CN119246570A - Titanium alloy bar quality detection method and system - Google Patents
Titanium alloy bar quality detection method and system Download PDFInfo
- Publication number
- CN119246570A CN119246570A CN202411775524.8A CN202411775524A CN119246570A CN 119246570 A CN119246570 A CN 119246570A CN 202411775524 A CN202411775524 A CN 202411775524A CN 119246570 A CN119246570 A CN 119246570A
- Authority
- CN
- China
- Prior art keywords
- gray level
- level image
- image
- quality
- bar
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30136—Metal
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The invention relates to the technical field of data processing, and particularly discloses a quality detection method and system for a titanium alloy bar, which can improve the efficiency of detecting defects of an internal structure of the titanium alloy bar and improve the accuracy of detecting the quality of the titanium alloy bar. The method comprises the steps of firstly, collecting transverse X-ray images and longitudinal X-ray images of a bar according to a projection strategy through an X-ray detection device, respectively extracting first gray level images of the transverse X-ray images and second gray level images of the longitudinal X-ray images, then, carrying out target image position matching on the first gray level images and the second gray level images to obtain target image position deviation degrees containing abnormal information, then, adjusting the projection strategy according to the target image position deviation degrees to obtain adjusted first gray level images and second gray level images, and finally, carrying out abnormal information identification analysis on the adjusted first gray level images and second gray level images to obtain bar quality detection results.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a titanium alloy bar quality detection method and system.
Background
The titanium alloy bar is used as an important metal material and has wide application in the fields of aerospace, ocean engineering, chemical industry and the like. With the development of these fields, these conventional quality detection methods are not only inefficient but also prone to erroneous judgment by relying only on manual visual inspection and sampling detection.
Existing nondestructive detection technologies, such as ultrasonic detection, X-ray detection, eddy current detection and the like, can detect internal defects, but have limited detection capability on micro defects, and for titanium alloy bars with higher production precision requirements, the micro defect problem easily generates larger potential safety hazards for normal input and use of subsequent titanium alloy bars.
The common X-ray intensity change after passing through the object is detected by the X-rays to form an image, so that the internal structure and defects of the titanium alloy bar are displayed, the detection speed of the X-ray detection is low only in one direction, the time cost is increased, and the sensitivity to finding the tiny defects in the titanium alloy bar is lacking in a direct X-ray detection mode, so that the quality of the obtained titanium alloy bar is unqualified.
Disclosure of Invention
The invention aims to provide a titanium alloy bar quality detection method and system, which solve the following technical problems:
How to improve the efficiency of detecting the defects of the internal structure of the titanium alloy bar and the accuracy of detecting the quality of the titanium alloy bar.
The aim of the invention can be achieved by the following technical scheme:
a quality detection method of a titanium alloy bar comprises the following steps:
S1, acquiring a transverse X-ray image and a longitudinal X-ray image of a bar by an X-ray detection device according to a projection strategy, and respectively extracting a first gray level image of the transverse X-ray image and a second gray level image of the longitudinal X-ray image;
S2, performing target image position matching on the first gray level image and the second gray level image to obtain the target image position deviation degree containing abnormal information;
S3, adjusting a projection strategy according to the position deviation degree of the target image to obtain an adjusted first gray level image and an adjusted second gray level image;
s4, carrying out abnormal information identification analysis on the adjusted first gray level image and second gray level image, and obtaining a bar quality detection result.
Preferably, the projection strategy comprises:
Setting an initial projection focus radius, an initial exposure frequency and an initial exposure interval duration;
and adjusting the initial projection focus radius, the initial exposure frequency and the initial exposure interval duration according to the target image position deviation degree.
Preferably, S2 includes:
Acquiring a coincidence line of the first gray level image and the second gray level image;
calculating a pixel average value of the overlapping line and comparing the pixel average value of the overlapping line with standard pixel thresholds of the first gray scale image and the second gray scale image:
if the pixel average value of the overlapping line belongs to the standard pixel threshold value, judging that abnormal information does not exist;
If the pixel average value of the overlapping line does not belong to the standard pixel threshold value, judging that abnormal information exists, identifying a first gray level image and a second gray level image where the overlapping line is located as target images, and further judging that:
and if the pixel average value of the overlapping line is larger than the standard pixel threshold value, judging that the position deviation degree of the target image is larger.
