Method for establishing high-temperature alloy hot corrosion model based on image recognition

Abstract

The invention discloses a method for establishing a high-temperature alloy hot corrosion model based on image recognition. The method comprises the following steps: preparing a sample and carrying out a hot corrosion test; shooting and recording the surface appearance of the sample after thermal corrosion in the thermal corrosion test, and preprocessing the image; performing gray analysis on the preprocessing result, and calculating the mean gray G and the gray distribution condition of the surface image of the sample after thermal corrosion; calculating corrosion morphology fractal dimensions D of different sample surfaces by using a box method; and establishing a high-temperature alloy thermal corrosion model based on the mean gray scale G and the corrosion morphology fractal dimension D. According to the method, the hot corrosion temperature and time can be speculated according to the surface topography characteristics of the high-temperature alloy subjected to hot corrosion, and a technical basis is provided for quickly determining the hot corrosion temperature and time in engineering practice.

Description

Technical Field

[0001] The invention relates to the technical field of high-temperature alloy thermal corrosion, and in particular to a method for establishing a high-temperature alloy thermal corrosion model based on image recognition. Background Art

[0002] High-temperature alloy materials represented by nickel-based alloys are widely used in key hot-end components of aircraft engines due to their excellent high-temperature mechanical properties. Marine gas turbines and carrier-based aircraft engine turbine components will deposit corrosive molten salts on the surface of turbine blades in a long-term high-humidity, high-salt fog marine atmosphere service environment. These deposited salts will destroy the protective oxide layer on the alloy surface in a high-temperature environment, leading to the occurrence of thermal corrosion.

[0003] Traditional methods for describing the degree of thermal corrosion of nickel-based high-temperature alloys include thermogravimetric testing, which characterizes the thermal corrosion process by mass changes (see the invention patent "Test method for thermal corrosion performance of nickel-based single crystal high-temperature alloys", application publication number CN110132826A); metallographic characterization method, which characterizes the degree of thermal corrosion by preparing metallographic samples through cutting and polishing and observing the thickness and morphology of the cross-sectional corrosion layer (see the invention patent "Analysis method for thermal corrosion performance of nickel-based single crystal high-temperature alloys", application publication number CN111896458A; invention patent "A method for assessing damage to thermal barrier coatings based on corrosion dynamics", application publication number CN110132826A). The above methods can establish a model of sample mass, corrosion layer thickness, thermal corrosion temperature and time, but the operation is complicated and requires the destruction of the sample, making it difficult to apply in practice. Therefore, there is an urgent need for a thermal corrosion temperature and time model that is more convenient to operate and has more accurate results, so as to more accurately judge the degree of thermal corrosion damage of the sample, the temperature of the thermal corrosion environment, and the duration of thermal corrosion. Summary of the invention

[0004] In order to solve the above problems, the present invention proposes a method for establishing a thermal corrosion model of high-temperature alloys based on image recognition. The thermal corrosion process is characterized by extracting the surface morphology characteristic parameters of the sample after thermal corrosion. It can express the relationship between the mean grayscale and fractal dimension of the thermal corrosion surface and the thermal corrosion temperature and time.

[0005] In order to achieve the above object, the present invention is implemented by the following technical solutions:

[0006] The present invention is a method for establishing a high-temperature alloy thermal corrosion model based on image recognition, comprising the following operations:

[0007] Prepare specimens and conduct hot corrosion tests;

[0008] Photograph and record the surface morphology of the sample after hot corrosion in the hot corrosion test, and pre-process the image;

[0009] Perform grayscale analysis on the preprocessing results and calculate the mean grayscale G and grayscale distribution of the surface image of the sample after thermal corrosion.

[0010] The fractal dimension D of the corrosion morphology on the surfaces of different samples was calculated using the box method;

[0011] A hot corrosion model of high-temperature alloy is established based on the mean grayscale G and the fractal dimension D of the corrosion morphology.

[0012] A further improvement of the present invention is that the sample is prepared and the hot corrosion test is carried out, specifically including:

[0013] The GH4169 alloy was made into several discs with a diameter of 20 mm and a thickness of 2 mm, which were then polished, cleaned and dried in sequence to obtain a plurality of spare specimens;

[0014] Multiple samples were divided into several groups, embedded in a mixed salt of Na2SO4 and NaCl with a mass ratio of 3:1, and placed in a high-temperature furnace at different temperatures for hot corrosion;

[0015] After the thermal corrosion test begins, several samples from each group are taken out at set intervals to cool in the air, boiled with deionized water, ultrasonically cleaned, and dried in sequence until the thermal corrosion test is completed.

[0016] A further improvement of the present invention is to photograph and record the surface morphology of the sample after thermal corrosion in the thermal corrosion test, and pre-process the image, specifically including:

[0017] Use a camera to take images of the surface morphology of the sample after thermal corrosion under a fixed light source;

[0018] The sample surface is identified and the redundant background is subtracted, the color image is converted into a grayscale image, and the grayscale pixel matrix A is established.

[0019] A further improvement of the present invention is to perform grayscale analysis on the preprocessing results, calculate the mean grayscale G and grayscale distribution of the surface image of the sample after thermal corrosion, and the specific operations include:

[0020] The grayscale is divided into 256 levels. The element range of the grayscale pixel matrix A is [0, 255], which represents the grayscale value of the corresponding pixel point. Black is 0 and white is 255. The mean grayscale G of each sample is counted to characterize the overall color level of the surface of the sample after thermal corrosion. The mean grayscale of the original sample surface before thermal corrosion is recorded as G0.

[0021] A further improvement of the present invention is that the fractal dimension D of the corrosion morphology of different sample surfaces is calculated using the box method, and the specific operation includes:

[0022] Cover the grayscale pixel matrix A with squares of a certain scale, and use the comparison result of the average grayscale of the image in the box and the average grayscale of the entire image as the basis for judgment, and count the number of boxes containing images;

[0023] The box size is changed, and the number of boxes and box size are plotted on a double logarithmic coordinate system. The slope of the linear region represents the fractal dimension D of the corrosion morphology, where the fractal dimension of the corrosion morphology of the original sample surface image before thermal corrosion is recorded as D0.

[0024] The further improvement of the present invention is that the high-temperature alloy hot corrosion model includes a grayscale model based on the mean grayscale G of the surface image of the sample after hot corrosion and a high-temperature hot corrosion fractal model based on the fractal dimension D of the corrosion morphology of the sample surface, wherein the relationship between the mean grayscale G and the test temperature in the grayscale model is expressed as:

[0025] S=K G T B

[0026]

[0027] Among them, S is the surface average grayscale decay rate, T is the thermal corrosion temperature, K G is the material condition coefficient, B is the grayscale variation index, and G0 is the average grayscale of the original sample surface before hot corrosion;

[0028] The relationship between the fractal dimension D of the corrosion morphology on the sample surface and the hot corrosion time in the high-temperature hot corrosion fractal model is expressed as:

[0029] D=K D ·t+C

[0030] Where t is the thermal corrosion time, K D is the material operating coefficient, and C is a constant.

[0031] The beneficial effects of the present invention are: 1. The present invention provides a new idea for estimating the temperature and time of thermal corrosion, and adopts a method of extracting characteristic parameters of thermal corrosion morphology by image recognition, which can accurately and effectively characterize the degree of thermal corrosion of the sample.

[0032] 2. The present invention has a certain degree of universality. The exponential relationship between the grayscale mean and the thermal corrosion temperature in the grayscale model and the linear relationship between the fractal dimension of the corrosion morphology and the corrosion time in the high-temperature thermal corrosion fractal model are common in the thermal corrosion of high-temperature alloys. The material condition coefficient K can be revised according to different sample materials and thermal corrosion conditions. G , K D .

[0033] 3. The present invention can be applied in engineering practice to quickly determine the thermal corrosion damage status of high-temperature alloy materials, and further determine the thermal corrosion temperature and time range. The method of extracting thermal corrosion characteristic parameters by image recognition also greatly avoids the deviation caused by the traditional manual visual method of determining the degree of thermal corrosion. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 is a flow chart of a method in an embodiment of the present invention;

[0035] Figure 2 is a schematic diagram of image processing of the surface morphology of a sample after thermal corrosion in an embodiment of the present invention;

[0036] Figure 3 is a schematic diagram of grayscale model data fitting in an embodiment of the present invention;

[0037] Figure 4 It is a schematic diagram of data fitting of a high-temperature thermal corrosion fractal model in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0039] like Figure 1 As shown, a method for establishing a high-temperature alloy thermal corrosion model based on image recognition in this embodiment includes the following operations:

[0040] Step 1, preparing a sample and conducting a high temperature alloy hot corrosion test T, specifically comprising:

[0041] Step 1.1, the high-temperature alloy GH4169 was cut into discs with a diameter of 20 mm and a thickness of 2 mm, and the samples were polished with SiC sandpaper of small to large meshes until smooth, immersed in an ethanol solution and cleaned in an ultrasonic cleaner for 5 minutes to remove surface abrasive residues and oil stains, and dried in a drying oven at 150°C for 30 minutes;

[0042] Step 1.2, place the sample in a quartz crucible, weigh Na2SO4 and NaCl in a mass ratio of 75% and 25%, mix and stir them thoroughly, pour them into the quartz crucible, cover the sample, put them into a tube furnace, and conduct 4 groups of tests respectively, with the temperature set to 650℃, 750℃, 900℃ constant temperature, and 650~900℃ variable temperature. According to the test plan, take out 2 samples from each group every 6 hours or 12 hours to cool naturally in the air, then boil them in deionized water for 30 minutes, ultrasonically clean them in ethanol for 10 minutes to remove residual salt on the surface, and finally dry them in a drying oven at 150℃ for 30 minutes, and take high-definition pictures of the front and back of the sample with a digital camera under a fixed light source until the 72-hour test is completed.

[0043] Step 2: pre-process the image of the surface morphology of the sample after thermal corrosion. Figure 2 As shown, specifically including:

[0044] Step 2.1, convert the image into data, scan the image from left to right and from top to bottom, identify the φ20mm circular range with data fluctuations, define it as the sample, and define the surrounding data uniform area as the background. Delete the background to obtain the thermal corrosion surface morphology image containing only the sample;

[0045] Step 2.2, convert the image into a grayscale image, and establish a grayscale pixel matrix A based on the image pixels.

[0046] Step 3, perform grayscale analysis on the preprocessing results, and calculate the mean grayscale G and grayscale distribution of the surface image of the sample after thermal corrosion;

[0047] The grayscale is divided into 256 levels, and the grayscale value corresponding to pure white is normalized to 255. All element values ​​in the grayscale pixel matrix A are mapped to the range of [0, 255] with this normalization ratio, where pure black is 0 and pure white is 255, recorded as matrix A';

[0048] (1) The mean value G of the calculated matrix A' is recorded as the mean grayscale of the image, and the mean grayscale of the image before the thermal corrosion of the sample is recorded as G0. The detailed data are shown in Table 1:

[0049] Table 1 Average gray scale of samples before and after thermal corrosion

[0050]

[0051]

[0052] Step 4, using the box method to calculate the fractal dimension D of the corrosion morphology of different sample surfaces, specifically including:

[0053] Step 4.1, according to the row and column size of matrix A', normalize it to 256X256 matrix A'', and use the mean value for each element.

[0054] Step 4.2, respectively according to the side length 2 n The matrix A'' is divided into squares (n is a number from 1 to 8), and the divided cells are calculated using the box method.

[0055] Step 4.3, plot the 8 grid sizes and calculation results on a double logarithmic coordinate, record its slope as the corrosion morphology fractal dimension D, and record the image fractal dimension of the sample before hot corrosion as D0. The detailed data of the 900℃ constant temperature and 650~900℃ variable temperature samples are shown in Table 2:

[0056] Table 2 Fractal dimension of surface morphology of samples before and after high temperature hot corrosion

[0057]

[0058] Step 5, establish a high-temperature alloy hot corrosion model based on the mean grayscale G and the corrosion morphology fractal dimension D. The high-temperature alloy hot corrosion model includes a grayscale model based on the mean grayscale G of the surface image of the sample after hot corrosion and a high-temperature hot corrosion fractal model based on the corrosion morphology fractal dimension D of the sample surface. The principle of the grayscale model is: in the hot corrosion of high-temperature alloys, as the hot corrosion occurs, the surface changes from the initial metallic silver-white to being covered with a dark brown corrosion skin. The color and coverage of the corrosion skin are different at different temperatures, which can be characterized by the mean grayscale G of the image. Its value is mainly related to the temperature and has nothing to do with the corrosion time. The principle of the high-temperature hot corrosion fractal model is: for low-temperature hot corrosion samples (650℃), the surface hot corrosion occurs more uniformly and slowly, and the fractal dimension D of the corrosion morphology of its image does not change significantly with the corrosion time. However, for high-temperature hot corrosion samples (900℃), there are a large number of corrosion pits, plow-type peeling and other obvious corrosion features in the surface corrosion layer, and the fractal dimension D of the corrosion morphology shows a decreasing trend with the corrosion time. In addition, the complexity of the sample surface after corrosion must be greater than that before corrosion. As the thermal corrosion deepens, when the fractal dimension of the sample surface image is close to the original fractal dimension D0 of the sample before corrosion, it can be approximately considered that the thermal corrosion has reached a critical point, the growth and shedding of the corrosion layer have reached a balance, and the thickness has not changed. This moment is the critical corrosion time cct.

[0059] In this embodiment, the surface mean grayscale decay rate S is calculated according to Table 1, and the expression is:

[0060]

[0061] The calculation results are shown in Table 3:

[0062] Table 3 Surface mean grayscale decay rate

[0063]

[0064] The relationship between the surface mean grayscale decay rate and the thermal corrosion temperature is as follows:

[0065] S=K G T B

[0066] Where T is the thermal corrosion temperature, K G is the material condition coefficient, and B is the grayscale change index.

[0067] The least squares method is used to fit the data in Table 3. The fitting results are shown in Figure 3 Show.

[0068] K G =2.47095E18,B=-5.97438

[0069] There is a relationship between the fractal dimension D of the corrosion morphology of the sample surface in high-temperature hot corrosion and the hot corrosion time t:

[0070] D=K D ·t+C

[0071] Calculate the material operating coefficient K according to the data in Table 2 D , constant C, the fitting results are as follows Figure 4 As shown. At the same time, the critical corrosion moment cct is calculated when the fractal dimension D of the corrosion morphology is equal to the fractal dimension D0 of the corrosion morphology of the original sample surface image before thermal corrosion:

[0072]

[0073] In summary, this embodiment clearly shows the relationship between the mean grayscale of the thermal corrosion surface, the fractal dimension and the thermal corrosion temperature and time, and provides a technical basis for quickly determining the thermal corrosion temperature and time in engineering practice.

[0074] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have the same meaning as in the context of the prior art, and will not be interpreted with an idealized or overly formal meaning unless defined similarly here.

[0075] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method 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 scope of protection of the present invention.

Claims

1. A method for establishing a high-temperature alloy thermal corrosion model based on image recognition, characterized in that: The following operations are included: Prepare specimens and conduct hot corrosion tests; Photograph and record the surface morphology of the sample after hot corrosion in the hot corrosion test, and pre-process the image; Perform grayscale analysis on the preprocessing results and calculate the mean grayscale G and grayscale distribution of the surface image of the sample after thermal corrosion. The fractal dimension D of the corrosion morphology on the surfaces of different samples was calculated using the box method; A hot corrosion model of high-temperature alloy is established based on the mean grayscale G and the fractal dimension D of the corrosion morphology.

2. The method for establishing a high-temperature alloy thermal corrosion model based on image recognition according to claim 1 is characterized in that: The preparation of the sample and the hot corrosion test specifically include: The GH4169 alloy was made into several discs with a diameter of 20 mm and a thickness of 2 mm, which were then polished, cleaned and dried in sequence to obtain a plurality of spare specimens; Multiple samples were divided into several groups, embedded in a mixed salt of Na2SO4 and NaCl with a mass ratio of 3:1, and placed in a high-temperature furnace at different temperatures for hot corrosion; After the thermal corrosion test begins, several samples from each group are taken out at set intervals to cool in the air, boiled with deionized water, ultrasonically cleaned, and dried in sequence until the thermal corrosion test is completed.

3. The method for establishing a high-temperature alloy thermal corrosion model based on image recognition according to claim 1 is characterized in that: The photographing and recording of the surface morphology of the sample after hot corrosion in the hot corrosion test and preprocessing the image specifically include: Use a camera to take images of the surface morphology of the sample after thermal corrosion under a fixed light source; The sample surface is identified and the redundant background is subtracted, the color image is converted into a grayscale image, and the grayscale pixel matrix A is established.

4. The method for establishing a high-temperature alloy thermal corrosion model based on image recognition according to claim 3 is characterized in that: The grayscale analysis of the preprocessing results is performed to calculate the mean grayscale G and grayscale distribution of the surface image of the sample after thermal corrosion. The specific operations include: The grayscale is divided into 256 levels. The element range of the grayscale pixel matrix A is [0, 255], which represents the grayscale value of the corresponding pixel point. Black is 0 and white is 255. The mean grayscale G of each sample is counted to characterize the overall color level of the surface of the sample after thermal corrosion. The mean grayscale of the original sample surface before thermal corrosion is recorded as G0.

5. The method for establishing a high-temperature alloy thermal corrosion model based on image recognition according to claim 3 is characterized in that: The box method is used to calculate the fractal dimension D of the corrosion morphology of different sample surfaces. The specific operations include: Cover the grayscale pixel matrix A with squares of a certain scale, and use the comparison result of the average grayscale of the image in the box and the average grayscale of the entire image as the basis for judgment, and count the number of boxes containing images; The box size is changed, and the number of boxes and box size are plotted on a double logarithmic coordinate system. The slope of the linear region represents the fractal dimension D of the corrosion morphology, where the fractal dimension of the corrosion morphology of the original sample surface image before thermal corrosion is recorded as D0.

6. The method for establishing a high-temperature alloy thermal corrosion model based on image recognition according to claim 1, characterized in that: The high-temperature alloy hot corrosion model includes a grayscale model based on the mean grayscale G of the surface image of the sample after hot corrosion and a high-temperature hot corrosion fractal model based on the fractal dimension D of the corrosion morphology of the sample surface, wherein the relationship between the mean grayscale G and the test temperature in the grayscale model is expressed as: S=K G T B Among them, S is the surface average grayscale decay rate, T is the thermal corrosion temperature, K G is the material condition coefficient, B is the grayscale variation index, and G0 is the average grayscale of the original sample surface before hot corrosion; The relationship between the fractal dimension D of the corrosion morphology on the sample surface and the hot corrosion time in the high-temperature hot corrosion fractal model is expressed as: D=K D ·t+C Where t is the thermal corrosion time, K D is the material operating coefficient, and C is a constant.

Images