# US 2021/0279853 A1 · System and method for automated microstructure analysis > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0279853 A1 - Document ID: US20210279853A1 - Status: Published application - Kind: A1 - Application number: 16/810,129 - Filed: 2020-03-05 - Published: 2021-09-09 - Earliest claimed: 2020-03-05 - Assignees: Siemens Aktiengesellschaft - Applicants: Siemens Aktiengesellschaft - Inventors: Arindam Dasgupta; Biswadip Dey; Anand A. Kulkarni; Amit Chakraborty - Web page: https://patentgrep.com/patent/US20210279853A1 ## CPC - G06T 7/0004: {Industrial image inspection} - G06N 20/00: Machine learning - G06T 5/70: Denoising; Smoothing - G06T 7/62: of area, perimeter, diameter or volume - G06T 2207/10056: Microscopic image - G06T 2207/20182: Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering - G06T 2207/30164: Workpiece; Machine component - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A computer-implemented method for assessing material microstructure of a machine component involves obtaining a raw image of a section of the component captured via a microscope. The method further includes pre-processing the raw image to generate a ternary image defined by pixel data including three levels of intensities. The method further includes identifying, from the ternary image, phase boundaries delineating at a phase in a primary constituent material of the component. The method further includes determining a volume associated with the phase based on the identified phase boundaries. The proposed method may be utilized, for example, as an automated tool for assessing material degradation and for quality control of gas turbine engine components. ## Claims ### Claim 1 A computer-implemented method for assessing material microstructure of a machine component, comprising: obtaining a raw image of a section of the component captured via a microscope, pre-processing the raw image to generate a ternary image defined by pixel data including three levels of intensities, identifying, from the ternary image, phase boundaries delineating a phase in a primary constituent material of the component, and determining a volume associated with the phase based on the identified phase boundaries. ### Claim 2 (depends on 1) The method of claim 1, wherein pre-processing the raw image comprises: applying histogram equalization on a gray-scale histogram of the raw image to obtain an intermediate gray-scale image with enhanced contrast, and transforming the intermediate gray-scale image into the ternary image based on defined first and second threshold intensity values. ### Claim 3 (depends on 1) The method of claim 1, wherein the three levels of intensities in the ternary image comprise: a lowest level of intensity including an intensity corresponding to a background, an intermediate level of intensity including an intensity corresponding to the phase, and a highest level of intensity including an intensity corresponding to the primary constituent material of the component. ### Claim 4 (depends on 1) The method of claim 1, wherein the phase boundaries are identified based on a determination of thresholding parameters indicative of points of inflection in the ternary image. ### Claim 5 (depends on 4) The method of claim 4, wherein the thresholding parameters are determined based on a machine learning algorithm trained on prior data. ### Claim 6 (depends on 1) The method of claim 1, comprising applying a smoothing filter to generate smoothened phase boundaries from the identified phase boundaries, wherein the smoothened phase boundaries are utilized in the determination of the volume associated with the phase. ### Claim 7 (depends on 6) The method of claim 6, wherein a bandwidth of the smoothing filter is determined based on a machine learning algorithm trained on prior data. ### Claim 8 (depends on 1) The method of claim 1, wherein determining the volume associated with the phase comprises determining a volume of at least one depletion region associated with the phase. ### Claim 9 (depends on 8) The method of claim 8, wherein the at least one depletion region comprises an inner depletion region located between the phase and an unaffected material and an outer depletion region located between the phase and a background, wherein identifying the phase boundaries comprises: identifying a first phase boundary separating the outer depletion region from the background, identifying a second phase boundary separating the phase from the outer depletion region, identifying a third phase boundary separating the phase from the inner depletion region, and identifying a fourth phase boundary separating the inner depletion region from the unaffected material. ### Claim 10 (depends on 1) The method of claim 1, wherein determining the volume associated with the phase comprises determining a volume of an un-depleted portion of the phase. ### Claim 11 (depends on 1) The method of claim 1, comprising applying the method to a sequence of microscope images of the machine component at different points during service and recording respective results in a searchable database. ### Claim 12 (depends on 1) The method of claim 1, comprising applying the method to a plurality of machine components of the same kind and recording respective results to create a statistical database of a level of phase depletion at different regions of the machine components. ### Claim 13 A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to: obtain a raw image of a section of the component captured via a microscope, pre-process the raw image to generate a ternary image defined by pixel data including three levels of intensities, identify, from the ternary image, phase boundaries delineating a phase in a primary constituent material of the component, and determine a volume associated with the phase based on the identified phase boundaries. ### Claim 14 A computing system comprising: a processor; and a memory storing instructions that, when executed by the processor, configure the computing system to: obtain a raw image of a section of the component captured via a microscope, pre-process the raw image to generate a ternary image defined by pixel data including three levels of intensities, identify, from the ternary image, phase boundaries delineating a phase a primary constituent material of the component, and determine a volume associated with the phase based on the identified phase boundaries. ### Claim 15 (depends on 14) The computing system of claim 14, wherein for pre-processing the raw image, the computing system is configured to: apply histogram equalization on a gray-scale histogram of the raw image to obtain an intermediate gray-scale image with enhanced contrast, and transform the intermediate gray-scale image into the ternary image based on defined first and second threshold intensity values. ### Claim 16 (depends on 14) The computing system of claim 14, wherein the three levels of intensities in the ternary image comprise: a lowest level of intensity including an intensity corresponding to a background, an intermediate level of intensity including an intensity corresponding to the phase, and a highest level of intensity including an intensity corresponding to the primary constituent material of the component. ### Claim 17 (depends on 14) The computing system of claim 14, wherein the computing system is configured to identify the phase boundaries based on the determination of thresholding parameters indicative of points of inflection in the ternary image. ### Claim 18 (depends on 17) The computing system of claim 17, wherein computing system is configured to determine the thresholding parameters based on a machine learning algorithm trained on prior data. ### Claim 19 (depends on 14) The computing system of claim 14, wherein the computing system is configured to apply a smoothing filter to generate smoothened phase boundaries from the identified phase boundaries, wherein the smoothened phase boundaries are utilized in the determination of the volume associated with the phase. ### Claim 20 (depends on 19) The computing system of claim 19, wherein the computing system is configured to determine a bandwidth of the smoothing filter based on a machine learning algorithm trained on prior data.