Title: Prediction and comparison of emitted radiation from a flat plate heat sink using linear regression analysis with artificial neural network and ANFIS

Authors: S. Manivannan; S. Prasanna Devi; R. Arumugam; S. Paramasivam; N.M. Sudharsan

Addresses: Electrical and Electronics Engineering Department, Anna University Chennai, Chennai – 600025, Tamil Nadu, India. ' Department of Industrial Engineering, Anna University Chennai, Chennai – 600025, Tamil Nadu, India. ' Electrical and Electronics Engineering Department, SSN College of Engineering, Old Mahabalipuram Road, SSN Nagar, Chennai – 603110, Tamil Nadu, India. ' ESAB Engineering Services Limited, G22, SIPCOT Industrial Park, Chennai – 602105, Tamil Nadu, India. ' Sarvajit-CAE, No. 12, 5th Street, Bakthavatchalam Nagar, Adyar, Chennai – 600020, Tamil Nadu, India

Abstract: This paper provides a comparison of multiple linear regression analysis with artificial neural network (ANN) and adaptive neuro fuzzy inference system (ANFIS), for predicting the emitted radiations from a flat plate heat sink. HFSS simulations were designed using Ansoft version 12 for the L27 orthogonal array and optimised using Taguchi design of experiments method. The heat sink geometry factors considered for the L27 (six factors, three levels) design are length, width, fin height, base height, fin thickness and number of fins and the response studied is the emitted radiation from the heat sink. A meta model is developed based on a multiple linear regression method using HFSS simulations. Also, the results of L27 orthogonal array were used to train the artificial neural network and the ANFIS-based intelligent networks. The accuracy of results for the prediction of emitted radiations using multiple linear regressions, ANN and ANFIS were compared with HFSS simulations. From the results, it is found that the ANFIS outperforms ANN and regression models for the prediction of the emitted radiations from the heat sink.

Keywords: radiation emissions; heat sinks; multiple linear regression analysis; MLRA; artificial neural networks; ANNs; adaptive neurofuzzy inference system; ANFIS; fuzzy logic; metamodelling.

DOI: 10.1504/IJIT.2011.043588

International Journal of Instrumentation Technology, 2011 Vol.1 No.1, pp.18 - 33

Received: 22 Apr 2010
Accepted: 22 Jun 2010

Published online: 30 Dec 2014 *

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