Component uniformity detection method based on titanium alloy cast ingot microscopic image

Abstract

The invention relates to the technical field of image data processing, in particular to a titanium alloy ingot microcosmic image-based component uniformity detection method, which comprises the following steps of: acquiring a sample image, determining the gray level of each crystal grain according to the number of pixel points and a gray value in each crystal grain of the sample image, and acquiring a principal component vector of the crystal grain, determining a phase structure attribution coefficient of the crystal grains according to the quantity and the die length of the principal component vectors of the crystal grains and the gray scale and the area of the crystal grains, further determining the structural crystal grains of each phase in the sample image, and determining the phase structure uniformity of the sample image according to the quantity of the structural phase crystal grains; and obtaining the component uniformity of the sample image by adopting a method which is the same as the phase structure uniformity, and determining the comprehensive uniformity of the sample image according to the component uniformity and the phase structure uniformity of the sample image. According to the method, the component uniformity of the sample is comprehensively evaluated by combining the component of the sample and the crystal grain morphology, and the reliability of component uniformity detection of the sample is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and particularly to a method for detecting the compositional uniformity based on the microscopic image of a titanium alloy ingot. Background Art

[0002] Titanium alloys are a type of metal alloy with excellent properties, mainly composed of titanium element and other alloying elements (such as iron, aluminum, vanadium, nickel, etc.). Evaluating the compositional uniformity of titanium alloys is not only crucial for the quality control and performance optimization of existing products, but also an important basis for developing new materials and promoting industrial progress. Through precise analysis and evaluation, the reliability, safety, and economy of materials can be effectively improved to meet the requirements of various industrial and application fields.

[0003] Currently, when detecting the compositional uniformity of a titanium alloy ingot sample, generally, the specific X-ray energy and intensity of each element are analyzed by an electron probe to determine the presence and relative content of each component in the sample, and then its compositional uniformity is calculated. However, the grains of different components in the titanium alloy may correspond to different morphological structures, and the distribution uniformity of these structures also affects the strength, plasticity, and toughness of the overall material to a certain extent, making the result of determining the compositional uniformity of the sample through the content of each component present in the sample inaccurate and unable to accurately reflect the compositional uniformity of the sample. Summary of the Invention

[0004] The present invention provides a method for detecting the compositional uniformity based on the microscopic image of a titanium alloy ingot to solve the existing problems.

[0005] The method for detecting the compositional uniformity based on the microscopic image of a titanium alloy ingot of the present invention adopts the following technical solution: An embodiment of the present invention provides a method for detecting the compositional uniformity based on the microscopic image of a titanium alloy ingot, and the method includes the following steps: Obtain a sample image, where the sample image contains a plurality of grains; According to the number of pixel points and the pixel point gray values included in each grain in the sample image, determine the gray level of each grain, divide the sample image into a plurality of blocks with a preset side length, obtain a plurality of principal component vectors in each grain, and determine the phase structure attribution coefficient of the grain according to the number and modulus length of the principal component vectors in the grain, the gray level and area of the grain, and further determine the grains of each phase structure in the sample image; According to the number of blocks and the number of grains of any phase structure in the block, determine the distribution uniformity of the grains of any phase structure in the sample image, and determine the phase structure uniformity of the sample image according to the distribution uniformity of the grains of any phase structure in the sample image; Obtain the sample components, determine the component uniformity of the sample image, and determine the comprehensive uniformity of the sample image according to the component uniformity and the phase structure uniformity of the sample image.

[0006] Further, the method for determining the gray level of each grain according to the number of pixel points and the gray values of the pixel points included in each grain in the sample image specifically includes: Obtain the average gray value of all pixel points in the th grain, calculate the average value of the absolute values of the differences between the average gray value and the gray values of all pixel points in the th grain, then obtain the inverse proportional normalization value of the average gray value, and record the product of the average value of the absolute values of the differences and the inverse proportional normalization value as the gray level of the

[0007] th grain. Perform principal component analysis on each grain to obtain several principal component vectors in the grain, and partition the sample image. Divide the sample image into several blocks with a preset side length of through the grid division method; Determine the phase structure attribution coefficient of the grain according to the number and modulus length of the principal component vectors in the grain, the gray level of the grain, and the area of the grain; Calculate the phase structure attribution coefficients of all grains in the sample image, preset a first threshold, and mark the grains with a phase structure attribution coefficient greater than or equal to the preset first threshold as phase grains, and mark the other grains in the sample image except for the phase grains as phase grains.

