Use of Radial Basis Function Neural Networks for Analysis of Unbalance in Rotating Machinery
G.R. Rameshkumar1, B.V.A. Rao2, K.P. Ramachandran3
1Dr. G.R. Rameshkumar, Department of Mechanical & Industrial Engineering, Caledonian College of Engineering, (A University college, Muscat, Sultanate of Oman.
2Prof. B.V.A. Rao, Advisor, Human Resources and International Relations, KL University, Vijayawada, India,
3Prof. K.P. Ramachandran, Associate Dean (PG&R), Caledonian College of Engineering, Muscat, Sultanate of Oman.
Manuscript received on July 01, 2012. | Revised Manuscript received on July 05, 2012. | Manuscript published on July 10, 2012. | PP: 168-171 | Volume-1, Issue-2, July 2012. | Retrieval Number: C8893019320/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. 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: Rotor unbalance is the most common cause of vibration in any rotating machinery. The Coast Down Time is used as a condition monitoring parameter to monitor the rotating machinery. The CDT is the total time taken by the system to dissipate the momentum acquired during sustained operation, which is an indicator of mechanical faults. Experiments were carried out on Forward Curved Centrifugal Blower to record the CDTs at selected blower shaft cut-off speeds of 1000 rpm, 1500 rpm, 2000 rpm and 2500 rpm respectively for various unbalance conditions. These experimental CDT data were used to train the neural network. The paper also discusses the successful incorporation of radial basis function neural network (RBF-NN) for the CDTs prediction for unbalance fault conditions. The results showed that the RBFNN predicted CDT values are very close to the experimental CDT values.
Keywords: Coast down time, Radial basis function neural network, Rotating machinery, Unbalance.