Crack and hydride identification method and system, equipment and medium

Abstract

The invention relates to the technical field of crack and hydride recognition, in particular to a crack and hydride recognition method and system, equipment and a medium, and mainly comprises the steps of reading and obtaining a material tissue image; and carrying out image processing according to the input image, extracting a single crack and hydride analysis, extracting the tissue characteristics of the single crack and hydride, carrying out statistics on the overall information of the crack and hydride in the material, and outputting the overall information. According to the method, cracks and hydrides are screened, so that the image recognition speed and accuracy can be greatly improved, the statistics and recognition time of hydrides and cracks such as zirconium alloy and titanium alloy is greatly shortened, and the labor cost is reduced. And secondly, by using the determined standard crack and hydride identification standard, a determined tissue judgment mode can be established, and human interference in tissue identification is eliminated, so that the identification of cracks and oxides is more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of crack and hydride identification, and in particular to a crack and hydride identification method and system, equipment and medium. Background Art

[0002] Zirconium alloy and titanium alloy are commonly used cladding materials and structural materials for nuclear reactors. Corrosion is the main factor affecting the service performance of zirconium alloy and titanium alloy, and the corrosion behavior of zirconium alloy and titanium alloy plays a decisive role in their service life. Since cracks and hydrides will form inside the zirconium alloy and titanium alloy after corrosion, which seriously affects the mechanical properties of zirconium alloy, the orientation and organization distribution of cracks and hydrides are important contents in material corrosion research.

[0003] At present, the commonly used method for analyzing zirconium alloy and titanium alloy hydride is still manual image analysis, that is, taking photos of the tissue through an optical / electronic scanning microscope for manual analysis. However, manual analysis is extremely labor-intensive, and the results are greatly affected by the subjective factors of the analyst, and the analysis efficiency is low, which greatly consumes the time and energy of the staff.

[0004] Although computer image analysis technology has been widely used in some engineering fields to identify tissue images, such as crack analysis and detection. At present, wavelet transform methods including fast Haar transform, fast Fourier transform, Sobel filter, Canny filter, percolation method based on image brightness, genetic algorithm, neural network algorithm and minimum path method are all used to explore tissue images, but they all have the disadvantages of difficult theory and complex implementation. Summary of the invention

[0005] The purpose of the present invention is to provide a crack and hydride identification method and system, equipment and medium to solve the above-mentioned problems in the prior art.

[0006] The embodiments of the present invention are implemented by the following technical solutions:

[0007] In a first aspect, the present invention provides a method for identifying cracks and hydrides, comprising:

[0008] Acquire a first image, and preprocess the first image to obtain a second image;

[0009] Identify the second image to obtain pixel points of individual cracks and hydrides, establish a coordinate system, map the pixel points of the cracks and hydrides into the coordinate system, and obtain the coordinate positions of the cracks and hydrides;

[0010] Obtain a set of coordinate positions of cracks and hydrides, and perform linear fitting on the point set by the least square method;

[0011] Determine the termination point of the individual crack and the hydride after linear fitting, calculate the slope between the termination point of the individual crack and the termination point of the hydride, and obtain the inclination angle of the individual crack and the hydride;

[0012] Outputs the identification results of individual cracks and hydrides.

[0013] Preferably, the preprocessing of the first image to obtain the second image includes:

[0014] Determine whether the first image is a grayscale image, if not, perform grayscale processing on the first image to obtain a grayscale image, if it is a grayscale image, do not perform processing;

[0015] After the grayscale image is binarized, it is output as a second image.

[0016] Preferably, identifying the second image to obtain individual crack and hydride pixel points includes:

[0017] Step 1: obtaining any non-zero pixel point in the second image as a detection pixel point, wherein the detection pixel point is used as a starting point for extraction, and the detection pixel point is stored in the first set;

[0018] Step 2: Identify several adjacent pixels of the detection pixel point, store the identified non-zero pixel points into a second set, reset the pixel values ​​of the original positions of the non-zero pixel points stored in the second set to zero, and delete the detection pixel points of the first set;

[0019] Step 3: Store the non-zero pixel points stored in the second set in the first set as detection pixel points, and repeat the method of step 2 until there are no non-zero pixel points stored in the first set as detection pixel points, and the extraction is completed.

[0020] Preferably, the determination of the termination point of a single crack and a hydride comprises:

[0021] Determine whether the individual cracks and hydrides have branches. If there are branches, perform geometric processing on the individual cracks and hydrides and determine the termination point.

[0022] If there is no branch, the termination point is identified directly.

[0023] Preferably, the geometric processing comprises:

[0024] The pixel width of the crack is thinned into a 1-pixel skeleton, and one of the first zero pixel points is obtained;

[0025] Determine the number of second zero pixel points of several pixel points adjacent to the first zero pixel point. If the number of second zero pixel points is 1, then the second zero pixel point is determined to be the end point of the crack and the hydride. If the number of second zero pixel points is 2, then the second zero pixel point is determined to be the middle pixel. If the number of second zero pixel points is greater than 2, then the second zero pixel point is determined to be the branch point of the crack and the hydride.

[0026] In a second aspect, the present invention provides a crack and hydride identification system, comprising:

[0027] An image acquisition module is configured to acquire a first image and preprocess the first image to obtain a second image;

[0028] A processing module is configured to identify the second image to obtain pixel points of individual cracks and hydrides, establish a coordinate system, map the pixel points of the cracks and hydrides into the coordinate system, and obtain coordinate positions of the cracks and hydrides;

[0029] The analysis module is configured to obtain a set of coordinate positions of cracks and hydrides, perform linear fitting on the point set by the least square method; determine the termination points of the individual cracks and hydrides after the linear fitting, calculate the slope between the termination point of the individual crack and the termination point of the hydride, and obtain the inclination angle of the individual crack and the hydride;

[0030] an output module configured to output identification results of individual cracks and hydrides;

[0031] A main control module, the main control module is connected to the image acquisition module, the processing module, the analysis module and the output module, and is used to execute the above-mentioned crack and hydride identification method.

[0032] In a third aspect, the present invention further provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned crack and hydride identification method when executing the computer program.

[0033] In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned method for identifying cracks and hydrides is implemented.

[0034] The technical solution of the embodiment of the present invention has at least the following advantages and beneficial effects:

[0035] The method provided by the present invention mainly includes reading and acquiring material tissue images; performing image processing according to the input image, extracting single cracks and hydrides, analyzing and extracting the tissue characteristics of single cracks and hydrides, and statistically analyzing the overall information of cracks and hydrides in the material and outputting it.

[0036] Secondly, by using the determined standard crack and hydride identification criteria, a determined organizational determination method can be established to eliminate the human interference in organizational identification, making it more accurate to identify cracks and oxides.

[0037] By extracting the geometric features of single cracks and hydrides and combining them with the global crack and hydride characteristics and distribution data, researchers can be given more quantitative information and achieve in-depth analysis of the material. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 Shown is a system structure diagram of the artificial intelligence crack and hydride identification system provided by the present invention.

[0040] Figure 2 The figure shows a schematic diagram of removing black edges of an image.

[0041] Figure 3 The result of image binarization segmentation is shown.

[0042] Figure 4 Shown is a schematic diagram of cracking and hydride extraction.

[0043] Figure 5 Shown is an example of crack and hydride refinement treatment. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0045] The terms "first, second" and the like in the specification and claims of this application and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. The naming or numbering of steps in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The named or numbered process steps can be changed in the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.

[0046] The division of modules in this application is a logical division. There may be other division methods when implemented in actual applications. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0047] Please refer to Figure 1-Figure 5 The present invention provides a method for identifying cracks and hydrides, comprising:

[0048] S101: Acquire a first image, and pre-process the first image to obtain a second image;

[0049] In this embodiment, the system starts to acquire image input, which can be understood as the input of existing images, or as real-time input based on detection equipment such as optical microscopes / scanning electron microscopes. The acquisition module not only includes reading existing tissue images, but also includes real-time in-situ reading of image information transmitted by cameras, optical microscopes, scanning / transmission electron microscopes, etc.

[0050] Secondly, the materials targeted by the present invention include not only zirconium alloys, titanium alloys and the like, but also other materials not explicitly listed.

[0051] S102: Identify the second image to obtain pixel points of individual cracks and hydrides, establish a coordinate system, map the pixel points of the cracks and hydrides into the coordinate system, and obtain the coordinate positions of the cracks and hydrides;

[0052] S103: obtaining a set of coordinate positions of cracks and hydrides, and performing linear fitting on the point set by a least square method;

[0053] In this embodiment, the linear equation of the fit is:

[0054] y=mx+b

[0055] Among them, x is the horizontal coordinate value of the coordinate position, y is the vertical coordinate value of the coordinate position, m is the slope, and b is the intercept.

[0056] Then set the objective function S(m, b) to minimize the residual sum of squares to obtain the optimal m and b.

[0057] Take the derivative of m and set it to 0:

[0058]

[0059] Take the derivative of b and set it to 0:

[0060]

[0061] In the formula, is the derivative of the objective function, is the derivative with respect to m, is the derivative of b, x i is the horizontal coordinate value of the i-th coordinate position, y i is the ordinate value of the i-th coordinate position.

[0062] After solving the above formula, we get the optimal m and b, and the fitted linear equation.

[0063] S104: determining the termination points of the individual cracks and the hydrides after the linear fitting, calculating the slope between the termination point of the individual crack and the termination point of the hydrides, and obtaining the inclination angle of the individual crack and the hydrides;

[0064] S105: Output the identification results of individual cracks and hydrides.

[0065] Among them, the identification results are specific in the extraction of geometric features of cracks and hydrides. The process of geometric feature extraction is to calculate the slope and inclination, and the obtained geometric features and spatial coordinates of cracks and hydrides are handed over to the output module for output to provide R&D personnel with more quantitative information and speed up the subsequent work process.

[0066] The method provided by the present invention mainly includes reading and acquiring material tissue images; performing image processing according to the input image, extracting single cracks and hydrides, analyzing and extracting the tissue characteristics of single cracks and hydrides, and statistically analyzing the overall information of cracks and hydrides in the material and outputting it.

[0067] In the present invention, screening cracks and hydrides can greatly improve the recognition speed and accuracy of images, greatly shorten the statistics and recognition time of hydrides and cracks of zirconium alloys, titanium alloys, etc., reduce labor costs, liberate more researchers, and speed up material research and development.

[0068] Secondly, by using the determined standard crack and hydride identification criteria, a determined organizational determination method can be established to eliminate the human interference in organizational identification, making it more accurate to identify cracks and oxides.

[0069] By extracting the geometric features of single cracks and hydrides and combining them with the global crack and hydride characteristics and distribution data, researchers can be given more quantitative information and achieve in-depth analysis of the material.

[0070] In an exemplary embodiment of the present invention, the preprocessing of the first image to obtain the second image includes:

[0071] S201: determining whether the first image is a grayscale image, if not, performing grayscale processing on the first image to obtain a grayscale image, and if it is a grayscale image, performing no processing;

[0072] S202: Binarize the grayscale image and output it as a second image.

[0073] First, a threshold T is given, and the pixel values ​​above this threshold are regarded as foreground, and the pixels below the threshold are regarded as background.

[0074]

[0075] Where I(x, y) is the grayscale value of the image at position (x, y), and Binary(x, y) is the value of the image after binarization at position (x, y).

[0076] In an exemplary embodiment of the present invention, the step of identifying the second image to obtain individual crack and hydride pixel points includes:

[0077] Step 1: obtaining any non-zero pixel point in the second image as a detection pixel point, wherein the detection pixel point is used as a starting point for extraction, and the detection pixel point is stored in the first set;

[0078] In this embodiment, the non-zero pixel points stored in the first set are used as the starting point for detection.

[0079] Step 2: Identify several adjacent pixels of the detection pixel point, store the identified non-zero pixel points into a second set, reset the pixel values ​​of the original positions of the non-zero pixel points stored in the second set to zero, and delete the detection pixel points of the first set;

[0080] Preferably, 8 adjacent pixels are used for recognition.

[0081] Step 3: Store the non-zero pixel points stored in the second set in the first set as detection pixel points, and repeat the method of step 2 until there are no non-zero pixel points stored in the first set as detection pixel points, and the extraction is completed.

[0082] It can be understood that each time a new non-zero pixel point is obtained, it is saved in the second set and also in the first set. When saving in the first set, the non-zero pixel point used as the detection pixel point last time needs to be deleted until no new non-zero pixel point appears and the first set is empty, then the detection is terminated.

[0083] Preferably, the determination of the termination point of a single crack and a hydride comprises:

[0084] Determine whether the individual cracks and hydrides have branches. If there are branches, perform geometric processing on the individual cracks and hydrides and determine the termination point.

[0085] If there is no branch, the termination point is identified directly.

[0086] Specifically, the geometric processing includes:

[0087] The pixel width of the crack is thinned into a 1-pixel skeleton, and one of the first zero pixel points is obtained;

[0088] Determine the number of second zero pixel points of several pixel points adjacent to the first zero pixel point. If the number of second zero pixel points is 1, then the second zero pixel point is determined to be the end point of the crack and the hydride. If the number of second zero pixel points is 2, then the second zero pixel point is determined to be the middle pixel. If the number of second zero pixel points is greater than 2, then the second zero pixel point is determined to be the branch point of the crack and the hydride.

[0089] In a second aspect, the present invention provides a crack and hydride identification system, comprising:

[0090] An image acquisition module is configured to acquire a first image and preprocess the first image to obtain a second image;

[0091] A processing module is configured to identify the second image to obtain pixel points of individual cracks and hydrides, establish a coordinate system, map the pixel points of the cracks and hydrides into the coordinate system, and obtain coordinate positions of the cracks and hydrides;

[0092] The analysis module is configured to obtain a set of coordinate positions of cracks and hydrides, perform linear fitting on the point set by the least square method; determine the termination points of the individual cracks and hydrides after the linear fitting, calculate the slope between the termination point of the individual crack and the termination point of the hydride, and obtain the inclination angle of the individual crack and the hydride;

[0093] an output module configured to output identification results of individual cracks and hydrides;

[0094] A main control module, the main control module is connected to the image acquisition module, the processing module, the analysis module and the output module, and is used to execute the above-mentioned crack and hydride identification method.

[0095] The present invention uses the length and inclination of cracks and hydrides as examples to demonstrate the method of extracting geometric features, which should not be understood as being limited to the examples described herein. First, a set of coordinate positions of each pixel point in a single crack or hydride in the world coordinate system is obtained, and then the point set is linearly fitted using the least squares method. Through the fitting results of a single crack or hydride, by calculating the distance between the two end points of a single crack or hydride, its length can be obtained, and by taking the inverse tangent of its slope, its inclination can be obtained.

[0096] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0097] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer software product is stored in a storage medium, including a number of 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 of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0098] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying cracks and hydrides, characterized in that: include: Acquire a first image, and preprocess the first image to obtain a second image; Identify the second image to obtain pixel points of individual cracks and hydrides, establish a coordinate system, map the pixel points of the cracks and hydrides into the coordinate system, and obtain the coordinate positions of the cracks and hydrides; Obtain a set of coordinate positions of cracks and hydrides, and perform linear fitting on the point set by the least square method; Determine the termination point of the individual crack and the hydride after linear fitting, calculate the slope between the termination point of the individual crack and the termination point of the hydride, and obtain the inclination angle of the individual crack and the hydride; Outputs the identification results of individual cracks and hydrides.

2. A crack and hydride identification method according to claim 1, characterized in that: The preprocessing of the first image to obtain the second image comprises: Determine whether the first image is a grayscale image, if not, perform grayscale processing on the first image to obtain a grayscale image, if it is a grayscale image, do not perform processing; After the grayscale image is binarized, it is output as a second image.

3. A crack and hydride identification method according to claim 2, characterized in that: The identifying the second image to obtain individual crack and hydride pixel points includes: Step 1: obtaining any non-zero pixel point in the second image as a detection pixel point, wherein the detection pixel point is used as a starting point for extraction, and the detection pixel point is stored in the first set; Step 2: Identify several adjacent pixels of the detection pixel point, store the identified non-zero pixel points into a second set, reset the pixel values ​​of the original positions of the non-zero pixel points stored in the second set to zero, and delete the detection pixel points of the first set; Step 3: Store the non-zero pixel points stored in the second set in the first set as detection pixel points, and repeat the method of step 2 until there are no non-zero pixel points stored in the first set as detection pixel points, and the extraction is completed.

4. A crack and hydride identification method according to claim 3, characterized in that: The determination of the termination point of a single crack and a hydride comprises: Determine whether the individual cracks and hydrides have branches. If there are branches, perform geometric processing on the individual cracks and hydrides and determine the termination point. If there is no branch, the termination point is identified directly.

5. A crack and hydride identification method according to claim 4, characterized in that: The geometric processing comprises: The pixel width of the crack is thinned into a 1-pixel skeleton, and one of the first zero pixel points is obtained; Determine the number of second zero pixel points of several pixel points adjacent to the first zero pixel point. If the number of second zero pixel points is 1, then the second zero pixel point is determined to be the end point of the crack and the hydride. If the number of second zero pixel points is 2, then the second zero pixel point is determined to be the middle pixel. If the number of second zero pixel points is greater than 2, then the second zero pixel point is determined to be the branch point of the crack and the hydride.

6. A crack and hydride identification system, characterized in that: include: An image acquisition module is configured to acquire a first image and preprocess the first image to obtain a second image; A processing module is configured to identify the second image to obtain pixel points of individual cracks and hydrides, establish a coordinate system, map the pixel points of the cracks and hydrides into the coordinate system, and obtain coordinate positions of the cracks and hydrides; The analysis module is configured to obtain a set of coordinate positions of cracks and hydrides, perform linear fitting on the point set by the least square method; determine the termination points of the individual cracks and hydrides after the linear fitting, calculate the slope between the termination point of the individual crack and the termination point of the hydride, and obtain the inclination angle of the individual crack and the hydride; an output module configured to output identification results of individual cracks and hydrides; A main control module, the main control module is connected to the image acquisition module, the processing module, the analysis module and the output module, and is used to execute a crack and hydride identification method as described in any one of claims 1-5.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, a crack and hydride identification method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a crack and hydride identification method according to any one of claims 1 to 5 is implemented.

Images