CN115047015A - Online X-ray nondestructive flaw detection method and system - Google Patents
Online X-ray nondestructive flaw detection method and system Download PDFInfo
- Publication number
- CN115047015A CN115047015A CN202210642087.7A CN202210642087A CN115047015A CN 115047015 A CN115047015 A CN 115047015A CN 202210642087 A CN202210642087 A CN 202210642087A CN 115047015 A CN115047015 A CN 115047015A
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- piece
- area
- matching
- 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
Images
Classifications
-
- 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
- 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
- G01N23/06—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 measuring the absorption
- G01N23/18—Investigating the presence of flaws defects or foreign matter
-
- 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
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/273—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion removing elements interfering with the pattern to be recognised
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
-
- 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
- G06T2207/10116—X-ray 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
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The invention discloses an online X-ray nondestructive flaw detection method and a system thereof, belonging to the technical field of flaw detection, wherein the method comprises the steps of obtaining an image to be detected containing structural characteristics when an object to be detected is triggered to infrared beams emitted downwards by a diffuse light barrier, inputting the image to be detected into a pre-trained image model for matching, and if an image matching value corresponding to the image to be detected obtained through matching is larger than an image matching threshold, passing the matching and removing the interference of the structural characteristics to generate an area to be identified, calculating local dynamic threshold comparison and area gray value comparison so as to judge whether the object to be detected is qualified. The invention realizes the high-definition online detection of the positions of flaws, strain, fracture and the like of the piece to be detected in a segmented asynchronous manner by performing model matching, interference removal and calculation on the brightness and the gray level of the identification area on the image to be detected, so that the labor input is reduced, the total detection time is shortened, and the production quality and the production efficiency are improved.
Description
Technical Field
The invention belongs to the technical field of flaw detection, and relates to an online X-ray nondestructive flaw detection method and system.
Background
In the current industrial production, whether defects such as flaws, strain, cracks and the like exist on the surface of a product required by appearance needs to be checked in the production process, so that the product is prevented from flowing into the market, and the traditional assembly line is easy to cause certain production influence due to the fact that manual checking is adopted, so that missing, wrong and the like are prone to occurring and result in failure.
The existing X-ray scanners in the market mostly use linear array scanning, the spatial resolution is low, the definition is not high enough, small flaws of a detection piece cannot be well detected and judged, and missing detection and error detection are easy. And because the X-ray scanner of dull and stereotyped, then because the size problem of dull and stereotyped, just can carry out the judgement of flaw, defect after need the concatenation to handle the completion to jumbo size object, the concatenation reduces the whole definition of image easily, and carries out the flaw after the concatenation is accomplished again and detect, can influence the check-out time of whole flow, reduces work efficiency, can not reach the detection speed of assembly line.
Therefore, engineering technicians in the field need to develop a high-definition online X-ray nondestructive inspection method and a high-definition online X-ray nondestructive inspection system which can realize segmented asynchronous inspection without splicing the whole image of the inspection piece, and can detect the positions of flaws, strain, fracture and the like of the inspection piece so as to improve the production efficiency.
Disclosure of Invention
The invention provides an online X-ray nondestructive flaw detection method and system, aiming at solving the problems in the background art and realizing the high-definition online detection of the positions of flaws, strain, fracture and the like of a detection piece in a segmented and asynchronous manner so as to reduce the manpower input, shorten the overall detection time and improve the production quality and the production efficiency.
In order to achieve the above object, the present invention provides an online X-ray nondestructive inspection method, which comprises the following steps:
the collection step comprises: when an infrared beam emitted downwards by a diffuse reflection barrier is triggered by a piece to be detected, collecting structural characteristics of the piece to be detected through an X-ray light source and inputting the structural characteristics into an image detection system to obtain a corresponding image to be detected containing the structural characteristics, wherein the structural characteristics comprise an appearance profile, an inner hole profile, a size, a sinking platform, a folding edge, a height and surface textures;
matching: inputting the obtained image to be detected containing the structural features into a pre-trained image model for matching, and if the image matching value corresponding to the image to be detected obtained through matching is larger than an image matching threshold value, the matching is passed;
the processing steps are as follows: removing interference on the matched structural features in the image to be detected to generate a region to be identified contained in the image to be detected;
a calculation step: and calculating local dynamic threshold value comparison and regional gray value comparison of the to-be-identified region through image processing, and judging that the to-be-detected part is unqualified when the local dynamic threshold value comparison is greater than a first preset ratio and/or the regional gray value comparison is greater than a second preset ratio, which indicates that the to-be-identified region is a flaw, strain or fracture region.
