
    • 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
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
    • G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10132—Ultrasound image
    • 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
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging
    • 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
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Acoustics & Sound (AREA)
  • Medical Informatics (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Crystallography & Structural Chemistry (AREA)
  • Food Science & Technology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Medicinal Chemistry (AREA)
  • Geometry (AREA)
  • Quality & Reliability (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)
  • Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)

Abstract

The invention relates to the defect detection field, and discloses a defect detection and safety state evaluation method of a steel tee joint, which comprises the steps of obtaining an X-ray flat image and an ultrasonic flat image and obtaining an ultrasonic signal set; performing image fusion on the X-ray flat image and the ultrasonic flat image to obtain a fusion image, and analyzing the fusion image to obtain first defect parameter data of the steel tee to be evaluated; analyzing based on the ultrasonic signal set to obtain second defect parameter data of the steel tee joint to be evaluated; calculating according to the first defect parameter data and the second defect parameter data to obtain a defect statistical coefficient; determining the hardness corresponding to the defect statistical coefficient based on a relation regression model preset by the defect statistical coefficient and the hardness relation; and carrying out quality safety evaluation based on the hardness to obtain an evaluation result of the steel tee joint.

Description

Defect detection and safety state assessment method for steel tee joint
Technical Field
The invention relates to the field of defect detection, in particular to a defect detection and safety state evaluation method for a steel tee joint.
Background
In the industrial and construction fields, steel tee is a common pipe connection part widely used in the fields of petroleum, chemical industry, energy, water service, etc. for splitting a pipe into two or more flow directions; along with the continuous development of pipeline construction, the steel tee joint also tends to develop towards the directions of high strength, large caliber, thick wall and high performance; unlike common pipe fittings, the large-caliber steel tee joint is generally formed into a finished product through a welding process, and various internal defects such as air holes, inclusions, cracks and the like can be generated in the large-caliber steel tee joint manufactured through the welding process; if the steel tee joint is directly put into use without repairing defects, the steel tee joint can be deformed due to the influence of the use environment and geometric structure complexity of the steel tee joint, and the defects can be converted into occurrence causes of leakage accidents when serious, so that the normal operation of the whole pipe system is influenced; therefore, how to find out the defects of the steel tee in time and evaluate and repair the safety state of the steel tee according to the defects of the steel tee so as to ensure the quality and the safety of the steel tee becomes the problem to be solved.
At present, the traditional steel tee joint defect detection method mainly depends on visual inspection and manual inspection; although the method is simple and visual, the method is greatly influenced by artificial subjective factors, misjudgment can be caused, and the efficiency is low; there are, of course, some improved detection methods, for example, chinese patent application publication No. CN114487131a discloses an ultrasonic detection method for cracks in the shoulder of a tee joint, and, for example, chinese patent application publication No. CN112304740a discloses a method for detecting and calculating the strength of a tee joint pipe, and although the method can detect the defects of a steel tee joint, the inventor researches and actually applies the method and the prior art to find that the method and the prior art have at least the following defects:
(1) The defect detection mode of the steel tee joint applied to production scenes is lacking, the existing mode cannot ensure the obvious characteristics of the steel tee joint and simultaneously reserve the detail characteristics of the steel tee joint, so that the defect detection accuracy is low, and missing detection or false detection is easy to generate;
(2) The safety evaluation of the steel tee joint is lacking, the quality detection period is long, the steel tee joint cannot be subjected to efficient quality classification, and the method is not suitable for a large-caliber steel tee joint production quality inspection scene.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a defect detection and safety state evaluation method for a steel tee joint.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a method for defect detection and safety state assessment of a steel tee, the method comprising:
acquiring an X-ray flat image and an ultrasonic flat image of a main pipe of the steel tee to be evaluated, acquiring an X-ray flat image and an ultrasonic flat image of a branch pipe of the steel tee to be evaluated, and acquiring an ultrasonic signal set of the steel tee to be evaluated;
performing image fusion on the X-ray flat image and the ultrasonic flat image to obtain a fusion image, and analyzing the fusion image to obtain first defect parameter data of the steel tee to be evaluated; analyzing based on the ultrasonic signal set to obtain second defect parameter data of the steel tee joint to be evaluated; the first defect parameter data comprise defect types, main pipe defect area, branch pipe defect area, main pipe defect area quantity and branch pipe defect area quantity; the second defect parameter data comprise measured thicknesses of a main pipe and a branch pipe;
calculating according to the first defect parameter data and the second defect parameter data to obtain a defect statistical coefficient; determining the hardness of the steel tee to be evaluated corresponding to the defect statistical coefficient based on a relation regression model preset by the defect statistical coefficient and the hardness relation;
Performing quality safety evaluation based on the hardness of the steel tee to be evaluated to obtain an evaluation result of the steel tee; the evaluation results include pass, fail but repairable and fail and unrepairable.
Further, the acquisition logic of the X-ray tiled images of the steel tee main pipe and the branch pipe to be evaluated is as follows:
respectively dividing equal annular virtual areas of a steel three-way main pipe and a branch pipe to be evaluated to obtain M main pipe annular division areas and N branch pipe annular division areas, wherein M, N is a positive integer greater than zero;
acquiring a main pipe local X-ray image of each main pipe annular dividing region and a branch pipe local X-ray image of each branch pipe annular dividing region through an X-ray detection device respectively;
acquiring acquisition rules of the main pipe and the branch pipe, and respectively carrying out image stitching on the main pipe local X-ray image and the branch pipe local X-ray image based on the acquisition rules so as to acquire an X-ray tiled image of the main pipe and an X-ray tiled image of the branch pipe of the steel tee to be evaluated.
Further, before image stitching is performed on the main tube local X-ray image, the method includes:
acquiring every two adjacent main tube local X-ray images;
taking one main pipe local X-ray image of every two adjacent main pipe local X-ray images as a target image and the other main pipe local X-ray image as a matching image;
Setting the step length as 1, and performing cross-correlation calculation on the matched image and the target image in a sliding window mode to obtain the similarity of each overlapping part;
and taking the overlapping part with the similarity larger than the preset similarity threshold value as the same area, dividing the same area in the target image or the matched image, and removing the divided part.
Further, the fused image comprises a fused image of a main pipe and a fused image of a branch pipe;
image fusion is carried out on an X-ray flat image and an ultrasonic flat image, and the method comprises the following steps:
taking an ultrasonic flat image of a main tube as a first ultrasonic image and an X-ray flat image of the main tube as a first X-ray image; and taking the ultrasonic tiled image of the branch pipe as a second ultrasonic image, and taking the X-ray tiled image of the branch pipe as a second X-ray image;
dividing the first ultrasound image and the first X-ray image into S parts based on the same rule, and dividing the second ultrasound image and the second X-ray image into D parts based on the same rule, S, D being a positive integer greater than zero;
calculating a first degree of difference of the same portion of the first ultrasonic image and the first X-ray image, and calculating a second degree of difference of the same portion of the second ultrasonic image and the second X-ray image;
Comparing the first difference with a preset first difference threshold, and comparing the second difference with a preset second difference threshold;
if the first difference degree is larger than a preset first difference degree threshold value, reserving the corresponding same part in the first ultrasonic image; if the first difference degree is smaller than or equal to a preset first difference degree threshold value, eliminating the corresponding same part in the first ultrasonic image to obtain a first ultrasonic image with a reserved part;
if the second difference degree is larger than a preset second difference degree threshold value, reserving the corresponding same part in the second ultrasonic image; if the second difference degree is smaller than or equal to a preset second difference degree threshold value, eliminating the corresponding same part in the first ultrasonic image to obtain a second ultrasonic image with a reserved part;
completely overlapping the first ultrasonic image of the reserved part on the first X-ray image to obtain a fusion image of the main tube; and completely overlapping the second ultrasonic image of the reserved part on the second X-ray image to obtain a fusion image of the branch pipe.
Further, analyzing the fused image includes:
graying the fusion image of the main pipe to obtain a main pipe gray image, and graying the fusion image of the branch pipe to obtain a branch pipe gray image;
Carrying out pixel point distinction on the main gray image by using a K-means clustering algorithm, taking an area formed by clustering the pixels in the main gray image as a first target area, carrying out pixel point distinction on the branch gray image by using the K-means clustering algorithm, and taking an area formed by clustering the pixels in the branch gray image as a second target area; the first target area comprises P main pipe abnormal areas, and the second target area comprises Q branch pipe abnormal areas;
respectively inputting the main pipe abnormal region and the abnormal region of the branch pipe into a preset defect classification model in an image form to identify defect types of the main pipe abnormal region and the branch pipe abnormal region; type marking is carried out on the main pipe abnormal region and the branch pipe abnormal region according to the identification result; the defect types include cracks, inclusions, and pinholes.
Further, analyzing based on the ultrasonic signal set, comprising:
extracting g main pipe ultrasonic signals in the ultrasonic signal set, and extracting h branch pipe ultrasonic signals in the ultrasonic signal set;
obtaining the reflection time of each main pipe ultrasonic signalAnd obtaining the reflection time of the ultrasonic signal of each branch pipe +.>；
The reflection time of each main pipe ultrasonic signal Respectively +.>And minimum reflection time of the host signal +.>Comparing and reflecting time of ultrasonic signal of each branch pipe>Respectively with the maximum reflection time of the branch signals +.>And minimum reflection time of the branch signal +.>Comparing;
if it isWill correspond->As an effective main tube ultrasonic signal, if +.>Or->Will correspond->As an inactive ultrasound signal;
if it isWill correspond->As an effective branchTube ultrasonic signal, if->Or->Will correspond->As an inactive branch ultrasonic signal;
and respectively carrying out thickness calculation according to the effective main pipe ultrasonic signals and the effective branch pipe ultrasonic signals to obtain the main pipe actual measurement thickness and the branch pipe actual measurement thickness.
Further, the logic for performing the calculation according to the first defect parameter data and the second defect parameter data is:
obtaining standard thickness data of a steel tee joint to be evaluated, which is pre-stored in a system database, wherein the standard thickness data comprises main pipe standard thickness data and branch pipe standard thickness data;
carrying out formula calculation based on the first defect parameter data, the second defect parameter data and the standard thickness data to obtain a defect statistical coefficient of the steel tee to be evaluated, wherein the calculation formula is as follows: The method comprises the steps of carrying out a first treatment on the surface of the Wherein: />For defect statistics coefficients, ++>For the i-th main pipe defect area, < +.>For the number of main tube defect areas of the ith, < +.>For the j-th defective area of the branch pipe, < >>Is j thNumber of defective areas of the branch line->For the i-th main pipe measured thickness, +.>For the standard thickness data of the main pipe->The thickness is measured for the j-th leg,for standard thickness data of branch pipe, +.>For the total number of the abnormal regions of the main tube>Is the total number of abnormal areas of the branch pipe.
Further, the construction logic of the relational regression model is as follows:
acquiring second historical data of the steel tee joint, wherein the second historical data at least comprises different defect statistical coefficients corresponding to the steel tee joint with different defect types, and the different defect statistical coefficients are calculated based on first defect parameter data, second defect parameter data and standard thickness data corresponding to the steel tee joint with different defect types;
under different defect statistical coefficients, testing the hardness of the corresponding steel tee joint by using a test device;
establishing a two-dimensional relation between the defect statistical coefficient and the hardness according to different defect statistical coefficients and the hardness of the corresponding steel tee joint to obtain a relation sample set comprising the relation between the defect statistical coefficient and the hardness;
Dividing a relation sample set into a relation training set and a relation test set, constructing a regression network, taking a defect statistical coefficient in the relation training set as input of the regression network, taking hardness in the relation training set as output of the regression network, training the regression network to obtain an initial regression model, verifying the initial regression model by using the relation test set, and outputting the initial regression model meeting preset accuracy as the relation regression model.
Further, the quality safety evaluation is carried out based on the hardness of the steel tee joint to be evaluated, and the method comprises the following steps:
comparing the hardness of the steel tee joint to be evaluated with a preset steel tee joint hardness threshold;
if the hardness of the steel tee joint to be evaluated is greater than a preset steel tee joint hardness threshold value, judging that the steel tee joint is qualified;
if the hardness of the steel tee to be evaluated is smaller than or equal to the preset steel tee hardness threshold, judging that the steel tee to be evaluated is unqualified, acquiring a defect area with the largest area of the steel tee to be evaluated, and evaluating the defect area with the largest area to determine whether the steel to be evaluated can be repaired.
Further, evaluating the defect area with the largest area includes:
extracting the defect area of the defect area with the largest area, and obtaining the defect type of the defect area with the largest area;
Carrying out formulated calculation based on the defect area of the defect area with the largest area and the defect type to obtain a repairability evaluation coefficient; the calculation formula is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein: />In order to evaluate the coefficient of repairability,for the defect type change value, when the defect type of the defect area with the largest area is a crack, the defect type change value is f 1 When the defect type of the defect area with the largest area is the air hole, the defect type change value is f 2 When the defect type of the defect area with the largest area is inclusion, the defect type change value is f 3 ,f 1 ＞f 2 ＞f 3 ＞0；/>A defect area which is a defect area having the largest area; />And->A weight factor greater than zero;
setting a repairability evaluation coefficient threshold, comparing the repairability evaluation coefficient with the repairability evaluation coefficient threshold, and if the repairability evaluation coefficient is greater than or equal to the repairability evaluation coefficient threshold, judging that the steel tee joint to be evaluated is unqualified and unrepairable; if the repairability evaluation coefficient is smaller than the repairability evaluation coefficient threshold value, judging that the steel tee joint to be evaluated is unqualified but repairable.
An electronic device comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the defect detection and safety state evaluation method of the steel tee when executing the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method of defect detection and safety state assessment for a steel tee as described above.
Compared with the prior art, the application has the beneficial effects that:
1. the application discloses a defect detection and safety state evaluation method of a steel tee joint, which comprises the steps of firstly, acquiring an X-ray flat image and an ultrasonic flat image, and acquiring an ultrasonic signal set; then, carrying out image fusion on the X-ray flat image and the ultrasonic flat image to obtain a fusion image, and analyzing the fusion image to obtain first defect parameter data of the steel tee joint to be evaluated; analyzing based on the ultrasonic signal set to obtain second defect parameter data of the steel tee joint to be evaluated; then calculating according to the first defect parameter data and the second defect parameter data to obtain a defect statistical coefficient; determining the hardness corresponding to the defect statistical coefficient based on a relation regression model preset by the defect statistical coefficient and the hardness relation; finally, carrying out quality safety evaluation based on the hardness to obtain an evaluation result of the steel tee joint; based on the steps, the method can ensure the remarkable characteristics of the steel tee joint, and simultaneously maintain the detailed characteristics of the steel tee joint, thereby being beneficial to improving the defect detection accuracy and avoiding or reducing the condition of missing detection or false detection.
2. The application discloses a defect detection and safety state evaluation method for a steel tee, which is beneficial to realizing high-efficiency quality classification of the steel tee by carrying out defect analysis based on a fusion image and carrying out quality safety evaluation according to the fusion image.
Drawings
FIG. 1 is a schematic diagram of a method for detecting defects and evaluating safety state of a steel tee joint according to the present application;
FIG. 2 is a schematic measurement diagram of a standard steel tee provided by the application;
fig. 3 is a schematic structural diagram of an electronic device according to the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Example 1
Referring to fig. 1, the disclosure of the present embodiment provides a method for detecting defects and evaluating safety states of a steel tee, the method comprising:
s101: acquiring an X-ray flat image and an ultrasonic flat image of a main pipe of the steel tee to be evaluated, acquiring an X-ray flat image and an ultrasonic flat image of a branch pipe of the steel tee to be evaluated, and acquiring an ultrasonic signal set of the steel tee to be evaluated;
it should be noted that: the X-ray tiled image is obtained by an X-ray detection device, including but not limited to an industrial X-ray machine, X-ray perspective equipment or X-ray flaw detector; the ultrasonic tiled image and the ultrasonic signal set are acquired by an ultrasonic detection device, wherein the ultrasonic detection device comprises, but is not limited to, a portable ultrasonic detector, an ultrasonic array detector or an ultrasonic measuring instrument and the like;
specifically, the acquisition logic of the X-ray tiled images of the steel tee main pipe and the branch pipe to be evaluated is as follows:
respectively dividing equal annular virtual areas of a steel three-way main pipe and a branch pipe to be evaluated to obtain M main pipe annular division areas and N branch pipe annular division areas, wherein M, N is a positive integer greater than zero;
Acquiring a main pipe local X-ray image of each main pipe annular dividing region and a branch pipe local X-ray image of each branch pipe annular dividing region through an X-ray detection device respectively;
acquiring acquisition rules of a main pipe and a branch pipe, and respectively carrying out image stitching on the local X-ray images of the main pipe and the local X-ray images of the branch pipe based on the acquisition rules so as to acquire X-ray tiled images of the main pipe and the branch pipe of the steel tee to be evaluated;
it should be noted that: the collection rules of the main pipe and the branch pipe are prestored in a system database, and the logic of the collection rules of the main pipe and the branch pipe is as follows: setting the shooting breadth of the X-ray detection device, shooting the steel tee main pipe and the branch pipe to be evaluated by using the X-ray detection device at a preset first position, adjusting the position of the X-ray detection device when shooting at the preset first position is completed, shooting the steel tee main pipe and the branch pipe to be evaluated by using the X-ray detection device at a preset second position, adjusting the position of the X-ray detection device when shooting at the preset second position is completed, shooting the steel tee main pipe and the branch pipe to be evaluated by using the X-ray detection device at a preset third position, and the like until shooting at a preset R position is completed, wherein R is a positive integer set larger than zero, and further explaining that: when the shooting breadth of the X-ray detection device is set to be 45 degrees, the X-ray detection device is moved to a preset first position of a main pipe and a branch pipe, the main pipe and the branch pipe are shot at 45 degrees to obtain 45-degree images of the first position, then the X-ray detection device is adjusted to move to a preset second position, the main pipe and the branch pipe are shot at 45 degrees to obtain 45-degree images of the second position, and the like, 45-degree images of 8 positions are obtained, 45-degree images of 8 positions are spliced, and 360-degree images are obtained, namely X-ray tiled images of the main pipe and the branch pipe are obtained;
Specifically, before image stitching is performed on the main tube local X-ray image, the method includes:
acquiring every two adjacent main tube local X-ray images;
taking one main pipe local X-ray image of every two adjacent main pipe local X-ray images as a target image and the other main pipe local X-ray image as a matching image;
setting the step length as 1, and performing cross-correlation calculation on the matched image and the target image in a sliding window mode to obtain the similarity of each overlapping part;
it should be appreciated that: the basic idea of the cross-correlation calculation is that one image is used as a template, the other image is used as a matching object, the matching object is placed on the template, the similarity of each overlapped part is calculated by sliding the matching object on the template in a window, and the same area of the two images can be obtained, wherein the calculation formula of the similarity comprises but is not limited to one of cosine similarity and Euclidean distance;
taking the overlapping part with the similarity larger than a preset similarity threshold value as the same area, dividing the same area in the target image or the matched image, and removing the divided part;
it should be noted that: processing logic before image stitching is performed on the branch pipe local X-ray images is the same as that of the main pipe local X-ray images, and details are referred to above, so that redundant description is omitted;
Also to be described is: the logic for acquiring the ultrasonic tiling images of the main pipe and the branch pipe of the steel tee joint to be evaluated is the same as that of the X-ray tiling images of the main pipe and the branch pipe of the steel tee joint to be evaluated, and details are referred to above and are not repeated;
it should be appreciated that: the image obtained by the X-ray detection device has the characteristic of a shadow image with high contrast, and is suitable for detecting larger and denser defects; the image acquired by the ultrasonic detection device has the characteristic of providing finer and finer characteristics about defects, and is sensitive to small-size, subsurface or deep defect detection; the X-ray flat image and the ultrasonic flat image are acquired, so that the method is beneficial to acquiring the obvious characteristics of the steel tee to be evaluated and retaining the detailed characteristics of the steel tee to be evaluated, and is beneficial to improving the defect detection accuracy of the steel tee to be evaluated subsequently;
s102: performing image fusion on the X-ray flat image and the ultrasonic flat image to obtain a fusion image, and analyzing the fusion image to obtain first defect parameter data of the steel tee to be evaluated; analyzing based on the ultrasonic signal set to obtain second defect parameter data of the steel tee joint to be evaluated; the first defect parameter data comprise defect types, main pipe defect area, branch pipe defect area, main pipe defect area quantity and branch pipe defect area quantity; the second defect parameter data comprise measured thicknesses of a main pipe and a branch pipe;
Specifically, the fusion image comprises a fusion image of a main pipe and a fusion image of a branch pipe;
in one embodiment, image fusion of an X-ray tile and an ultrasound tile includes: extracting (a main pipe and a branch pipe) an X-ray flat image and an ultrasonic flat image, and preprocessing the X-ray flat image and the ultrasonic flat image to ensure that the X-ray flat image and the ultrasonic flat image have the same size and resolution; the preprocessing can use an image interpolation technology to zoom or cut the image, so that the X-ray tiled image and the ultrasonic tiled image have consistent sizes; setting the transparency of an X-ray flat image or an ultrasonic flat image to be 100%, superposing the X-ray flat image on the ultrasonic flat image or superposing the ultrasonic flat image on the X-ray flat image to obtain a fusion image of a main pipe and a fusion image of a branch pipe;
in another embodiment, image fusion of an X-ray tile and an ultrasound tile includes:
taking an ultrasonic flat image of a main tube as a first ultrasonic image and an X-ray flat image of the main tube as a first X-ray image; and taking the ultrasonic tiled image of the branch pipe as a second ultrasonic image, and taking the X-ray tiled image of the branch pipe as a second X-ray image;
Dividing the first ultrasound image and the first X-ray image into S parts based on the same rule, and dividing the second ultrasound image and the second X-ray image into D parts based on the same rule, S, D being a positive integer greater than zero;
it should be noted that: the method comprises the steps that S parts are obtained after a first ultrasonic image and a first X-ray image are divided based on the same rule, and the dividing mode and the size of areas of the S parts in the first ultrasonic image and the S parts in the first X-ray image are completely the same; likewise, the principle of the D parts is also the same, and will not be described in detail here;
calculating a first degree of difference of the same portion of the first ultrasonic image and the first X-ray image, and calculating a second degree of difference of the same portion of the second ultrasonic image and the second X-ray image;
it should be noted that: the calculation formula of the difference degree includes, but is not limited to, one of a mean square error or an absolute difference (pixel difference method);
comparing the first difference with a preset first difference threshold, and comparing the second difference with a preset second difference threshold;
if the first difference degree is larger than a preset first difference degree threshold value, reserving the corresponding same part in the first ultrasonic image; if the first difference degree is smaller than or equal to a preset first difference degree threshold value, eliminating the corresponding same part in the first ultrasonic image to obtain a first ultrasonic image with a reserved part;
If the second difference degree is larger than a preset second difference degree threshold value, reserving the corresponding same part in the second ultrasonic image; if the second difference degree is smaller than or equal to a preset second difference degree threshold value, eliminating the corresponding same part in the first ultrasonic image to obtain a second ultrasonic image with a reserved part;
completely overlapping the first ultrasonic image of the reserved part on the first X-ray image to obtain a fusion image of the main tube; and completely overlapping the second ultrasonic image of the reserved part on the second X-ray image to obtain a fusion image of the branch pipe;
it should be noted that: the transparency of the first ultrasound image of the reserved portion and the second ultrasound image of the reserved portion is 100%; the method is beneficial to preserving the remarkable characteristics of the steel tee joint to be evaluated and preserving the detailed characteristics of the steel tee joint to be evaluated at the same time by extracting the reserved part based on the difference degree of the ultrasonic images and superposing the reserved part on the X-ray images; thereby being beneficial to improving the detection accuracy of the defects of the steel tee joint to be evaluated subsequently;
specifically, analyzing the fused image includes:
graying the fusion image of the main pipe to obtain a main pipe gray image, and graying the fusion image of the branch pipe to obtain a branch pipe gray image;
Carrying out pixel point distinction on the main gray image by using a K-means clustering algorithm, taking an area formed by clustering the pixels in the main gray image as a first target area, carrying out pixel point distinction on the branch gray image by using the K-means clustering algorithm, and taking an area formed by clustering the pixels in the branch gray image as a second target area; the first target area comprises P main pipe abnormal areas, the second target area comprises Q branch pipe abnormal areas, and P, Q is a positive integer greater than zero;
respectively inputting the main pipe abnormal region and the abnormal region of the branch pipe into a preset defect classification model in an image form to identify defect types of the main pipe abnormal region and the branch pipe abnormal region; type marking is carried out on the main pipe abnormal region and the branch pipe abnormal region according to the identification result; the defect types include cracks, inclusions, and pinholes;
specifically, the generation logic of the preset defect classification model is as follows:
acquiring first historical data of a steel tee, wherein the first historical data comprises fusion images of main pipes of the steel tee with different defect types and fusion images of branch pipes of the steel tee with different defect types;
performing defect type labeling on the fusion images of the steel tee main pipes with different defect types, and performing defect type labeling on the fusion images of the steel tee branch pipes with different defect types;
Taking the fusion image of the main pipe and the fusion image of the branch pipe after the defect type is marked as an image sample set, and dividing the image sample set into an image training set and an image testing set;
constructing a classification network, taking a fusion image of a main pipe and a fusion image of a branch pipe in an image training set as input of the classification network, taking defect type labels of the fusion image of the main pipe and the defect type labels of the fusion image of the branch pipe in the image training set as output of the classification network, and training the classification network to obtain an initial classification model;
verifying the initial classification model by using the image test set, and outputting the initial classification model meeting the preset accuracy as a preset defect classification model;
it should be noted that: the classification network is specifically one of a decision tree classification model, a support vector classification model, a random forest classification model or a neural network classification model;
counting the number of pixel point clusters in each main pipe abnormal region, and taking the number of pixel point clusters in each main pipe abnormal region as the area of each main pipe abnormal region; counting the number of pixel point clusters in each branch abnormal region, and taking the number of pixel point clusters in each branch abnormal region as the area of each main pipe abnormal region;
Specifically, the analysis based on the ultrasonic signal set includes:
extracting g main pipe ultrasonic signals in the ultrasonic signal set, and extracting h branch pipe ultrasonic signals in the ultrasonic signal set;
obtaining the reflection time of each main pipe ultrasonic signalAnd obtaining the reflection time of the ultrasonic signal of each branch pipe +.>；
The reflection time of each main pipe ultrasonic signalRespectively +.>And minimum reflection time of the host signal +.>Comparing and reflecting time of ultrasonic signal of each branch pipe>Respectively with the maximum reflection time of the branch signals +.>And minimum reflection time of the branch signal +.>Comparing;
if it isWill correspond->As an effective main tube ultrasonic signal, if +.>Or->Will correspond->As an inactive ultrasound signal;
if it isWill correspond->As an effective branch ultrasonic signal, if->Or->Will correspond->As an inactive branch ultrasonic signal;
respectively carrying out thickness calculation according to the effective main pipe ultrasonic signals and the effective branch pipe ultrasonic signals to obtain the main pipe actual measurement thickness and the branch pipe actual measurement thickness;
it should be noted that: as shown in FIG. 2 (a measurement schematic of a standard steel tee), the maximum reflection time of the main pipe signal And minimum reflection time of the host signal +.>Based on the standard steel tee, the further explanation is that: if the wall thickness of the main pipe is V and the internal diameter of the main pipe is r, the reflection time of the ultrasonic signal of the main pipe is obtained by obtaining 2V+rObtaining the maximum reflection time of the main tube signal +.>The method comprises the steps of carrying out a first treatment on the surface of the Whereas the minimum reflection time for the host signal +.>In other words, the scheme detects the defect type of the steel tee joint, such as cracks, inclusions and air holes, so the minimum reflection time of the main pipe signal is +.>It is impossible to be less than r +.>Thus, the reflection time of the main tube ultrasonic signal in the r condition is +.>Minimum reflection time as main tube signal +.>The method comprises the steps of carrying out a first treatment on the surface of the Also to be described is: the calculation formula of the measured thickness of the main pipe is +.>The method comprises the steps of carrying out a first treatment on the surface of the Wherein: />For the measured thickness of the main tube>For the propagation speed of the ultrasound signal, < > for>Is->The effective main tube ultrasonic signal, +.>The total number of the ultrasonic signals is effectively used as the main pipe; similarly, maximum reflection time for the branch signal +.>And minimum reflection time of the branch signal +.>The principle of determining the thickness of the main pipe is the same as that of the branch pipe, and detailed description thereof is omitted;
S103: calculating according to the first defect parameter data and the second defect parameter data to obtain a defect statistical coefficient; determining the hardness of the steel tee to be evaluated corresponding to the defect statistical coefficient based on a relation regression model preset by the defect statistical coefficient and the hardness relation;
specifically, the logic for performing the calculation according to the first defect parameter data and the second defect parameter data is:
obtaining standard thickness data of a steel tee joint to be evaluated, which is pre-stored in a system database, wherein the standard thickness data comprises main pipe standard thickness data and branch pipe standard thickness data;
carrying out formula calculation based on the first defect parameter data, the second defect parameter data and the standard thickness data to obtain a defect statistical coefficient of the steel tee to be evaluated, wherein the calculation formula is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein: />For defect statistics coefficients, ++>For the i-th main pipe defect area, < +.>For the number of main tube defect areas of the ith, < +.>For the j-th defective area of the branch pipe, < >>For the number of defective areas of the j-th branch, for example>For the i-th main pipe measured thickness, +.>For the standard thickness data of the main pipe->The thickness is measured for the j-th leg,for standard thickness data of branch pipe, +. >For the total number of the abnormal regions of the main tube>Is the total number of abnormal areas of the branch pipe;
specifically, the construction logic of the relational regression model is as follows:
acquiring second historical data of the steel tee joint, wherein the second historical data at least comprises different defect statistical coefficients corresponding to the steel tee joint with different defect types, and the different defect statistical coefficients are calculated based on first defect parameter data, second defect parameter data and standard thickness data corresponding to the steel tee joint with different defect types;
under different defect statistical coefficients, testing the hardness of the corresponding steel tee joint by using a test device;
it should be noted that: the second historical data of the steel tee joint is pre-stored in a system database, and the hardness of the steel tee joint is obtained through test by a test device, wherein the test device comprises, but is not limited to, a 100-ton mechanical property tester, a high-low temperature mechanical tester, a normal-low temperature impact tester and the like;
establishing a two-dimensional relation between the defect statistical coefficient and the hardness according to different defect statistical coefficients and the hardness of the corresponding steel tee joint to obtain a relation sample set comprising the relation between the defect statistical coefficient and the hardness;
dividing a relation sample set into a relation training set and a relation test set, constructing a regression network, taking a defect statistical coefficient in the relation training set as input of the regression network, taking hardness in the relation training set as output of the regression network, training the regression network to obtain an initial regression model, verifying the initial regression model by using the relation test set, and outputting the initial regression model meeting preset accuracy as the relation regression model;
It should be noted that: the regression network is specifically one of a linear regression model, a support vector regression model, a polynomial regression model, a decision tree regression model, a random forest regression model or a neural network regression model;
s104: performing quality safety evaluation based on the hardness of the steel tee to be evaluated to obtain an evaluation result of the steel tee; the evaluation results include pass, fail but repairable and fail and unrepairable;
in one embodiment, the quality safety assessment based on the hardness of the steel tee to be evaluated includes:
comparing the hardness of the steel tee joint to be evaluated with a preset steel tee joint hardness threshold;
if the hardness of the steel tee joint to be evaluated is greater than a preset steel tee joint hardness threshold value, judging that the steel tee joint is qualified;
if the hardness of the steel tee to be evaluated is smaller than or equal to the preset steel tee hardness threshold, judging that the steel tee to be evaluated is unqualified, acquiring a defect area with the largest area of the steel tee to be evaluated, and evaluating the defect area with the largest area to determine whether the steel to be evaluated can be repaired;
in another embodiment, evaluating the defect region having the largest area includes:
Extracting the defect area of the defect area with the largest area, and obtaining the defect type of the defect area with the largest area;
it should be noted that: the defect area with the largest area is specifically one of a main pipe defect area and a branch pipe defect area, and further explaining that when the defect area of the main pipe defect area is the largest, the defect area with the largest area is the corresponding main pipe defect area, and conversely, when the defect area of the branch pipe defect area is the largest, the defect area with the largest area is the corresponding branch pipe defect area;
carrying out formulated calculation based on the defect area of the defect area with the largest area and the defect type to obtain a repairability evaluation coefficient; the calculation formula is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein: />In order to evaluate the coefficient of repairability,for the defect type change value, when the defect type of the defect area with the largest area is a crack, the defect type change value is f 1 When the defect type of the defect area with the largest area is the air hole, the defect type change value is f 2 When the defect type of the defect area with the largest area is inclusion, the defect type change value is f 3 ,f 1 ＞f 2 ＞f 3 ＞0；/>A defect area which is a defect area having the largest area; />And->A weight factor greater than zero; / >
Setting a repairability evaluation coefficient threshold, comparing the repairability evaluation coefficient with the repairability evaluation coefficient threshold, and if the repairability evaluation coefficient is greater than or equal to the repairability evaluation coefficient threshold, judging that the steel tee joint to be evaluated is unqualified and unrepairable; if the repairability evaluation coefficient is smaller than the repairability evaluation coefficient threshold value, judging that the steel tee joint to be evaluated is unqualified but repairable;
it should be appreciated that: based on the wooden barrel principle, if the defect area with the largest area reaches the condition of unrepairable, the defect area also indicates that the corresponding steel tee joint to be evaluated is unrepairable and is returned to a factory for smelting; conversely, if the defect area with the largest area has repairable conditions, the defect area also indicates that the corresponding steel tee to be evaluated is repairable, and the steel tee to be evaluated should be returned to a factory for repair in time; the method can realize the safety detection of the large-caliber steel tee joint by carrying out quality safety evaluation based on the hardness of the steel tee joint to be evaluated based on the relation between the defect statistical coefficient and the hardness, and is suitable for the production scene of the steel tee joint in batches.
Example 2
Referring to fig. 3, the disclosure provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the method for detecting defects and evaluating safety states of a steel tee provided by the above methods when executing the computer program.
Since the electronic device described in this embodiment is an electronic device for implementing the method for detecting the defect and evaluating the safety state of the steel tee in this embodiment, based on the method for detecting the defect and evaluating the safety state of the steel tee described in this embodiment, those skilled in the art can understand the specific implementation of the electronic device and various modifications thereof, so how to implement the method in this embodiment of the application will not be described in detail herein. As long as the person skilled in the art implements the electronic device adopted by the defect detection and safety state evaluation method of the steel tee joint in the embodiment of the application, the electronic device belongs to the scope of protection required by the application.
Example 3
The embodiment discloses a computer readable storage medium, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the defect detection and safety state evaluation method of the steel tee joint provided by the methods when executing the computer program.
The above formulas are all formulas with dimensionality removed and numerical value calculated, the formulas are formulas with the latest real situation obtained by software simulation by collecting a large amount of data, and the selection of part or all preset parameters, weights and thresholds in the formulas is set by a person skilled in the art according to the real situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present invention are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center over a wired network or a wireless network. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely one, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.

Claims (12)

1. A method for detecting defects and evaluating safety states of a steel tee joint, the method comprising:
acquiring an X-ray flat image and an ultrasonic flat image of a main pipe of the steel tee to be evaluated, acquiring an X-ray flat image and an ultrasonic flat image of a branch pipe of the steel tee to be evaluated, and acquiring an ultrasonic signal set of the steel tee to be evaluated;
performing image fusion on the X-ray flat image and the ultrasonic flat image to obtain a fusion image, and analyzing the fusion image to obtain first defect parameter data of the steel tee to be evaluated; analyzing based on the ultrasonic signal set to obtain second defect parameter data of the steel tee joint to be evaluated; the first defect parameter data comprise defect types, main pipe defect area, branch pipe defect area, main pipe defect area quantity and branch pipe defect area quantity; the second defect parameter data comprise measured thicknesses of a main pipe and a branch pipe;
calculating according to the first defect parameter data and the second defect parameter data to obtain a defect statistical coefficient; determining the hardness of the steel tee to be evaluated corresponding to the defect statistical coefficient based on a relation regression model preset by the defect statistical coefficient and the hardness relation;
Performing quality safety evaluation based on the hardness of the steel tee to be evaluated to obtain an evaluation result of the steel tee; the evaluation results include pass, fail but repairable and fail and unrepairable.
2. The method for detecting defects and evaluating safety states of a steel tee according to claim 1, wherein the logic for acquiring the X-ray tiled images of main pipes and branch pipes of the steel tee to be evaluated is as follows:
respectively dividing equal annular virtual areas of a steel three-way main pipe and a branch pipe to be evaluated to obtain M main pipe annular division areas and N branch pipe annular division areas;
acquiring a main pipe local X-ray image of each main pipe annular dividing region and a branch pipe local X-ray image of each branch pipe annular dividing region through an X-ray detection device respectively;
acquiring acquisition rules of the main pipe and the branch pipe, and respectively carrying out image stitching on the main pipe local X-ray image and the branch pipe local X-ray image based on the acquisition rules so as to acquire an X-ray tiled image of the main pipe and an X-ray tiled image of the branch pipe of the steel tee to be evaluated.
3. The method for detecting defects and evaluating safety states of a steel tee according to claim 2, comprising, before image stitching of the main tube partial X-ray images:
Acquiring every two adjacent main tube local X-ray images;
taking one main pipe local X-ray image of every two adjacent main pipe local X-ray images as a target image and the other main pipe local X-ray image as a matching image;
setting the step length as 1, and performing cross-correlation calculation on the matched image and the target image in a sliding window mode to obtain the similarity of each overlapping part;
and taking the overlapping part with the similarity larger than the preset similarity threshold value as the same area, dividing the same area in the target image or the matched image, and removing the divided part.
4. A method of detecting defects and evaluating a safety state of a steel tee according to claim 3, wherein the fused image comprises a fused image of a main pipe and a fused image of a branch pipe;
image fusion is carried out on an X-ray flat image and an ultrasonic flat image, and the method comprises the following steps:
taking an ultrasonic flat image of a main tube as a first ultrasonic image and an X-ray flat image of the main tube as a first X-ray image; and taking the ultrasonic tiled image of the branch pipe as a second ultrasonic image, and taking the X-ray tiled image of the branch pipe as a second X-ray image;
Dividing the first ultrasound image and the first X-ray image into S parts based on the same rule, and dividing the second ultrasound image and the second X-ray image into D parts based on the same rule;
calculating a first degree of difference of the same portion of the first ultrasonic image and the first X-ray image, and calculating a second degree of difference of the same portion of the second ultrasonic image and the second X-ray image;
comparing the first difference with a preset first difference threshold, and comparing the second difference with a preset second difference threshold;
if the first difference degree is larger than a preset first difference degree threshold value, reserving the corresponding same part in the first ultrasonic image; if the first difference degree is smaller than or equal to a preset first difference degree threshold value, eliminating the corresponding same part in the first ultrasonic image to obtain a first ultrasonic image with a reserved part;
if the second difference degree is larger than a preset second difference degree threshold value, reserving the corresponding same part in the second ultrasonic image; if the second difference degree is smaller than or equal to a preset second difference degree threshold value, eliminating the corresponding same part in the first ultrasonic image to obtain a second ultrasonic image with a reserved part;
Completely overlapping the first ultrasonic image of the reserved part on the first X-ray image to obtain a fusion image of the main tube; and completely overlapping the second ultrasonic image of the reserved part on the second X-ray image to obtain a fusion image of the branch pipe.
5. The method for detecting defects and evaluating safety states of a steel tee according to claim 4, wherein analyzing the fused image comprises:
graying the fusion image of the main pipe to obtain a main pipe gray image, and graying the fusion image of the branch pipe to obtain a branch pipe gray image;
carrying out pixel point distinction on the main gray image by using a K-means clustering algorithm, taking an area formed by clustering the pixels in the main gray image as a first target area, carrying out pixel point distinction on the branch gray image by using the K-means clustering algorithm, and taking an area formed by clustering the pixels in the branch gray image as a second target area; the first target area comprises P main pipe abnormal areas, and the second target area comprises Q branch pipe abnormal areas;
respectively inputting the main pipe abnormal region and the abnormal region of the branch pipe into a preset defect classification model in an image form to identify defect types of the main pipe abnormal region and the branch pipe abnormal region; type marking is carried out on the main pipe abnormal region and the branch pipe abnormal region according to the identification result; the defect types include cracks, inclusions, and pinholes.
6. The method for detecting defects and evaluating safety states of a steel tee according to claim 5, wherein the analysis based on the ultrasonic signal set comprises:
extracting g main pipe ultrasonic signals in the ultrasonic signal set, and extracting h branch pipe ultrasonic signals in the ultrasonic signal set;