[0008] Further, the method for determining the phase structure attribution coefficient of the grain specifically includes: Obtain the attribution coefficient factor according to the gray level and area of the grain; Calculate the value of the modulus length of the maximum principal component vector of the th grain minus the sum of the modulus lengths of all the remaining principal component vectors, and record the normalized value of the product of the sum value and the attribution coefficient factor of the th grain as the phase structure attribution coefficient of the th grain.

[0009] Further, the specific calculation method of the attribution coefficient factor of the th grain is: According to the gray level of the th grain, the maximum area of all grains in the block to which the th grain belongs and the The difference in the area of ​​the first grain is used to determine The attribution coefficient factor of the grain, The gray level of each grain and the The maximum area of ​​all grains in the block to which the first grain belongs is The difference in the area of ​​the grains is directly proportional.

[0010] Furthermore, the determination of the distribution uniformity of grains of any phase structure in the sample image includes the following specific methods: All blocks are combined in pairs without repetition to obtain several block combinations. According to the number of grains in two blocks in the block combination, the distribution uniformity of grains of any phase structure in the sample image is determined.

[0011] Furthermore, the distribution uniformity of grains of any phase structure in the sample image includes the following specific methods: Get The absolute value of the difference in the number of phase structure grains in the two blocks in each block combination is The reciprocal of the mean of the absolute value of the difference between the number of phase structure grains in two blocks in all block combinations is recorded as The uniformity of distribution of phase structure grains.

[0012] Furthermore, the determining of the phase structure uniformity of the sample image includes the following specific methods: According to the sample image The distribution uniformity of phase grains and The distribution uniformity of the phase grains determines the uniformity of the phase structure of the sample image. The distribution uniformity of phase grains and The distribution uniformity of the phase grains is directly proportional.

[0013] Furthermore, the method of determining the comprehensive uniformity of the sample image according to the component uniformity and phase structure uniformity of the sample image includes the following specific methods: The comprehensive uniformity of the sample image is determined according to the phase structure uniformity of the sample image and the component uniformity of the sample, and the phase structure uniformity of the sample image and the component uniformity of the sample are in a positive proportional relationship.

[0014] Furthermore, the obtaining of sample components and determining the component uniformity of the sample image includes the following specific methods: The sample surface is irradiated with an electron probe to obtain the sample components, and the component uniformity of the sample image is obtained with the help of the phase structure uniformity calculation method.

[0015] The beneficial effects of the technical solution of the present invention are as follows: According to the number of pixel points and the pixel point gray values included in each grain in the sample image, determine the gray level of each grain, divide the sample image into several blocks with a preset side length, obtain several principal component vectors in each grain, and determine the phase structure attribution coefficient of the grain according to the number and modulus length of the principal component vectors in the grain, the gray level and area of the grain, and further determine the α-phase grains and β-phase grains in the sample image. According to the number of blocks and the number of grains with any phase structure in the block, determine the distribution uniformity of the grains with any phase structure in the sample image. According to the distribution uniformity of the grains with any phase structure in the sample image, determine the phase structure uniformity of the sample image. Obtain the sample components, determine the component uniformity of the sample image, improve the comprehensiveness and reliability of the component uniformity detection of the titanium alloy ingot micrograph, and determine the comprehensive uniformity of the sample image according to the component uniformity and phase structure uniformity of the sample image, thereby improving the accuracy of the component uniformity detection of the titanium alloy ingot micrograph. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0017] Figure 1 FIG. is a flowchart of the steps of the method for detecting the component uniformity based on the titanium alloy ingot micrograph of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following will, in conjunction with the accompanying drawings and preferred embodiments, describe in detail the specific implementation manners, structures, features and effects of the method for detecting the component uniformity based on the titanium alloy ingot micrograph proposed by the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0020] The following will specifically describe the specific solution of the method for detecting the component uniformity based on the titanium alloy ingot micrograph provided by the present invention with reference to the accompanying drawings.

[0021] Please refer toFigure 1 , which shows a flowchart of the steps of a method for detecting the compositional uniformity based on the microscopic image of a titanium alloy ingot provided by an embodiment of the present invention. The method includes the following steps: Step S001: Obtain a sample image, where the sample image contains a number of grains.

[0022] It should be noted that, in order to detect the compositional uniformity of the microscopic image of a titanium alloy ingot, a representative sample needs to be cut from the titanium alloy ingot, and the microscopic image of the sample is obtained.

[0023] Specifically, in order to implement the method for detecting the compositional uniformity based on the microscopic image of a titanium alloy ingot proposed in this embodiment, first, the surface microscopic image of the titanium alloy ingot sample needs to be collected. The specific process is as follows: The obtained sample is ground and polished to obtain a smooth surface suitable for microscopic observation. The surface of the sample is treated with an appropriate chemical etchant, and the treated sample is placed under a microscope. The focal length and the lens barrel are adjusted to make the microscopic structure of the sample clearly appear, thereby obtaining the surface microscopic image of the titanium alloy ingot sample. The obtained microscopic image is grayscale processed, and the grayscale processed image is denoted as the sample image.

[0024] So far, the sample image is obtained through the above method.

[0025] Step S002: Determine the gray level of each grain according to the number of pixel points and the pixel point gray values contained in each grain in the sample image. Divide the sample image into several blocks with a preset side length, obtain several principal component vectors in each grain, and determine the phase structure attribution coefficient of the grain according to the number and modulus length of the principal component vectors in the grain, the gray level and area of the grain, and further determine the grains of each phase structure in the sample image.

[0026] It should be noted that the microscopic structure of titanium alloy contains various components, which often appear in the form of grains. On the microscopic scale, the grains of titanium alloy can exhibit different tissue morphologies, such as uniform grains, flaky grains or needle-shaped grains, etc. Different grains are composed of different phases, and the differences between different phases can be observed through a microscope. The structure of titanium alloy grains is mainly α phase (hexagonal close-packed structure) and β phase (body-centered cubic structure). Grains of different phases will also have certain differences in morphology and gray level. In order to detect the compositional uniformity of the sample image, it is necessary to determine the number of grains of different phases in the sample image.

[0027] Step (2.1), determine the gray level of each grain according to the number of pixel points and the pixel point gray values contained in each grain in the sample image.

[0028] It should be noted that in the optical microscope or scanning electron microscope images, Due to its close-packed hexagonal structure, the α-phase grains may result in relatively low reflectivity or high absorptivity, thus showing a darker gray level. At the same time, the gray level distribution of the α-phase grains may be relatively consistent within the grains, but there may be a sudden change in gray level near the grain boundaries. While the β-phase grains have higher reflectivity due to their different electron densities and surface characteristics, and usually show a brighter gray level in the image. At the same time, the gray level distribution inside them is relatively uniform.

[0029] Use the Canny edge detection algorithm to perform edge detection on the sample image to obtain several edge lines. Take the closed area formed by each edge line in the sample image as a grain. The sample image contains several grains of the same size. Determine the gray level of each grain according to the number of pixel points and the gray values of the pixel points contained in each grain.

[0030] As an embodiment, the specific calculation method for the gray level of each grain is: In the formula, represents the gray level of the th grain; represents the number of pixel points contained in the th grain; represents the gray value of the th pixel point in the th grain; represents the average gray value of all pixel points in the th grain; represents taking the absolute value.

[0031] It should be noted that represents the gray level uniformity of the th grain. The larger the value, the greater the difference between the gray value of each pixel point contained in the th grain and the average gray value of all pixel points, and the more uneven the gray level of the th grain. represents the overall gray level of the th grain, which is measured by the difference between the average gray value of all pixel points and the maximum gray value in the th grain. The larger the value, the smaller the value, indicating that the overall gray level of the th grain is darker. Take as the inverse proportional normalization value of

[0032] Based on the above formula, the gray levels of all grains in the sample image are calculated. If the gray level of the grain is larger, it belongs to The greater the possibility of phase grains, the smaller the gray level, The greater the possibility of phase grains.

[0033] It should be noted that, when only a part of a pixel is in a certain grain, the calculation is also performed based on the entire pixel.

[0034] It should be noted that the Canny edge detection algorithm is an existing technology and will not be described in detail here.

[0035] Step (2.2), divide the sample image into several blocks with preset side lengths, obtain several principal component vectors in each grain, determine the phase structure attribution coefficient of the grain according to the number and modulus of the principal component vectors in the grain, the grayscale level and area of ​​the grain, and further determine the grains of each phase structure in the sample image.

[0036] It should be noted that the above steps only determine the possible phase structure of the grains based on their grayscale characteristics, but different phase structures also have differences in morphology. The phase has a hexagonal close-packed structure, and the grains are usually small, usually in the form of strips or flakes. The phase is a body-centered cubic structure with large grains, usually equiaxed or blocky. In order to more accurately determine the phase structure corresponding to different grains, it is necessary to determine the phase structure of the grains in combination with morphological characteristics.

[0037] First, principal component analysis is performed on each grain to obtain several principal component vectors in the grain, and the sample image is partitioned. The sample image is divided into several grids with a preset side length of of blocks.

[0038] It should be noted that based on experience The value of is 50, which can be adjusted according to actual conditions and is not specifically limited in this embodiment.

[0039] Then, the phase structure attribution coefficient of the grains is determined according to the number and modulus of the principal component vectors in the grains, the grayscale level of the grains, and the area of ​​the grains.

[0040] As an embodiment, the specific calculation method of the phase structure attribution coefficient of the grains is: In the formula, Indicates The phase structure attribution coefficient of each grain; Indicates The number of principal component vectors of each grain; Denote the modulus length of the maximum principal component vector of the th grain; Denote the modulus length of the th principal component vector of the th grain; Denote the gray level of the th grain; Denote the maximum area of all grains in the block where the th grain belongs;

[0041] It should be noted that Denote the morphological feature of the th grain. Since the phase grains usually appear as strips or flakes, there will be a maximum principal component vector in the phase grains to represent the extension trend of their shape. Therefore, the larger the value, the greater the possibility that the th grain is a phase grain. Denote the relative area size of the th grain. Since the phase grains are usually relatively small, while the phase grains are relatively large. Therefore, the larger the

[0042] value, the smaller the area of the th grain, and the greater the possibility that the th grain is a phase grain. Calculate the phase structure attribution coefficient of all grains in the sample image. Preset the first threshold. Denote the grains with the phase structure attribution coefficient greater than or equal to the preset first threshold as

[0043] phase grains, and denote the other grains in the sample image except the phase grains as

[0044] phase grains, so as to obtain the number of phase grains and The number of grains of any phase structure.

[0045] Step S003: Determine the distribution uniformity of grains of any phase structure in the sample image according to the number of blocks and the number of grains of any phase structure in each block, and determine the phase structure uniformity of the sample image according to the distribution uniformity of grains of any phase structure in the sample image.

[0046] It should be noted that after obtaining the number of grains of any phase structure in the sample image, the distribution uniformity of grains of any phase structure in the sample image can be determined according to the proportion of the number of grains of any phase structure in the sample image, so as to determine the phase structure uniformity of the sample image.

[0047] Step (3.1): Determine the distribution uniformity of grains of any phase structure in the sample image according to the number of blocks and the number of grains of any phase structure in each block.

[0048] For the entire sample image, non-repetitive pairwise combinations of all blocks are performed to obtain a number of block combinations (for example, if the blocks are 1, 2, 3, and 4, the block combinations are 12, 13, 14, 23, 24, and 34). According to the number of grains in the two blocks within the block combination, the distribution uniformity of grains of any phase structure in the sample image is determined.

[0049] Specifically: Obtain The absolute value of the difference in the proportion of the number of grains of any phase structure in the two blocks of each block combination, and The reciprocal of the average value of the absolute values of the differences in the proportion of the number of grains of any phase structure in the two blocks of all block combinations is denoted as The distribution uniformity of grains of any phase structure.

[0050] As an embodiment, the specific calculation method of the distribution uniformity of grains of any phase structure is: In the formula, represents The distribution uniformity of grains of any phase structure; represents the number of block combinations; represents the number of blocks; represents The proportion of the number of grains of any phase structure in the th block; represents The proportion of the number of grains of any phase structure in the th block; represents taking the absolute value.

[0051] It should be noted that the difference in the proportion of the number of grains of any phase structure in any two blocks in the sample image is used to measure the The uniformity of the distribution of grains with a phase structure The larger the value, the more similar the proportion of the number of grains with a phase structure in any two blocks in the sample image indicating that the uniformity of grains with a phase structure in the sample image is greater, that is the distribution of grains with a phase structure is more uniform The uniformity of the distribution of grains with a phase structure in the sample image is obtained

[0052] Thus, the uniformity of the distribution of grains with a phase and grains with a

[0053] Step (3.2), determine the phase structure uniformity of the sample image according to the uniformity of the distribution of grains with any phase structure in the sample image

[0054] It should be noted that since the titanium alloy contains grains with different phase structures, for the sample image, it is necessary to combine the uniformity of the distribution of grains with different phase structures to measure the phase structure uniformity of the sample

[0055] Specifically, according to the grains with a phase and the uniformity of the distribution of grains with a In the formula represents the phase structure uniformity of the sample image represents the uniformity of the distribution of grains with a phase in the sample image represents the uniformity of the distribution of grains with a phase in the sample image represents the exponential function with the natural constant as the base

[0056] Thus far, the phase structure uniformity of the sample image is obtained by the above method

[0057] Step S004: Obtain the sample components, determine the component uniformity of the sample image, and determine the comprehensive uniformity of the sample image according to the component uniformity and phase structure uniformity of the sample image

[0058] It should be noted that the phase structure uniformity of the sample image is obtained through the above steps. However, to more accurately and comprehensively detect the compositional uniformity of the sample image, it is also necessary to conduct a comprehensive detection by combining the distribution uniformity of each component of the sample

[0059] First, irradiate the surface of the sample with an electron probe to obtain the sample components

[0060] It should be noted that when a high-energy electron beam interacts with the surface of a sample, the main effects generated include electron excitation and X-ray radiation. When the components in the sample are excited by the electron beam, characteristic X-rays will be emitted. The unique X-ray energy and intensity of each component can be used to determine the presence and relative content of each component in the sample.

[0061] Then, by means of the method for calculating the uniformity of the phase structure in the above steps, the component uniformity of the sample image is obtained. , and then, based on the uniformity of the phase structure and the component uniformity, the comprehensive uniformity of the sample image is determined.

[0062] As an embodiment, the specific calculation method for the comprehensive uniformity of the sample image is as follows: It should be noted that represents the comprehensive uniformity of the sample image; represents the uniformity of the phase structure of the sample image; represents the component uniformity of the sample; represents the sigmoid normalization function.

[0063] It should be noted that the comprehensive uniformity of the sample image is determined by integrating the phase structure uniformity and the component uniformity, and the result is normalized to the range. If the larger the value, the more uniform the composition of the sample image, and vice versa.

[0064] So far, this embodiment is completed.

[0065] It should be noted that the model used in this embodiment is only used to represent the negative correlation relationship and to constrain the result of the model output to be within the interval. In specific implementation, it can be replaced with other models with the same purpose. This embodiment only takes the model as an example for description, and does not make specific limitations on it. Among them, refers to the input of the model.

[0066] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for detecting the compositional uniformity based on the microscopic image of a titanium alloy ingot, characterized in that, The method includes the following steps: Obtain a sample image, where the sample image contains several grains; According to the number of pixel points and the pixel point gray values included in each grain in the sample image, determine the gray level of each grain, divide the sample image into several blocks with a preset side length, obtain several principal component vectors in each grain, and determine the phase structure attribution coefficient of the grain according to the number and modulus length of the principal component vectors in the grain, the gray level and area of the grain, and further determine the grains of each phase structure in the sample image; According to the number of blocks and the number of grains of any phase structure in the block, determine the distribution uniformity of the grains of any phase structure in the sample image, and determine the phase structure uniformity of the sample image according to the distribution uniformity of the grains of any phase structure in the sample image; Obtain the sample components, determine the component uniformity of the sample image, and determine the comprehensive uniformity of the sample image according to the component uniformity and the phase structure uniformity of the sample image.

2. The method for detecting the compositional uniformity based on the microscopic image of a titanium alloy ingot according to claim 1, characterized in that, The specific method for determining the gray level of each grain according to the number of pixel points and the pixel point gray values included in each grain in the sample image is as follows: Obtain the average gray value of all pixel points in the -th grain, calculate the average value of the absolute values of the differences between the average gray value and the gray values of all pixel points in the -th grain, then obtain the inverse normalization value of the average gray value, and record the product of the average value of the absolute values of the differences and the inverse normalization value as the gray level of the -th grain.

3. The method for detecting the compositional uniformity based on the microscopic image of a titanium alloy ingot according to claim 1, characterized in that, The specific method for determining the phase structure attribution coefficient of the grain and further determining the grains of each phase structure in the sample image is as follows: Perform principal component analysis on each grain to obtain several principal component vectors in the grain, and partition the sample image. Divide the sample image into several blocks with a preset side length of by the grid division method; Determine the phase structure attribution coefficient of the grain according to the number and modulus length of the principal component vectors in the grain, the gray level of the grain, and the area of the grain; Calculate the phase structure attribution coefficients of all grains in the sample image, preset a first threshold, and mark the grains whose phase structure attribution coefficients are greater than or equal to the preset first threshold as phase grains, and mark the other grains in the sample image except for the phase grains as phase grains.

4. The method for detecting the compositional uniformity based on the microscopic image of a titanium alloy ingot according to claim 3, characterized in that, The specific method for determining the phase structure attribution coefficient of the grain is as follows: Obtain the attribution coefficient factor according to the gray level and the area of the grain; Calculate the difference between the magnitude of the maximum principal component vector of the th grain and the sum of the magnitudes of the remaining principal component vectors, and normalize the product of the sum value and the attribution coefficient factor of the th grain, which is denoted as the phase structure attribution coefficient of the th grain.

5. The method for detecting the compositional uniformity based on the microscopic image of a titanium alloy ingot according to claim 4, characterized in that, The specific calculation method of the attribution coefficient factor of the th crystal grain is as follows: According to the gray level of the th grain, the difference between the maximum area of all grains in the block to which the th grain belongs and the area of the th grain, determine the attribution coefficient factor of the th grain, and the gray level of the th grain and the difference between the maximum area of all grains in the block to which the th grain belongs and the area of the th grain are in a direct proportional relationship.

6. The method for detecting the compositional uniformity based on the microscopic image of a titanium alloy ingot according to claim 1, characterized in that, The specific method for determining the distribution uniformity of the grains of any phase structure in the sample image is as follows: Perform non-repeating pairwise combinations on all blocks to obtain several block combinations, and determine the distribution uniformity of the grains of any phase structure in the sample image according to the number of grains in the two blocks within the block combination.

7. The method for detecting the compositional uniformity based on the microscopic image of a titanium alloy ingot according to claim 6, characterized in that, The specific method for the distribution uniformity of the grains of any phase structure in the sample image is as follows: Obtain The absolute value of the difference in the proportion of the number of phase structure grains in two blocks within each block combination, and The reciprocal of the mean of the absolute values of the differences in the proportion of the number of phase structure grains in two blocks within all block combinations is denoted as The distribution uniformity of the phase structure grains.

8. The method for detecting the compositional uniformity based on the microscopic image of a titanium alloy ingot according to claim 1, characterized in that, The specific method for determining the phase structure uniformity of the sample image is as follows: According to the distribution uniformity of phase grains and the distribution uniformity of phase grains in the sample image, determine the phase structure uniformity of the sample image. The distribution uniformity of phase grains and the distribution uniformity of phase grains are in a direct proportional relationship.

9. The method for detecting the compositional uniformity based on the microscopic image of a titanium alloy ingot according to claim 1, characterized in that, The specific method for determining the comprehensive uniformity of the sample image is as follows: Determine the comprehensive uniformity of the sample image according to the phase structure uniformity of the sample image and the component uniformity of the sample, and the phase structure uniformity of the sample image and the component uniformity of the sample are in a proportional relationship.

10. The method for detecting the composition uniformity based on the microscopic image of a titanium alloy ingot according to claim 1, wherein, The specific method for obtaining the sample components and determining the component uniformity of the sample image is as follows: Irradiate the surface of the sample with an electron probe to obtain the sample components, and obtain the component uniformity of the sample image by means of the calculation method of the phase structure uniformity.

Images