CN112816557B - Defect detection method, device, equipment and storage medium - Google Patents
Defect detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112816557B CN112816557B CN201911130013.XA CN201911130013A CN112816557B CN 112816557 B CN112816557 B CN 112816557B CN 201911130013 A CN201911130013 A CN 201911130013A CN 112816557 B CN112816557 B CN 112816557B
- Authority
- CN
- China
- Prior art keywords
- defect
- scanning image
- detected
- determining
- area
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
- G01N29/11—Analysing solids by measuring attenuation of acoustic waves
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4409—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by comparison
- G01N29/4418—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by comparison with a model, e.g. best-fit, regression analysis
Landscapes
- Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- Engineering & Computer Science (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
本发明实施例公开了一种缺陷检测方法、装置、设备和存储介质，缺陷检测方法包括：根据待检测对象的超声脉冲反射C扫描图像，确定待检测对象的缺陷区域；根据缺陷区域的位置，从待检测对象的超声脉冲反射A扫描图像提取缺陷A扫描图像部分；根据缺陷A扫描图像部分，确定待检测对象的缺陷性质。本发明实施例根据缺陷区域找到相对应的缺陷A扫描图像部分，根据缺陷A扫描图像部分对缺陷性质进行确定。通过结合超声脉冲反射C扫描图像和A扫描图像对缺陷性质进行确定为后续对缺陷面积进一步判定提供基础，提高了缺陷检测的效率；通过C扫描图像和A扫描图像结合自动对缺陷性质进行判断提高了缺陷检测的自动化程度。
The embodiment of the present invention discloses a defect detection method, device, equipment and storage medium. The defect detection method includes: determining the defect area of the to-be-detected object according to the ultrasonic pulse reflection C-scan image of the to-be-detected object; according to the position of the defect area, The defect A-scan image portion is extracted from the ultrasonic pulse reflection A-scan image of the object to be inspected; the defect property of the object to be inspected is determined according to the defect A-scan image portion. In the embodiment of the present invention, the corresponding defect A-scanning image part is found according to the defect area, and the defect property is determined according to the defect A-scanning image part. Determining defect properties by combining ultrasonic pulse reflection C-scan images and A-scan images provides a basis for further determination of defect area, and improves the efficiency of defect detection; the combination of C-scan images and A-scan images automatically determines defect properties to improve The degree of automation of defect detection.
Description
Technical Field
The embodiment of the invention relates to the technical field of ultrasonic nondestructive testing, in particular to a defect detection method, a defect detection device, defect detection equipment and a storage medium.
Background
With the development of material technology, more and more advanced materials are put into use. Advanced composite laminates used on large passenger aircraft have become an important development in the aerospace field. As internal defects such as delamination, inclusions, porosity, pore density and gel enrichment may occur during the production of the composite laminate. It is therefore necessary to perform defect detection on the composite laminate before it is put into use.
At present, ultrasonic nondestructive testing is one of the important methods for testing the quality of mechanical engineering materials. The principle of the method is that when ultrasonic waves are transmitted in a detected material, acoustic characteristics of the material and changes of internal tissues have certain influence on the transmission of the ultrasonic waves. The common ultrasonic nondestructive detection method is to obtain an A scanning image and a C scanning image by an ultrasonic pulse reflection method, judge the defect property by an experienced professional combining the A scanning image and the C scanning image, and judge the defect area information according to the defect property.
However, due to the complexity of the composite material structure, the ultrasonic signal is complex, and the defect property judgment of the combination of the A scanning image and the C scanning image by experienced professionals is difficult, the automation degree of defect detection is low, the detection time is long, the efficiency is low, and certain human errors are caused.
Disclosure of Invention
The embodiment of the invention provides a defect detection method, a defect detection device, defect detection equipment and a storage medium, which are used for improving the defect detection efficiency and reducing manual false detection.
In a first aspect, an embodiment of the present invention provides a defect detection method, including:
determining a defect area of the object to be detected according to the ultrasonic pulse reflection C scanning image of the object to be detected;
extracting a defect A scanning image part from an ultrasonic pulse reflection A scanning image of an object to be detected according to the position of the defect area;
and scanning the image part according to the defect A, and determining the defect property of the object to be detected.
In a second aspect, an embodiment of the present invention further provides a defect detection apparatus, including:
the defect area determining module is used for determining the defect area of the object to be detected according to the ultrasonic pulse reflection C scanning image of the object to be detected;
the defect A scanning image part extracting module is used for extracting a defect A scanning image part from an ultrasonic pulse reflection A scanning image of the object to be detected according to the position of the defect area;
and the defect property determining module is used for determining the defect property of the object to be detected according to the defect A scanning image part.
