Predictions of Machine Vibrations Using Artificial Neural Networks Trained by Gravitational Search Algorithm and Back-Propagation Algorithm
作者： Quang Hung Do
DOI:
关键词:
摘要: Since the vibration is main factor to result in machine faults, predictions of vibrations are necessary for improving operational efficiency, product quality, and safety. This raises need have an effective model that can be used predict vibrations. In this study, Artificial Neural Network (ANN) along with Gravitational Search Algorithm (GSA) a Back-Propagation (BP) - Gradient Descent Momentum (GDM) proposed. We first identify factors may cause then construct dataset. The hybrid algorithm improved GSA GDM utilized optimize weights between layers biases neural network. A real application illustrate applicability model. results show proposed approach achieves high accuracy. also compared those obtained from ANN-based models trained by other algorithms. comparative analysis indicates performs better than others. It expected prediction aid development novel issues faced tools industry.
ceser.in参考文章(22)
Dietmar G. Maringer, Portfolio management with heuristic optimization ,(2005)
Hua Su, Kil To Chong, A. G. Parlos, A neural network method for induction machine fault detection with vibration signal international conference on computational science and its applications. pp. 1293- 1302 ,(2005) , 10.1007/11424826_137
Ken-Ichi Funahashi, On the approximate realization of continuous mappings by neural networks Neural Networks. ,vol. 2, pp. 183- 192 ,(1989) , 10.1016/0893-6080(89)90003-8
Vesna Ranković, Aleksandar Novaković, Nenad Grujović, Dejan Divac, Nikola Milivojević, Predicting piezometric water level in dams via artificial neural networks Neural Computing and Applications. ,vol. 24, pp. 1115- 1121 ,(2014) , 10.1007/S00521-012-1334-2
Jatinder N.D Gupta, Randall S Sexton, Comparing backpropagation with a genetic algorithm for neural network training Omega-international Journal of Management Science. ,vol. 27, pp. 679- 684 ,(1999) , 10.1016/S0305-0483(99)00027-4
Leong Kwan Li, Sally Shao, Ka-Fai Cedric Yiu, A new optimization algorithm for single hidden layer feedforward neural networks11The third author would like to thank the support of RGC Grant PolyU. (5365/09E), NSFC Grant (10901170) and the Research Committee of the Hong Kong Polytechnic University. soft computing. ,vol. 13, pp. 2857- 2862 ,(2013) , 10.1016/J.ASOC.2012.04.034
Yaguo Lei, Zhengjia He, Yanyang Zi, Qiao Hu, Fault diagnosis of rotating machinery based on a new hybrid clustering algorithm The International Journal of Advanced Manufacturing Technology. ,vol. 35, pp. 968- 977 ,(2008) , 10.1007/S00170-006-0780-3
H. Adeli, S.L. Hung, An adaptive conjugate gradient learning algorithm for efficient training of neural networks Applied Mathematics and Computation. ,vol. 62, pp. 81- 102 ,(1994) , 10.1016/0096-3003(94)90134-1
SeyedAli Mirjalili, Siti Zaiton Mohd Hashim, Hossein Moradian Sardroudi, Training feedforward neural networks using hybrid particle swarm optimization and gravitational search algorithm Applied Mathematics and Computation. ,vol. 218, pp. 11125- 11137 ,(2012) , 10.1016/J.AMC.2012.04.069
Ali Nazari, Artificial neural networks for prediction compressive strength of geopolymers with seeded waste ashes Neural Computing and Applications. ,vol. 23, pp. 391- 402 ,(2013) , 10.1007/S00521-012-0931-4