An Investigation of Grinding Process Optimization via Evolutionary Algorithms

In this paper, the performance of some evolutionary algorithms on grinding process optimization of silicon carbide (SiC) is investigated. The grinding of SiC is not an easy task due to its low fracture toughness, therefore making the material sensitive to cracking. The efficient grinding involves the optimal selection of operating parameters to maximize the material removal rate (MRR) while maintaining the required surface finish and limiting surface damage. In this work, optimization based on the available model has been carried out to obtain optimum parameters for silicon carbide grinding via three prominent evolutionary algorithms. They are particle swarm optimization (PSO), differential evolution (DE) and genetic algorithm (GA). The objective of this optimization process is to maximize the MRR, subject to surface finish and damage constraints of the grinding process. Numerical results show that PSO is comparatively superior in comparison with DE and GA algorithms for grinding process optimization in terms of its accuracy and convergent capability