In a third aspect, an embodiment of the present invention further provides a computer device, including:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method of defect detection as in any of the embodiments of the invention.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the defect detection method according to any embodiment of the present invention.
The method and the device determine the defect area based on the ultrasonic pulse reflection C scanning image of the object to be detected, find the corresponding defect A scanning image part according to the defect area, and determine the defect property according to the defect A scanning image part. The defect properties are determined by combining the ultrasonic pulse reflection C scanning image and the ultrasonic pulse reflection A scanning image, so that a basis is provided for further judging the defect area subsequently, and the defect detection efficiency is improved; and the defect property is automatically judged by combining the C scanning image and the A scanning image, so that the automation degree of defect detection is improved.
Drawings
FIG. 1 is a flowchart illustrating a defect detection method according to a first embodiment of the present invention;
FIG. 2 is a flowchart of a defect detection method according to a second embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a defect detection apparatus according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device in the fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Fig. 1 is a flowchart of a defect detection method in a first embodiment of the present invention, and this embodiment is applicable to a case where a defect property of an object to be detected is determined according to an ultrasonic pulse reflection C scan image and an a scan image of the object to be detected. The method may be performed by a defect detection apparatus, which may be implemented in software and/or hardware, and may be configured in a computer device, for example, the computer device may be a device with communication and computing capabilities, such as a background server. As shown in fig. 1, the method specifically includes:
The object to be detected is a material which needs to be subjected to defect detection, for example, the material to be detected can be a composite material part, and ultrasonic defect detection is performed on the composite material part. The ultrasonic pulse reflection C scanning image is an image obtained by directing ultrasonic waves to an object to be detected, reflecting a part of sound waves when the ultrasonic waves enter the object to be detected and encounter defects, and converting and displaying the reflected waves through a receiver. The C scanning image is displayed as cross-section images of the internal defect of the object to be detected at different depths, and the shape and the control position of the internal defect of the object to be detected can be visually known through the C scanning image. The C scanning image is displayed by converting the ultrasonic reflection echo energy in the depth direction of each collected position into a voltage signal through the principle of digital ultrasonic scanning imaging, and carrying out 256-level digital processing on the amplitude of the voltage signal, so that cross-section images of the interior of the object to be detected with different energy represented by different gray values can be obtained.
The defect area refers to a position range where an internal defect caused in a manufacturing process appears inside an object to be detected, for example, defect types include delamination, inclusion, pores, pore density, glue enrichment and the like in a composite laminated member. The defect area may be determined by the gray value in the C-scan image.
Specifically, a composite material part needing to detect the defects is determined, ultrasonic pulse reflection is carried out on the part, a C scanning image is obtained, and the defect area on the current cross section is determined according to the gray level change condition of the cross section image of the part in the C scanning image.
Optionally, determining a defect region of the object to be detected according to the ultrasonic pulse reflection C-scan image of the object to be detected includes:
taking an ultrasonic pulse reflection C scanning image of the object to be detected as the input of a defect position prediction model, and determining the defect area of the object to be detected according to the output of the model;
wherein training the defect location prediction model by:
acquiring an ultrasonic pulse reflection C scanning image sample of a test object;
marking the position of a defect area in the C scanning image sample;
and training to obtain the defect prediction model according to the marked C scanning image sample.
The defect position prediction model is obtained by training a test set of an object to be detected based on a machine learning algorithm, the ultrasonic pulse reflection C scanning image of the object to be detected is input, the defect region of the object to be detected is output, and the output form comprises coordinate point information of the defect region or the edge of the defect region displayed on the C scanning image.
The method comprises the steps that a defect position prediction model needs to be trained before a defect region of an object to be detected is determined, wherein a test object in the training process refers to a detection object with a known defect position prepared for training the model or a detection object with the defect position determined manually, optional test objects comprise a comparison test block, and the comparison test block refers to a composite material part with the known defect position and defect area information and is used for providing accurate reference for the object to be detected with unknown defect information. The marking means that a defect area of the test object is marked on the C-scan image according to the C-scan image of the test object, and a mode of confirming a boundary coordinate point of the defect area can be adopted.
Specifically, ultrasonic pulse reflection C scanning images of a large number of composite material parts with defects inside are collected and used as a model training sample set, boundary coordinate points of defect areas of the C scanning images in the training sample set are labeled, and characteristic values of the defect areas are extracted. Alternatively, the more coordinate point information of the defect region boundary, the more accurately the defect region information can be represented, and the extracted feature value may be a gray value in the C-scan image, which can represent the gray value of the defect region. And inputting the marked C scanning image with the information of the boundary coordinate points of the defect region and the characteristic value information into a machine learning algorithm model, and training the algorithm model to obtain a final defect position prediction model by continuously learning the gray information of the marked defect region and the gray information of the non-defect region.
