Authors: Chinmaya P. Mohanty; Siba Sankar Mahapatra; Jambeswar Sahu
Addresses: Department of Mechanical Engineering, National Institute of Technology, Rourkela 769008, India ' Department of Mechanical Engineering, National Institute of Technology, Rourkela 769008, India ' Department of Mechanical Engineering, National Institute of Technology, Rourkela 769008, India
Abstract: In the present study, a Box-Behnken design of experiment strategy is adopted to obtain necessary information from a proposed numerical simulation model using thermal-structural analysis with reduced number of runs. Influence of important process parameters on several output responses has been studied to gain insight into machining performance. The numerical model is validated through conducting necessary experiments. Subsequently, artificial neural network (ANN) is used to establish relation between input parameters and the responses. The model provides an inexpensive and time saving alternative to study the performance of machining before actual cutting operation. The model can be used for selecting ideal process states to improve machining efficiency.
Keywords: electrical discharge machining; EDM; electro-discharge machining; response surface methodology; RSM; finite element analysis; FEA; artificial neural networks; ANNs; pulse-on-time; flushing pressure; residual stress; thermal-structural modelling; process performance; performance evaluation; Box-Behnken; design of experiments; DOE; numerical simulation; ANOVA; material removal rate; MRR; tool wear rate; TWR.
International Journal of Productivity and Quality Management, 2015 Vol.16 No.3, pp.347 - 371
Received: 26 Dec 2013
Accepted: 20 Mar 2014
Published online: 18 Aug 2015 *