Image processing approach to automate feature measuring and process parameter optimizing of laser additive manufacturing process. (September 2021)

• Record Type: Journal Article
• Authors: Patil, Deepika B.; Nigam, Akriti; Mohapatra, Subrajeet
• Is Part Of: Journal of manufacturing processes. Volume 69(2021)
• Page Start: 630
• Page End: 647
• Publication Date: 2021-09
• Subjects: Laser additive manufacturing -- Image processing -- Geometric features -- Measurement -- Optimization -- Edge detection; Production management -- Data processing -- Periodicals; Manufacturing processes -- Periodicals; Procestechnologie; Productietechniek; Production -- Gestion -- Informatique -- Périodiques; Fabrication -- Périodiques; Manufacturing processes; Production management -- Data processing; Periodicals; 670.5
• DOI: 10.1016/j.jmapro.2021.07.064
• Languages: English
• ISSNs: 1526-6125

Abstract

Abstract: The present research work focuses on the development of image processing technique that can automatically extract the deposition geometric features and optimize the process parameters required for manufacturing components by laser additive manufacturing process. This paper reports (i) manufacturing of vertical and horizontal wall components and capturing its images, (ii) developing robust image-processing technique for feature extraction and measurement, (iii) formulating a component sorting methodology with a capability to accept and reject component, and (iv) developing the process parameter optimizing model to identify the optimized combination of process parameters used to manufacture components. The developed image processing algorithm has been validated against the manual measurement method and CAD model. It has been observed that the proposed image processing algorithm can measure the geometric features of the vertical and horizontal wall components with an error of less than 3%. The optimization study gave the optimized value of laser power as 820 W, 850 W, 800 W and 860 W, scanning speed as 500 mm/min, 500 mm/min, 730 mm/min and 700 mm/min, and powder feed rate as 6 g/min, 10 g/min, 7 g/min and 7 g/min for effective vertical wall width, effective vertical wall height, effective horizontal wall width and effective horizontal wall height, respectively. The optimized process parameters were validated experimentally on laser based additive manufacturing process. The optimized values of effective vertical wall width, effective vertical wall height, effective horizontal wall width and effective horizontal wall height are 5.003, 14.003, 20.003 and 6.002, respectively, with corresponding experimental values as 5.028, 14.016, 20.018 and 6.028, respectively. Therefore, for the fast-growing additive manufacturing industry the proposed image processing methodology will offer benefits of automatic feature measuring process and process parameter optimizing with high accuracy and less human interference. In future, the image processing algorithm will be further developed for the real-time feature extraction of the depositions done by laser based additive manufacturing process. Highlights: Laser additive manufacturing of vertical and horizontal wall by depositing Inconel 625 on mild steel substrate. Development of robust image processing technique to automate the feature extraction of additive manufactured components. Methodology to identify the optimized combination of process parameters used in laser additive manufacturing. Validating the accuracy of the proposed approach with the currently used manual measurement method. The proposed approach can measure the geometric features of the components with an error of less than 3%.