Title: Online multi-response assessment using Taguchi and artificial neural network

Authors: S.S. Panda, S.S. Mahapatra

Addresses: Department of Mechanical Engineering, Indian Institute of Technology Patna, Patna 800013, India. ' Department of Mechanical Engineering, National Institute of Technology Rourkela, Rourkela 769008, India

Abstract: Engineering problems often embody many characteristics of a multi-response optimisation problem, and these responses are often conflicting in nature. To address this issue, this work uses grey-based Taguchi method to express surface roughness of drilled holes and drill flank wear into an equivalent single response. Experiments have been conducted in a radial drilling machine with five input parameters using L27 orthogonal array. It has been observed that combined response of flank wear and surface roughness is affected by almost all input parameters; however, drill diameter is statistically most significant. The prediction results obtained via. Taguchi method is compared with Back Propagation Neural Network (BPNN). [Received 20 November 2008; Revised 4 September 2009; Accepted 1 March 2010]

Keywords: factorial setting; DOE; design of experiments; grey Taguchi methods; artificial neural networks; ANNs; drilling; multi-response optimisation; surface roughness; hole drilling; drill flank wear; orthogonal array.

DOI: 10.1504/IJMR.2010.033469

International Journal of Manufacturing Research, 2010 Vol.5 No.3, pp.305 - 326

Published online: 02 Jun 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article