Machining performance analysis in end milling: Predicting using ANN and a comparative optimisation study of ANN/BB-BC and ANN/PSO

Abstract

In engineering practice, it is interesting to find top-performing and newly-developed optimisers to solve particular engineering optimisation problems efficiently. However, until new optimisers are extensively used on problems, their potentials may be least known. This paper presents applications of a multi-objective surrogate-based optimisation of end milling machine performance. Back-propagation neural networks are trained in generating objective functions for surface roughness and tool wear. The optimisers are the big-bang big-crunch (BB-BC) and particle swarm optimisation (PSO). The novelty of the paper lies in the application of the newly developed BB-BC in the machining field and the novel combination of the artificial neural network (ANN) with BB-BC. The results obtained from the two case studies presented indicate that the proposed approach is capable of selecting optimal solutions.