Abstract
Rotor systems are of considerable importance in most modern industrial machinery, and the evaluation of the working conditions and longevity of their core component—the rolling bearing—has gained considerable research interest. In this study, a scale-normalized bearing health indicator based on the improved phase space warping (PSW) and hidden Markov model regression was established. This indicator was then used as the input for the encoder–decoder LSTM neural network with an attention mechanism to predict the rolling bearing RUL. Experiments show that compared with traditional health indicators such as kurtosis and root mean square (RMS), this scale-normalized bearing health indicator directly indicates the actual damage degree of the bearing, thereby enabling the LSTM model to predict RUL of the bearing more accurately.
Highlights
Health Indicator and a long- and short-term memory (LSTM) ModelBearing reliability evaluation and remaining useful life (RUL) prediction have received extensive attention due to the increasingly extreme working conditions of the entire system [1,2]
Most extant studies on the RUL prediction of rolling bearings have limited themselves to online public data sets, which do not consider the actual damage degree of the bearing and rarely consider the starting and ending points for the bearing RUL prediction or the damage type of the bearing
Compared with the traditional health indicators used for life prediction, the standardized phase space warping (PSW) indicator based on hidden Markov model regression (HMMR) and improved PSW proposed in this paper can effectively evaluate the actual damage size in the bearing
Summary
Bearing reliability evaluation and remaining useful life (RUL) prediction have received extensive attention due to the increasingly extreme working conditions of the entire system [1,2]. Huang [8] introduced the transfer learning method and constructed a transfer depth-wise separable convolution recurrent network to predict the bearing RUL from the same public datasets considering different work conditions. Machines 2021, 9, 238 transfer learning method and constructed a transfer depth-wise separable convolution recurrent network to predict the bearing RUL from the same public datasets considering different work conditions. Purposed ensemble empirical model decomposition and wavelet packet decomposition to detect the initial faults in rotating machinery, and the Nirwan [25] used the acoustic emission to detect faults Such mentioned works provided relatively accurate detection results, the detection models or the extracted features originated from extensive calculations. In. Section 5, the health indicator threshold, indicating the true damage extent, was defined as the end of bearing lifetime, which allows the proposed encoder-decoder long-short term memory (LSTM) model with an attention mechanism to predict the bearing RUL. The results through analyzing the experimental data of bearing life proved the effectiveness of the proposed method, see Section 6
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
