CN115015270A - Near-surface defect on-wing detection method for aero-engine component based on hot air infrared - Google Patents
Near-surface defect on-wing detection method for aero-engine component based on hot air infrared Download PDFInfo
- Publication number
- CN115015270A CN115015270A CN202210577318.0A CN202210577318A CN115015270A CN 115015270 A CN115015270 A CN 115015270A CN 202210577318 A CN202210577318 A CN 202210577318A CN 115015270 A CN115015270 A CN 115015270A
- Authority
- CN
- China
- Prior art keywords
- defect
- infrared
- metal part
- aircraft engine
- infrared image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 180
- 238000001514 detection method Methods 0.000 title claims abstract description 131
- 239000002184 metal Substances 0.000 claims abstract description 88
- 238000000034 method Methods 0.000 claims abstract description 85
- 230000008569 process Effects 0.000 claims abstract description 68
- 230000000694 effects Effects 0.000 claims abstract description 35
- 238000012549 training Methods 0.000 claims abstract description 13
- 238000005457 optimization Methods 0.000 claims abstract description 11
- 238000013507 mapping Methods 0.000 claims abstract description 10
- 230000005284 excitation Effects 0.000 claims description 26
- 230000006870 function Effects 0.000 claims description 17
- 230000008859 change Effects 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000004088 simulation Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000001052 transient effect Effects 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 5
- 238000010438 heat treatment Methods 0.000 claims description 5
- 239000000463 material Substances 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 5
- 238000002474 experimental method Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 230000008878 coupling Effects 0.000 claims description 3
- 238000010168 coupling process Methods 0.000 claims description 3
- 238000005859 coupling reaction Methods 0.000 claims description 3
- 238000005315 distribution function Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000013077 scoring method Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims 3
- 238000004451 qualitative analysis Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 8
- 238000012423 maintenance Methods 0.000 description 5
- 239000002131 composite material Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 229920000049 Carbon (fiber) Polymers 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004917 carbon fiber Substances 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 238000007373 indentation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 1
- 239000012720 thermal barrier coating Substances 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N25/00—Investigating or analyzing materials by the use of thermal means
- G01N25/72—Investigating presence of flaws
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- 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
- G01N2021/8883—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 involving the calculation of gauges, generating models
-
- 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
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30136—Metal
-
- 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)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Software Systems (AREA)
- Pathology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Quality & Reliability (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Radiation Pyrometers (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention discloses a hot air infrared-based aeroengine component near-surface defect on-wing detection method, which comprises the following steps: acquiring an infrared image of an aircraft launching component and recording parameters; constructing a finite element model of a hot air forced convection aviation component, and acquiring surface temperature difference data of a defect area; constructing a mapping relation between the parameters and the maximum temperature difference of the surface of the defect area; evaluating the space-time characteristic information of the infrared image, and extracting defect characteristic information; constructing and training a comprehensive scoring model of the maximum temperature difference of the surface of the defect area, the defect characteristic information and the infrared detection effect, and carrying out parameter global optimization; and according to the optimal infrared detection process parameter combination, quickly and accurately detecting the metal part of the aero-engine to be maintained in practice. The method can efficiently realize the optimized control of the detection parameters, ensure the precision of infrared detection, improve the detection efficiency of the aircraft engine part containing the defects, and further realize the qualitative analysis and quantitative identification of the defects.
Description
Technical Field
The invention relates to the technical field of aircraft maintenance, in particular to a hot air infrared-based aeroengine component near-surface defect on-wing detection method.
Background
Due to the fact that the aero-engine runs under severe working environments such as high temperature, high pressure and high speed for a long time, the service performance of key parts is reduced, and damage phenomena may occur, for example, typical defects such as cracks, coating falling off, creep deformation, indentation and corrosion easily occur on the near surface of metal parts of the aero-engine. As the core of civil aircrafts, the task of timely observing the internal conditions of an aircraft engine and judging whether the internal conditions meet the airworthiness standard or not is important, if the internal conditions are not timely found and the aircraft engine continues to be in service, the efficiency of the aircraft engine is influenced, and in severe cases, component failure and fracture occur, so that flight safety accidents are possibly caused.
At present, for the defect detection of the near surface of a metal part of an aeroengine, the most common methods applied by domestic aviation maintenance enterprises are a hole detection method and a conventional nondestructive detection method, which are only suitable for visual defects, are easy to cause false detection and missing detection due to human factors, and cannot effectively ensure the detection efficiency and precision.
