Loading...

Fault Growth Forecasting of Rotatory Systems Using Wavelet Transform and Artificial Neural Network Algorithm

Sohrabi, Ahmad | 2017

458 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 49385 (08)
  4. University: Sharif University of Technology
  5. Department: Civil Engineering
  6. Advisor(s): Behzad, Mahdi; Mahdigholi, Hamid
  7. Abstract:
  8. Failure of mechanical parts in the industry lead to a larger system downtime and even imposing economic losses to the factory. For this Purpose, for many years, researchers have been trying to find ways to predict early failure and to prevent losses from occurring. Creation of new sciences like artificial intelligence, helped researchers in this field.In the current study, using experimental data of a set of bearings that have been tested and recorded in the Intelligent Systems Research Center, A new approach with sufficient accuracy is presented for the prediction algorithm. Among the features extracted, three features of entropy, root mean square and maximum are the most appropriate characteristics to describe the difference between normal and failure conditions, and finally as a tool for signal processing wavelet transform of extracted features and also parallel and serial-parallel architecture of NARX network are used for prediction purpose. According to this fact that the forecast accuracy is affected by appropriate time delays, genetic optimization algorithm is used and the appropriate time delays are presented to the neural network in an intelligent manner. The results of the algorithms presented in this study is telling the truth that this algorithm not only have great potential for prediction of trained data but also can predict other bearings vibration time series that were not presented to the NARX networkWrite English abstract of your thesis here
  9. Keywords:
  10. Prediction ; Neural Network ; Genetic Algorithm ; Time Series ; Wavelet Transform

 Digital Object List

 Bookmark

No TOC