Adaptive Particle Swarm Optimization with Neural Network for Machinery Fault Detection
B. Kishore1, M.R.S. Satyanarayana2, K.Sujatha3
1B. Kishore, Department of Mechanical Engineering, GITAM School of Tchnology, GITAM University, Hyderabad, India,.
2Dr. M. R. S. Satyanarayana, Department of Mechanical Engineering, GITAM Institute of Technology, GITAM University, Visakhapatnam, India,.
3K. Sujatha, Department of Computer Science & Engineering, MIRACLE College of Engineering, JNTU K, Visakhapatnam, India.
Manuscript received on August 04, 2013. | Revised Manuscript received on August 28, 2013. | Manuscript published on September 05, 2013. | PP: 42-46 | Volume-3, Issue-4, September 2013. | Retrieval Number: D1767093413/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Rotating machines are one of the most important elements in almost all the industries and continuous condition monitoring of these crucial parts is essential for preventing early failure, production line breakdown, improving plant safety, efficiency and reliability. Faults may also be developed over a long period of time or even suddenly. However manual fault detection techniques are error prone. This paper identifies and utilizes the distribution information of the population to estimate the evolutionary states. Based on the states, Adaptive control strategies are developed for the inertia weight and acceleration coefficients for faster convergence speed. The Particle Swarm Optimization (PSO) is thus systematically extended to Adaptive Particle Swarm Optimization (APSO), so as to bring about outstanding performance when solving global optimization problems. This paper proposes an adaptive particle swarm optimization with adaptive parameters. Adaptive control strategies are developed for the inertia weight and acceleration coefficients for faster convergence speed.
Keywords: Artificial Neural Network, Adaptive Particle swarm Optimization (APSO), Fault detection, Particle swarm Optimization (PSO).