Preferably, before the acquiring step, the method further comprises:
a transmission step: a piece to be detected is placed on a production line, a conveyor belt drives the piece to be detected to enter a detection channel, and a diffuse reflection light barrier, an X-ray light source and an image processing system are installed above the detection channel.
Preferably, after the calculating step, the method further comprises:
a marking step: and marking unqualified positions of the identification area where the to-be-detected piece is located, producing unqualified information, and removing a production line when the to-be-detected piece enters the next station.
Preferably, the calculating the to-be-identified region by image processing includes region grayscale enhancement, grayscale value comparison, and local dynamic threshold comparison, where the formula is as follows:
and (3) regional gray level enhancement: dst round ((src 0-src 1): coef) + src0
Where src0 represents input image 0, src1 represents input image 1, dst represents the processing result, coef represents the enhancement coefficient, and round represents rounding.
Local dynamic threshold comparison: judging whether io > is it + shift, judging whether io > is it-shift in a dark area, judging whether it-shift is io + it + shift in a gray value stable area, and judging whether io > is it-shift or whether io > is it + shift in an area with larger change;
wherein io represents an original image, it represents a threshold image, and shift represents a threshold;
gray value comparison: judging dst as src < th in bright area, judging dst as src < th in dark area;
where src denotes an original image, th denotes a threshold value, and dst denotes a processing result.
Preferably, the matching step includes:
matching detection can be carried out on the detection image within a set angle range according to the image model;
according to the information of the position, the angle, the distortion and the deformation after the image model matching detection, the image model is transformed, so that the image model is matched to the corresponding position of the image to be detected;
carrying out operation correction of removing, filling, offsetting, zooming or screening on the image characteristics of the image to be detected according to the image model;
correcting the right angle, the arc and the inner hole of the image to be detected according to the image model; and
and performing regional correction on the image to be detected according to the image model.
Preferably, the training step of the image model includes:
acquiring a plurality of pieces to be detected, photographing, performing gray level processing on the obtained pictures of the pieces to be detected, and generating images to be detected corresponding to the pieces to be detected;
after the image to be detected is subjected to characteristic marking, an image detection area and an image characteristic marking area corresponding to the marked image to be detected are obtained; and
and training the marked image features to generate single-layer or multi-layer feature information to obtain the image model.
Preferably, when the acquisition area of the to-be-detected piece exceeds the downward irradiation area of the X-ray light source, the moving distance is automatically calculated according to the length of the to-be-detected piece by using a segmented image acquisition mode, and after the to-be-detected piece moves to a proper position, each area included in the to-be-detected piece is acquired through the X-ray light source and is respectively input into an image detection system for detection.
Preferably, the image detection system performs detection by:
after the X-ray light source collects a first region reg1 contained in the piece to be detected;
performing image model matching on a first to-be-detected image corresponding to the first region reg1, performing interference removal on structural features in the to-be-detected image, calculating a region brightness value and a region gray value of an identification region, and judging whether a current processing region of the to-be-detected image is qualified, and simultaneously performing the following judgment operations:
operation 1: if the detection piece is too long, before the whole detection piece is collected, automatically calculating the moving distance according to the length of the detection piece, and collecting a second region reg2 contained in the detection piece through the X-ray light source after the detection piece moves to a proper position;
operation 2: if the acquisition area of the detection piece is within the area irradiated downwards by the X-ray light source, starting the conveyor belt to wait for the next detection piece until the acquisition of the next detection piece is completed, and obtaining an area reg2 of a second detection piece;
and starting the acquisition process of the next area or the next detection piece according to the judgment of the operation 1 and the operation 2 while calculating the model matching and the interference removal of the second region to be identified reg2 and judging whether the position is qualified.
