Optimization of Abrasive Jet Machining Processes Using Evolutionary Algorithms

Authors:

Abstract
Abrasive Jet Machining is a non-traditional machining process with the considerable versatility of use, mostly in cutting, cleaning, and deburring hard and brittle materials. In AJM, optimal parameters involve such things as abrasive flow rate, pressure, and standoff distance, all of which are very important for attaining the appropriate performance metrics with respect to material removal rate (MRR) and surface finish. It applies evolutionary algorithms, specifically Genetic Algorithms (GA) and Particle Swarm Optimization (PSO), to the optimization of AJM processes. The evolutionary algorithms may efficiently locate optimal parameter combinations from computer simulations of various machining conditions into significant reductions in energy, wear, and increases in accuracy in machining. The computational approach given below provides a robust framework for achieving precision in AJM, beating traditional optimization techniques. Experimental verification has demonstrated the effectiveness of proposed EA-based models in optimizing efficiency in AJM.

This publication has 35 references indexed in Scilit: