CN113066072A - Method and system for detecting microcrack defects of guide blades of aero-engine - Google Patents
Method and system for detecting microcrack defects of guide blades of aero-engine Download PDFInfo
- Publication number
- CN113066072A CN113066072A CN202110379197.4A CN202110379197A CN113066072A CN 113066072 A CN113066072 A CN 113066072A CN 202110379197 A CN202110379197 A CN 202110379197A CN 113066072 A CN113066072 A CN 113066072A
- Authority
- CN
- China
- Prior art keywords
- gray
- matrix
- frequency
- gray scale
- detail information
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 34
- 239000011159 matrix material Substances 0.000 claims abstract description 147
- 238000001514 detection method Methods 0.000 claims abstract description 81
- 238000012545 processing Methods 0.000 claims abstract description 67
- 239000002245 particle Substances 0.000 claims description 18
- 238000005457 optimization Methods 0.000 claims description 15
- 238000013507 mapping Methods 0.000 claims description 11
- 230000002708 enhancing effect Effects 0.000 claims description 10
- 238000003384 imaging method Methods 0.000 claims description 10
- 238000003709 image segmentation Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 8
- 230000000873 masking effect Effects 0.000 claims description 2
- 238000007689 inspection Methods 0.000 claims 2
- 230000000694 effects Effects 0.000 abstract description 11
- 238000005516 engineering process Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000009659 non-destructive testing Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002498 deadly effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006247 magnetic powder Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000002601 radiography Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a method and a system for detecting microcrack defects of a guide blade of an aeroengine, wherein the detection method comprises the following steps: acquiring a DR detection image of a part to be detected of the guide vane of the aircraft engine through a DR detection system; obtaining an original gray matrix according to the DR detection image; obtaining a DR detection image gray distribution histogram and a signal-to-noise ratio according to the DR detection image; obtaining an enhanced gray matrix according to the gray distribution histogram, the signal-to-noise ratio and the DR detection image; carrying out mask processing on the original gray matrix to obtain a low-frequency gray matrix; and obtaining a high-frequency gray scale detail information matrix according to the enhanced gray scale matrix and the low-frequency gray scale matrix, wherein the high-frequency gray scale detail information matrix represents the microcrack defect condition of the part to be detected of the guide vane of the aircraft engine. The method has the advantages that the effect of improving the contrast of the DR detection image is achieved, the defect outline of detail information in the image is highlighted, and the defect of the microcrack of the guide blade of the aircraft engine can be clearly identified.
Description
Technical Field
The invention relates to the technical field of image enhancement, in particular to a method and a system for detecting microcrack defects of a guide blade of an aircraft engine.
Background
In an aircraft engine, a blade is one of the key components for providing power for the engine, and the main functions of the blade are to compress the air in the engine and the working condition of the blade directly influences the working efficiency, safety and reliability of the engine. For engine turbine blades, guide blades and working blades are key parts for completing functional conversion in the engine. Under the high-speed running state of the engine, the blades are subjected to complex load and tensile stress and torsional stress caused by high-speed rotation, so the quality detection of the guide blades becomes a central part of the quality evaluation of the aeroengine.
The safety of the guide vane is a deadly feature concerning engine and flight safety. After the guide vane is cast, nondestructive detection is needed, generally, ultrasonic detection and magnetic powder detection are often adopted for tiny defects of the guide vane, detected signals are analyzed, and then defect information can be further obtained. The shape and the characteristics of the tiny defect need to be seen more intuitively, and a DR (Digital Radiography) detection system is adopted to acquire a DR defect image and add image processing at the rear end.
DR is an emerging imaging technology applied to industrial nondestructive testing for producing high quality DR digital images with sufficient information. The acquired DR digital image can be optimized and perfected by utilizing a digital image processing technology, a better observation effect can be achieved, and engineers can find small defects of the workpiece hidden in the DR image in time conveniently. Methods for DR image enhancement processing are mainly classified into two categories: enhance the DR image contrast and highlight detail information of the DR image. For a DR image with low contrast and less detail information, the target detail enhancement cannot be effectively carried out by using the traditional histogram enhancement method. In digital image processing technology, there is an algorithm for limiting contrast adaptive histogram equalization, in which the clipping threshold is adjustable, but the manual adjustment does not reach the optimal adjustment parameter.
In view of the above, a new detection method is needed to improve the detection accuracy.
Disclosure of Invention
The invention aims to provide a method and a system for detecting microcrack defects of a guide blade of an aeroengine, which can clearly identify the microcrack defects of the guide blade of the aeroengine.
In order to achieve the purpose, the invention provides the following scheme:
a method for detecting microcrack defects of an aeroengine guide blade comprises the following steps:
acquiring a DR detection image of a part to be detected of the guide vane of the aircraft engine through a DR detection system;
obtaining an original gray matrix according to the DR detection image;
obtaining a gray distribution histogram and a signal-to-noise ratio of the DR detection image according to the DR detection image;
obtaining an enhanced gray matrix according to the gray distribution histogram, the signal-to-noise ratio and the DR detection image;
carrying out mask processing on the original gray matrix to obtain a low-frequency gray matrix;
and obtaining a high-frequency gray scale detail information matrix according to the enhanced gray scale matrix and the low-frequency gray scale matrix, wherein the high-frequency gray scale detail information matrix represents the microcrack defect condition of the part to be detected of the guide vane of the aircraft engine.
Optionally, the DR detection system comprises a digital ray system and a digital flat panel detector imaging system;
emitting X rays to the part to be measured of the guide blade of the aircraft engine through the digital ray system;
the digital flat panel detector imaging system acquires X rays reflected by the part to be detected of the guide vane of the aircraft engine and converts the X rays into DR detection images.
Optionally, the obtaining an enhanced gray-scale matrix according to the gray-scale distribution histogram, the signal-to-noise ratio, and the DR detection image specifically includes:
determining an image segmentation mode and a gray scale mapping range according to the distribution characteristics of the gray scale distribution histogram;
obtaining an optimal cutting threshold value by adopting a particle swarm optimization algorithm according to the gray distribution histogram and the signal-to-noise ratio;
and processing the DR detection image by adopting a particle swarm optimization algorithm and an image enhancement algorithm for limiting contrast self-adaptive histogram equalization according to the image segmentation mode, the gray scale mapping range and the optimal cutting threshold value to obtain an enhanced gray matrix.
Optionally, the grayscale mapping range is [ a minimum grayscale value of the DR detection image, a maximum grayscale value of the DR detection image ].
Optionally, the masking the original grayscale matrix to obtain a low-frequency grayscale matrix specifically includes:
and carrying out fuzzy processing on the original gray matrix by adopting Gaussian fuzzy processing based on a spatial mean filter to obtain a low-frequency gray matrix.
Optionally, the obtaining a high-frequency grayscale detail information matrix according to the enhanced grayscale matrix and the low-frequency grayscale matrix specifically includes:
obtaining a high-frequency gray level detail information matrix according to a formula D-2B-C;
wherein D is a high-frequency gray scale detail information matrix, B is a preliminarily enhanced gray scale matrix, and C is a low-frequency gray scale matrix.
Optionally, the method for detecting the microcrack defect of the aeroengine guide blade further comprises the following steps:
and performing Gaussian mask cycle processing on the high-frequency gray scale detail information matrix for multiple times to obtain an enhanced high-frequency gray scale detail information matrix.
Optionally, the performing, for multiple times, gaussian mask cycle processing on the high-frequency grayscale detail information matrix to obtain an enhanced high-frequency grayscale detail information matrix specifically includes:
aiming at the ith Gaussian mask cycle processing, the method uses a formula Grayi＝2Grayi-1-Grayg-(i-1)Obtaining a high-frequency gray scale detail information matrix after the ith mask cycle processing;
wherein i is the number of cycles, GrayiIs a high-frequency Gray scale detail information matrix, Gray, after the ith Gaussian mask processingi-1Is a high-frequency Gray scale detail information matrix, Gray, after the i-1 Gauss mask processingg-(i-1)To Grayi-1High-frequency Gray level detail information matrix, Gray, after gaussian filtering0An initial high frequency Gray scale detail information matrix, Gray, obtained from the enhanced Gray scale matrix and the low frequency Gray scale matrixg-0To Gray0And (5) carrying out Gaussian filtering on the high-frequency gray level detail information matrix.
Optionally, the number of times of performing the cycle processing on the high-frequency grayscale detail information matrix by performing the multiple gaussian mask cycle processing is 2 to 3 times.
In order to achieve the above purpose, the invention also provides the following scheme:
an aeroengine guide vane microcrack defect detection system, comprising:
the DR detection system is used for detecting the part to be detected of the guide blade of the aircraft engine to obtain a DR detection image;
the calculating unit is connected with the DR detection system and used for calculating an original gray matrix, a gray distribution histogram and a signal-to-noise ratio of the DR detection image;
the enhancement unit is connected with the calculation unit and used for enhancing the DR detection image according to the gray distribution histogram and the signal-to-noise ratio to obtain an enhanced gray matrix;
the mask unit is connected with the calculation unit and is used for performing mask processing on the original gray matrix to obtain a low-frequency gray matrix;
and the detail processing unit is respectively connected with the enhancing unit and the mask unit and is used for obtaining a high-frequency gray scale detail information matrix according to the enhancing gray scale matrix and the low-frequency gray scale matrix, and the high-frequency gray scale detail information matrix represents the microcrack defect condition of the part to be detected of the guide vane of the aircraft engine.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects: the DR detection system is used for obtaining a DR detection image of a part to be detected of the guide vane of the aircraft engine, obtaining an original gray matrix, a gray distribution histogram and a signal-to-noise ratio of the DR detection image, and obtaining a high-frequency gray detail information matrix according to the original gray matrix, the gray distribution histogram and the signal-to-noise ratio, wherein the high-frequency gray detail information matrix represents the defect condition of the microcrack, so that the effect of increasing the contrast of the DR detection image is achieved, the detail information defect outline in the image is highlighted, and the defect of the microcrack of the guide vane of the aircraft engine can be clearly identified.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in 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 it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is an overall flow chart of the method for detecting microcrack defects of an aircraft engine guide blade according to the invention;
FIG. 2 is a flow chart of obtaining an enhanced gray matrix;
FIG. 3 is a schematic block structure diagram of a system for detecting microcrack defects in an aircraft engine guide blade according to the invention.
Description of the symbols:
DR detection system-1, calculation unit-2, enhancement unit-3, mask unit-4, detail processing unit-5.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a method and a system for detecting microcrack defects of guide vanes of an aero-engine.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As shown in FIG. 1, the method for detecting the microcrack defect of the guide blade of the aircraft engine comprises the following steps:
s1: acquiring a DR detection image of a part to be detected of the guide vane of the aircraft engine through a DR detection system;
s2: obtaining an original gray matrix according to the DR detection image;
s3: and obtaining a gray distribution histogram and a signal-to-noise ratio of the DR detection image according to the DR detection image.
In order to improve the detection precision, in the method for detecting the microcrack defect of the guide blade of the aircraft engine, when a gray distribution histogram is obtained, each frame of DR detection image can be converted into a format image of a cross-platform computer image visual library, a corresponding time stamp can be analyzed, and each pixel point of the format image is identified to obtain the gray distribution histogram.
S4: obtaining an enhanced gray matrix according to the gray distribution histogram, the signal-to-noise ratio and the DR detection image;
s5: carrying out mask processing on the original gray matrix to obtain a low-frequency gray matrix;
s6: and obtaining a high-frequency gray scale detail information matrix according to the enhanced gray scale matrix and the low-frequency gray scale matrix, wherein the high-frequency gray scale detail information matrix represents the microcrack defect condition of the part to be detected of the guide vane of the aircraft engine.
Wherein the DR detection system comprises a digital ray system and a digital flat panel detector imaging system;
emitting X rays to the part to be measured of the guide blade of the aircraft engine through the digital ray system;
the digital flat panel detector imaging system acquires X rays reflected by the part to be detected of the guide vane of the aircraft engine and converts the X rays into DR detection images.
Through the digital ray system and the digital flat panel detector imaging system, a high-quality DR digital image can be obtained, the information quantity of the obtained DR digital image is sufficient, sufficient guarantee is provided for subsequent image processing, and the defect of the guide vane microcrack can be clearly identified.
Further, as shown in fig. 2, S4: obtaining an enhanced gray matrix according to the gray distribution histogram, the signal-to-noise ratio and the DR detection image, specifically comprising:
s41: and determining an image segmentation mode and a gray scale mapping range according to the distribution characteristics of the gray scale distribution histogram.
The image segmentation method is generally m × n (m is 2, 4, 8, 16; n is 2, 4, 8, 16, etc.), and the optimal parameter selection is specifically performed according to the image features. The grayscale mapping range is [ the minimum grayscale value of the DR detection image, the maximum grayscale value of the DR detection image ].
S42: and obtaining an optimal cutting threshold value by adopting a particle swarm optimization algorithm according to the gray distribution histogram and the signal-to-noise ratio. Specifically, the method comprises the following steps:
the ith particle of the particle swarm optimization algorithm is denoted as Xi＝(xi1,xi2,...,xiD) The best position it has experienced (with the best adaptation value) is noted as Pi＝(pi1,pi2,...,piD). The index at the best position that all particles in the population have experienced is denoted by g, i.e. pg. Velocity V of the particle ii＝(vi1,vi2,...,viD) And (4) showing. For each generation, its D-dimension (1. ltoreq. D. ltoreq.D) varies according to the following formula:
Vid＝w*Vid+c1*rand()*(pid-xid)+c2*Rand*(pgd-xid)；
xid＝xid+Vid；
wherein w is the inertial weight, c1, c2 are the acceleration constants, and Rand () are two at [0, 1%]Random values that vary within a range. Taking the image signal-to-noise ratio as input: piAnd obtaining an optimal output g through a particle swarm algorithm, which is equivalent to an optimal clipping threshold value in a contrast-limited self-adaptive histogram equalization algorithm. In the present embodiment, the optimal clipping threshold Cliplimit is 3.89.
S43: and processing the DR detection image by adopting a particle swarm optimization algorithm and an image enhancement algorithm for limiting contrast self-adaptive histogram equalization according to the image segmentation mode, the gray scale mapping range and the optimal cutting threshold value to obtain an enhanced gray matrix.
The invention introduces an optimization algorithm: particle Swarm Optimization (PSO), also known as Particle Swarm Optimization, treats each individual as a Particle (dot) without volume in a D-dimensional search space, flying at a speed that is dynamically adjusted based on its own flight experience and the flight experience of the partner. And finally, the optimal clipping threshold Cliplimit is searched, and the image Signal-to-Noise Ratio (SNR) is used as an optimization basis, so that the optimal effect of tuning is achieved.
The optimal cutting threshold value is obtained through a particle swarm optimization algorithm, the optimal image contrast enhancement effect is achieved, after the detection image is subjected to contrast limiting self-adaptive histogram equalization algorithm processing, a high-frequency image gray level information matrix is obtained through Gaussian blur processing, Gaussian mask circulation is conducted on the high-frequency image gray level information matrix for multiple times, the image contrast is further improved, the image detail information is highlighted, the effect of increasing the image contrast is achieved, and the detail information defect outline in the image is highlighted.
Further, S5: performing mask processing on the original gray matrix to obtain a low-frequency gray matrix, which specifically comprises: and carrying out fuzzy processing on the original gray matrix by adopting Gaussian fuzzy processing based on a spatial mean filter to obtain a low-frequency gray matrix.
Preferably, S6: obtaining a high-frequency gray detail information matrix according to the enhanced gray matrix and the low-frequency gray matrix, and specifically comprising the following steps:
obtaining a high-frequency gray level detail information matrix according to a formula D-2B-C;
wherein D is a high-frequency gray scale detail information matrix, B is a preliminarily enhanced gray scale matrix, and C is a low-frequency gray scale matrix.
Further, the method for detecting the microcrack defect of the guide blade of the aero-engine further comprises the following steps:
s7: and performing Gaussian mask cycle processing on the high-frequency gray scale detail information matrix for multiple times to obtain an enhanced high-frequency gray scale detail information matrix. The method specifically comprises the following steps:
aiming at the ith Gaussian mask cycle processing, the method uses a formula Grayi＝2Grayi-1-Grayg-(i-1)Obtaining a high-frequency gray scale detail information matrix after the ith mask cycle processing;
wherein i is cycleNumber of cycles, GrayiIs a high-frequency Gray scale detail information matrix, Gray, after the ith Gaussian mask processingi-1Is a high-frequency Gray scale detail information matrix, Gray, after the i-1 Gauss mask processingg-(i-1)To Grayi-1High-frequency Gray level detail information matrix, Gray, after gaussian filtering0An initial high frequency Gray scale detail information matrix, Gray, obtained from the enhanced Gray scale matrix and the low frequency Gray scale matrixg-0To Gray0And (5) carrying out Gaussian filtering on the high-frequency gray level detail information matrix.
Preferably, the number of cycles i is 2 or 3.
The specific circulating steps are as follows:
wherein, Gray(D)An initial high frequency Gray scale detail information matrix, Gray, obtained from the enhanced Gray scale matrix and the low frequency Gray scale matrix(g-D)To GrayDHigh-frequency Gray level detail information matrix, Gray, after gaussian filtering1For a high-frequency Gray-scale detail information matrix, Gray, after a first Gaussian mask processingg-1Processing Gray for Gaussian filtering1High frequency Gray scale detail information matrix of, and the same way as, Gray2For a high-frequency Gray-scale detail information matrix, Gray, after a second Gaussian mask processing3The high-frequency gray scale detail information matrix after the third Gaussian mask processing is performed. The number of gaussian mask cycles is determined according to the specific image. When the guide vane of the aero-engine is subjected to Gaussian mask cycle processing, the optimal times are 2, the effect of highlighting detail information is achieved, and the image contrast is improved.
The final result of the target image processing can exactly identify the tiny defects on the guide blade, so that the nondestructive testing engineer can conveniently observe the tiny defects, and the image processing method is feasible and effective for DR detection image processing of the micro cracks of the guide blade of the aircraft engine.
In addition, the invention also provides a system for detecting the microcrack defect of the guide blade of the aero-engine, which can clearly identify the microcrack defect of the guide blade of the aero-engine.
As shown in FIG. 3, the system for detecting the microcrack defect of the guide blade of the aircraft engine comprises a DR detection system 1, a calculation unit 2, an enhancement unit 3, a mask unit 4 and a detail processing unit 5.
Specifically, the DR detection system 1 is used for detecting a part to be detected of an aircraft engine guide vane to obtain a DR detection image;
the calculating unit 2 is connected with the DR detection system 1, and the calculating unit 2 is used for calculating an original gray matrix, a gray distribution histogram and a signal-to-noise ratio of the DR detection image;
the enhancement unit 3 is connected with the calculation unit 2, and the enhancement unit 3 is used for enhancing the DR detection image according to the gray distribution histogram and the signal-to-noise ratio to obtain an enhanced gray matrix;
the mask unit 4 is connected with the calculation unit 2, and is used for performing mask processing on the original gray matrix to obtain a low-frequency gray matrix;
the detail processing unit 5 is respectively connected with the enhancing unit 3 and the mask unit 4, the detail processing unit 5 is used for obtaining a high-frequency gray scale detail information matrix according to the enhancing gray scale matrix and the low-frequency gray scale matrix, and the high-frequency gray scale detail information matrix represents the micro-crack defect condition of the part to be detected of the guide vane of the aircraft engine.
Further, the DR detection system comprises a digital ray system and a digital flat panel detector imaging system;
the digital ray system is used for emitting X rays to the part to be measured of the guide blade of the aircraft engine;
the digital flat panel detector imaging system is used for acquiring X rays reflected by the to-be-detected part of the guide vane of the aircraft engine and converting the X rays into DR detection images.
Specifically, the enhancing unit 3 includes: the cutting method comprises a segmentation mode determining module, a cutting threshold determining module and a processing module;
the segmentation mode determining module is used for determining an image segmentation mode and a gray scale mapping range according to the distribution characteristics of the gray scale distribution histogram;
the cutting threshold determining module is used for obtaining an optimal cutting threshold by adopting a particle swarm optimization algorithm according to the gray distribution histogram and the signal-to-noise ratio;
and the processing module is used for processing the DR detection image by adopting a particle swarm optimization algorithm and an image enhancement algorithm for limiting contrast self-adaptive histogram equalization according to the image segmentation mode, the gray scale mapping range and the optimal cutting threshold value to obtain an enhanced gray matrix.
The invention has the following beneficial effects:
(1) parameters in a row contrast ratio limiting self-adaptive histogram equalization algorithm can be flexibly and accurately adjusted, so that the image contrast ratio is improved;
(2) obtaining an optimal cutting threshold value by utilizing a particle swarm optimization algorithm to achieve an optimal image contrast enhancement effect;
(3) after the target image is subjected to contrast-limiting adaptive histogram equalization algorithm processing, extracting high-frequency image gray level information together with the original image subjected to Gaussian blur processing to obtain image gray level detail information;
(4) and (4) performing Gaussian mask circulation processing on the image generated in the step (3) for multiple times. The cycle number of the Gaussian mask can be selected according to the processing result of the Gaussian mask each time, so that the effects of further improving the image contrast and highlighting the image detail information are achieved;
(5) the whole processing process not only achieves the effect of increasing the contrast of the image, but also highlights the defect outline of the detail information in the image.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (10)
1. A method for detecting microcrack defects of an aeroengine guide blade is characterized by comprising the following steps:
acquiring a DR detection image of a part to be detected of the guide vane of the aircraft engine by a digital X-ray photography DR detection system;
obtaining an original gray matrix according to the DR detection image;
obtaining a gray distribution histogram and a signal-to-noise ratio of the DR detection image according to the DR detection image;
obtaining an enhanced gray matrix according to the gray distribution histogram, the signal-to-noise ratio and the DR detection image;
carrying out mask processing on the original gray matrix to obtain a low-frequency gray matrix;
and obtaining a high-frequency gray scale detail information matrix according to the enhanced gray scale matrix and the low-frequency gray scale matrix, wherein the high-frequency gray scale detail information matrix represents the microcrack defect condition of the part to be detected of the guide vane of the aircraft engine.
2. The method for detecting the microcrack defect of the aero-engine guide blade as claimed in claim 1, wherein the DR detection system comprises a digital ray system and a digital flat panel detector imaging system;
emitting X rays to the part to be measured of the guide blade of the aircraft engine through the digital ray system;
the digital flat panel detector imaging system acquires X rays reflected by the part to be detected of the guide vane of the aircraft engine and converts the X rays into DR detection images.
3. The method for detecting the microcrack defect of the aero-engine guide blade according to claim 1, wherein the obtaining an enhanced gray matrix according to the gray distribution histogram, the signal-to-noise ratio and the DR detection image specifically comprises:
determining an image segmentation mode and a gray scale mapping range according to the distribution characteristics of the gray scale distribution histogram;
obtaining an optimal cutting threshold value by adopting a particle swarm optimization algorithm according to the gray distribution histogram and the signal-to-noise ratio;
and processing the DR detection image by adopting a particle swarm optimization algorithm and an image enhancement algorithm for limiting contrast self-adaptive histogram equalization according to the image segmentation mode, the gray scale mapping range and the optimal cutting threshold value to obtain an enhanced gray matrix.
4. The method as claimed in claim 3, wherein the grayscale mapping range is [ the minimum grayscale value of the DR inspection image, the maximum grayscale value of the DR inspection image ].
5. The method for detecting the microcrack defect of the aero-engine guide blade according to claim 1, wherein the masking processing is performed on the original gray matrix to obtain a low-frequency gray matrix, and specifically comprises:
and carrying out fuzzy processing on the original gray matrix by adopting Gaussian fuzzy processing based on a spatial mean filter to obtain a low-frequency gray matrix.
6. The method for detecting the microcrack defect of the aero-engine guide blade according to claim 1, wherein the obtaining a high-frequency grayscale detail information matrix according to the enhanced grayscale matrix and the low-frequency grayscale matrix specifically includes:
obtaining a high-frequency gray level detail information matrix according to a formula D-2B-C;
wherein D is a high-frequency gray scale detail information matrix, B is a preliminarily enhanced gray scale matrix, and C is a low-frequency gray scale matrix.
7. The aero engine guide blade micro-crack defect detection method according to any one of claims 1 to 6, wherein the aero engine guide blade micro-crack defect detection method further comprises:
and performing Gaussian mask cycle processing on the high-frequency gray scale detail information matrix for multiple times to obtain an enhanced high-frequency gray scale detail information matrix.
8. The method for detecting the microcrack defect of the aero-engine guide blade according to claim 7, wherein the performing the gaussian mask cycle processing on the high-frequency grayscale detail information matrix for a plurality of times to obtain an enhanced high-frequency grayscale detail information matrix specifically comprises:
aiming at the ith Gaussian mask cycle processing, the method uses a formula Grayi＝2Grayi-1-Grayg-(i-1)Obtaining a high-frequency gray scale detail information matrix after the ith mask cycle processing;
wherein i is the number of cycles, GrayiIs a high-frequency Gray scale detail information matrix, Gray, after the ith Gaussian mask processingi-1Is a high-frequency Gray scale detail information matrix, Gray, after the i-1 Gauss mask processingg-(i-1)To Grayi-1High-frequency Gray level detail information matrix, Gray, after gaussian filtering0An initial high frequency Gray scale detail information matrix, Gray, obtained from the enhanced Gray scale matrix and the low frequency Gray scale matrixg-0To Gray0And (5) carrying out Gaussian filtering on the high-frequency gray level detail information matrix.
9. The method for detecting the microcrack defect of the aero-engine guide blade according to claim 7, wherein the cycle processing number of the multiple Gaussian mask cycle processing on the high-frequency gray scale detail information matrix is 2-3.
10. An aeroengine guide vane microcrack defect detection system, comprising:
the DR detection system is used for detecting the part to be detected of the guide blade of the aircraft engine to obtain a DR detection image;
the calculating unit is connected with the DR detection system and used for calculating an original gray matrix, a gray distribution histogram and a signal-to-noise ratio of the DR detection image;
the enhancement unit is connected with the calculation unit and used for enhancing the DR detection image according to the gray distribution histogram and the signal-to-noise ratio to obtain an enhanced gray matrix;
the mask unit is connected with the calculation unit and is used for performing mask processing on the original gray matrix to obtain a low-frequency gray matrix;
and the detail processing unit is respectively connected with the enhancing unit and the mask unit and is used for obtaining a high-frequency gray scale detail information matrix according to the enhancing gray scale matrix and the low-frequency gray scale matrix, and the high-frequency gray scale detail information matrix represents the microcrack defect condition of the part to be detected of the guide vane of the aircraft engine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110379197.4A CN113066072B (en) | 2021-04-08 | 2021-04-08 | Method and system for detecting microcrack defects of guide blade of aero-engine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110379197.4A CN113066072B (en) | 2021-04-08 | 2021-04-08 | Method and system for detecting microcrack defects of guide blade of aero-engine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113066072A true CN113066072A (en) | 2021-07-02 |
| CN113066072B CN113066072B (en) | 2023-06-06 |
Family
ID=76566289
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110379197.4A Active CN113066072B (en) | 2021-04-08 | 2021-04-08 | Method and system for detecting microcrack defects of guide blade of aero-engine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113066072B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114719749A (en) * | 2022-04-06 | 2022-07-08 | 重庆大学 | Metal surface crack detection and real size measurement method and system based on machine vision |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104134211A (en) * | 2014-07-23 | 2014-11-05 | 西安工程大学 | Band steel defect detection method based on multi-resolution filtering of Gaussian filter |
| CN106204478A (en) * | 2016-07-06 | 2016-12-07 | 电子科技大学 | The magneto optic images based on background noise feature space strengthens algorithm |
| US20170337686A1 (en) * | 2016-05-19 | 2017-11-23 | Sichuan University | Kind of x-ray chest image rib suppression method based on poisson model |
| CN109727233A (en) * | 2018-12-18 | 2019-05-07 | 武汉精立电子技术有限公司 | A kind of LCD defect inspection method |
| CN110118775A (en) * | 2019-05-10 | 2019-08-13 | 重庆交通大学 | Plantmix's cement stabilized macadam aggregate forms rapid detection method |
| CN110333267A (en) * | 2019-07-01 | 2019-10-15 | 武汉科技大学 | One kind being based on RSBSS Infrared Non-destructive Testing thermal imaging imperfection image processing method and system |
| CN111145144A (en) * | 2019-12-06 | 2020-05-12 | 西安理工大学 | Method for evaluating surface roughness of honing cylinder sleeve |
| CN112150437A (en) * | 2020-09-23 | 2020-12-29 | 南昌航空大学 | DR (digital radiography) detection image processing method for crack defects of diffuser in laser additive manufacturing |
-
2021
- 2021-04-08 CN CN202110379197.4A patent/CN113066072B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104134211A (en) * | 2014-07-23 | 2014-11-05 | 西安工程大学 | Band steel defect detection method based on multi-resolution filtering of Gaussian filter |
| US20170337686A1 (en) * | 2016-05-19 | 2017-11-23 | Sichuan University | Kind of x-ray chest image rib suppression method based on poisson model |
| CN106204478A (en) * | 2016-07-06 | 2016-12-07 | 电子科技大学 | The magneto optic images based on background noise feature space strengthens algorithm |
| CN109727233A (en) * | 2018-12-18 | 2019-05-07 | 武汉精立电子技术有限公司 | A kind of LCD defect inspection method |
| CN110118775A (en) * | 2019-05-10 | 2019-08-13 | 重庆交通大学 | Plantmix's cement stabilized macadam aggregate forms rapid detection method |
| CN110333267A (en) * | 2019-07-01 | 2019-10-15 | 武汉科技大学 | One kind being based on RSBSS Infrared Non-destructive Testing thermal imaging imperfection image processing method and system |
| CN111145144A (en) * | 2019-12-06 | 2020-05-12 | 西安理工大学 | Method for evaluating surface roughness of honing cylinder sleeve |
| CN112150437A (en) * | 2020-09-23 | 2020-12-29 | 南昌航空大学 | DR (digital radiography) detection image processing method for crack defects of diffuser in laser additive manufacturing |
Non-Patent Citations (2)
| Title |
|---|
| JEENA R S: "Contrast Enhancement for the detection of Stroke Signs in CT using PCA Based Image Fusion", 《COLLEGE OF ENGINEERING TRIVANDRUM》 * |
| 敖波: "2A50锻铝三点弯曲试验与高分辨率CT成像分析", 《材料工程》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114719749A (en) * | 2022-04-06 | 2022-07-08 | 重庆大学 | Metal surface crack detection and real size measurement method and system based on machine vision |
| CN114719749B (en) * | 2022-04-06 | 2023-07-14 | 重庆大学 | Metal surface crack detection and real size measurement method and system based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113066072B (en) | 2023-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112115895B (en) | Pointer type instrument reading identification method, pointer type instrument reading identification device, computer equipment and storage medium | |
| CN107657088B (en) | Rolling bearing fault diagnosis method based on MCKD algorithm and support vector machine | |
| CN106446809B (en) | The filtering method of aero-engine loading spectrum based on rain flow method | |
| CN113469951B (en) | Hub defect detection method based on cascade region convolutional neural network | |
| CN107369176B (en) | System and method for detecting oxidation area of flexible IC substrate | |
| CN111161224A (en) | Casting internal defect grading evaluation system and method based on deep learning | |
| CN112085734A (en) | GAN-based image restoration defect detection method | |
| CN111931601A (en) | System and method for correcting error class label of gear box | |
| CN114169377A (en) | G-MSCNN-based fault diagnosis method for rolling bearing in noisy environment | |
| CN113066072B (en) | Method and system for detecting microcrack defects of guide blade of aero-engine | |
| CN111553898A (en) | Fabric defect detection method based on convolutional neural network | |
| CN113139549A (en) | Parameter self-adaptive panorama segmentation method based on multitask learning | |
| CN117746077A (en) | Chip defect detection method, device, equipment and storage medium | |
| Lan et al. | PCB defect detection algorithm of improved YOLOv8 | |
| Chen et al. | A real-time detection system for multiscale surface defects of 3D printed ceramic parts based on deep learning | |
| CN116484258A (en) | Elevator traction machine bearing fault diagnosis method | |
| Hu et al. | Printed Circuit Board (PCB) Surface Micro Defect Detection Model Based on Residual Network with Novel Attention Mechanism. | |
| CN115689995A (en) | Circular hole edge sub-pixel level extraction method under complex illumination background condition | |
| CN112508862B (en) | Method for enhancing magneto-optical image of crack by improving GAN | |
| Zhang et al. | Quantitative nondestructive testing of broken wires for wire rope based on multi-image fusion | |
| CN114862796A (en) | A unmanned aerial vehicle for fan blade damage detects | |
| CN112508945A (en) | Nondestructive testing method for solid rocket engine based on computer vision | |
| CN113421212A (en) | Medical image enhancement method, device, equipment and medium | |
| CN113436163A (en) | Method for identifying and processing flow field characteristics of schlieren image in impeller mechanical blade lattice test | |
| CN112459970B (en) | Wind turbine generator anomaly detection method using data counterstudy |
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 |