Preferably, the method for adjusting the projection strategy in S3 includes:
if the position deviation degree of the target image is larger, the initial projection focus radius is reduced, the initial exposure frequency is increased, and the initial exposure interval duration is delayed:
reduced projected focal radius ;
Increased exposure frequency;
Time length of delayed exposure interval;
Wherein, For the initial projection focus radius,For the initial exposure frequency,The initial exposure interval duration; as a result of the first correction factor, As a result of the second correction factor being,Is the third correction coefficient; The average value of the pixels for the line of weakness, Is the standard pixel threshold.
Preferably, in S4, the process of performing the anomaly information recognition analysis on the adjusted first gray scale image and the second gray scale image is:
respectively extracting boundary lines and abnormal region contours of the adjusted first gray level image and the second gray level image through a Canny algorithm;
acquiring boundary lines of the first gray level image and the second gray level image and the outline of an abnormal region of the boundary lines to acquire the area of the abnormal region of the first gray level image respectively Area of abnormal region of the second gray level imagePerimeter of abnormal region、By the formulaRespectively calculating and acquiring abnormal region structure values of the first gray level image and the second gray level image、;
By the abnormal region structure value of the first gray scale image having the abnormal region outline in the continuous time periodAbnormal region structure value of the second gray level imageReconstructing a three-dimensional data model of the data set, acquiring a three-dimensional shape of the point cloud of the display abnormal region, and outputting structural characteristics of the abnormal region;
the outlier region structural feature includes outlier region noise parameters Volume parameters of abnormal region。
Preferably, the method of S4 obtaining the bar quality detection result is:
By the formula Calculating to obtain detection coefficient;
Wherein, For the first preset weight coefficient,The second preset weight coefficient is the second preset weight coefficient; standard noise parameters are normal areas; Presetting a deviation value for regional noise; Is a normal region standard volume parameter; Is a preset function.
Preferably, the method further comprises:
Will detect the coefficient And a preset detection coefficient threshold intervalAnd (3) performing comparison:
If it is ∈Judging that the defect exists, the defect area is small, and the bar quality is qualified;
If it is >Judging that the defect exists, the defect area is large, and the quality of the bar is unqualified;
If it is <Judging that the defect does not exist and the bar quality is excellent.
A titanium alloy bar quality detection system for implementing a titanium alloy bar quality detection method, comprising:
The image acquisition module is used for acquiring transverse X-ray images and longitudinal X-ray images of the bar according to a projection strategy through the X-ray detection equipment and respectively extracting a first gray level image of the transverse X-ray images and a second gray level image of the longitudinal X-ray images;
The image processing module is used for carrying out target image position matching on the first gray level image and the second gray level image to obtain the target image position deviation degree containing abnormal information;
The projection strategy is adjusted according to the position deviation degree of the target image, and an adjusted first gray level image and second gray level image are obtained;
The data analysis module is used for identifying and analyzing the abnormal information of the adjusted first gray level image and the second gray level image and obtaining a bar quality detection result.
The invention has the beneficial effects that:
(1) According to the invention, according to a preset projection strategy, the projection strategy reflects the process of projecting the inside of the bar at different angles, the internal image acquisition is carried out in the transverse direction and the longitudinal direction of the X-ray irradiation respectively, the first gray level image is extracted from the acquired transverse X-ray image, the second gray level image is extracted from the longitudinal X-ray image, the internal structures of the bar at different angles are respectively displayed by the transverse image and the longitudinal image, and the appearance of tiny problems in the bar can be found according to the actual detection standard.
(2) The invention adjusts the projection strategy of the X-ray detection equipment according to the position deviation degree of the target image, reduces and eliminates the position deviation problem by designing the adjustment process of the projection strategy, enables the subsequently acquired image to more accurately reflect the internal structure of the bar, and realizes the quality assessment of the bar by acquiring the detection coefficient result through carrying out the abnormal information identification analysis on the adjusted first gray level image and the second gray level image and according to the result of calculating the abnormal information identification, and identifies the information such as the position, the size, the shape and the like possibly including an abnormal region according to the detection result, thereby carrying out accurate assessment on the whole quality of the bar according to qualitative and quantitative analysis.
Of course, it is not necessary for any of the products of the invention to be practiced with all of the advantages described above.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a step diagram of a method for detecting the quality of a titanium alloy bar;
FIG. 2 is a block diagram of a titanium alloy bar quality inspection system according to the present invention.
Detailed Description
The following description of the embodiments of the present invention 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 invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the invention provides a method for detecting quality of a titanium alloy bar, which comprises the following steps:
S1, acquiring a transverse X-ray image and a longitudinal X-ray image of a bar by an X-ray detection device according to a projection strategy, and respectively extracting a first gray level image of the transverse X-ray image and a second gray level image of the longitudinal X-ray image;
S2, performing target image position matching on the first gray level image and the second gray level image to obtain the target image position deviation degree containing abnormal information;
S3, adjusting a projection strategy according to the position deviation degree of the target image to obtain an adjusted first gray level image and an adjusted second gray level image;
s4, carrying out abnormal information identification analysis on the adjusted first gray level image and second gray level image, and obtaining a bar quality detection result.
According to the technical scheme, the titanium alloy bar quality detection method is characterized in that firstly, an X-ray detection device is used, according to a preset projection strategy, the projection strategy reflects the process of projecting the inside of the bar at different angles, the projection angle and the projection direction are set in advance according to requirements, the bar is subjected to X-ray irradiation, internal image acquisition is respectively carried out from the transverse direction and the longitudinal direction of the X-ray irradiation, a first gray level image is extracted from the acquired transverse X-ray image, and a second gray level image is extracted from the longitudinal X-ray image, wherein the gray level image is a black-and-white image, the brightness value of each pixel represents the X-ray absorptivity of the point, so that the density distribution of the inside of the bar is reflected, and the transverse image and the longitudinal image respectively display the internal structure of the bar at different angles, so that the appearance of tiny problems inside the bar can be found according to practical detection standards.
Then, the first gray level image and the second gray level image are subjected to matching analysis of the position relationship in a target image position matching mode, the characteristic information of the images is automatically learned by a convolutional neural network to determine the positions of the target images in two directions, the positions of the abnormal areas which occur simultaneously in the actual bar are generally consistent in two directions for the subsequent abnormal detection requirement, the position deviation degree of the target images is obtained through calculation and judgment according to the images containing abnormal information, and particularly, the severity degree of the abnormality can be estimated by calculating the position deviation degree of the target images containing the abnormal information in the first gray level image and the second gray level image through a matching algorithm. This can be typically achieved by calculating the structure of the abnormal region in the target image. For example, the position difference of the wire frame of the target image in the two images can be calculated, and the analysis result of the position deviation degree can be used as the reference basis for the subsequent adjustment of the projection strategy by calculating the position deviation degree of the target image in the two directions.
And then, adjusting the projection strategy of the X-ray detection equipment according to the position deviation degree of the target image, reducing and eliminating the position deviation problem by designing the adjustment process of the projection strategy, and enabling the subsequently acquired image to more accurately reflect the internal structure of the bar, wherein the specific mode of the information acquired by the adjusted projection strategy is to acquire the transverse X-ray image and the longitudinal X-ray image of the bar again and extract new first gray level image and second gray level image.
Finally, the method comprises the steps of carrying out abnormal information identification analysis on the adjusted first gray level image and the second gray level image, detecting and locating abnormal areas such as tiny cracks, inclusions, the occurrence degree of air holes and the like by using an image processing algorithm such as a convolutional neural network, and according to the result of calculating the abnormal information identification, realizing the quality assessment of the bar by obtaining a detection coefficient result, identifying information including the position, the size, the shape and the like of the abnormal areas possibly according to the detection result, and accurately assessing the overall quality of the bar according to qualitative and quantitative analysis results.
As one embodiment of the present invention, the projection strategy includes:
Setting an initial projection focus radius, an initial exposure frequency and an initial exposure interval duration;
and adjusting the initial projection focus radius, the initial exposure frequency and the initial exposure interval duration according to the target image position deviation degree.
In the technical scheme, the projection strategy in the embodiment ensures a specific projection mode and setting related parameters for projecting the interior of the bar, mainly comprises the steps of setting the initial projection focal radius according to the imaging requirement and the equipment performance of the bar, selecting a proper focal radius, and adjusting the exposure time including the bar exposure frequency and the bar exposure interval duration according to the material, thickness, required image quality, power of an X-ray source and other factors of the detected bar, so that the interior condition of the bar can be clearly detected and displayed according to the conventional projection efficiency.
As one embodiment of the present invention, S2 includes:
Acquiring a coincidence line of the first gray level image and the second gray level image;
calculating a pixel average value of the overlapping line and comparing the pixel average value of the overlapping line with standard pixel thresholds of the first gray scale image and the second gray scale image:
if the pixel average value of the overlapping line belongs to the standard pixel threshold value, judging that abnormal information does not exist;
If the pixel average value of the overlapping line does not belong to the standard pixel threshold value, judging that abnormal information exists, identifying a first gray level image and a second gray level image where the overlapping line is located as target images, and further judging that:
and if the pixel average value of the overlapping line is larger than the standard pixel threshold value, judging that the position deviation degree of the target image is larger.
In the above technical solution, the obtaining manner of the position deviation degree in step S2 in the present embodiment is that the feature points can be obtained from the two gray-scale images according to the feature point detection algorithm, such as SIFT, and the feature points have local uniqueness, and can represent the key structure in the images, and by matching the feature points, the geometric transformation required for transforming the first image into the second image, such as affine transformation or perspective transformation, can be estimated, the estimated transformation is applied, the first image is registered into the coordinate system of the second image, and in the registered image, the overlapping line can be extracted by using the edge detection algorithm. Therefore, according to the characteristic change acquisition mode of the first gray level image and the second gray level image, the fact that an intersecting 'overlapping line' exists between the actual plane images is known, then the pixel average value of the overlapping line is calculated, the pixel average value of the overlapping line is compared with the standard pixel threshold value of the first gray level image and the standard pixel threshold value of the second gray level image, whether the overlapping line meets the pixel standard requirement of detection setting is judged, further, the image setting that the target image, namely the first gray level image and the second gray level image, has the 'overlapping line' is judged, and further, the position deviation degree of the target image is judged.
As an embodiment of the present invention, the method for adjusting the projection strategy in S3 includes:
if the position deviation degree of the target image is larger, the initial projection focus radius is reduced, the initial exposure frequency is increased, and the initial exposure interval duration is delayed:
reduced projected focal radius ;
Increased exposure frequency;
Time length of delayed exposure interval;
Wherein, For the initial projection focus radius,For the initial exposure frequency,The initial exposure interval duration; as a result of the first correction factor, As a result of the second correction factor being,Is the third correction coefficient; The average value of the pixels for the line of weakness, Is the standard pixel threshold.
In the above technical solution, in this embodiment, the degree of deviation of the position of the target image is adjusted to be larger, and the definition of the bar material projected at present is optimized by reducing the focal radius of the initial projection, increasing the exposure frequency and the exposure interval duration.
Wherein the correction coefficient、、And the projection strategy is executed through the adjusted projection focus radius, exposure frequency and exposure interval duration, so that the effect of improving the analysis and judgment accuracy and adaptively reducing the adjustment calculation force requirement of the early X-ray projection detection can be realized.
As one embodiment of the present invention, the process of performing the anomaly information identification analysis on the adjusted first gray scale image and second gray scale image in S4 includes:
respectively extracting boundary lines and abnormal region contours of the adjusted first gray level image and the second gray level image through a Canny algorithm;
acquiring boundary lines of the first gray level image and the second gray level image and the outline of an abnormal region of the boundary lines to acquire the area of the abnormal region of the first gray level image respectively Area of abnormal region of the second gray level imagePerimeter of abnormal region、By the formulaRespectively calculating and acquiring abnormal region structure values of the first gray level image and the second gray level image、;
By the abnormal region structure value of the first gray scale image having the abnormal region outline in the continuous time periodAbnormal region structure value of the second gray level imageReconstructing a three-dimensional data model of the data set of the display device, acquiring a three-dimensional shape of a point cloud displaying an abnormal region, and outputting structural characteristics of the abnormal region, wherein the structural characteristics of the abnormal region comprise noise parameters of the abnormal regionVolume parameters of abnormal region。
According to the technical scheme, boundary lines and abnormal region outlines of a first gray level image and a second gray level image which contain abnormal information are respectively extracted through a Canny algorithm, wherein the pixels in the images are compared with one or more thresholds according to gray values of the pixels in the images through threshold segmentation, the images are divided into different regions, the abnormal region outlines and the boundary lines obtained through extraction of a region of interest according to a threshold segmentation result are substituted into a convolutional neural network model for analysis, the boundary lines and the abnormal region outlines of the first gray level image and the second gray level image are collected and used as input, the abnormal region area of the first gray level image, the abnormal region area of the second gray level image and the abnormal region perimeter of the second gray level image are output, and the structural feature acquisition of the abnormal region is achieved through a structural calculation formula.