In addition, the present invention also provides an online X-ray nondestructive inspection system using the online X-ray nondestructive inspection method described in any one of the above, the system including:
the acquisition module is used for acquiring the structural characteristics of the piece to be detected by an X-ray light source and inputting the structural characteristics into an image detection system when the piece to be detected triggers an infrared beam emitted downwards by a diffuse reflection light barrier, so as to obtain a to-be-detected image which corresponds to the piece to be detected and contains the structural characteristics, wherein the structural characteristics comprise an appearance profile, an inner hole profile, a size, a sinking platform, a folding edge, a height and surface textures;
the matching module is used for inputting the obtained image to be detected containing the structural features into a pre-trained image model for matching, and if the image matching value corresponding to the image to be detected obtained through matching is larger than the image matching threshold value, the matching is passed;
the processing module is used for removing interference of the structural features in the image to be detected which passes the matching, and generating a region to be identified contained in the image to be detected;
the calculation module is used for calculating local dynamic threshold value comparison and area gray value comparison of the area to be identified through image processing, and when the local dynamic threshold value comparison is larger than a first preset ratio and/or the area gray value comparison is larger than a second preset ratio, the area to be identified is a flaw, strain or fracture area, and the piece to be detected is judged to be unqualified;
and the marking module is used for marking unqualified positions of the identification area where the piece to be detected which is judged to be unqualified is located, producing unqualified information, and removing a production line when the next station is entered.
Preferably, the system further comprises, before the acquisition module:
the conveying module is used for placing the piece to be detected on a production line, the conveying belt drives the piece to be detected to enter a detection channel, and a diffuse reflection light barrier, an X-ray light source and an image processing system are installed above the detection channel.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides an online X-ray nondestructive inspection detection method and a system thereof.A structural characteristic of an article to be detected is collected by an X-ray light source and input into an image detection system when the article to be detected triggers an infrared light beam emitted downwards by a diffuse light barrier, an image to be detected containing the structural characteristic corresponding to the article to be detected is obtained and input into a pre-trained image model for matching, if an image matching value corresponding to the image to be detected obtained by matching is greater than an image matching threshold value, the matching is passed and the interference of the structural characteristic is removed, and an area to be identified contained in the image to be detected is generated; and calculating local dynamic threshold value comparison and regional gray value comparison of the to-be-identified region through image processing, and judging that the to-be-detected part is unqualified when the local dynamic threshold value comparison is greater than a first preset ratio and/or the regional gray value comparison is greater than a second preset ratio, which indicates that the to-be-identified region is a flaw, strain or fracture region. The invention realizes the high-definition online detection of the positions of flaws, strain, fracture and the like of the piece to be detected in a segmented asynchronous manner by performing model matching, interference removal and calculation on the brightness and the gray level of the identification area on the image to be detected, so that the labor input is reduced, the total detection time is shortened, and the production quality and the production efficiency are improved.
To more clearly illustrate the structural features and effects of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
Drawings
FIG. 1 is a first flowchart of an online X-ray nondestructive inspection method according to a preferred embodiment of the present invention;
FIG. 2 is a second flow chart of the online nondestructive X-ray inspection method according to the preferred embodiment of the present invention;
FIG. 3 is a schematic diagram of the program modules of the online X-ray nondestructive inspection system of the present invention;
FIG. 4 is a schematic view of the acquisition and inspection process in the on-line nondestructive X-ray inspection method of the present invention;
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein may be combined with other embodiments.
In order to achieve the above object, an embodiment of the present invention provides an online X-ray nondestructive testing method, which is shown in fig. 1, and is a first flowchart of a preferred embodiment of the online X-ray nondestructive testing method, where the online X-ray nondestructive testing method includes the following steps:
s1: when the piece to be detected triggers infrared light beams emitted downwards by the diffuse reflection light barrier, structural characteristics of the piece to be detected are collected through an X-ray light source and input into an image detection system, and an image to be detected containing the structural characteristics corresponding to the piece to be detected is obtained, wherein the structural characteristics comprise an appearance profile, an inner hole profile, a size, a sinking platform, a folding edge, a height and surface textures.