Inputting an ultrasonic pulse reflection C-scan image of an object to be detected in an unknown defect region into a defect position prediction model, outputting defect region information obtained by judgment by the model through judging gray scale information in the C-scan image, optionally outputting coordinate point information of a defect region boundary, and forming a defect region on the C-scan image by utilizing the coordinate point information. The defect position prediction model is obtained by learning a large amount of marked defect information, so that the defect position prediction model learns the characteristic information of the defect region, and the defect region is determined by using the defect position prediction model, which is favorable for improving the accuracy of detecting the defect region.
And 102, extracting a defect A scanning image part from an ultrasonic pulse reflection A scanning image of the object to be detected according to the position of the defect area.
The position of the defect region refers to information that can characterize the defect region obtained according to the defect position prediction model, and optionally, may be a position coordinate point, including a horizontal axis coordinate value of a center point of the defect region. The ultrasonic pulse reflection A scanning image is an image obtained according to waveform energy information of ultrasonic waves reflected back, the A scanning image is actually an ultrasonic pulse echo image, the abscissa of the A scanning image represents ultrasonic propagation time, the ordinate represents echo height, namely amplitude of the ultrasonic waves, in the same uniform medium, the propagation time is in direct proportion to depth, therefore, the echo position of the ordinate can determine defect depth information in an object to be detected, and defect properties can be judged from the defect depth information. The defect a-scan image portion refers to a portion of the waveform image representing a defective area in the entire a-scan image.
Specifically, according to coordinate point information of a defect area in the object to be detected, which is obtained by the defect position prediction model, a corresponding position is found from an ultrasonic pulse reflection A scanning image of the object to be detected, and a defect A scanning image of the corresponding position is determined and is used as a defect A scanning image part. Accurate determination of the A-scan image portion of the defective region can provide a good basis for subsequent defect property determination, and interference of the A-scan image of the non-defective region is avoided.
Optionally, extracting a defect a-scan image portion from the ultrasound pulse reflection a-scan image of the object to be detected according to the position of the defect region, including:
according to the mapping relation of the ultrasonic pulse reflection C scanning image and the ultrasonic pulse reflection A scanning image of the object to be detected with respect to the image position, according to the position of the defect area determined by the C scanning image, extracting a mapping part from the A scanning image, and determining a defect A scanning image part.
The mapping relation of the image positions means that waveform information corresponding to the ultrasonic pulse reflection A scanning image of the same detection object can be found according to the position information of a certain point in the ultrasonic pulse reflection C scanning image, namely, the coordinate point information on the C scanning image and the coordinate point information on the A scanning image can establish a corresponding relation, so that the corresponding position representations are the same on the object to be detected. The mapping part is a part which is mapped in the A scanning image according to the mapping relation of the image position and represents a defect area on the C scanning image, and can be a section of waveform signal in the A scanning image.
Specifically, according to coordinate point information of a defect area in an object to be detected, which is obtained by a defect position prediction model, and according to the position mapping relation between an ultrasonic pulse reflection C scanning image and an ultrasonic pulse reflection A scanning image, points of each coordinate point of the C scanning image, which are mapped in the A scanning image, are respectively found, and finally the found points in the A scanning image are combined to form a defect A scanning image part. The defect area can be accurately determined from the A scanning image according to the mapping relation, and the accuracy of determining the range of the defect area on the A scanning image is improved.
The defect property comprises a macroscopic defect and a microscopic defect, wherein the microscopic defect refers to a defect with a very small defect area caused in the manufacturing process of the composite material, and for example, the microscopic defect comprises a pore defect, such as dense pores and the like; the macro defects refer to defects with the defect area larger than the pore diameter in the manufacturing process, for example, the macro defects comprise layering, foreign matter inclusion, pores and the like, and are generally distributed at a certain depth of the composite material and cannot penetrate through the thickness of the whole composite material.
Specifically, according to the determined energy fluctuation of ultrasonic wave reflection in the defect a scanned image part, a region with abnormal energy fluctuation is determined, and the defect property of the object to be detected is determined according to the region range and the amplitude, optionally, if the positions of the defect waves at different positions in the defect a scanned image part are basically consistent, the defect wave is a macro defect, and otherwise, the defect wave is a micro defect.
Optionally, the determining the defect property of the object to be detected according to the defect a scanning image part includes:
taking a defect A scanning image part of the object to be detected as the input of a defect property prediction model, and determining the defect property of the object to be detected according to the output of the model;
wherein training the defect property prediction model by:
acquiring an ultrasonic pulse reflection A scanning image sample of a test object;
marking the position of a defect area in the A scanning image sample;
and training to obtain the defect property prediction model according to the marked A scanning image sample.
The defect property prediction model is obtained by training a test set of an object to be detected based on a machine learning algorithm, and is input as an ultrasonic pulse reflection A scanning image of the defect of the object to be detected and output as the defect property of the object to be detected.
Before determining the properties of the defect region of the object to be detected, a defect property prediction model needs to be trained, wherein the test object in the training process refers to a detection object with known defect properties prepared for training the model or a detection object with which the defect properties can be determined manually, optional test objects comprise a reference block, and the reference block refers to a composite material part with known defect positions and defect property information and is used for providing accurate reference for the object to be detected with unknown defect properties. Marking means that a defect area of a test object is marked on an A-scan image according to the A-scan image of the test object, whether the defect area belongs to a macro defect or a micro defect is marked, and inputting a training sample set can intercept the A-scan image of the defect part in the A-scan image and add a property mark.
Specifically, a large number of ultrasonic pulse reflection A scanning images of composite material parts with defects inside are collected and used as a model training sample set, the A scanning images in the training sample set are subjected to defect area partial interception, and the defect properties of the intercepted defect area partial are judged. Optionally, the defect property of the defect region is determined according to whether the positions of the defect waves at different positions are consistent, if so, the defect is a macro defect, otherwise, the defect is a micro defect. Inputting the marked A scanning image of the defect part with the defect property information into a machine learning algorithm model, and training the algorithm model to obtain a final defect property prediction model by continuously learning the relation between the amplitude information and the mark of the marked defect region.
Inputting a defect A scanning image part of an object to be detected with unknown defect properties into a defect property prediction model, and outputting defect property information obtained through judgment by the model through judging the amplitude information and the position in the defect A scanning image part. The defect property prediction model is obtained by learning a large amount of marked defect property information and the amplitude values in the A scanning image, so that the defect property prediction model learns the characteristic information of the defect region. The defect region property is determined by using the defect property prediction model, so that the automation degree of defect region detection is improved.
The embodiment of the invention is based on training the defect position prediction model, and realizes automatic identification of the defect area according to the ultrasonic pulse reflection C scanning image of the object to be detected; and extracting the part of the A scanning image of the defect area according to the mapping relation between the C scanning image and the A scanning image, and testing the part of the A scanning image of the defect area according to the defect property prediction model to obtain a property judgment result of the defect area. The defect position prediction model and the defect property prediction model are combined to realize automatic determination of the defect property, so that an essential basis is provided for determining the defect area information according to the defect property subsequently, and the accuracy and the automation degree of ultrasonic defect detection are improved.
Example two
Fig. 2 is a flowchart of a defect detection method in the second embodiment of the present invention, and the second embodiment further optimizes the first embodiment to determine the area information of the defect region for determining the defect property. As shown in fig. 2, the method includes:
And 204, if the defect property is a macro defect, determining the defect area and the defect depth of the object to be detected.
The defect area refers to the actual area of the defect region on the object to be detected, and optionally, the unit of the defect area may be square millimeters. The defect depth refers to information about the buried depth of the detected defect region in the object to be detected, and optionally, the unit of the defect depth may be millimeter or micrometer. The defect area and the defect depth information are judged, so that the related information of the defect in the object to be detected can be known, and the subsequent defect treatment is facilitated.
Specifically, after judging that the defect property is a macro defect according to the defect property prediction model, identifying a defect region determined by the defect position prediction model to obtain defect area information; defect depth information is determined from the defect a scanned image portion.
Optionally, if the defect property is a macro defect, determining the defect area and the defect depth of the object to be detected includes:
and if the defect property is a macro defect, determining the defect area from the defect area of the C scanning image and determining the defect depth from the defect A scanning image part according to a macro defect area evaluation algorithm.
The macro defect area evaluation algorithm is an area calculation algorithm set for the area characteristics of macro defects, and can be determined according to the defect area. Optionally, the macroscopic defect area assessment algorithm includes determining the defect area of the object to be detected by using the defect area characteristics in the C-scan image of the reference block. The reference block refers to a part with the same thickness, structure form, forming process and material type number as the object to be detected, and the reference block has the defect of known thickness information and area information.
Specifically, a contrast block with known defects and various information is preset for each type of object to be detected, after the defect property of the object to be detected is determined, the contrast block corresponding to the object to be detected is determined, an ultrasonic pulse reflection C scanning image of the contrast block is collected, and the defect area of the object to be detected is determined according to the gray level or gray level attenuation threshold of the C scanning image with the known embedded defects on the contrast block. Optionally, the gray attenuation rule of the defect region is determined according to the C-scan image of the reference block, the threshold value for identifying the defect region and the non-defect region is obtained, and the correlation between the gray attenuation information and the threshold value and the area information is established. So as to determine the area of the C scanning image of the object to be detected according to the correlation relationship.
And determining the defect A scanning image part of the object to be detected and the defect A scanning image part of the comparison test block, and determining the depth information of the defect A scanning image part of the object to be detected according to the defect A scanning image part of the comparison test block with the known embedded depth. Optionally, a corresponding relationship is established according to the relationship between the occurrence position of the defect wave and the depth information, and then the defect depth information can be obtained according to the occurrence position of the defect wave with unknown defect depth. After the macro defect property is determined, the defect area information and the depth information of the object to be detected are determined according to the relevant information of the corresponding reference block, so that the difference of the identification results caused by the difference of internal materials of different models is avoided, and the detection accuracy of the defect information of the object to be detected is improved.
And step 205, if the defect property is a microscopic defect, determining the defect area of the object to be detected.
Specifically, after the defect property is judged to be the micro defect according to the defect property prediction model, the defect region determined by the defect position prediction model is identified to obtain the defect area information. Alternatively, a method of determining the area of the defect region of the object to be detected according to the information of the area of the defect region of the reference block may be adopted.
Optionally, if the defect property is a microscopic defect, determining the defect area of the object to be detected includes:
and if the defect property is a micro defect, determining the defect area from the defect area of the C scanning image according to a micro defect area evaluation algorithm.
The microscopic defect area evaluation algorithm is an area calculation algorithm set according to the area characteristics of the microscopic defects, and can be determined according to the defect pores. Optionally, the microscopic defect area evaluation algorithm includes determining a defect area of the object to be measured by using a preset porosity evaluation curve. The preset porosity evaluation curve is a relation curve of composite material pores of different types, ultrasonic attenuation and material thickness obtained by analyzing A scanning image information obtained by performing ultrasonic pulse reflection A scanning on a reference block. The relationship between the area information of the defect and the ultrasonic attenuation can be obtained from the preset porosity evaluation curve.
Specifically, ultrasonic pulse reflection A scanning images of different types of reference blocks are obtained, and preset porosity evaluation curves of different types are determined according to waveform amplitude change signals on the A scanning images. And when the defect property is determined to be the micro defect, acquiring a scanning image part of the defect A, acquiring corresponding defect wave position and amplitude information, finding a corresponding point on a preset porosity evaluation curve of the same model, and determining the area information of the micro defect.
Optionally, after determining the defect property, area and depth information of the object to be detected, comparing the defect property, area and depth information with the acceptance standard of the object to be detected, and judging whether the defect area and depth information meet the requirements, if so, the defect of the object to be detected is qualified, otherwise, the defect is not qualified.
After the defect property of the object to be detected is determined, different area rating algorithms are set according to different defect properties, and targeted defect area calculation is performed, so that the accuracy of defect area calculation is improved. In the calculation process of the defect area and the depth information, the calculation basis is the information obtained in the defect property judgment process, and the related information of the defect can be obtained by reflecting the C scanning image and the A scanning image by the ultrasonic pulse from the object to be detected, so that the overall automation degree and accuracy of the defect detection are improved, the automatic evaluation of the object to be detected is realized, the personnel cost is reduced, and the detection efficiency is improved.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a defect detection apparatus in a third embodiment of the present invention, and this embodiment is applicable to a case where the defect property of an object to be detected is determined according to an ultrasonic pulse reflection C scan image and an a scan image of the object to be detected. As shown in fig. 3, the apparatus includes:
and a defect area determining module 310, configured to determine a defect area of the object to be detected according to the ultrasonic pulse reflection C scan image of the object to be detected.
And a defect a scan image part extracting module 320, configured to extract a defect a scan image part from the ultrasonic pulse reflection a scan image of the object to be detected according to the position of the defect region.
And the defect property determining module 330 is configured to determine the defect property of the object to be detected according to the defect a scanned image portion.
The method and the device determine the defect area based on the ultrasonic pulse reflection C scanning image of the object to be detected, find the corresponding defect A scanning image part according to the defect area, and finally determine the defect property according to the defect A scanning image part. The defect properties are determined by combining the ultrasonic pulse reflection C scanning image and the ultrasonic pulse reflection A scanning image, so that a basis is provided for further judging the defect area subsequently, and the defect detection efficiency is improved; and the defect property is automatically judged by combining the C scanning image and the A scanning image, so that the automation degree of defect detection is improved.
Optionally, according to the position of the defect area, the defect a scanned image part extracting module 320 is specifically configured to:
according to the mapping relation of the ultrasonic pulse reflection C scanning image and the ultrasonic pulse reflection A scanning image of the object to be detected with respect to the image position, according to the position of the defect area determined by the C scanning image, extracting a mapping part from the A scanning image, and determining a defect A scanning image part.
Optionally, the defective area determining module 310 is specifically configured to:
taking an ultrasonic pulse reflection C scanning image of the object to be detected as the input of a defect position prediction model, and determining the defect area of the object to be detected according to the output of the model;
wherein training the defect location prediction model by:
acquiring an ultrasonic pulse reflection C scanning image sample of a test object;
marking the position of a defect area in the C scanning image sample;
and training to obtain the defect prediction model according to the marked C scanning image sample.
Optionally, the defect property determining module 330 is specifically configured to:
taking a defect A scanning image part of the object to be detected as the input of a defect property prediction model, and determining the defect property of the object to be detected according to the output of the model;
wherein training the defect property prediction model by:
acquiring an ultrasonic pulse reflection A scanning image sample of a test object;
marking the position of a defect area in the A scanning image sample;
and training to obtain the defect property prediction model according to the marked A scanning image sample.
Optionally, the apparatus further comprises:
the macroscopic defect determining module is used for determining the defect area and the defect depth of the object to be detected if the defect property is macroscopic defect;
and the microscopic defect determining module is used for determining the defect area of the object to be detected if the defect property is microscopic defect.
Optionally, the macro defect determining module is specifically configured to:
and if the defect property is a macro defect, determining the defect area from the defect area of the C scanning image and determining the defect depth from the defect A scanning image part according to a macro defect area evaluation algorithm.
Optionally, the microscopic defect determining module is specifically configured to:
and if the defect property is a micro defect, determining the defect area from the defect area of the C scanning image according to a micro defect area evaluation algorithm.
The defect detection device provided by the embodiment of the invention can execute the defect detection method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the defect detection method.
Example four
Fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention. FIG. 4 illustrates a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention. The computer device 12 shown in FIG. 4 is only one example and should not bring any limitations to the functionality or scope of use of embodiments of the present invention.
As shown in FIG. 4, computer device 12 is in the form of a general purpose computing device. The components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory device 28, and a bus 18 that couples various system components including the system memory device 28 and the processing unit 16.
The system storage 28 may include computer system readable media in the form of volatile storage, such as Random Access Memory (RAM)30 and/or cache storage 32. Computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 4, and commonly referred to as a "hard drive"). Although not shown in FIG. 4, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Storage 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in storage 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
The processing unit 16 executes various functional applications and data processing by running programs stored in the system storage device 28, for example, to implement the defect detection method provided by the embodiment of the present invention, including:
determining a defect area of the object to be detected according to the ultrasonic pulse reflection C scanning image of the object to be detected;
extracting a defect A scanning image part from an ultrasonic pulse reflection A scanning image of an object to be detected according to the position of the defect area;
and scanning the image part according to the defect A, and determining the defect property of the object to be detected.
EXAMPLE five
The fifth embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the defect detection method provided in the fifth embodiment of the present invention, and the method includes:
determining a defect area of the object to be detected according to the ultrasonic pulse reflection C scanning image of the object to be detected;
extracting a defect A scanning image part from an ultrasonic pulse reflection A scanning image of an object to be detected according to the position of the defect area;
and scanning the image part according to the defect A, and determining the defect property of the object to be detected.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (8)
1. A method of defect detection, comprising:
determining a defect area of the object to be detected according to the ultrasonic pulse reflection C scanning image of the object to be detected;
extracting a defect A scanning image part from an ultrasonic pulse reflection A scanning image of an object to be detected according to the position of the defect area;
scanning the image part according to the defect A, and determining the defect property of the object to be detected;
determining a defect region of an object to be detected according to an ultrasonic pulse reflection C scanning image of the object to be detected, comprising:
taking an ultrasonic pulse reflection C scanning image of the object to be detected as the input of a defect position prediction model, and determining the defect area of the object to be detected according to the output of the model;
wherein training the defect location prediction model by:
acquiring an ultrasonic pulse reflection C scanning image sample of a test object;
marking the position of a defect area in the C scanning image sample;
training to obtain the defect prediction model according to the marked C scanning image sample;
after determining the defect property of the object to be detected, the method further comprises the following steps:
if the defect property is a macro defect, determining the defect area and the defect depth of the object to be detected;
if the defect property is a microscopic defect, determining the defect area of the object to be detected;
the object to be detected is a composite material part, the defect area is determined through the gray value in the C scanning image, and the defect area on the current cross section is determined according to the gray change condition of the part cross section image in the C scanning image.
2. The method of claim 1, wherein extracting a defect a-scan image portion from an ultrasound pulse reflection a-scan image of an object to be inspected based on a location of a defect region comprises:
according to the mapping relation of the ultrasonic pulse reflection C scanning image and the ultrasonic pulse reflection A scanning image of the object to be detected with respect to the image position, according to the position of the defect area determined by the C scanning image, extracting a mapping part from the A scanning image, and determining a defect A scanning image part.
3. The method of claim 1, wherein determining the nature of the defect in the object to be inspected from the defect a scan image portion comprises:
taking a defect A scanning image part of the object to be detected as the input of a defect property prediction model, and determining the defect property of the object to be detected according to the output of the model;
wherein training the defect property prediction model by:
acquiring an ultrasonic pulse reflection A scanning image sample of a test object;
marking the position of a defect area in the A scanning image sample;
and training to obtain the defect property prediction model according to the marked A scanning image sample.
4. The method of claim 1, wherein determining the defect area and defect depth of the object to be inspected if the defect property is a macro defect comprises:
and if the defect property is a macro defect, determining the defect area from the defect area of the C scanning image and determining the defect depth from the defect A scanning image part according to a macro defect area evaluation algorithm.
5. The method according to claim 1, wherein if the defect property is a microscopic defect, determining the defect area of the object to be detected comprises:
and if the defect property is a micro defect, determining the defect area from the defect area of the C scanning image according to a micro defect area evaluation algorithm.
6. A defect detection apparatus, comprising:
the defect area determining module is used for determining the defect area of the object to be detected according to the ultrasonic pulse reflection C scanning image of the object to be detected;
the defect A scanning image part extracting module is used for extracting a defect A scanning image part from an ultrasonic pulse reflection A scanning image of the object to be detected according to the position of the defect area;
the defect property determining module is used for scanning the image part according to the defect A and determining the defect property of the object to be detected;
a defective area determination module, specifically configured to:
taking an ultrasonic pulse reflection C scanning image of the object to be detected as the input of a defect position prediction model, and determining the defect area of the object to be detected according to the output of the model;
wherein training the defect location prediction model by:
acquiring an ultrasonic pulse reflection C scanning image sample of a test object;
marking the position of a defect area in the C scanning image sample;
training to obtain the defect prediction model according to the marked C scanning image sample;
the macroscopic defect determining module is used for determining the defect area and the defect depth of the object to be detected if the defect property is macroscopic defect;
the microscopic defect determining module is used for determining the defect area of the object to be detected if the defect property is microscopic defect;
the object to be detected is a composite material part, the defect area is determined through the gray value in the C scanning image, and the defect area on the current cross section is determined according to the gray change condition of the part cross section image in the C scanning image.
7. A computer device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the defect detection method of any of claims 1-5.
8. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method for defect detection according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911130013.XA CN112816557B (en) | 2019-11-18 | 2019-11-18 | Defect detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911130013.XA CN112816557B (en) | 2019-11-18 | 2019-11-18 | Defect detection method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112816557A CN112816557A (en) | 2021-05-18 |
| CN112816557B true CN112816557B (en) | 2022-02-18 |
Family
ID=75852598
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911130013.XA Active CN112816557B (en) | 2019-11-18 | 2019-11-18 | Defect detection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112816557B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113588609B (en) * | 2021-07-13 | 2022-09-20 | 广东固特超声股份有限公司 | Detection method for cleanliness of ultrasonic cleaning object |
| CN113744252A (en) * | 2021-09-07 | 2021-12-03 | 全芯智造技术有限公司 | Method, apparatus, storage medium and program product for marking and detecting defects |
| CN114113328A (en) * | 2021-11-03 | 2022-03-01 | 哈尔滨飞机工业集团有限责任公司 | Method for detecting debonding defect of aluminum panel and honeycomb glued joint |