As one embodiment of the present invention, the manner of S4 obtaining the bar quality detection result is:
By the formula Calculating to obtain detection coefficient;
Wherein, For the first preset weight coefficient,The second preset weight coefficient is the second preset weight coefficient; standard noise parameters are normal areas; Presetting a deviation value for regional noise; Is a normal region standard volume parameter; Is a preset function.
In the above technical solution, in this embodiment, the results of the bar quality detection are calculated and analyzed, and according to the formulaCalculating to obtain detection coefficientJudging whether the detection condition of the quality of the current bar meets the requirement or not by acquiring the detection coefficient, wherein the main factors of the quality of the bar are the size of the abnormal structural characteristics in the bar, the noise ambiguity of the abnormal region and the like, and the embodiment acquires the noise parameters of the abnormal region through the recognition of the abnormal informationVolume parameters of abnormal regionFurther analysis is carried out, and the influence of the abnormal condition on the quality of the carbon rod is reflected.
Wherein, 、、、Are all obtained after fitting according to empirical test data, and、All greater than 0 and not described in detail herein; is preset in advance according to a history database and is obtained by real-time acquisition and analysis according to an actual training network, which is not described in detail herein, a preset function For a detection function set according to historical data conditions, ensuring a range of detection coefficients within a specific reasonable interval, and presetting the functionThe method is set according to the material history abnormal characteristic influence of the current bar and the standard parameters of an actual problem abnormal characteristic list, such as a data quality analysis function used by a common data quality evaluation model.
As an embodiment of the present invention, further comprising:
Will detect the coefficient And a preset detection coefficient threshold intervalAnd (3) performing comparison:
If it is ∈Judging that the defect exists, the defect area is small, and the bar quality is qualified;
If it is >Judging that the defect exists, the defect area is large, and the quality of the bar is unqualified;
If it is <Judging that the defect does not exist and the bar quality is excellent.
In the above technical solution, in this embodiment, the detection coefficients are compared with each otherJudging that the defect area has larger problem under the condition of exceeding a preset threshold value, wherein the quality detection of the bar does not meet the standard, and the preset detection coefficient threshold value intervalIs obtained by fitting according to empirical data.
Referring to fig. 2, a titanium alloy bar quality detection system is used for implementing a titanium alloy bar quality detection method, and includes:
The image acquisition module is used for acquiring transverse X-ray images and longitudinal X-ray images of the bar according to a projection strategy through the X-ray detection equipment and respectively extracting a first gray level image of the transverse X-ray images and a second gray level image of the longitudinal X-ray images;
The image processing module is used for carrying out target image position matching on the first gray level image and the second gray level image to obtain the target image position deviation degree containing abnormal information;
The projection strategy is adjusted according to the position deviation degree of the target image, and an adjusted first gray level image and second gray level image are obtained;
The data analysis module is used for identifying and analyzing the abnormal information of the adjusted first gray level image and the second gray level image and obtaining a bar quality detection result.