In this embodiment, the member to be detected may be a circular, rectangular or anisotropic metal casting, a sheet metal part or a plate of a plastic product, the X-ray source is a plate which can penetrate through the material by using X-rays (also gamma rays or other high-energy rays), and due to different absorption and scattering effects of the material on the X-rays, the film is not sensitive to light differently, so that images with different blackness are formed on the negative film, which can be used for judging material defects, and of course, the X-rays can be replaced by gamma rays or other high-energy rays; the diffuse reflection light barriers are infrared beams which are arranged on two sides of the X-ray light source and emit downwards, when a piece to be detected is in contact with the infrared beams, the diffuse reflection light barriers send signals for the piece to be detected to the X-ray light source, the X-ray light source starts to collect structural characteristics of the piece to be detected and input the structural characteristics into the image detection system, and an image to be detected corresponding to the piece to be detected is obtained, wherein the structural characteristics comprise an appearance profile, an inner hole profile, a size, a sinking platform, a folding edge, a height, surface textures and the like.
Further, when the acquisition area of the piece to be detected exceeds the area irradiated downwards by the X-ray light source, the moving distance is automatically calculated according to the length of the detection piece by utilizing a segmented image acquisition mode, and after the detection piece moves to a proper position, each area contained in the piece to be detected is acquired by the X-ray light source and is respectively input into an image detection system for detection.
It should be noted that the collection area of the to-be-detected piece exceeds the area of downward irradiation of the X-ray light source, which means that the length or width of the to-be-detected piece exceeds the diameter of the area of downward irradiation of the X-ray light source, the to-be-detected piece may be a short to-be-detected piece or a long to-be-detected piece, and for the long to-be-detected piece, the to-be-detected piece may be divided into a plurality of detection areas.
Wherein the image detection system performs detection including:
after the X-ray light source collects a first region reg1 contained in the piece to be detected;
performing image model matching on a first to-be-detected image corresponding to the first region reg1, performing interference removal on structural features in the to-be-detected image, calculating a region brightness value and a region gray value of an identification region, and judging whether a current processing region of the to-be-detected image is qualified, and simultaneously performing the following judgment operations:
operation 1: if the detection piece is too long, before the whole detection piece is collected, automatically calculating the moving distance according to the length of the detection piece, and collecting a second region reg2 contained in the detection piece through the X-ray light source after the detection piece moves to a proper position;
operation 2: if the acquisition area of the detection piece is within the area irradiated downwards by the X-ray light source, starting the conveyor belt to wait for the next detection piece until the acquisition of the next detection piece is completed, and obtaining an area reg2 of a second detection piece;
and starting the acquisition process of the next area or the next detection piece according to the judgment of the operation 1 and the operation 2 while calculating the model matching and the interference removal of the second region to be identified reg2 and judging whether the position is qualified.
In this embodiment, as shown in fig. 4, a schematic processing diagram of acquisition and detection in the online X-ray nondestructive inspection method of the present invention is shown. The method has the advantages that the asynchronous processing mode is adopted for simultaneously detecting a plurality of areas, specifically, in the moving and structural feature acquisition process of the piece to be detected, the image to be detected is acquired in the previous step of synchronous processing, and the total time of the piece to be detected can be reduced. For example, assuming that T1 is a scanning time, T2 is a detection time, the synchronous processing mode is a mode in which the total time required for acquiring an image of each object to be detected is T1+ T2, and the asynchronous processing mode is a mode in which acquisition and processing are separated, and after the image of an object to be detected (for example, a first region to be detected) is acquired, an image acquisition operation of a next object to be detected (for example, a second region to be detected) can be performed without waiting for a result, so that it can be known that the total time required for acquiring and detecting an image of an object to be detected in the asynchronous processing mode is T1+ T2.
S2: and inputting the obtained image to be detected containing the structural features into a pre-trained image model for matching, and if the image matching value corresponding to the image to be detected obtained through matching is larger than an image matching threshold value, the matching is passed.
Further, the S2 includes:
matching detection can be carried out on the detection image within a set angle range according to the image model;
according to the information of the position, the angle, the distortion and the deformation after the image model matching detection, the image model is transformed, so that the image model is matched to the corresponding position of the image to be detected;
carrying out operation correction of removing, filling, offsetting, zooming or screening on the image characteristics of the image to be detected according to the image model;
correcting the right angle, the arc and the inner hole of the image to be detected according to the image model; and
and performing regional correction on the image to be detected according to the image model.
Further, the training step of the image model comprises:
a1: acquiring a plurality of pieces to be detected, photographing, performing gray level processing on the obtained pictures of the pieces to be detected, and generating images to be detected corresponding to the pieces to be detected;
a2: after the image to be detected is subjected to characteristic marking, an image detection area and an image characteristic marking area corresponding to the marked image to be detected are obtained; and
a3: and training the marked image features to generate single-layer or multi-layer feature information to obtain the image model.
S3: and removing interference of the matched structural features in the image to be detected to generate a region to be identified contained in the image to be detected.
For example, in an alternative embodiment, the image to be detected obtained by the rectangular sheet metal part to be detected includes the outline, the size, the inner hole, the folding edge position, the surface texture, the convex hull, the sinking platform and the like of the image, and may include the image with the positions of flaws, strains, fractures and the like, wherein the image features include the outline, the surface texture, the size, the hole, the folding edge, the convex hull and the sinking platform on the part to be detected, and after the image features are removed, the area to be identified remains.
S4: and calculating local dynamic threshold value comparison and regional gray value comparison of the to-be-identified region through image processing, and judging that the to-be-detected part is unqualified when the local dynamic threshold value comparison is greater than a first preset ratio and/or the regional gray value comparison is greater than a second preset ratio, which indicates that the to-be-identified region is a flaw, strain or fracture region.
The region to be identified is calculated through image processing, wherein the region to be identified comprises regional gray scale enhancement, gray scale value comparison and local dynamic threshold value comparison, and the formula is as follows:
and (3) regional gray level enhancement: dst round ((src 0-src 1) × coef) + src0
Where src0 represents input image 0, src1 represents input image 1, dst represents the processing result, coef represents the enhancement coefficient, and round represents rounding.
Local dynamic threshold comparison: judging whether io > is it + shift, judging whether io > is it-shift in a dark area, judging whether it-shift is io + it + shift in a gray value stable area, and judging whether io > is it-shift or whether io > is it + shift in an area with larger change;
wherein io represents an original image, it represents a threshold image, and shift represents a threshold;
gray value comparison: judging dst as src > th in bright area, and judging dst as src < th in dark area;
where src denotes an original image, th denotes a threshold value, and dst denotes a processing result.
Further, referring to fig. 2, a second flow chart of the online X-ray nondestructive inspection method according to the preferred embodiment of the present invention is shown, before the step S1, the method further includes:
s0: the method comprises the following steps that a piece to be detected is placed on a production line, a conveyor belt drives the piece to be detected to enter a detection channel, and a diffuse reflection light barrier, an X-ray light source and an image processing system are arranged above the detection channel.
And, after the step of S4, further comprising:
s5: and marking unqualified positions of the identification area where the to-be-detected piece is located, producing unqualified information, and removing a production line when the to-be-detected piece enters the next station.
In addition, the present invention further provides an online X-ray nondestructive inspection system, which is shown in fig. 3 and is a schematic diagram of program modules of the online X-ray nondestructive inspection system according to the present invention, and the online X-ray nondestructive inspection method according to any one of the above is applied to the online X-ray nondestructive inspection system, and the system includes:
the conveying module 10 is used for placing the piece to be detected on a production line, the conveying belt drives the piece to be detected to enter a detection channel, and a diffuse reflection light barrier, an X-ray light source and an image processing system are installed above the detection channel.
The acquisition module 20 is configured to acquire a structural characteristic of the to-be-detected piece by using an X-ray light source and input the structural characteristic into an image detection system when the to-be-detected piece triggers an infrared beam emitted downward by a diffuse reflection barrier, so as to obtain a to-be-detected image including the structural characteristic corresponding to the to-be-detected piece, where the structural characteristic includes an outline, an inner hole outline, a size, a sinking platform, a folded edge, a height, and a surface texture;
the matching module 30 is configured to input the obtained image to be detected including the structural features into a pre-trained image model for matching, and if an image matching value corresponding to the image to be detected obtained through matching is greater than an image matching threshold, the matching is passed;
the processing module 40 is configured to perform interference removal on the structure features in the image to be detected that pass the matching, and generate an area to be identified included in the image to be detected;
the calculation module 50 is configured to calculate a local dynamic threshold comparison and a regional gray value comparison of the to-be-identified region through image processing, and when the local dynamic threshold comparison is greater than a first preset ratio and/or the regional gray value comparison is greater than a second preset ratio, it indicates that the to-be-identified region is a flaw, strain or fracture region, and it is determined that the to-be-detected object is not qualified;
and the marking module 60 is used for marking unqualified positions of the identification area where the piece to be detected is located, producing unqualified information, and removing a production line when the identification area enters the next station.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides an online X-ray nondestructive inspection detection method and a system thereof.A structural characteristic of an article to be detected is collected by an X-ray light source and input into an image detection system when the article to be detected triggers an infrared light beam emitted downwards by a diffuse light barrier, an image to be detected containing the structural characteristic corresponding to the article to be detected is obtained and input into a pre-trained image model for matching, if an image matching value corresponding to the image to be detected obtained by matching is greater than an image matching threshold value, the matching is passed and the interference of the structural characteristic is removed, and an area to be identified contained in the image to be detected is generated; and calculating local dynamic threshold value comparison and regional gray value comparison of the to-be-identified region through image processing, and judging that the to-be-detected part is unqualified when the local dynamic threshold value comparison is greater than a first preset ratio and/or the regional gray value comparison is greater than a second preset ratio, which indicates that the to-be-identified region is a flaw, strain or fracture region. The invention realizes the high-definition online detection of the positions of flaws, strain, fracture and the like of the piece to be detected in a segmented asynchronous manner by performing model matching, interference removal and calculation on the brightness and the gray level of the identification area on the image to be detected, so that the labor input is reduced, the total detection time is shortened, and the production quality and the production efficiency are improved.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The technical principle of the present invention has been described above with reference to specific embodiments, which are merely preferred embodiments of the present invention. The protection scope of the present invention is not limited to the above embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. Those skilled in the art will conceive of other embodiments of this invention that fall within the scope of this invention without the exercise of inventive faculty.
Claims (10)
1. An online X-ray nondestructive inspection detection method is characterized by comprising the following steps:
the collection step comprises: when a piece to be detected triggers an infrared beam emitted downwards by a diffuse reflection optical barrier, collecting structural characteristics of the piece to be detected through an X-ray light source and inputting the structural characteristics into an image detection system to obtain a to-be-detected image containing structural characteristics corresponding to the piece to be detected, wherein the structural characteristics comprise an appearance profile, an inner hole profile, a size, a sinking platform, a folding edge, a height and surface texture;
matching: inputting the obtained image to be detected containing the structural features into a pre-trained image model for matching, and if the image matching value corresponding to the image to be detected obtained through matching is larger than an image matching threshold value, the matching is passed;
the processing steps are as follows: removing interference on the matched structural features in the image to be detected to generate a region to be identified contained in the image to be detected;
a calculation step: and calculating local dynamic threshold value comparison and area gray value comparison of the area to be identified through image processing, and judging that the piece to be detected is unqualified when the local dynamic threshold value comparison is larger than a first preset ratio and/or the area gray value comparison is larger than a second preset ratio, which indicates that the area to be identified is a flaw, strain or fracture area.
2. The online X-ray nondestructive inspection method according to claim 1, further comprising, before the acquiring step:
a transmission step: the method comprises the following steps that a piece to be detected is placed on a production line, a conveyor belt drives the piece to be detected to enter a detection channel, and a diffuse reflection light barrier, an X-ray light source and an image processing system are arranged above the detection channel.
3. The online X-ray nondestructive inspection method according to claim 1, further comprising, after the calculating step:
a marking step: and marking unqualified positions of the identification area where the to-be-detected piece is located, producing unqualified information, and removing a production line when the to-be-detected piece enters the next station.
4. The online X-ray nondestructive inspection method according to claim 1, wherein the calculation of the area to be identified by image processing includes area grayscale enhancement, grayscale value contrast, and local dynamic threshold contrast, wherein the formula is as follows:
and (3) regional gray level enhancement: dst round ((src 0-src 1): coef) + src0
Where src0 represents input image 0, src1 represents input image 1, dst represents the processing result, coef represents the enhancement coefficient, and round represents rounding.