In recent years, the active infrared thermography detection technology is widely applied to nondestructive detection of aviation engine components, has strong field adaptability, and can quickly realize single large-area detection of the aviation engine components. At present, the carbon fiber composite material is detected by adopting a hot air infrared technology, but no system is used for carrying out hot air active infrared detection research on a metal part containing a thermal barrier coating. In summary, the on-site detection method of the aeroengine on the wing is not perfect enough, and an efficient and accurate method is urgently needed to realize the on-wing detection of the near-surface defects of the metal parts of the aeroengine.
Disclosure of Invention
The invention aims to make up for the defects of the prior art, and provides a hot air infrared-based aeroengine component near-surface defect on-wing detection method to solve the technical problems of high difficulty in detecting defects of metal components of in-service aeroengines and the like.
In order to solve the technical problems, the invention adopts the following technical scheme:
a near-surface defect on-wing detection method for an aircraft engine component based on hot air infrared comprises the following steps:
selecting aeroengine metal parts with different defect types, carrying out experiments to obtain infrared images of the aeroengine metal parts, and recording current infrared detection process parameters;
constructing a hot air forced convection heating aircraft engine metal part and an internal heat conduction process by adopting finite element simulation, collecting surface temperature difference data of a defect area, and fitting a temperature rule change relation;
constructing a mapping relation between the infrared detection process parameters and the maximum temperature difference of the surface of the defect area;
evaluating the spatiotemporal characteristic information of the infrared image through an evaluation function of a user-defined defect detection effect, and extracting defect characteristic information;
constructing and training a comprehensive grading model of the maximum temperature difference of the surface of the defect area, the defect characteristic information and the infrared detection effect by means of a GA-BP neural network, and carrying out global optimization on infrared detection process parameters to obtain an optimal infrared detection process parameter combination;
and according to the optimal infrared detection process parameter combination, quickly and accurately detecting the metal part of the aero-engine to be maintained in practice.
Further, the infrared detection process parameters comprise excitation parameters, material properties, defect characteristics and environmental factors, the excitation parameters comprise excitation temperature and excitation wind speed, the material properties comprise density of the metal part of the aircraft engine, thermal conductivity of the metal part of the aircraft engine and surface emissivity of the metal part of the aircraft engine, the defect characteristics comprise defect size and defect depth, and the environmental factors comprise detection environment temperature and detection environment humidity.
Further, the specific process of establishing the hot air forced convection heating aero-engine metal component and internal heat conduction process by adopting finite element simulation, acquiring surface temperature difference data of the defect area and fitting the temperature law change relationship comprises the following steps:
s201, constructing a finite element model of the metal part of the hot air forced convection aircraft engine, and analyzing a coupling mechanism of the heat wave acting on the surface of the metal part of the aircraft engine after the hot air is applied and the distribution condition of the transient temperature field in the metal part, wherein the finite element model is expressed as follows:
in the formula, q (x, y, z, t) is a hot air excitation function; α (x, y, z) is the thermal diffusivity of the metal part of the aircraft engine;energy for heat conduction inside metal parts of aircraft engines;the temperature change rate of the metal part of the aircraft engine; t (x, y, z, T) is the transient temperature field of the metal part of the aircraft engine; t is 0 (x, y, z,0) is the initial temperature of the metal part of the aircraft engine; λ (x, y, z) is the thermal conductivity of the metal part of the aircraft engine; k is the reflection coefficient of the defects of the metal parts of the aircraft engine to the heat waves, wherein the total reflection value is 1; h is the convective heat transfer coefficient; t is hot air excitation time;
s202, further simulating and simulating infrared detection process parameters and the surface temperature distribution rule of the metal part of the aircraft engine, comparing and analyzing simulation data with the infrared image acquired in the step S1, and correcting the finite element model, wherein the process is represented as follows:
wherein [ K ]]Is a conductive matrix; { T } is the temperature vector; [ C ]]Is a specific heat capacity matrix;is the temperature derivative over time, i.e. the rate of change of temperature with time; { Q } is the node heat flow vector; { β } is a correction coefficient of the model.
Further, the specific process of establishing the mapping relationship between the infrared detection process parameters and the maximum temperature difference of the surface of the defect area comprises the following steps:
in the formula: t is in Is the excitation temperature; f is the excitation wind speed; t is amk To detect ambient temperature; h amk To detect ambient humidity; phi is the defect diameter of the metal part of the aircraft engine; h is Deep to Is the defect depth of the metal part of the aircraft engine; ρ is the density of the metal part of the aircraft engine; λ is the thermal conductivity of the metal part of the aircraft engine; epsilon is the surface emissivity of the metal part of the aircraft engine; s max Maximum temperature difference of the surface of the defect region, S max Larger values of (a) indicate closer to ideal detection effects.
Further, the specific process of "evaluating the spatiotemporal feature information of the infrared image by customizing the evaluation function of the defect detection effect, and extracting the defect feature information" is as follows:
the defect characteristic information comprises a defect integrity degree P and a defect significance degree P T ;
The defect integrity P is evaluated by a proportional function of the bright spot area in the infrared image and the defect area in the visible image, and is expressed as:
in the formula: num is the total number of all pixel points in the bright spot area in the infrared image, which is not zero, namely navigationThe size of the defect area of the empty engine metal part; sum is the total number of all pixel points in the visible light image defect area, which is not zero; a is ij Pixel points in the thermal image defect area; b ij Pixel points in the visible light image defect area;
the defect integrity P is changed in the range of (0, 1), the numerical value of P is closer to 1, the integrity is higher, and the detection effect is better;
the defect integrity P evaluates a defect area in the infrared image, compares and judges whether the frame of infrared image meets a standard, and if P is more than 0.85 and less than or equal to 1, the frame of infrared image is reserved; if P is more than 0 and less than or equal to 0.85, discarding the frame of infrared image, and comparing the defect integrity of the adjacent frame of infrared image timing sequence until the infrared image timing sequence which best meets the defect integrity standard is found;
the area of the bright spots in the infrared image is the number of the pixel points in the defect area, and the temperature value of the pixel points in the infrared image exceeding T is counted avg Evaluating the defect significance P by a temperature probability distribution function T Expressed as:
P T =P[T ij ≥T avg ]=Num(T ij ≥T avg )/N
in the formula: t is ij The temperature values of all pixel points in the infrared image are obtained; t is avg The average temperature value of all pixel points in a non-bright spot area in the infrared image is obtained; and N is the total number of all pixel points of the infrared image.
Further, before the "evaluating the spatio-temporal feature information of the infrared image by the customized evaluation function of the defect detection effect and extracting the defect feature information", the denoising process is performed on the infrared image, and the processing process is as follows: carrying out graying processing, background noise reduction and detail enhancement on the infrared image; segmenting the infrared image to obtain a defect area and a non-defect area; and carrying out defect positioning through the defect area and the non-defect area in the infrared image.
Further, the specific process of establishing and training the maximum temperature difference of the surface of the defect area, the defect characteristic information and the comprehensive scoring model of the infrared detection effect by means of the GA-BP neural network to perform global optimization of the infrared detection process parameters and obtain the optimal infrared detection process parameter combination is as follows:
evaluating the detection effect by adopting a comprehensive weighting scoring method of percentage, and constructing a comprehensive scoring model of the maximum temperature difference of the surface of the defect area, the defect characteristic information and the infrared detection effect, wherein the comprehensive scoring model is expressed as follows:
Y=(w 1 S+w 2 P T +w 3 P)×100%
in the formula: y is infrared detection effect comprehensive score; w is a 1 、w 2 、w 3 Respectively the maximum temperature difference S of the surface of the defect region max Defect significance P T The proportion weight of the defect integrity P;
the comprehensive scoring model is constructed and trained by using a GA-BP neural network, a network structure is determined and a weight and a threshold are initialized, a fitness function is determined after encoding and initializing a population, global parameter optimization is carried out, an optimal weight and a threshold are obtained after decoding the weight and the threshold, the correctness of the comprehensive scoring model is evaluated according to network training errors, an optimal infrared detection process parameter combination corresponding to the optimal comprehensive scoring is finally output, the optimal infrared detection process parameter combination under the current detection condition is loaded into a detection system and data storage is carried out, and the subsequent detection work is conveniently carried out.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the method provided by the invention, hot air active infrared detection research is fused with a machine learning algorithm, and infrared detection process parameters can be accurately controlled so as to quickly and accurately achieve the optimal detection effect.
2. The method provided by the invention can efficiently realize the optimized control of the detection parameters, ensure the precision of infrared detection, improve the detection efficiency of the metal parts of the aeroengine with the defects, and further realize the qualitative analysis and quantitative identification of the defects.
3. The method provided by the invention can be used for efficiently detecting the defects generated in the service process of the metal parts of the aircraft engine, providing accurate and powerful technical support and providing practical value for engineering application.
Drawings
In order that the advantages of the invention will be readily understood, a more particular description of the invention briefly described above will be rendered by reference to specific embodiments that are illustrated in the appended drawings. Understanding that these drawings depict only typical embodiments of the invention and are not therefore to be considered to be limiting of its scope, the invention will be described and explained with additional specificity and detail through the use of the accompanying drawings.
FIG. 1 is a flow chart of a hot air infrared-based method for detecting near-surface defects of an aircraft engine component on a wing according to an embodiment of the invention;
FIG. 2 is a schematic diagram of the infrared image denoising processing and defect feature extraction process in the embodiment of the present invention;
FIG. 3 is a diagram of a neural network model for inputting IR testing process parameters and outputting IR testing result composite scores according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a genetic algorithm training process in a network model according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a process of training and constructing a mapping relationship between infrared detection process parameters and infrared detection effect comprehensive scores by using a neural network in an embodiment of the present invention;
FIG. 6 is a diagram illustrating the result of the error in the hot-air active infrared detection parameter neural network model training in the embodiment of the present invention;
FIG. 7 is a diagram of a fitness function iterative optimization-based optimal composite score result of a hot-blast active infrared detection parameter model according to an embodiment of the present invention;
fig. 8 is a detection result graph before and after optimization of detection parameters in the application example of the present invention.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the present invention. It will be apparent, however, to one skilled in the art, that embodiments of the invention may be practiced without one or more of these specific details. In other instances, well-known features have not been described in detail so as not to obscure the embodiments of the invention.
In the following description, a detailed structure will be presented for a thorough understanding of embodiments of the invention. It is apparent that the implementation of the embodiments of the present invention is not limited to the specific details familiar to those skilled in the art. The following detailed description of preferred embodiments of the invention, however, the invention is capable of other embodiments in addition to those detailed.
Examples
Embodiments of the invention are described in further detail below with reference to the accompanying drawings:
as shown in FIG. 1, the embodiment of the invention provides a hot air infrared-based aeroengine component near-surface defect on-wing detection method, which comprises the following steps:
s1, selecting aeroengine metal parts with different defect types, carrying out experiments to obtain infrared images of the aeroengine metal parts, and recording current infrared detection process parameters.
In the present embodiment, the specific process of step S1 is as follows:
s101, before collection, calibrating a high-performance thermal infrared imager to eliminate interference of equipment factors, and powering on an infrared detection system.
S102, collecting and recording metal parts of the aircraft engine by using a high-performance thermal infrared imager, analyzing infrared detection process parameters and temperature field distribution, obtaining temperature field information according to an original infrared image, and further evaluating the maximum temperature difference of the surface of the defect.
In this embodiment, the infrared detection process parameters include excitation parameters, material properties, defect characteristics, and environmental factors, the excitation parameters include excitation temperature and excitation wind speed, the material properties include density of the aircraft engine metal part, thermal conductivity of the aircraft engine metal part, and surface emissivity of the aircraft engine metal part, the defect characteristics include defect size and defect depth, and the environmental factors include detection ambient temperature and detection ambient humidity.
S2, constructing a hot air forced convection heating aircraft engine metal part and an internal heat conduction process by adopting finite element simulation, collecting surface temperature difference data of a defect area, and fitting a temperature rule change relation.
In the present embodiment, the specific process of step S2 is as follows:
s201, constructing a finite element model of the metal part of the hot air forced convection aircraft engine, and analyzing a coupling mechanism of the heat wave acting on the surface of the metal part of the aircraft engine after the hot air is applied and the distribution condition of the transient temperature field in the metal part, wherein the finite element model is expressed as follows:
in the formula, q (x, y, z, t) is a hot air excitation function; α (x, y, z) is the thermal diffusivity of the metal part of the aircraft engine;energy for heat conduction inside metal parts of aircraft engines;the temperature change rate of the metal part of the aircraft engine; t (x, y, z, T) is the transient temperature field of the metal part of the aircraft engine; t is 0 (x, y, z,0) is the initial temperature of the metal part of the aircraft engine; λ (x, y, z) is the thermal conductivity of the metal part of the aircraft engine; k is the reflection coefficient of the defects of the metal parts of the aircraft engine to the heat waves, wherein the total reflection value is 1; h is the convective heat transfer coefficient; t is hot air excitation time.
S202, further simulating and simulating infrared detection process parameters and the surface temperature distribution rule of the metal part of the aircraft engine, comparing and analyzing simulation data with the infrared image acquired in the step S1, and correcting a finite element model, wherein the finite element model is expressed as:
wherein [ K ]]Is a conductive matrix; { T } is the temperature vector; [ C ]]Is a specific heat capacity matrix;is the temperature derivative over time, i.e. the rate of change of temperature with time; { Q } is the node heat flow vector; { β } is a correction coefficient of the model.
S3, constructing a mapping relation between the infrared detection process parameters and the maximum temperature difference of the surface of the defect area, as shown in figure 3.
In the present embodiment, the specific process of step S3 is as follows:
in the formula: t is in Is the excitation temperature; f is the excitation wind speed; t is amk To detect ambient temperature; h amk To detect ambient humidity; phi is the defect diameter of the metal part of the aircraft engine; h is Deep to Is the defect depth of the metal part of the aircraft engine; ρ is the density of the metal part of the aircraft engine; lambda is the coefficient of thermal conductivity of the metal part of the aircraft engine; epsilon is the surface emissivity of the metal part of the aircraft engine; s max Maximum temperature difference of the surface of the defect region, S max Larger values of (a) indicate closer to ideal detection effects.
And S4, evaluating the spatio-temporal characteristic information of the infrared image through self-defining an evaluation function of the defect detection effect, and extracting the defect characteristic information.
In the present embodiment, the specific process of step S4 is as follows:
s401, first, perform noise reduction processing on the infrared image, as shown in fig. 2, the processing procedure is as follows: carrying out graying processing, background noise reduction and detail enhancement on the infrared image; segmenting the infrared image to obtain a defect area and a non-defect area; and carrying out defect positioning on a defect area and a non-defect area in the infrared image, and evaluating the area of the bright spot in the infrared image according to the defect significance.
S402, extracting defect characteristic information, wherein the defect characteristic information comprises a defect integrity degree P and a defect significance degree P T 。
Defect integrity P: the defect integrity P is evaluated by a proportional function of the bright spot area in the infrared image and the defect area in the visible image, and is expressed as:
in the formula: num is the total number of all pixel points in the bright spot area in the infrared image, which is not zero, and is the defect area size of the metal part of the aircraft engine; sum is the total number of all pixel points in the visible light image defect area, which is not zero; a is ij Pixel points in the thermal image defect area; b ij The pixel points of the visible light image defect area.
The defect integrity P evaluates a defect area in the infrared image, compares and judges whether the infrared image of the frame meets the standard or not, if the defect integrity P is larger than 0.85 and smaller than 1 (note: 1 indicates that the size and the edge of the defect in the infrared image are completely consistent with the size and the edge of the real defect), the infrared image of the frame is reserved, if the defect integrity P is larger than 0 and smaller than 0.85, the infrared image of the frame is discarded, the defect integrity of the infrared image timing diagram of the adjacent frame is compared until the infrared image timing diagram which best meets the defect integrity standard is found, and each step of the process is prepared for optimizing detection process parameters.
Significance of defect P T : the number of the pixel points in the defect area is determined as the area of the bright spot in the infrared image, and the temperature value of the pixel points in the infrared image exceeding T is counted avg Evaluating the defect significance P by a temperature probability distribution function T Expressed as:
P T =P[T ij ≥T avg ]=Num(T ij ≥T avg )/N
in the formula: t is a unit of ij The temperature values of all pixel points in the infrared image are obtained; t is avg For non-bright spot areas in infrared imageAverage temperature values of all pixel points; and N is the total number of all pixel points of the infrared image.
S5, constructing and training a comprehensive scoring model of the maximum temperature difference of the surface of the defect area, the defect characteristic information and the infrared detection effect by means of a GA-BP neural network, performing global optimization on infrared detection process parameters, and obtaining the optimal infrared detection process parameter combination, as shown in FIG. 5.
In this embodiment, the specific process of step S5 is as follows:
s501, constructing a comprehensive scoring model: in order to achieve a better infrared detection effect, a comprehensive weighting scoring method of percentage is adopted to evaluate the detection effect, and the higher and more stable comprehensive scoring indicates that the infrared detection effect is better. Specifically, a comprehensive scoring model of the maximum temperature difference of the surface of the defect area, the defect characteristic information and the infrared detection effect is constructed, and the comprehensive scoring model is expressed as follows:
Y=(w 1 S+w 2 P T +w 3 P)×100%
in the formula: y is infrared detection effect comprehensive score; w is a 1 、w 2 、w 3 Respectively the maximum temperature difference S of the surface of the defect region max Defect significance P T And the proportion weight of the defect integrity P.
S502, a comprehensive scoring model is constructed and trained by using a GA-BP neural network, a network structure is determined, a weight and a threshold value are initialized, a fitness function is determined after a population is encoded and initialized, global parameter optimization is carried out, and an optimal weight and a threshold value are obtained after the weight and the threshold value are decoded, as shown in FIG. 4. And evaluating the correctness of the comprehensive scoring model according to the network training error, finally outputting the optimal infrared detection process parameter combination corresponding to the optimal comprehensive scoring, loading the optimal infrared detection process parameter combination under the current detection condition into a detection system and storing data, so as to facilitate the subsequent detection work, as shown in fig. 6.
And S6, according to the optimal infrared detection process parameter combination, quickly and accurately detecting the metal part of the aero-engine to be maintained in practice.
In the present embodiment, the specific process of step S6 is as follows: the method comprises the steps of performing infrared detection on invisible near-surface defects of the metal part of the aero-engine in an outfield maintenance environment, performing infrared detection according to the optimal infrared detection process parameter combination, performing comparative analysis on infrared detection effect comprehensive grading, and achieving efficient and accurate detection on the near-surface defects of the metal part of the aero-engine, as shown in fig. 7.
Application example
In order to verify the infrared detection effect after the detection parameters are optimized, the detection work of the RB211-22B three-rotor turbofan engine blade cracks is carried out in an engine maintenance workshop. According to the optimal detection parameter combination: excitation temperature T 1 Excitation wind speed F 1 Excitation time t 1 And repeating the infrared detection experiment for 3 times, and calculating the comprehensive score Y of the infrared detection effect of the aviation blade by normalizing the maximum surface temperature difference, the defect significance and the defect integrity of the aviation blade 1 。
The infrared detection result of the near-surface crack of the aviation blade is shown in fig. 8. Fine hot spots on the surface of the aircraft blade can be observed, and a heat generation area is mainly concentrated at the tip of the crack close to the middle position and is transmitted to the periphery.
According to the method provided by the invention, the temperature field information of the defects of the metal parts of the aircraft engine can be acquired through the infrared image, the maximum temperature difference of the surface is evaluated by using the temperature distribution data, the optimal parameter combination under the current detection condition can be quickly found by adopting a standard high-level programming language and constructing a comprehensive grading model of hot air infrared detection process parameters and the defect detection effect, a reference is provided for the selection of the detection parameters of the metal parts of the aircraft engine in a subsequent outfield maintenance workshop, meanwhile, the detection efficiency of the metal parts of the aircraft engine with the defects is greatly improved on the premise of ensuring the detection precision, and the qualitative analysis and the quantitative identification of the defects are further realized.
In summary, the present invention is not limited to the above-mentioned embodiments, and those skilled in the art can propose other embodiments within the technical teaching of the present invention, but these embodiments are included in the scope of the present invention.
Claims (7)
1. A near-surface defect on-wing detection method for an aircraft engine component based on hot air infrared is characterized by comprising the following steps:
selecting aeroengine metal parts with different defect types, carrying out experiments to obtain infrared images of the aeroengine metal parts, and recording current infrared detection process parameters;
constructing a hot air forced convection heating aero-engine metal part and an internal heat conduction process by adopting finite element simulation, collecting surface temperature difference data of a defect area, and fitting a temperature rule change relation;
constructing a mapping relation between the infrared detection process parameters and the maximum temperature difference of the surface of the defect area;
evaluating the spatiotemporal characteristic information of the infrared image through an evaluation function of a user-defined defect detection effect, and extracting defect characteristic information;
constructing and training a comprehensive grading model of the maximum temperature difference of the surface of the defect area, the defect characteristic information and the infrared detection effect by means of a GA-BP neural network, and carrying out global optimization on infrared detection process parameters to obtain an optimal infrared detection process parameter combination;
and according to the optimal infrared detection process parameter combination, quickly and accurately detecting the metal part of the aero-engine to be maintained in practice.
2. The method of claim 1, wherein the infrared inspection process parameters include excitation parameters including excitation temperature and excitation wind speed, material properties including density of the aircraft engine metal part, thermal conductivity of the aircraft engine metal part, and surface emissivity of the aircraft engine metal part, defect characteristics including defect size and defect depth, and environmental factors including inspection ambient temperature and inspection ambient humidity.
3. The method according to claim 1, wherein the specific process of establishing the hot air forced convection heating aircraft engine metal component and internal heat conduction process by adopting finite element simulation, collecting surface temperature difference data of the defect area and fitting the temperature law change relationship comprises the following steps:
s201, constructing a finite element model of the metal part of the hot air forced convection aircraft engine, and analyzing a coupling mechanism of the heat wave acting on the surface of the metal part of the aircraft engine after the hot air is applied and the distribution condition of the transient temperature field in the metal part, wherein the finite element model is expressed as follows:
wherein q (x, y, z, t) is a hot air excitation function; α (x, y, z) is the thermal diffusivity of the metal part of the aircraft engine;energy for heat conduction inside metal parts of aircraft engines;the temperature change rate of the metal part of the aircraft engine; t (x, y, z, T) is the transient temperature field of the metal part of the aircraft engine; t is 0 (x, y, z,0) is the initial temperature of the metal part of the aircraft engine; λ (x, y, z) is the thermal conductivity of the metal part of the aircraft engine; k is a reflection coefficient of the defects of the metal parts of the aero-engine to the heat waves, wherein the total reflection value is 1; h is the convective heat transfer coefficient; t is hot air excitation time;
s202, further simulating and simulating infrared detection process parameters and the surface temperature distribution rule of the metal part of the aircraft engine, comparing and analyzing simulation data with the infrared image acquired in the step S1, and correcting the finite element model, wherein the process is represented as follows:
4. The method according to claim 3, wherein the specific process of constructing the mapping relationship between the infrared detection process parameter and the maximum temperature difference of the surface of the defect region is as follows:
in the formula: t is in Is the excitation temperature; f is the excitation wind speed; t is amk To detect ambient temperature; h amk To detect ambient humidity; phi is the defect diameter of the metal part of the aircraft engine; h is Deep to Is the defect depth of the metal part of the aircraft engine; ρ is the density of the metal part of the aircraft engine; λ is the thermal conductivity of the metal part of the aircraft engine; epsilon is the surface emissivity of the metal part of the aircraft engine; s max Maximum temperature difference of the surface of the defect region, S max Larger values of (a) indicate closer to ideal detection effects.
5. The method according to claim 4, wherein the specific process of evaluating the spatiotemporal feature information of the infrared image by the customized evaluation function of the defect detection effect and extracting the defect feature information is as follows:
the defect characteristic information comprises a defect integrity degree P and a defect significance degree P T ;
The defect integrity P is evaluated by a proportional function of the bright spot area in the infrared image and the defect area in the visible image, and is expressed as:
in the formula: num is the total number of all pixel points in the bright spot area in the infrared image, which is not zero, and is the defect area size of the metal part of the aircraft engine; sum is the total number of all pixel points in the visible light image defect area, which is not zero; a is ij Pixel points in the thermal image defect area; b ij Pixel points in the visible light image defect area;
the defect integrity P is changed in the range of (0, 1), the numerical value of P is closer to 1, the integrity is higher, and the detection effect is better;
the defect integrity P evaluates a defect area in the infrared image, compares and judges whether the frame of infrared image meets a standard, and if P is more than 0.85 and less than or equal to 1, the frame of infrared image is reserved; if P is more than 0 and less than or equal to 0.85, discarding the frame of infrared image, and comparing the defect integrity of the adjacent frame of infrared image timing sequence until the infrared image timing sequence which best meets the defect integrity standard is found;
the area of the bright spots in the infrared image is the number of the pixel points in the defect area, and the temperature value of the pixel points in the infrared image exceeding T is counted avg Evaluating the defect significance P by a temperature probability distribution function T Expressed as:
P T =P[[T ij ≥T avg ]=Num(T ij ≥T avg )/N
in the formula: t is ij The temperature values of all pixel points in the infrared image are obtained; t is a unit of avg The average temperature value of all pixel points in a non-bright spot area in the infrared image is obtained; and N is the total number of all pixel points of the infrared image.
6. The method according to claim 5, wherein before said "evaluating spatio-temporal feature information of said infrared image by self-defining evaluation function of defect detection effect, extracting defect feature information" further performing noise reduction processing on said infrared image, the processing procedure is as follows: carrying out graying processing, background noise reduction and detail enhancement on the infrared image; segmenting the infrared image to obtain a defect area and a non-defect area; and carrying out defect positioning through the defect area and the non-defect area in the infrared image.
7. The method according to claim 5 or 6, wherein the specific process of establishing and training a comprehensive scoring model of the maximum temperature difference of the surface of the defect area, the defect characteristic information and the infrared detection effect by means of a GA-BP neural network to perform global optimization of the infrared detection process parameters and obtain the optimal infrared detection process parameter combination is as follows:
evaluating the detection effect by adopting a comprehensive weighting scoring method of percentage, and constructing a comprehensive scoring model of the maximum temperature difference of the surface of the defect area, the defect characteristic information and the infrared detection effect, wherein the comprehensive scoring model is expressed as follows:
Y=(w 1 S+w 2 P T +w 3 P)×100%
in the formula: y is the infrared detection effect comprehensive score; w is a 1 、w 2 、w 3 Respectively the maximum temperature difference S of the surface of the defect region max Defect significance P T The proportion weight of the defect integrity P;
and constructing and training the comprehensive grading model by using a GA-BP neural network, determining a network structure, initializing a weight and a threshold, encoding and initializing a population, determining a fitness function, performing global parameter optimization, decoding the weight and the threshold to obtain an optimal weight and a threshold, evaluating the correctness of the comprehensive grading model according to a network training error, finally outputting an optimal infrared detection process parameter combination corresponding to the optimal comprehensive grading, loading the optimal infrared detection process parameter combination under the current detection condition into a detection system, and storing data, thereby facilitating the subsequent detection work.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210577318.0A CN115015270A (en) | 2022-05-25 | 2022-05-25 | Near-surface defect on-wing detection method for aero-engine component based on hot air infrared |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210577318.0A CN115015270A (en) | 2022-05-25 | 2022-05-25 | Near-surface defect on-wing detection method for aero-engine component based on hot air infrared |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115015270A true CN115015270A (en) | 2022-09-06 |
Family
ID=83068520
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210577318.0A Pending CN115015270A (en) | 2022-05-25 | 2022-05-25 | Near-surface defect on-wing detection method for aero-engine component based on hot air infrared |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115015270A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111721810A (en) * | 2020-07-09 | 2020-09-29 | 中国民航大学 | Turbine blade defect infrared detection system of fusion constant temperature heating cabinet |
CN115372412A (en) * | 2022-10-24 | 2022-11-22 | 北京汉飞航空科技有限公司 | Characteristic measurement method for turbine blade based on six-point positioning |
CN116501001A (en) * | 2023-06-27 | 2023-07-28 | 江苏宝孚克新能源科技有限公司 | Flexible aluminum alloy cable production process optimization control method and system |
CN116563280A (en) * | 2023-07-07 | 2023-08-08 | 深圳市鑫典金光电科技有限公司 | Composite copper heat dissipation bottom plate processing detection method and system based on data analysis |
-
2022
- 2022-05-25 CN CN202210577318.0A patent/CN115015270A/en active Pending
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111721810A (en) * | 2020-07-09 | 2020-09-29 | 中国民航大学 | Turbine blade defect infrared detection system of fusion constant temperature heating cabinet |
CN115372412A (en) * | 2022-10-24 | 2022-11-22 | 北京汉飞航空科技有限公司 | Characteristic measurement method for turbine blade based on six-point positioning |
CN115372412B (en) * | 2022-10-24 | 2023-01-10 | 北京汉飞航空科技有限公司 | Characteristic measurement method for turbine blade based on six-point positioning |
CN116501001A (en) * | 2023-06-27 | 2023-07-28 | 江苏宝孚克新能源科技有限公司 | Flexible aluminum alloy cable production process optimization control method and system |
CN116501001B (en) * | 2023-06-27 | 2023-09-05 | 江苏宝孚克新能源科技有限公司 | Flexible aluminum alloy cable production process optimization control method and system |
CN116563280A (en) * | 2023-07-07 | 2023-08-08 | 深圳市鑫典金光电科技有限公司 | Composite copper heat dissipation bottom plate processing detection method and system based on data analysis |
CN116563280B (en) * | 2023-07-07 | 2023-09-12 | 深圳市鑫典金光电科技有限公司 | Composite copper heat dissipation bottom plate processing detection method and system based on data analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115015270A (en) | Near-surface defect on-wing detection method for aero-engine component based on hot air infrared | |
Gao et al. | Physics-based image segmentation using first order statistical properties and genetic algorithm for inductive thermography imaging | |
Goranson | Fatigue issues in aircraft maintenance and repairs | |
CN112766103B (en) | Machine room inspection method and device | |
Thompson | A unified approach to the model‐assisted determination of probability of detection | |
CN109459286A (en) | Real-time detection method is damaged in a kind of thermal barrier coating of turbine blade simulation test procedure | |
Jiang et al. | A method of predicting visual detectability of low-velocity impact damage in composite structures based on logistic regression model | |
Zhao et al. | A coefficient clustering analysis for damage assessment of composites based on pulsed thermographic inspection | |
CN114677362B (en) | Surface defect detection method based on improved YOLOv5 | |
Grooteman | A stochastic approach to determine lifetimes and inspection schemes for aircraft components | |
Ostash et al. | Evaluation of aluminium alloys degradation in aging aircraft | |
Wang et al. | Application of unsupervised adversarial learning in radiographic testing of aeroengine turbine blades | |
Vittal et al. | Review of approaches to gas turbine life management | |
CN116825243B (en) | Multi-source data-based thermal barrier coating service life prediction method and system | |
Dabetwar et al. | Performance evaluation of deep learning algorithms for heat loss damage classification in buildings from UAV-borne infrared images | |
Lindgren | US Air Force perspective on validated NDE–Past, present, and future | |
Tu et al. | Distance Effect in Transient Thermography for Internal Defects Detection in Composites | |
Schworer et al. | Newton-raphson versus fisher scoring algorithms in calculating maximum likelihood estimates | |
CN115471453A (en) | Power equipment fault diagnosis method based on image processing | |
Ehtisham et al. | Predicting the defects in wooden structures by using pre-trained models of Convolutional Neural Network and Image Processing | |
CN114970675A (en) | Artificial nose refrigerator food freshness detection system and method based on feature selection | |
CN113884538A (en) | Infrared thermal image detection method for micro defects in large wind turbine blade | |
Tian et al. | A statistical framework for improved automatic flaw detection in nondestructive evaluation images | |
Pilet et al. | A building envelope characterization workflow for in-situ thermal performance assessment | |
Lindgren | SHM reliability and implementation–A personal military aviation perspective |
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 |