obtaining the reflection time of each main pipe ultrasonic signalAnd acquiring the reflection time of the ultrasonic signal of each branch pipe；
The reflection time of each main pipe ultrasonic signalRespectively +.>And minimum reflection time of the host signal +.>Comparing and reflecting time of ultrasonic signal of each branch pipe>Respectively with the maximum reflection time of the branch signals +.>And minimum reflection time of the branch signal +.>Comparing;
if it isWill correspond->As an effective main tube ultrasonic signal, if +.>Or->Will correspond->As an inactive ultrasound signal;
if it isWill correspond->As an effective branch ultrasonic signal, if->Or->Will correspond->As an inactive branch ultrasonic signal;
and respectively carrying out thickness calculation according to the effective main pipe ultrasonic signals and the effective branch pipe ultrasonic signals to obtain the main pipe actual measurement thickness and the branch pipe actual measurement thickness.
7. The method for detecting defects and evaluating safety states of a steel tee as set forth in claim 6, wherein the logic for calculating the first and second defect parameter data is:
obtaining standard thickness data of a steel tee joint to be evaluated, which is pre-stored in a system database, wherein the standard thickness data comprises main pipe standard thickness data and branch pipe standard thickness data;
carrying out formula calculation based on the first defect parameter data, the second defect parameter data and the standard thickness data to obtain a defect statistical coefficient of the steel tee to be evaluated, wherein the calculation formula is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein: />For defect statistics coefficients, ++>For the i-th main pipe defect area, < +.>For the number of main tube defect areas of the ith, < +.>For the j-th defective area of the branch pipe, < >>Defective area of the branch pipe of the j-thDomain number->For the i-th main pipe measured thickness, +.>For the standard thickness data of the main pipe->The thickness is measured for the j-th leg,for standard thickness data of branch pipe, +.>For the total number of the abnormal regions of the main tube>Is the total number of abnormal areas of the branch pipe.
8. The method for detecting defects and evaluating safety states of a steel tee according to claim 7, wherein the construction logic of the relational regression model is as follows:
Acquiring second historical data of the steel tee joint, wherein the second historical data at least comprises different defect statistical coefficients corresponding to the steel tee joint with different defect types, and the different defect statistical coefficients are calculated based on first defect parameter data, second defect parameter data and standard thickness data corresponding to the steel tee joint with different defect types;
under different defect statistical coefficients, testing the hardness of the corresponding steel tee joint by using a test device;
establishing a two-dimensional relation between the defect statistical coefficient and the hardness according to different defect statistical coefficients and the hardness of the corresponding steel tee joint to obtain a relation sample set comprising the relation between the defect statistical coefficient and the hardness;
dividing a relation sample set into a relation training set and a relation test set, constructing a regression network, taking a defect statistical coefficient in the relation training set as input of the regression network, taking hardness in the relation training set as output of the regression network, training the regression network to obtain an initial regression model, verifying the initial regression model by using the relation test set, and outputting the initial regression model meeting preset accuracy as the relation regression model.
9. The method for detecting defects and evaluating safety states of a steel tee according to claim 8, wherein the quality safety evaluation is performed based on the hardness of the steel tee to be evaluated, comprising:
Comparing the hardness of the steel tee joint to be evaluated with a preset steel tee joint hardness threshold;
if the hardness of the steel tee joint to be evaluated is greater than a preset steel tee joint hardness threshold value, judging that the steel tee joint is qualified;
if the hardness of the steel tee to be evaluated is smaller than or equal to the preset steel tee hardness threshold, judging that the steel tee to be evaluated is unqualified, acquiring a defect area with the largest area of the steel tee to be evaluated, and evaluating the defect area with the largest area to determine whether the steel to be evaluated can be repaired.
10. The method for detecting defects and evaluating safety states of a steel tee according to claim 9, wherein evaluating the defect area having the largest area comprises:
extracting the defect area of the defect area with the largest area, and obtaining the defect type of the defect area with the largest area;
carrying out formulated calculation based on the defect area of the defect area with the largest area and the defect type to obtain a repairability evaluation coefficient; the calculation formula is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein: />For repairability evaluation coefficient, < >>For the defect type change value, when the defect type of the defect area with the largest area is a crack, the defect type change value is f 1 When the defect type of the defect area with the largest area is the air hole, the defect type change value is f 2 When the defect type of the defect area with the largest area is inclusion, the defect type change value is f 3 ,f 1 ＞f 2 ＞f 3 ＞0；/>A defect area which is a defect area having the largest area; />And->A weight factor greater than zero;
setting a repairability evaluation coefficient threshold, comparing the repairability evaluation coefficient with the repairability evaluation coefficient threshold, and if the repairability evaluation coefficient is greater than or equal to the repairability evaluation coefficient threshold, judging that the steel tee joint to be evaluated is unqualified and unrepairable; if the repairability evaluation coefficient is smaller than the repairability evaluation coefficient threshold value, judging that the steel tee joint to be evaluated is unqualified but repairable.
11. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements a method for defect detection and safety state assessment of a steel tee according to any one of claims 1 to 10 when executing the computer program.
12. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and when executed by a processor, the computer program implements a method for detecting defects and evaluating safety states of a steel tee according to any one of claims 1 to 10.
CN202311212960.XA 2023-09-20 2023-09-20 Defect detection and safety state assessment method for steel tee joint Active CN116953196B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311212960.XA CN116953196B (en) 2023-09-20 2023-09-20 Defect detection and safety state assessment method for steel tee joint