According to the technical scheme, the image acquisition module is utilized to acquire gray images of different angles of the bar detected by the X-rays, the matching of the target images is carried out according to the gray images of different angles, the judgment of the deviation degree is carried out according to the position of the target image containing abnormal information, the adjustment of the projection strategy is carried out according to the deviation degree, the definition of the internal structure of the bar is accurately achieved, finally, the data analysis module is utilized to realize the identification and analysis of the abnormal information data of the adjusted gray images, finally, the bar quality detection result is acquired, and the screening of the qualified condition of the bar is carried out according to the detection result.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, devices, non-volatile computer storage medium embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the section of the method embodiments being relevant.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the attached documents. In some cases, the acts or steps recited in the present application may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing is merely illustrative and explanatory of the principles of this application, as various modifications and additions may be made to the specific embodiments described, or similar arrangements may be substituted by those skilled in the art, without departing from the principles of this application or beyond the scope of this application as defined in the claims.
Claims (8)
1. A method for detecting the quality of a titanium alloy bar, which is characterized by comprising the following steps:
S1, acquiring a transverse X-ray image and a longitudinal X-ray image of a bar by an X-ray detection device according to a projection strategy, and respectively extracting a first gray level image of the transverse X-ray image and a second gray level image of the longitudinal X-ray image;
S2, performing target image position matching on the first gray level image and the second gray level image to obtain the target image position deviation degree containing abnormal information;
S3, adjusting a projection strategy according to the position deviation degree of the target image to obtain an adjusted first gray level image and an adjusted second gray level image;
s4, carrying out abnormal information identification analysis on the adjusted first gray level image and second gray level image, and obtaining a bar quality detection result.
2. The method for detecting the quality of a titanium alloy bar according to claim 1, wherein the projection strategy comprises:
Setting an initial projection focus radius, an initial exposure frequency and an initial exposure interval duration;
and adjusting the initial projection focus radius, the initial exposure frequency and the initial exposure interval duration according to the target image position deviation degree.
3. The method for detecting the quality of a titanium alloy bar according to claim 2, wherein the step S2 includes:
Acquiring a coincidence line of the first gray level image and the second gray level image;
calculating a pixel average value of the overlapping line and comparing the pixel average value of the overlapping line with standard pixel thresholds of the first gray scale image and the second gray scale image:
if the pixel average value of the overlapping line belongs to the standard pixel threshold value, judging that abnormal information does not exist;
If the pixel average value of the overlapping line does not belong to the standard pixel threshold value, judging that abnormal information exists, identifying a first gray level image and a second gray level image where the overlapping line is located as target images, and further judging that:
and if the pixel average value of the overlapping line is larger than the standard pixel threshold value, judging that the position deviation degree of the target image is larger.
4. A method for detecting quality of a titanium alloy bar according to claim 3, wherein the method for adjusting the projection strategy in S3 comprises:
if the position deviation degree of the target image is larger, the initial projection focus radius is reduced, the initial exposure frequency is increased, and the initial exposure interval duration is delayed:
reduced projected focal radius ;
Increased exposure frequency;
Time length of delayed exposure interval;
Wherein, For the initial projection focus radius,For the initial exposure frequency,The initial exposure interval duration; as a result of the first correction factor, As a result of the second correction factor being,Is the third correction coefficient; The average value of the pixels for the line of weakness, Is the standard pixel threshold.
5. The method for detecting the quality of the titanium alloy bar according to claim 1, wherein the process of performing the anomaly information identification analysis on the adjusted first gray level image and second gray level image in S4 is as follows:
respectively extracting boundary lines and abnormal region contours of the adjusted first gray level image and the second gray level image through a Canny algorithm;
acquiring boundary lines of the first gray level image and the second gray level image and the outline of an abnormal region of the boundary lines to acquire the area of the abnormal region of the first gray level image respectively Area of abnormal region of the second gray level imagePerimeter of abnormal region、By the formulaRespectively calculating and acquiring abnormal region structure values of the first gray level image and the second gray level image、;
By the abnormal region structure value of the first gray scale image having the abnormal region outline in the continuous time periodAbnormal region structure value of the second gray level imageReconstructing a three-dimensional data model of the data set, acquiring a three-dimensional shape of the point cloud of the display abnormal region, and outputting structural characteristics of the abnormal region;
The abnormal region structural feature includes an abnormal region noise parameter Volume parameters of abnormal region。
6. The method for detecting the quality of the titanium alloy bar according to claim 5, wherein the method for obtaining the quality detection result of the bar in S4 is as follows:
By the formula Calculating to obtain detection coefficient;
Wherein, For the first preset weight coefficient,The second preset weight coefficient is the second preset weight coefficient; standard noise parameters are normal areas; Presetting a deviation value for regional noise; Is a normal region standard volume parameter; Is a preset function.
