A high temperature endoscopy observation and evaluation method for gas turbine blades

Abstract

The invention discloses a high-temperature endoscopic observation and evaluation method for gas turbine blades, and specifically relates to the field of blade endoscopic observation. The method ensures the authenticity of blade image information by performing thermal radiation interference analysis on endoscopic images collected in a high-temperature environment; performs medium refractive index change analysis on corrected blade image data to evaluate the optical distortion of the blade image; determines whether the blade image meets the requirements for extracting surface defect features of the blade according to the authenticity and optical distortion of the blade image data; performs surface defect feature analysis on the distortion-compensated blade image data to identify and evaluate the severity of cracks, wear and corrosion; performs a comprehensive analysis on the authenticity of the image data, the optical distortion of the image data and the severity of the defects of the image data to determine the health status of the gas turbine blade, thereby achieving accurate evaluation of the blade, providing a reliable basis for the maintenance of the gas turbine and improving the safety of the gas turbine.

Description

Technical Field

[0001] The present invention relates to the field of blade endoscope observation, and more particularly to a high-temperature endoscope observation and evaluation method for gas turbine blades. Background Art

[0002] With the development of modern industry, gas turbines have become important power devices in the fields of aerospace, electric power, and petrochemicals. The blades of gas turbines run for a long time in a high-temperature environment and are easily affected by factors such as high temperature, stress, corrosion, and wear, resulting in defects such as cracks, wear, and corrosion on the surface, which seriously affect the performance and safety of the gas turbine. Traditional gas turbine blade inspection mainly relies on manual inspection and external inspection equipment after shutdown, and it is difficult to conduct real-time and accurate health status assessment of the blades during operation. High-temperature environments will produce thermal radiation interference and optical distortion, making it difficult for traditional inspection methods to accurately judge the defect characteristics of the blade surface, resulting in misjudgment or missed judgment, which in turn affects the normal operation and safety of the turbine. Summary of the invention

[0003] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a high-temperature endoscopic observation and evaluation method for a gas turbine blade to solve the problems raised in the above-mentioned background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A high temperature endoscopy observation and evaluation method for a gas turbine blade comprises the following steps:

[0006] Step S1: Performing thermal radiation interference analysis on the endoscopic image collected in a high temperature environment to evaluate the authenticity of the blade image data;

[0007] Step S2: analyzing the change of medium refractive index on the corrected blade image data to evaluate the degree of optical distortion of the blade image data;

[0008] Step S3: judging whether the requirements for extracting blade surface defect features are met based on the authenticity and optical distortion of the blade image data;

[0009] Step S4: when the requirements for extracting blade surface defect features are met, performing blade surface defect feature analysis on the distortion-compensated blade image data to evaluate the severity of defects in the blade image data;

[0010] Step S5: Comprehensively analyze the authenticity of the blade image data, the optical distortion of the blade image data, and the severity of defects in the blade image data to determine the health status of the gas turbine blade.

[0011] In a preferred embodiment, in step S1: an image authenticity coefficient is defined to evaluate the authenticity of the blade image data, and the expression of the image authenticity coefficient is: ;

[0012] in, represents the image authenticity coefficient; and Represent the number of rows and columns of the image matrix respectively; Represents the image brightness difference matrix before and after correction; , Represent the row and column coordinates of the image respectively;

[0013] Image brightness difference matrix before and after correction It is calculated by the normalized image brightness and the corrected image brightness, and the expression is: ;

[0014] in, Represents the brightness of the image after correction; Represents the brightness of the normalized image.

[0015] In a preferred embodiment, in step S2: the optical distortion coefficient is calculated by the brightness difference and refractive index change of the image, and the expression of the optical distortion coefficient is: ;

[0016] in, represents the optical distortion coefficient; Indicates the change of refractive index of gas medium; represents the image coordinate number of the blade image data matrix obtained after thermal radiation interference correction, ; represents the total number of image coordinates of the blade image data matrix obtained after thermal radiation interference correction; Indicates at location The brightness of the leaf image after thermal radiation interference correction; Indicates at location The actual brightness of the leaf image is obtained through experiments or reference data.

[0017] In a preferred embodiment, in step S3: a threshold value of the image authenticity coefficient is set, and the image authenticity coefficient is compared with the image authenticity coefficient threshold value:

[0018] When the image authenticity coefficient is greater than or equal to the image authenticity coefficient threshold, it means that the image can accurately reflect the actual state of the blade and has a high authenticity;

[0019] When the image authenticity coefficient is less than the image authenticity coefficient threshold, it means that there is a significant difference between the corrected image data and the actual condition of the blade surface, and the authenticity of the blade image data is poor;

[0020] Set the optical distortion coefficient threshold and compare the optical distortion coefficient with the optical distortion coefficient threshold:

[0021] When the optical distortion coefficient is greater than or equal to the optical distortion coefficient threshold, it indicates that the leaf image has high optical distortion;

[0022] When the optical distortion coefficient is less than the optical distortion coefficient threshold, it indicates that the optical distortion degree of the leaf image is low;

[0023] When the image authenticity coefficient is greater than or equal to the image authenticity coefficient threshold, and the optical distortion coefficient is less than the optical distortion coefficient threshold, it indicates that the blade image data meets the requirements for extracting blade surface defect features.

[0024] In a preferred embodiment, in step S4: the crack length, the wear area and the corrosion depth are normalized, and the defect severity coefficient is calculated according to the normalized crack length, the wear area and the corrosion depth. The expression of the defect severity coefficient is: ;

[0025] in, Indicates the defect severity coefficient; , , Respectively represent the normalized crack length, wear area and corrosion depth; , , Defect severity scores representing crack length, wear area, and corrosion depth, respectively.

[0026] In a preferred embodiment, in step S5: the image authenticity coefficient corresponding to the authenticity of the image data, the optical distortion coefficient corresponding to the optical distortion of the image data, and the defect severity coefficient corresponding to the defect severity of the image data are normalized, and proportional coefficients are preset for the normalized image authenticity coefficient, optical distortion coefficient, and defect severity coefficient, respectively, to calculate the health status index of the gas turbine blade, specifically: ;

[0027] in, Indicates the health status index of gas turbine blades; represents the image authenticity coefficient; represents the optical distortion coefficient; Indicates the defect severity coefficient; , , Preset proportional coefficients representing image authenticity coefficient, optical distortion coefficient and defect severity coefficient respectively;

[0028] Set a health status index threshold and compare the health status index with the health status index threshold:

[0029] When the health status index is greater than or equal to the health status index threshold, it is determined that the health status of the gas turbine blade is good;

[0030] When the health status index is less than the health status index threshold, it is determined that the health status of the gas turbine blade is poor.

[0031] Technical effects and advantages of the method of the present invention:

[0032] By analyzing the thermal radiation interference of the endoscopic images collected in a high-temperature environment, the authenticity of the blade image data can be effectively evaluated to ensure that the acquired blade image can accurately reflect the actual state of the blade. The medium refractive index change analysis is performed on the corrected blade image data to evaluate the optical distortion of the blade image data and further correct the optical distortion caused by the high-temperature environment. According to the authenticity and optical distortion of the image data, it is judged whether it meets the requirements for extracting the defect characteristics of the blade surface; when the image meets the requirements for extracting the defect characteristics of the blade surface, the defect characteristics of cracks, wear and corrosion on the blade surface are analyzed to help evaluate the actual damage degree of the blade. The authenticity of the image data, the optical distortion of the image data and the severity of the defects of the image data are comprehensively analyzed to calculate the health status index of the blade, provide a scientific basis for blade maintenance decisions, and warn of potential damage to the blade in advance, which greatly improves the operating efficiency and safety of the gas turbine, extends the service life of the blade, and provides a reliable technical guarantee for the safe operation of the gas turbine. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A schematic diagram of a high-temperature endoscopic observation and evaluation method for a gas turbine blade according to the present invention; DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] Reference Figure 1 .

[0036] The embodiment provides a high temperature endoscopic observation and evaluation method for a gas turbine blade of the present invention, which comprises the following steps:

[0037] Step S1: Performing thermal radiation interference analysis on the endoscopic image collected in a high temperature environment to evaluate the authenticity of the blade image data;

[0038] Step S2: analyzing the change of medium refractive index on the corrected blade image data to evaluate the degree of optical distortion of the blade image data;

[0039] Step S3: judging whether the requirements for extracting blade surface defect features are met based on the authenticity and optical distortion of the blade image data;

[0040] Step S4: when the requirements for extracting blade surface defect features are met, performing blade surface defect feature analysis on the distortion-compensated blade image data to evaluate the severity of defects in the blade image data;

[0041] Step S5: Comprehensively analyze the authenticity of the blade image data, the optical distortion of the blade image data, and the severity of defects in the blade image data to determine the health status of the gas turbine blade.

[0042] In step S1: In a high temperature environment, the surface of the gas turbine blade will be affected by high temperature radiation during operation, generating a large amount of heat energy, causing the brightness of the image collected by the endoscope to be distorted. Thermal radiation will affect the authenticity of the blade image, causing blurring and loss of detail information, and failing to accurately reflect the actual state of the blade.

[0043] Thermal radiation interference analysis is performed on endoscopic images collected in high temperature environments to evaluate the authenticity of blade image data, specifically:

[0044] In the high temperature environment of gas turbine operation, the image data of the blade surface is collected through a high temperature endoscope. The high temperature endoscope lens needs to be able to withstand high temperatures and work normally in an operating environment exceeding 1200°C. The clarity of the blade image is ensured by selecting a high-resolution sensor. The blade image acquisition frequency is generally set to 30 frames per second to ensure that sufficient image data is obtained in a dynamic high temperature environment.

[0045] The collected leaf image data is represented by a matrix, and each element in the matrix Representative position The brightness value of the pixel at , Represent the row and column coordinates of the image respectively. The size of the image matrix is ;in and Represent the number of rows and columns of the image matrix respectively.

[0046] Preprocess the collected leaf images to reduce the impact of noise, including:

[0047] A Gaussian filter is used to denoise the original image, smooth the high-frequency noise caused by the sensor and the environment, and obtain the brightness of the denoised image.

[0048] The image is normalized to obtain the normalized image brightness to ensure the consistency of image data under different lighting conditions.

[0049] Under high temperature conditions, the thermal radiation intensity of the blade surface interferes with the image brightness, which can be calculated using the Stefan-Boltzmann law. In order to obtain the blade surface temperature matrix, an infrared thermometer can be used to measure the blade surface temperature in real time.

[0050] Correcting the brightness interference caused by thermal radiation in the image is the key to evaluating the authenticity of the image. The brightness interference caused by thermal radiation on the image can be expressed as: ;

[0051] in, Indicates the brightness of the interference of thermal radiation on the image; It is the proportionality coefficient of the optical system, which is obtained through experimental measurement. The value of the proportionality coefficient is determined by the characteristics of the sensor and the transmittance of the optical lens; Indicates the thermal radiation intensity on the blade surface; , Represent the row and column coordinates of the image respectively.

[0052] Based on the interference brightness of thermal radiation on the image, the corrected image brightness can be expressed as: ;

[0053] in, Represents the brightness of the image after correction; Represents the brightness of the normalized image; Indicates the brightness of the interference of thermal radiation on the image; , Represent the row and column coordinates of the image respectively.

[0054] The image authenticity coefficient is defined to evaluate the authenticity of the blade image data. The expression of the image authenticity coefficient is: ;

[0055] in, represents the image authenticity coefficient; and Represent the number of rows and columns of the image matrix respectively; Represents the image brightness difference matrix before and after correction; , Represent the row and column coordinates of the image respectively.

[0056] Image brightness difference matrix before and after correction It is calculated by the normalized image brightness and the corrected image brightness, and the expression is: ;

[0057] in, Represents the brightness of the image after correction; Represents the brightness of the normalized image.

[0058] The closer the image authenticity coefficient is to 1, the more consistent the image data after thermal radiation correction is with the actual condition of the blade surface, and the higher the authenticity of the blade image. When the image authenticity coefficient is closer to 0, it means that the image data is greatly affected by high temperature radiation interference, and the corrected image still has obvious distortion and cannot truly reflect the details of the blade surface, which means that the brightness information of the blade image is far from the actual situation, resulting in insufficient accuracy of the image data.

[0059] In step S2: during the endoscopic observation of the gas turbine blade, the high temperature environment will cause the refractive index of the gas medium around the blade to change, causing the light to bend during propagation, thereby causing optical distortion of the image. By analyzing the change in the refractive index of the gas medium, it helps to ensure that the blade image can truly reflect the details of the blade surface. Optical distortion makes it impossible for the corrected image to truly reflect the geometric structure and defect information of the blade surface, affecting the accuracy of evaluating the degree of optical distortion of the blade image data.

[0060] The medium refractive index change analysis is performed on the corrected blade image data to evaluate the optical distortion of the blade image data, specifically:

[0061] After completing the thermal radiation correction interference, the blade image data matrix is ​​obtained , Represents the corrected image brightness , Represent the row and column coordinates of the image respectively.

[0062] For each blade image coordinate, the change in the refractive index of the gas medium is calculated as follows: ;

[0063] in, Indicates the change of refractive index of gas medium; Represents the refractive index in a high temperature environment, and uses an optical model to estimate the refractive index in a high temperature environment. Indicates the refractive index under standard conditions.

[0064] In order to quantify the degree of optical distortion of leaf image data, the optical distortion coefficient is defined and calculated by the brightness difference and refractive index change of the image. The expression of the optical distortion coefficient is: ;

[0065] in, represents the optical distortion coefficient; Indicates the change of refractive index of gas medium; represents the image coordinate number of the blade image data matrix obtained after thermal radiation interference correction, ; represents the total number of image coordinates of the blade image data matrix obtained after thermal radiation interference correction; Indicates at location The brightness of the leaf image after thermal radiation interference correction; Indicates at location The actual brightness of the leaf image is obtained through experiments or reference data.

[0066] The larger the optical distortion coefficient, the higher the degree of optical distortion of the leaf image data, the corrected leaf image cannot accurately reflect the characteristics of the leaf surface, and the deviation between the brightness information and the actual situation is large. The smaller the optical distortion coefficient, the lower the degree of optical distortion of the leaf image data, the corrected leaf image can accurately reflect the characteristic details of the leaf surface, the difference between the brightness information of the leaf image and the actual situation is small, and it has higher reliability and practicality.

[0067] In step S3: according to the authenticity and optical distortion of the blade image data, it is determined whether it meets the requirements for extracting the blade surface defect features, specifically:

[0068] The image authenticity coefficient threshold is set. The image authenticity coefficient threshold is set by professionals in this field according to the size of the image authenticity coefficient and other actual conditions such as the authenticity of the leaf image data. The image authenticity coefficient is compared with the image authenticity coefficient threshold:

[0069] When the image authenticity coefficient is greater than or equal to the image authenticity coefficient threshold, it indicates that the corrected image data is highly consistent with the actual condition of the blade surface, which means that the image can accurately reflect the actual state of the blade and has high authenticity. The image data is suitable for subsequent defect feature extraction and analysis.

[0070] When the image authenticity coefficient is less than the image authenticity coefficient threshold, it means that there is a significant difference between the corrected image data and the actual condition of the blade surface, which means that the image may be interfered by thermal radiation. The authenticity of the blade image data is poor and cannot be used for effective defect feature extraction. The data needs to be re-collected.

[0071] The optical distortion coefficient threshold is set. The optical distortion coefficient threshold is set by professionals in the field according to the size of the optical distortion coefficient and other actual conditions such as the degree of optical distortion of the leaf image data. The optical distortion coefficient is compared with the optical distortion coefficient threshold:

[0072] When the optical distortion coefficient is greater than or equal to the optical distortion coefficient threshold, it indicates that the leaf image has high optical distortion, which means that the details and features in the image may be distorted due to optical interference, affecting the extraction of leaf surface defect features. Additional correction measures are needed to improve image quality.

[0073] When the optical distortion coefficient is less than the optical distortion coefficient threshold, it means that the optical distortion degree of the blade image is low, the blade image data is clearer, has good quality, can better reflect the detailed features of the blade surface, and is suitable for subsequent defect feature extraction and analysis.

[0074] When the image authenticity coefficient is greater than or equal to the image authenticity coefficient threshold, and the optical distortion coefficient is less than the optical distortion coefficient threshold, a higher image authenticity coefficient indicates that the image is highly consistent with the actual situation and can truly present the surface characteristics of the blade, which means that the thermal radiation correction effectively eliminates most of the interference, so that the image can better express the physical characteristics and surface state of the blade. A lower optical distortion coefficient means that the degree of distortion in the image is low, the details in the image are not significantly optically disturbed, and the morphology and structure of the blade can be restored more realistically, indicating that the blade image data meets the requirements for extracting the surface defect characteristics of the blade.

[0075] In step S4: Blades are core components of gas turbines. They are exposed to high temperature environments for a long time and are prone to defects such as cracks, wear and corrosion. If these defects are not detected and evaluated in time, they may cause the blades to break or fail during operation, leading to serious mechanical failures or safety accidents. Defect feature analysis of image data can accurately identify various defects on the surface of the blades. By calculating the severity of the defects and quantifying the degree of blade damage, we can have a more comprehensive understanding of the health of the blades and determine whether maintenance or replacement of the blades is needed. This helps to warn of potential failure risks in advance, avoid maintenance costs and downtime losses caused by blade failure, and extend the service life of the blades, improve the operating efficiency and safety of the gas turbine, and provide a scientific basis for maintenance and overhaul decisions.

[0076] When the requirements for extracting blade surface defect features are met, blade surface defect feature analysis is performed on the blade image data after distortion compensation to evaluate the severity of the defects in the blade image data, specifically:

[0077] In a high temperature environment, the refractive index of the gas medium changes, causing the light to refract during propagation, resulting in image distortion. In order to restore the true shape of the blade surface, the image is compensated for refraction distortion based on Snell's law. According to the refractive index data of the gas medium in a high temperature environment, a refractive index distribution matrix of different areas on the blade surface is established, and each element represents the refractive index value at a position in the image. By correcting the curvature of the light propagation path in the image, the position of each pixel is adjusted to the compensated image coordinates to obtain the image data after distortion compensation.

[0078] After distortion compensation, the image data enters the defect feature extraction stage, using the Canny edge detection algorithm to extract cracks, wear, and corrosion from the distortion-compensated image data, including:

[0079] Gaussian filtering is performed on the blade image data after distortion compensation, and smoother blade image data is obtained through filtering processing.

[0080] The brightness gradient of each pixel in the blade image data after filtering is calculated to obtain the gradient amplitude and gradient direction. By calculating the gradient amplitude, the potential defect edge position in the blade image data is determined.

[0081] The non-maximum value of the gradient amplitude is suppressed and the local maximum value is retained to ensure that the extracted edges represent the real defect features of the blade surface.

[0082] The low threshold and high threshold are used to classify the edges, and the edges that meet the high threshold and the low threshold edges connected to the high threshold edges are retained to obtain a complete edge image.

[0083] The complete edge image obtained by Canny edge detection is processed by morphological expansion and corrosion to form a complete defect feature area. The crack length, wear area, and corrosion degree in the defect feature area are calculated, including:

[0084] The crack area within the defect feature area is edge tracked, all pixel points on the crack edge are identified, and all pixel points are defined as a set of coordinate points. The total crack length is obtained by calculating the Euclidean distance between adjacent coordinate points and accumulating all distances.

[0085] The worn area within the defect feature area is converted into a binary image, with the pixel value of the worn area set to 1 and the pixel value of the non-worn area set to 0. All pixels with a value of 1 in the binary image are accumulated to obtain the worn area of ​​the worn area.

[0086] In the corrosion area within the defect feature area, the gray value reflects the depth of corrosion. By extracting the maximum gray value and the minimum gray value in the corrosion area, the difference between the maximum gray value and the minimum gray value is calculated as the corrosion depth.

[0087] The crack length, wear area and corrosion depth are normalized, and the defect severity coefficient is calculated according to the normalized crack length, wear area and corrosion depth. The expression of the defect severity coefficient is: ;

[0088] in, Indicates the defect severity coefficient; , , Respectively represent the normalized crack length, wear area and corrosion depth; , , Defect severity scores representing crack length, wear area, and corrosion depth, respectively, are assessed based on defect type and location.

[0089] The larger the defect severity coefficient, the more obvious the defect characteristics on the blade surface, the stronger the impact of cracks, wear and corrosion on the blade, indicating that the blade may have more serious structural problems, which may affect the performance and safety of the blade. In practical applications, a higher defect severity coefficient means that emergency repairs or blade replacement are required to prevent potential failures. The smaller the defect severity coefficient, the less obvious the defect characteristics on the blade surface, and the relatively smaller impact of cracks, wear and corrosion on the blade, which means that the blade is in good condition and can continue to be used under normal working conditions. A lower defect severity coefficient indicates that the image data is more accurate and can effectively reflect the true state of the blade.

[0090] In step S5: the authenticity of the blade image data, the optical distortion of the blade image data, and the severity of defects in the blade image data are comprehensively analyzed to determine the health status of the gas turbine blades, specifically:

[0091] The image authenticity coefficient corresponding to the authenticity of the image data, the optical distortion coefficient corresponding to the optical distortion of the image data, and the defect severity coefficient corresponding to the defect severity of the image data are normalized, and proportional coefficients are preset for the normalized image authenticity coefficient, optical distortion coefficient, and defect severity coefficient, respectively, to calculate the health status index of the gas turbine blade, specifically: ;

[0092] in, Indicates the health status index of gas turbine blades; represents the image authenticity coefficient; represents the optical distortion coefficient; Indicates the defect severity coefficient; , , They represent the preset proportional coefficients of the image authenticity coefficient, the optical distortion coefficient, and the defect severity coefficient, respectively, and are all greater than 0.

[0093] A health status index threshold is set. The health status index threshold is set by professionals in the field according to the size of the health status index and other actual conditions such as the health status of the gas turbine blades. The health status index is compared with the health status index threshold:

[0094] When the health status index is greater than or equal to the health status index threshold, it is judged that the health status of the gas turbine blade is good, with high operating reliability and safety, which means that defects such as cracks, wear and corrosion on the blade surface have no obvious negative impact on the performance and structural integrity of the blade, and the blade can continue to operate stably at high temperatures. When the health status index is greater than or equal to the health status index threshold, it means that the health monitoring and assessment of the blade is effective, the working state of the blade meets the expected operating standards, and can continuously ensure the normal operation of the gas turbine.

[0095] When the health status index is less than the health status index threshold, it is determined that the health status of the gas turbine blade is poor, the blade has obvious defects or damage, the overall health status is poor, and there are potential risks to operational reliability and safety. A health status index less than the health status index threshold means that defect features in the image data, such as cracks, wear, and corrosion, may affect the structural integrity and performance of the blade. A low health status index also indicates that the image data may have large optical distortion or the image is not realistic enough, further increasing the complexity of blade status assessment. When the health status index is less than the health status index threshold, the blade needs to be inspected and evaluated in detail, and maintenance measures should be considered, or the blade should be replaced to avoid failures or safety accidents.

[0096] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or may be transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0097] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0098] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0099] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0100] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0101] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0102] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0103] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0104] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A high temperature endoscopy observation and evaluation method for a gas turbine blade, characterized in that: The following steps are involved: Step S1: Performing thermal radiation interference analysis on the endoscopic image collected in a high temperature environment to evaluate the authenticity of the blade image data; The image authenticity coefficient is defined to evaluate the authenticity of the blade image data. The expression of the image authenticity coefficient is: ; in, represents the image authenticity coefficient; and Represent the number of rows and columns of the image matrix respectively; Represents the image brightness difference matrix before and after correction; , Represent the row and column coordinates of the image respectively; Image brightness difference matrix before and after correction It is calculated by the normalized image brightness and the corrected image brightness, and the expression is: ; in, Represents the brightness of the image after correction; Represents the brightness of the normalized image; Step S2: analyzing the change of medium refractive index on the corrected blade image data to evaluate the degree of optical distortion of the blade image data; Step S3: judging whether the blade image data meets the requirements for extracting blade surface defect features according to the authenticity and optical distortion of the blade image data; Set the image authenticity coefficient threshold and compare the image authenticity coefficient with the image authenticity coefficient threshold: When the image authenticity coefficient is greater than or equal to the image authenticity coefficient threshold, it means that the image can accurately reflect the actual state of the blade and has a high authenticity; When the image authenticity coefficient is less than the image authenticity coefficient threshold, it means that there is a significant difference between the corrected image data and the actual condition of the blade surface, and the authenticity of the blade image data is poor; Set the optical distortion coefficient threshold and compare the optical distortion coefficient with the optical distortion coefficient threshold: When the optical distortion coefficient is greater than or equal to the optical distortion coefficient threshold, it indicates that the leaf image has high optical distortion; When the optical distortion coefficient is less than the optical distortion coefficient threshold, it indicates that the optical distortion degree of the leaf image is low; When the image authenticity coefficient is greater than or equal to the image authenticity coefficient threshold, and the optical distortion coefficient is less than the optical distortion coefficient threshold, it indicates that the blade image data meets the requirements for extracting blade surface defect features; Step S4: when the requirements for extracting blade surface defect features are met, performing blade surface defect feature analysis on the distortion-compensated blade image data to evaluate the severity of defects in the blade image data; Step S5: Comprehensively analyze the authenticity of the blade image data, the optical distortion of the blade image data, and the severity of defects in the blade image data to determine the health status of the gas turbine blade.

2. A high temperature endoscopic observation and evaluation method for a gas turbine blade according to claim 1, characterized in that: In step S2, the medium refractive index change analysis is performed on the corrected blade image data to evaluate the optical distortion degree of the blade image data, specifically: The optical distortion coefficient is calculated by the brightness difference and refractive index change of the image. The expression of the optical distortion coefficient is: ； in, represents the optical distortion coefficient; Indicates the change of refractive index of gas medium; represents the image coordinate number of the blade image data matrix obtained after thermal radiation interference correction, ; represents the total number of image coordinates of the blade image data matrix obtained after thermal radiation interference correction; Indicates at location The brightness of the leaf image after thermal radiation interference correction; Indicates at location The actual brightness of the leaf image is obtained through experiments or reference data.

3. A high temperature endoscopic observation and evaluation method for gas turbine blades according to claim 2, characterized in that: In step S4, when the requirements for extracting blade surface defect features are met, blade surface defect feature analysis is performed on the distortion-compensated blade image data to evaluate the severity of the defects in the blade image data, specifically: The crack length, wear area and corrosion depth are normalized, and the defect severity coefficient is calculated according to the normalized crack length, wear area and corrosion depth. The expression of the defect severity coefficient is: ； in, Indicates the defect severity coefficient; , , Respectively represent the normalized crack length, wear area and corrosion depth; , , Defect severity scores representing crack length, wear area, and corrosion depth, respectively.

4. A high temperature endoscopic observation and evaluation method for gas turbine blades according to claim 3, characterized in that: In step S5, the authenticity of the blade image data, the optical distortion of the blade image data, and the severity of defects in the blade image data are comprehensively analyzed to determine the health status of the gas turbine blades, specifically: The image authenticity coefficient corresponding to the authenticity of the image data, the optical distortion coefficient corresponding to the optical distortion of the image data, and the defect severity coefficient corresponding to the defect severity of the image data are normalized, and proportional coefficients are preset for the normalized image authenticity coefficient, optical distortion coefficient, and defect severity coefficient, respectively, to calculate the health status index of the gas turbine blade, specifically: ; in, Indicates the health status index of gas turbine blades; represents the image authenticity coefficient; represents the optical distortion coefficient; Indicates the defect severity coefficient; , , Preset proportional coefficients representing image authenticity coefficient, optical distortion coefficient and defect severity coefficient respectively; Set a health status index threshold and compare the health status index with the health status index threshold: When the health status index is greater than or equal to the health status index threshold, it is determined that the health status of the gas turbine blade is good; When the health status index is less than the health status index threshold, it is determined that the health status of the gas turbine blade is poor.

Images