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311212960.XA CN116953196B (en) 2023-09-20 2023-09-20 Defect detection and safety state assessment method for steel tee joint

Publications (2)

Publication Number Publication Date
CN116953196A true CN116953196A (en) 2023-10-27
CN116953196B CN116953196B (en) 2023-12-05

Family

ID=88449592

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311212960.XA Active CN116953196B (en) 2023-09-20 2023-09-20 Defect detection and safety state assessment method for steel tee joint

Country Status (1)

Country Link
CN (1) CN116953196B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114119524A (en) * 2021-11-17 2022-03-01 中国农业大学 Hot-rolled steel strip defect detection method for improving Faster R-CNN
CN115018853A (en) * 2022-08-10 2022-09-06 南通市立新机械制造有限公司 Mechanical component defect detection method based on image processing
CN115937147A (en) * 2022-12-09 2023-04-07 北京小米移动软件有限公司 Defect detection parameter determination method, device, equipment and storage medium
CN116129242A (en) * 2023-02-01 2023-05-16 大连海洋大学 Aluminum product surface defect identification method based on improved YOLOv4
CN116188475A (en) * 2023-05-05 2023-05-30 德中(深圳)激光智能科技有限公司 Intelligent control method, system and medium for automatic optical detection of appearance defects
CN116256434A (en) * 2023-02-03 2023-06-13 温州市特种设备检测科学研究院(温州市特种设备应急处置中心) Method and equipment for calculating defect detection rate of manual ultrasonic transverse wave detection

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114119524A (en) * 2021-11-17 2022-03-01 中国农业大学 Hot-rolled steel strip defect detection method for improving Faster R-CNN
CN115018853A (en) * 2022-08-10 2022-09-06 南通市立新机械制造有限公司 Mechanical component defect detection method based on image processing
CN115937147A (en) * 2022-12-09 2023-04-07 北京小米移动软件有限公司 Defect detection parameter determination method, device, equipment and storage medium
CN116129242A (en) * 2023-02-01 2023-05-16 大连海洋大学 Aluminum product surface defect identification method based on improved YOLOv4
CN116256434A (en) * 2023-02-03 2023-06-13 温州市特种设备检测科学研究院(温州市特种设备应急处置中心) Method and equipment for calculating defect detection rate of manual ultrasonic transverse wave detection
CN116188475A (en) * 2023-05-05 2023-05-30 德中(深圳)激光智能科技有限公司 Intelligent control method, system and medium for automatic optical detection of appearance defects

Also Published As

Publication number Publication date
CN116953196B (en) 2023-12-05

Similar Documents

Publication Publication Date Title
CN112232400B (en) Stainless steel weld ultrasonic defect detection method based on depth feature fusion
US20160252481A1 (en) Pipe Damage Assessment System and Method
CN109190272B (en) Concrete structure defect detection method based on elastic waves and machine learning
US9335296B2 (en) Systems and methods for steam generator tube analysis for detection of tube degradation
US8387444B2 (en) Method of modeling steam generator and processing steam generator tube data of nuclear power plant
Guan et al. Automatic fault diagnosis algorithm for hot water pipes based on infrared thermal images
CN112116566A (en) Land oil and gas pipeline defect diagnosis method based on hyperspectral remote sensing technology
CN114778684A (en) Steel pipe performance evaluation method and system based on service scene
AU2020271967A1 (en) Method for determining the geometry of a defect on the basis of non-destructive measurement methods using direct inversion
CN106932469B (en) Heat exchange tube defect detection method based on eddy current signal characteristics
CN117237364B (en) Welded pipe quality detection method based on image characteristics
CN116953196B (en) Defect detection and safety state assessment method for steel tee joint
Ebrahimi et al. Automated condition assessment of sanitary sewer pipes using LiDAR inspection data
CN112525923A (en) Shared juice platform pipeline inner wall detection method and system and readable storage medium
CN115144259B (en) Method and system for detecting deformation resistance of steel
Udpa et al. Automated analysis of eddy current signals in steam generator tube inspection
KR101131996B1 (en) An Eddy Current Examination Method for the Outside Diameter Axial Cracks in Steam Generator Tubes Using Motorized Rotating Pancake Coil
CN112649354A (en) Comprehensive evaluation method for measuring corrosion of metal pipeline by multiple sensors
CN115935241B (en) Multi-parameter mutually-fused pipe cleaner real-time positioning method and device
Wang et al. Research on the error correction algorithm for caliper center offset in the offshore pipeline
Zhang et al. Diagnosis and recognition of pipeline damage defects based on improved convolutional neural network
Skow et al. In-line inspection tool performance evaluation using field excavation data
Zhang et al. Diagnosis and Recognition of Pipeline Damage Defects Based on Neural Network Algorithm
WO2022209169A1 (en) Information processing device, determination method, and determination program
Fathi et al. High-Precision Single-Leak Detection and Localization in Single-Phase Liquid Pipelines Using the Negative Pressure Wave Technique: An Application in a Real-Field Case Study

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant