Abstract: The present application relates to a method for statistical distribution characterization of dendritic structures in original position of single crystal superalloy, and relates to the technical field of analysis of metal material composition and microstructure, comprising the following steps: step 1, processing a to-be-tested sample and determining a calibration coefficient; step 2, obtaining a two-dimensional element content distribution map of the to-be-tested sample; and step 3, determining the number and average spacing of primary dendrites. A composition distribution region analyzed in the present application is larger than the area of a distribution region of the traditional microscopic analysis method, and the sample preparation is simple. The distribution, number and average spacing of the primary dendrites can be obtained without metallographic corrosion sampling.

Abstract: A quantitative statistical characterization method of micron-level second phase in aluminum alloy based on deep learning is disclosed. The method includes obtaining a feature database of the standard sample, training the feature database by the image segmentation network U-Net based on deep learning to obtain a U-Net segmentation model, selecting the corresponding parameters of the optimal precision and establishing a U-Net target model; clipping the aluminum alloy image to be detected and inputting the clipped images into the U-net target model, obtaining the size, area and position information of the second phase through the connected region algorithm, carrying out statistical distribution of the data set combined with the mathematical statistical method, and restoring the position information to the surface of the aluminum alloy to be tested to obtain the full-field quantitative statistical distribution and visualization results.

Abstract: The invention belongs to the technical field of quantitative statistical distribution analysis for micro-structures of metal materials, and relates to a method for automatic quantitative statistical distribution characterization of dendrite structures in a full view field of metal materials. According to the method based on deep learning in the present invention, dendrite structure feature maps are marked and trained to obtain a corresponding object detection model, so as to carry out automatic identification and marking of dendrite structure centers in a full view field; and in combination with an image processing method, feature parameters in the full view field such as morphology, position, number and spacing of all dendrite structures within a large range are obtained quickly, thereby achieving quantitative statistical distribution characterization of dendrite structures in the metal material.

Abstract: The present application relates to a method for statistical distribution characterization of dendritic structures in original position of single crystal superalloy, and relates to the technical field of analysis of metal material composition and microstructure, comprising the following steps: step 1, processing a to-be-tested sample and determining a calibration coefficient; step 2, obtaining a two-dimensional element content distribution map of the to-be-tested sample; and step 3, determining the number and average spacing of primary dendrites. A composition distribution region analyzed in the present application is larger than the area of a distribution region of the traditional microscopic analysis method, and the sample preparation is simple. The distribution, number and average spacing of the primary dendrites can be obtained without metallographic corrosion sampling.

Abstract: An apparatus and a method for preparing glow discharge sputtering samples for materials microscopic characterization are provided. The apparatus includes a glow discharge sputtering unit, a glow discharge power supply, a gas circuit automatic control unit, a spectrometer, and a computer. The structure of the glow discharge sputtering unit is optimized to be more suitable for sample preparation by simulation. By adding a magnetic field to the glow discharge plasma, uniform sample sputtering is realized within a large size range of the sample surface. The spectrometer monitors multi-element signal in a depth direction of the sample sputtering, so that precise preparation of different layer microstructures is realized. In conjunction with the acquisition of the sample position marks and the precise spatial coordinates (x, y, z) information, the correspondence between the surface space coordinates and the microstructure of the sample is conveniently realized.

Abstract: The present invention discloses a high throughput statistical characterization method of metal micromechanical properties, which comprises: grinding and polishing a metal sample until specular reflection finish satisfies a test requirement; marking position coordinates of a to-be-measured area on the metal sample by a microhardness tester to ensure the comparison of the same to-be-measured area; conducting an isostatic pressing strain test on the to-be-measured area by an isostatic pressing technology; and comparing high throughput characterization of components, microstructures, microdefects and three-dimensional surface morphology of the metal sample before and after isostatic pressing strain to obtain the full-view-field cross-scale high throughput statistical characterization of micromechanical property uniformity of the metal sample.

Abstract: The invention belongs to the technical field of quantitative statistical distribution analysis for micro-structures of metal materials, and relates to a method for automatic quantitative statistical distribution characterization of dendrite structures in a full view field of metal materials. According to the method based on deep learning in the present invention, dendrite structure feature maps are marked and trained to obtain a corresponding object detection model, so as to carry out automatic identification and marking of dendrite structure centers in a full view field; and in combination with an image processing method, feature parameters in the full view field such as morphology, position, number and spacing of all dendrite structures within a large range are obtained quickly, thereby achieving quantitative statistical distribution characterization of dendrite structures in the metal material.

Abstract: The present invention discloses, a full-view-field quantitative statistical distribution representation method for microstructures of ?? phases in a metal material, comprising the following steps: step a: labeling ?? phases, cloud clutters and ? matrixes by Labelme, and then making standard feature training samples; step b: building a deep learning-based feature recognition and extraction model by means of BDU-Net; step e: collecting ?? feature maps in the metal material to be detected; step d: automatically recognizing and extracting the ?? phases; and step e: performing in-situ quantitative statistical distribution representation on the ? phases in the full view field within a large range.

Abstract: The invention belongs to the technical field of the quantitative statistical distribution analysis of the features from characteristic images of microstructures and precipitated phases in metal materials, and relates to a quantitative statistical distribution characterization method of precipitate particles with the full field of view in a metal material. The method comprises the following steps of electrolytic corrosion of a metallic material specimen, automatic collection of characteristic images of microstructure, automatic stitching and fusion of the full-view-field microstructure images, automatic identification and segmentation of the precipitate particles and quantitative distribution characterization of the precipitate particles with the full field of view in a large-range scale.

Abstract: An apparatus and method for a large-scale high-throughput quantitative characterization and three-dimensional reconstruction of a material structure. The apparatus having a glow discharge sputtering unit, a sample transfer device, a scanning electron microscope unit and a GPU computer workstation. The glow discharge sputtering unit can achieve large size (cm order), nearly flat and fast sample preparation, and controllable achieve layer-by-layer ablation preparation along the depth direction of the sample surface; rapid scanning electron microscopy (SEM) can achieve large-scale and high-throughput acquisition of sample characteristic maps. The sample transfer device is responsible for transferring the sample between the glow discharge sputtering source and the scanning electron microscope in an accurately positioning manner.

Abstract: An apparatus and method for a large-scale high-throughput quantitative characterization and three-dimensional reconstruction of a material structure. The apparatus having a glow discharge sputtering unit, a sample transfer device, a scanning electron microscope unit and a GPU computer workstation. The glow discharge sputtering unit can achieve large size (cm order), nearly flat and fast sample preparation, and controllable achieve layer-by-layer ablation preparation along the depth direction of the sample surface; rapid scanning electron microscopy (SEM) can achieve large-scale and high-throughput acquisition of sample characteristic maps. The sample transfer device is responsible for transferring the sample between the glow discharge sputtering source and the scanning electron microscope in an accurately positioning manner.

Abstract: The invention belongs to the technical field of the quantitative statistical distribution analysis of the features from characteristic images of microstructures and precipitated phases in metal materials, and relates to a quantitative statistical distribution characterization method of precipitate particles with the full field of view in a metal material. The method comprises the following steps of electrolytic corrosion of a metallic material specimen, automatic collection of characteristic images of microstructure, automatic stitching and fusion of the full-view-field microstructure images, automatic identification and segmentation of the precipitate particles and quantitative distribution characterization of the precipitate particles with the full field of view in a large-range scale.