Loading...

Prognostics of Rolling Element Bearings and Determining the Condition Monitoring Intervals Using LSTM

Hosseinli, Ali | 2022

154 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 54898 (08)
  4. University: Sharif University of Technology
  5. Department: Mechanical Engineering
  6. Advisor(s): Behzad, Mehdi
  7. Abstract:
  8. This study proposes a method to predict the remaining useful life (RUL) of the rolling element bearings (REBs) by forecasting the future trend of the peak of the acceleration signal. It is also employed to determine an appropriate time interval between the measurements of REBs vibration to reduce the error of forecasting and avoid collecting too much data in addition to increasing the reliability. In the first step, in order to achieve better results, the history of the acceleration peak is transformed into a stationary space before using the long short-term memory (LSTM) model to make it normally distributed and stationary. Then, LSTM forecasts the future trend of the stationary time series with every new measurement. This trend is returned into the original space to calculate the remaining time that every forecasted trend takes to reach a predetermined threshold, and the RUL of the REB is estimated at every moment. Also, to find out an appropriate interval between measurements, the LSTM is used to estimate the points between the measurements when the interval is longer than the default, and the error of forecasting due to extending the intervals is shown. The proposed method is applied to the accelerated-life tests on REBs. The results demonstrate a good performance
  9. Keywords:
  10. Remaining Useful Life ; Long Short Term Memory (LSTM) ; Data Driven Method ; Rolling Bearing ; Recurrent Neural Networks ; Time Series ; Rolling Element Bearings (REBs)

 Digital Object List

 Bookmark

No TOC