CFNN-PSO: An Iterative Predictive Model for Generic Parametric Design of Machining Processes

Every production process consists of a large number of dependent and independent variables, which substantially influence the quality of the machined parts. Due to the large impact of process variabilities, it is difficult to design optimal models for the machining processes. Mathematical or numerical models for production processes are resource driven, which are not cost effective approaches in terms of computation and economical production. In this paper, a new artificial neural network (ANN) based predictive model is introduced, which exploits particle swarm optimization (PSO) algorithm to minimize the root mean square errors (RMSE) for the network training. This approach can effectively obtain an optimized predictive model that can calculate precise output responses for the production processes. In order to verify the proposed approach, two case studies are considered from literature and shown to produce significant improvements. Furthermore, the proposed model is validated on abrasive water jet machining (AWJM) with industrial garnet abrasives and optimal machining conditions have been obtained with optimized responses, which are substantially improved while compared with gray relational analysis (GRA).