| CN114463282B (en) * | 2022-01-13 | 2024-10-22 | 江苏六道建材有限公司 | Defect detection method, device, electronic equipment and computer readable medium |
| CN116046907B (en) * | 2022-11-07 | 2025-07-01 | 中国航空制造技术研究院 | An ultrasonic automatic identification method for composite material defects considering detection probability |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3865675B2 (en) * | 2002-09-27 | 2007-01-10 | 株式会社日立製作所 | Ultrasonic flaw detection result display method and ultrasonic flaw detector |
| CN102507740A (en) * | 2011-11-29 | 2012-06-20 | 汕头华兴冶金设备股份有限公司 | Detecting method and detecting system for detecting rectangular metal bars |
| CN103323526A (en) * | 2013-05-30 | 2013-09-25 | 哈尔滨工业大学 | Welding line defect detection and identification method based on ultrasonic phased array and support vector machine |
| CN105527346A (en) * | 2014-09-29 | 2016-04-27 | 张学一 | Full-waveform acquisition ultrasound automatic detection system based on high-speed A/D card |
| JP6546826B2 (en) * | 2015-10-08 | 2019-07-17 | 株式会社日立パワーソリューションズ | Defect inspection method and apparatus therefor |
| CN106248803B (en) * | 2016-07-07 | 2019-02-05 | 北京航空航天大学 | A defect determination method for flash memory plastic packaged devices based on acoustic scanning |
| CN107290428B (en) * | 2017-06-23 | 2020-02-07 | 上海新跃联汇电子科技有限公司 | Ultrasonic rail flaw detection trolley system based on deep learning and control method thereof |
| CN107451997A (en) * | 2017-07-31 | 2017-12-08 | 南昌航空大学 | A kind of automatic identifying method of the welding line ultrasonic TOFD D scanning defect types based on deep learning |
| CN108226291B (en) * | 2017-12-07 | 2020-08-11 | 中航复合材料有限责任公司 | Method for evaluating ultrasonic detection probability of composite laminated structure defects |
| CN109283253A (en) * | 2018-11-28 | 2019-01-29 | 燕山大学 | A method for defect detection of lightweight ceramic matrix porous composites based on ultrasonic principle |
| CN110243937B (en) * | 2019-06-17 | 2020-11-17 | 江南大学 | Flip-chip welding spot defect intelligent detection method based on high-frequency ultrasound |
| CN110320285A (en) * | 2019-07-08 | 2019-10-11 | 创新奇智(青岛)科技有限公司 | A kind of steel rail defect recognition methods, system and electronic equipment based on ultrasonic signal |
-
2019
- 2019-11-18 CN CN201911130013.XA patent/CN112816557B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112816557A (en) | 2021-05-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112816557B (en) | Defect detection method, device, equipment and storage medium | |
| CN112816556B (en) | Defect detection method, device, equipment and storage medium | |
| JP7156782B2 (en) | Wrinkle Characterization and Performance Prediction for Composite Structures | |
| CN102183582B (en) | Ultrasonic non-destructive testing device and method thereof | |
| CN108226290A (en) | A kind of inside parts defect three-dimensional parameter extracting method based on ultrasonic phase array | |
| CN108844978B (en) | Novel method for detecting internal defects of honeycomb | |
| CN111553877A (en) | A method for damage identification and life evaluation of blades based on terahertz ceramic matrix composites | |
| US8205500B2 (en) | Systems and methods for inspecting an object using ultrasound | |
| CN118130487B (en) | Welding detection method and system based on scaffold | |
| CN117686588B (en) | Nondestructive monitoring system and method for welding quality of gas pipeline | |
| de Castro et al. | Baseline-free damage imaging algorithm using spatial frequency domain virtual time reversal | |
| CN112014476A (en) | Method and system for classifying and quantitatively evaluating manufacturing defects of carbon fiber composite material | |
| Zhao et al. | Automated quantification of small defects in ultrasonic phased array imaging using AWGA-gcForest algorithm | |
| CN113256566A (en) | Pipeline weld defect identification method | |
| JP2007155724A (en) | Method and system for ultrasonic inspection | |
| Aldrin et al. | The need and approach for characterization-US air force perspectives on materials state awareness | |
| CN115389514A (en) | Material defect detection method and device | |
| CN102621221A (en) | Defect classification method based on phased ultrasonic wave | |
| Aldrin et al. | Design and demonstration of automated data analysis algorithms for ultrasonic inspection of complex composite panels with bonds | |
| CN114660172A (en) | Transmission type ultrasonic imaging method for defects of complex curved surface workpiece | |
| Smith et al. | Model‐assisted probability of detection validation for immersion ultrasonic application | |
| CN118443802A (en) | Petrochemical engineering hidden pipeline detection method, petrochemical engineering hidden pipeline detection equipment, medium and product | |
| Aldrin et al. | Intelligence augmentation in nondestructive evaluation | |
| CN115308310B (en) | Ultrasonic flaw detection identification method for inner wall of pipeline | |
| CN117092211A (en) | Lamb wave-based damage space identification positioning technology in strong noise environment |
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 |