Title: Identifying the behaviour of laser solid freeform fabrication system using aggregated neural network and the great salmon run optimisation algorithm

Authors: Ahmad Mozaffari; Alireza Fathi

Addresses: Department of Mechanical Engineering, Babol University of Technology, P.O. Box 484, Babol, Iran. ' Department of Mechanical Engineering, Babol University of Technology, P.O. Box 484, Babol, Iran

Abstract: Bio inspiration is a branch of artificial simulation science that shows pervasive contributions to variety of engineering fields such as automated pattern recognition, systematic fault detection, machine learning and applied optimisation. In this paper, a new bio-inspired optimisation algorithm which is the simulation of 'the great salmon run' (TGSR) is developed. Thereafter, it has been used to predict the efficient structure of an aggregated artificial neural network (AANN) to identify the behaviour of laser solid freeform fabrication (LSFF) system. Our experiments show that the combination of AANN and an appropriate supervised method is best suit for modelling cited engineering process. To prove the superiority of TGSR in both robustness and quality, it has been compared with most of the state-of-the-art optimisation techniques such as fast simulated annealing (FSA), parallel migrating genetic algorithm (PMGA), differential evolutionary with parent centric crossover (DEPCX), unified particle swarm optimisation (UPSO), shuffle frog leaping algorithm (SFLA), artificial bee colony (ABC), firefly algorithm (FA) and cuckoo search (CS). The obtained results confirm the acceptable potential of the proposed method to be applied on complex engineering systems.

Keywords: natural inspiration; TGSR optimisation; engineering optimisation; aggregated ANNs; artificial neural networks; laser SFF; solid freeform fabrication; great salmon run; bio-inspired computation; rapid prototyping; modelling.

DOI: 10.1504/IJBIC.2012.049901

International Journal of Bio-Inspired Computation, 2012 Vol.4 No.5, pp.330 - 343

Received: 13 Jun 2012
Accepted: 04 Aug 2012
Published online: 22 Sep 2014 *

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