Degradation Trend Prediction for Rotating Machinery Using Long-Range Dependence and Particle Filter Approach

Abstract

Timely maintenance and accurate fault prediction of rotating machinery are essential for ensuring system availability, minimizing downtime, and contributing to sustainable production. This paper proposes a novel approach based on long-range dependence (LRD) and particle filter (PF) for degradation trend prediction of rotating machinery, taking the rolling bearing as an example. In this work, the degradation prediction is evaluated based on two health indicators time series; i.e., equivalent vibration severity (EVI) time series and kurtosis time series. Specifically, the degradation trend prediction issues here addressed have the following two distinctive features: (i) EVI time series with weak LRD property and (ii) kurtosis time series with sharp transition points (STPs) in the forecasted region. The core idea is that the parameters distribution of the LRD model can be updated recursively by the particle filter algorithm; i.e., the parameters degradation of the LRD model are restrained, and thus the prognostic results could be generated real-time, wherein the initial LRD model is designed randomly. The prediction results demonstrate that the significant improvements in prediction accuracy are obtained with the proposed method compared to some state-of-the-art approaches such as the autoregressive-moving-average (ARMA) model and the fractional order characteristic (FOC) model, etc.

An Improved Recursive ARIMA Method with Recurrent Process for Remaining Useful Life Estimation of Bearings

“…end for (20) Train the Rotation Forest in training set (21) for training set do (22) y � D (k) (F (k) ) (23) end for (24) Calculate y〈k〉 (25) for training and testing set do (26) y � D (k) (F (k) ) (27) end for (28) Calculate changes (29) s � MSE(y (k) , y (k) ) (30) until k > k m ax or s < eps (31) Construct F<k> (32) for j from 1 to k do (33) Calculate e (k) , F (k) , y (k) (34) end for (35)…”

“…Derived from this combination, the differential process is further added to it, giving rise to the autoregressive integrated moving average (ARIMA). Researchers solve forecasting tasks with all types of ARIMA models since the time they are invented [22][23][24]. e long-range dependence expressed in the MA terms of these models is critical in the prognostics of bearings [25].…”

“…us, the family of ARMA models is hard to be modeled by the ANN and other similar ML structures [32][33][34]. In the application of time series models to HI or RUL prediction, researchers mainly combine the ARMA family and ML methods as two independent parts, such as combining ARMA and SVM [35] and particle filter (PF) [23]. Even the ARNN has been used for such simply combination [36], or adding complexity from exogenous input to it [37].…”

Detecting Coal Pulverizing System Anomaly Using a Gated Recurrent Unit and Clustering

“…Lin employs the ARIMA algorithm to predict the fault of a throttle valve [9]. Li predicts the degradation trend of rotating machinery using a particle filter algorithm [10]. Although the signal processing and analysis approach has good performance on anomaly detection, it is difficult to manually interrogate for the presence of damage, and it has the limitation of processing low-dimensional data.…”