Local dynamic threshold comparison: judging whether io > is it + shift, judging whether io > is it-shift in a dark area, judging whether it-shift is io + it + shift in a gray value stable area, and judging whether io > is it-shift or whether io > is it + shift in an area with larger change;
wherein io represents an original image, it represents a threshold image, and shift represents a threshold;
gray value comparison: judging dst as src < th in bright area, judging dst as src < th in dark area;
where src denotes an original image, th denotes a threshold value, and dst denotes a processing result.
5. The online X-ray nondestructive inspection method according to claim 1, wherein the matching step includes:
matching detection can be carried out on the detection image within a set angle range according to the image model;
according to the information of the position, the angle, the distortion and the deformation after the image model matching detection, the image model is subjected to transformation processing, so that the image model is matched to the corresponding position of the image to be detected;
carrying out operation correction of removing, filling, offsetting, zooming or screening on the image characteristics of the image to be detected according to the image model;
correcting the right angle, the arc and the inner hole of the image to be detected according to the image model; and
and performing regional correction on the image to be detected according to the image model.
6. The online X-ray nondestructive inspection method according to claim 1, wherein the training step of the image model includes:
acquiring a plurality of pieces to be detected, photographing, performing gray level processing on the obtained pictures of the pieces to be detected, and generating images to be detected corresponding to the pieces to be detected;
after the image to be detected is subjected to characteristic marking, an image detection area and an image characteristic marking area corresponding to the marked image to be detected are obtained; and
and training the marked image features to generate single-layer or multi-layer feature information to obtain the image model.
7. The on-line X-ray nondestructive inspection method of claim 1, wherein when the acquisition area of the piece to be inspected exceeds the area irradiated downwards by the X-ray light source, the moving distance is automatically calculated according to the length of the piece to be inspected by means of sectional image acquisition, and after the piece to be inspected moves to a proper position, each area included in the piece to be inspected is acquired by the X-ray light source and is respectively input into an image inspection system for inspection.
8. The online X-ray nondestructive inspection method according to claim 7, wherein the image inspection system performs inspection including:
after the X-ray light source collects a first region reg1 contained in the piece to be detected;
performing image model matching on a first to-be-detected image corresponding to the first region reg1, performing interference removal on structural features in the to-be-detected image, calculating a region brightness value and a region gray value of an identification region, and judging whether a current processing region of the to-be-detected image is qualified, and simultaneously performing the following judgment operations:
operation 1: if the detection piece is too long, automatically calculating the moving distance according to the length of the detection piece before the whole detection piece is collected, and collecting a second region reg2 contained in the detection piece through the X-ray light source after the detection piece moves to a proper position;
and operation 2: if the acquisition area of the detection piece is within the area irradiated downwards by the X-ray light source, starting the conveyor belt to wait for the next detection piece until the acquisition of the next detection piece is completed, and obtaining an area reg2 of a second detection piece;
and starting the acquisition process of the next area or the next detection piece according to the judgment of the operation 1 and the operation 2 while calculating the model matching and the interference removal of the second region to be identified reg2 and judging whether the position is qualified.
9. An online X-ray nondestructive inspection system to which the online X-ray nondestructive inspection method according to any one of claims 1 to 8 is applied, the system comprising:
the acquisition module is used for acquiring the structural characteristics of the piece to be detected by an X-ray light source and inputting the structural characteristics into an image detection system when the piece to be detected triggers an infrared beam emitted downwards by a diffuse reflection light barrier, so as to obtain a to-be-detected image which corresponds to the piece to be detected and contains the structural characteristics, wherein the structural characteristics comprise an appearance profile, an inner hole profile, a size, a sinking platform, a folding edge, a height and surface textures;
the matching module is used for inputting the obtained image to be detected containing the structural features into a pre-trained image model for matching, and if the image matching value corresponding to the image to be detected obtained through matching is larger than the image matching threshold value, the matching is passed;
the processing module is used for removing interference of the structural features in the image to be detected which passes the matching, and generating a region to be identified contained in the image to be detected;
the calculation module is used for calculating local dynamic threshold comparison and area gray value comparison of the area to be identified through image processing, and when the local dynamic threshold comparison is larger than a first preset ratio and/or the area gray value comparison is larger than a second preset ratio, the area to be identified is a flaw, strain or fracture area, and the workpiece to be detected is judged to be unqualified;
and the marking module is used for marking unqualified positions of the identification area where the piece to be detected which is judged to be unqualified is located, producing unqualified information, and removing a production line when the next station is entered.