7. The method for detecting the quality of a titanium alloy bar according to claim 6, further comprising:
Will detect the coefficient And a preset detection coefficient threshold intervalAnd (3) performing comparison:
If it is ∈Judging that the defect exists, the defect area is small, and the bar quality is qualified;
If it is >Judging that the defect exists, the defect area is large, and the quality of the bar is unqualified;
If it is <Judging that the defect does not exist and the bar quality is excellent.
8. A titanium alloy bar quality inspection system for implementing the titanium alloy bar quality inspection method of any one of claims 1-7, comprising:
The image acquisition module is used for acquiring transverse X-ray images and longitudinal X-ray images of the bar according to a projection strategy through the X-ray detection equipment and respectively extracting a first gray level image of the transverse X-ray images and a second gray level image of the longitudinal X-ray images;
The image processing module is used for carrying out target image position matching on the first gray level image and the second gray level image to obtain the target image position deviation degree containing abnormal information;
The projection strategy is adjusted according to the position deviation degree of the target image, and an adjusted first gray level image and second gray level image are obtained;
The data analysis module is used for identifying and analyzing the abnormal information of the adjusted first gray level image and the second gray level image and obtaining a bar quality detection result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411775524.8A CN119246570B (en) | 2024-12-05 | 2024-12-05 | Titanium alloy bar quality detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411775524.8A CN119246570B (en) | 2024-12-05 | 2024-12-05 | Titanium alloy bar quality detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119246570A true CN119246570A (en) | 2025-01-03 |
| CN119246570B CN119246570B (en) | 2025-04-04 |
Family
ID=94028569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411775524.8A Active CN119246570B (en) | 2024-12-05 | 2024-12-05 | Titanium alloy bar quality detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119246570B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119804327A (en) * | 2025-03-13 | 2025-04-11 | 杭州普络飞新材料科技有限公司 | PCM board quality inspection system |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4125771A (en) * | 1977-11-18 | 1978-11-14 | Net Systems Inc. | Apparatus for determining stress in nickel and titanium alloyed materials |
| JP2005167773A (en) * | 2003-12-04 | 2005-06-23 | Canon Inc | Image processing method and apparatus |
| US20130058556A1 (en) * | 2011-09-02 | 2013-03-07 | Toshiba Medical Systems Corporation | X-ray diagnostic apparatus, x-ray diagnostic method and stent for x-ray diagnosis |
| CN103149222A (en) * | 2013-02-28 | 2013-06-12 | 重庆大学 | Flaw detection device in real-time imaging of ray |
| CN103705258A (en) * | 2013-11-19 | 2014-04-09 | 江苏康众数字医疗设备有限公司 | Automatic exposure control method and automatic exposure control device for imaging device |
| JP2017104329A (en) * | 2015-12-10 | 2017-06-15 | 東芝メディカルシステムズ株式会社 | X-ray diagnostic apparatus and X-ray CT apparatus |
| DE102018105709A1 (en) * | 2017-03-15 | 2018-09-20 | Werth Messtechnik Gmbh | Method for computer tomographic measurements of workpieces |
| US20220139002A1 (en) * | 2018-09-14 | 2022-05-05 | Planmed Oy | Self-calibration procedure for digital breast tomosynthesis imaging apparatus |
| CN117788531A (en) * | 2023-11-28 | 2024-03-29 | 中国人民解放军战略支援部队信息工程大学 | Photon detector acquisition projection image module seam filling method based on image registration |
| CN118196080A (en) * | 2024-05-13 | 2024-06-14 | 宝鸡拓普达钛业有限公司 | Intelligent defect identification method and system for titanium alloy product |
| CN118566266A (en) * | 2024-08-01 | 2024-08-30 | 中铁电气化铁路运营管理有限公司 | X-ray based nondestructive detection method and system for internal defects of power supply equipment |
-
2024
- 2024-12-05 CN CN202411775524.8A patent/CN119246570B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4125771A (en) * | 1977-11-18 | 1978-11-14 | Net Systems Inc. | Apparatus for determining stress in nickel and titanium alloyed materials |
