Method for On-Line Remaining Useful Life and Wear Prediction for Adjustable Journal Bearings Utilizing a Combination of Physics-Based and Data-Driven Models: A Numerical Investigation

Abstract

RUL (remaining useful life) estimation is one of the main functions of the predictive analytics systems for rotary machines. Data-driven models based on large amounts of multisensory measurements data are usually utilized for this purpose. The use of adjustable bearings, on the one hand, improves a machine’s performance. On the other hand, it requires considering the additional variability in the bearing parameters in order to obtain adequate RUL estimates. The present study proposes a hybrid approach to such prediction models involving the joint use of physics-based models of adjustable bearings and data-driven models for fast on-line prediction of their parameters. The approach provides a rather simple way of considering the variability of the properties caused by the control systems. It has been tested on highly loaded locomotive traction motor axle bearings for consideration and prediction of their wear and RUL. The proposed adjustable design of the bearings includes temperature control, resulting in an increase in their expected service life. The initial study of the system was implemented with a physics-based model using Archard’s law and Reynolds equation and considering load and thermal factors for wear rate calculation. The dataset generated by this model is used to train an ANN for high-speed on-line bearing RUL and wear prediction. The results show good qualitative and quantitative agreement with the statistics of operation of traction motor axle bearings. A number of recommendations for further improving the quality of predicting the parameters of active bearings are also made as a summary of the work.

Data-Driven Predictive Maintenance Policy Based on Dynamic Probability Distribution Prediction of Remaining Useful Life

“…The ensemble of the derived RULs and their HI trajectories were fused to estimate the final RUL directly. Shutin et al [32] proposed a hybrid approach to such prediction models involving the joint use of physics-based models of adjustable bearings and datadriven models for fast on-line prediction of their parameters. It had been tested on highly loaded locomotive traction motor axle bearings for consideration and prediction of their wear and RUL.…”

Parallel processing of sensor signals using deep learning method for aero-engine remaining useful life prediction

“…Such methods open new avenues in certain RUL prediction tasks, such as tool wear prediction [16] and material fatigue life prediction [17]. Shutin et al [18] achieved fast online prediction of RUL for rotating instruments by jointly using a physically based adjustable bearing model and a data-driven model. Chao et al [19] proposed a data-driven model with physical enhancements that can be used for RUL prediction of aero-engines by combining the information of a physically based physical performance model with a deep learning algorithm.…”

Vibration-Based Wear Condition Estimation of Journal Bearings Using Convolutional Autoencoders

“…In some work, the abnormal conditions are classified into different types of abnormal condition such as Run-in, Steady1, Steady2, Pre-critical and critical [15], or the flow regime is classified from the measured data [16,17]. Other studies focus on areas such as the anomaly detection of force signals [18], the classification of operational states [15,17,[19][20][21], load prediction [22], the estimation of model-based remaining useful life and wear prediction [23], and supervised wear volume estimation [24]. Data-driven regression models have been recently employed to assess the influence of temperature, bearing load, and rotational speed on the variation in friction torque and friction coefficient [25].…”