An approach for optimization of the insert grinding process using artificial intelligence

• Grant number: 22/01711-7
• Support Opportunities: Scholarships in Brazil - Master
• Start date: October 01, 2022
• End date: October 31, 2024
• Field of knowledge: Engineering - Mechanical Engineering - Manufacturing Processes
• Principal Investigator: João Vitor de Carvalho Fontes
• Grantee: Mateus Keniti Nakashima Sinzato
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil
• Associated scholarship(s): 23/06179-4 - Hard turning of 4142 alloy steel with grinded tools for special edge preparation, BE.EP.MS

Abstract

Grinding is an abrasive process often employed in secondary operations due to the possibility of obtaining narrow dimensional and geometric tolerances, besides low surface roughness. Besides hardened steels, that usually undergo finishing operations with grinding wheels, other materials may also be ground, like cermets: composites with ceramic particles and metallic matrix. Popularly known as hard metals, these materials mainly constituted by tungsten carbides and cobalt have wide application as machining tools. In this case, grinding is one among several abrasive processes that can be applied to the preparation of cutting edges; but it is verified a lack of publications on this purpose, although their increasing number in the last few years. This master's project intends to apply artificial intelligence algorithms as an optimization tool for carbide inserts grinding considering, for example, properties of the grinding wheel and machining parameters as input factors and geometric features of the products, as well as components of the grinding force as response outputs. The work is planned to be developed starting from a preliminary model based on Taguchi methodology with a small orthogonal array and, after the analysis of variance, propose a more robust model, always having on hand artificial intelligence such as fuzzy inference, genetic algorithms and neural networks.