| JP2005167773A (en) * | 2003-12-04 | 2005-06-23 | Canon Inc | Image processing method and apparatus |
| US20130058556A1 (en) * | 2011-09-02 | 2013-03-07 | Toshiba Medical Systems Corporation | X-ray diagnostic apparatus, x-ray diagnostic method and stent for x-ray diagnosis |
| CN103149222A (en) * | 2013-02-28 | 2013-06-12 | 重庆大学 | Flaw detection device in real-time imaging of ray |
| CN103705258A (en) * | 2013-11-19 | 2014-04-09 | 江苏康众数字医疗设备有限公司 | Automatic exposure control method and automatic exposure control device for imaging device |
| JP2017104329A (en) * | 2015-12-10 | 2017-06-15 | 東芝メディカルシステムズ株式会社 | X-ray diagnostic apparatus and X-ray CT apparatus |
| DE102018105709A1 (en) * | 2017-03-15 | 2018-09-20 | Werth Messtechnik Gmbh | Method for computer tomographic measurements of workpieces |
| US20220139002A1 (en) * | 2018-09-14 | 2022-05-05 | Planmed Oy | Self-calibration procedure for digital breast tomosynthesis imaging apparatus |
| CN117788531A (en) * | 2023-11-28 | 2024-03-29 | 中国人民解放军战略支援部队信息工程大学 | Photon detector acquisition projection image module seam filling method based on image registration |
| CN118196080A (en) * | 2024-05-13 | 2024-06-14 | 宝鸡拓普达钛业有限公司 | Intelligent defect identification method and system for titanium alloy product |
| CN118566266A (en) * | 2024-08-01 | 2024-08-30 | 中铁电气化铁路运营管理有限公司 | X-ray based nondestructive detection method and system for internal defects of power supply equipment |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119804327A (en) * | 2025-03-13 | 2025-04-11 | 杭州普络飞新材料科技有限公司 | PCM board quality inspection system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119246570B (en) | 2025-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115082464B (en) | Method and system for identifying weld data in welding process of dust remover | |
| CN118602979B (en) | Weld joint morphology and surface defect online detection and evaluation method and system | |
| Li et al. | Improving automatic detection of defects in castings by applying wavelet technique | |
| EP1430446B1 (en) | Image processing method for appearance inspection | |
| CN115601359A (en) | Welding seam detection method and device | |
| CN112862744A (en) | Intelligent detection method for internal defects of capacitor based on ultrasonic image | |
| CN115096893A (en) | Airplane structural member defect nondestructive testing method based on machine vision | |
| CN111815555A (en) | Adversarial neural network combined with local binary image detection method and device for metal additive manufacturing | |
| CN103149222A (en) | Flaw detection device in real-time imaging of ray | |
| CN108846397A (en) | A kind of cable semi-conductive layer automatic testing method based on image procossing | |
| CN115684176A (en) | Online visual inspection system for film surface defects | |
| CN119444664B (en) | A visual inspection method for welding quality | |
| CN116381053A (en) | Ultrasonic detection method and system for welding metal materials | |
| CN119246570B (en) | Titanium alloy bar quality detection method and system | |
| CN119151928A (en) | Defect detection method, device, equipment and medium based on few sample learning | |
| Hao et al. | An image-based hairline crack identification method for metal parts | |
| CN117358944A (en) | An additive manufacturing method for multi-joint ultra-long stainless steel oil pipelines | |
| CN120495220B (en) | A method and system for analyzing metal wire data | |
| CN119574571B (en) | Automobile body weld joint detection method and system based on machine vision | |
| CN118135439B (en) | Method for identifying and measuring concrete cracks by using unmanned aerial vehicle | |
| CN114677331A (en) | Pipe defect detection method and device based on fusion of gray level image and depth data | |
| CN118212206A (en) | A solder joint defect detection method, system and storage medium | |
| CN115908275A (en) | On-line measurement method of hot ring rolling deformation geometric state based on deep learning | |
| CN108122226B (en) | Method and device for detecting glass defects | |
| CN120259282B (en) | A burr detection method and system for copper rod electrolytic polishing |
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 |