10. The online nondestructive X-ray inspection system of claim 9 further comprising, prior to the acquisition module:
the conveying module is used for placing the piece to be detected on a production line, the conveying belt drives the piece to be detected to enter a detection channel, and a diffuse reflection light barrier, an X-ray light source and an image processing system are installed above the detection channel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210642087.7A CN115047015A (en) | 2022-06-07 | 2022-06-07 | Online X-ray nondestructive flaw detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210642087.7A CN115047015A (en) | 2022-06-07 | 2022-06-07 | Online X-ray nondestructive flaw detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115047015A true CN115047015A (en) | 2022-09-13 |
Family
ID=83160503
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210642087.7A Pending CN115047015A (en) | 2022-06-07 | 2022-06-07 | Online X-ray nondestructive flaw detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115047015A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116852374A (en) * | 2023-08-08 | 2023-10-10 | 荆州双金再生资源有限公司 | Intelligent robot control system based on machine vision |
| WO2024108882A1 (en) * | 2022-11-24 | 2024-05-30 | 江苏时代新能源科技有限公司 | Detection apparatus, defect detection method and apparatus, computer device, and storage medium |
-
2022
- 2022-06-07 CN CN202210642087.7A patent/CN115047015A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024108882A1 (en) * | 2022-11-24 | 2024-05-30 | 江苏时代新能源科技有限公司 | Detection apparatus, defect detection method and apparatus, computer device, and storage medium |
| CN116852374A (en) * | 2023-08-08 | 2023-10-10 | 荆州双金再生资源有限公司 | Intelligent robot control system based on machine vision |
| CN116852374B (en) * | 2023-08-08 | 2024-04-26 | 深圳创劲鑫科技有限公司 | Intelligent robot control system based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115047015A (en) | Online X-ray nondestructive flaw detection method and system | |
| CN114943739B (en) | Aluminum pipe quality detection method | |
| CN109886298A (en) | A kind of detection method for quality of welding line based on convolutional neural networks | |
| CN113325001A (en) | Automatic distinguishing and detecting equipment and method for surface appearance flaws of copper foil | |
| CN112884743B (en) | Detection method and device, detection equipment and storage medium | |
| CN107561091A (en) | A kind of detecting system and detection method of oblique fire formula solid wood board face crack | |
| US20220076021A1 (en) | System and method for automatic visual inspection with deep learning | |
| CN112730454B (en) | Intelligent damage detection method for composite material based on fusion of optical, infrared thermal wave and ultrasonic wave | |
| CN105510364A (en) | Nondestructive testing system for industrial part flaws based on X rays and detection method thereof | |
| CN115601359A (en) | Welding seam detection method and device | |
| CN116105604B (en) | Steel pipe quality detection system and detection method | |
| CN110728269B (en) | High-speed rail contact net support pole number plate identification method based on C2 detection data | |
| CN113781458A (en) | Artificial intelligence based identification method | |
| CN113916127A (en) | Visual inspection system and method for appearance of valve guide pipe finished product | |
| CN117788400A (en) | Binocular vision-based photovoltaic module defect detection method and system | |
| CN117871671A (en) | Adhesive layer ultrasonic defect detection method based on deep learning | |
| CN115266774B (en) | Artificial intelligence-based weld joint ray detection and evaluation method | |
| CN112798608B (en) | Optical detection device and optical detection method for side wall of inner cavity of mobile phone camera support | |
| CN115420763A (en) | Method for establishing database for detecting foreign matters in tank body | |
| US8306311B2 (en) | Method and system for automated ball-grid array void quantification | |
| CN115018829A (en) | Glass flaw positioning method and device | |
| CN114170318A (en) | Image processing method, apparatus, system, medium, and electronic device | |
| CN112264731A (en) | Control method and device for improving welding quality | |
| CN112926439B (en) | Detection method and device, detection equipment and storage medium | |
| KR102421050B1 (en) | A Method of Radiographic Film Reading Using Artificial Intelligence |
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 |