Remaining Useful Life Prediction for Rolling Bearings With a Novel Entropy-Based Health Indicator and Improved Particle Filter Algorithm

Abstract

Due to the importance of bearings in modern machinery, the prediction of the remaining useful life (RUL) of rolling bearings has been widely studied. When predicting the RUL of rolling bearings in engineering practice, the RUL is usually predicted based on historical data, and as the historical data increases, the prediction results should be more accurate. However, the existing methods usually have the shortcomings of low prediction accuracy, large cumulative error and failure to dynamically give prediction results with the increase of historical data, which are not suitable for engineering practice.To address the above problems, a novel RUL prediction method is proposed. The proposed method consists of 3 parts: First, the multi-scale entropy-based feature -namely "average multi-scale morphological gradient power spectral information entropy (AMMGPSIE)"from the rolling bearings as the Health indicator (HI) is extracted to ensure all the fault-related information is well-included; Then, the HI is processed with the enhanced Hodrick Prescott trend-filtering with boundary lines (HPTF-BL) to ensure good performance and small fluctuation on the HI; Finally, the deterioration curve is predicted using an LSTM neural network and the improved Particle Filter algorithm that we proposed. The proposed method is validated using the experimental bearing degradation dataset and the casing data of a centrifugal pump bearing from an actual industrial site. Comparing the results with other recent RUL prediction methods, the proposed method achieved state-ofthe-art feasibility and effectiveness, conform to the needs of practical application of the project.

Rolling bearing degradation trend prediction based on composite multiscale grey entropy and dynamic particle filter

“…In the prediction of dynamic system state values, the state x t needs to be estimated based on the observations y 0:t = {y i , i = 0, 1, …, t}. Under the rule of minimum mean squared error, the unbiased estimation of the state value at time t can be calculated as (18) where p (x t |x t−1 ) is state transition PDF, which can be calculated by (15). In update step, the observation value y t at time t is used to correct the prior PDF, thereby the posterior PDF can be obtained, that is…”

“…The most usually used state space models of the traditional PF algorithm are the double exponential model and the Paris model [16,17]. These two models can describe the fatigue degradation process of rolling bearing well, but cannot handle other types of degradation [18].…”

A New Strategy for Bearing Health Assessment with a Dynamic Interval Prediction Model

“…Liu S et al [ 16 ] established a degradation model that integrates multiple degradation stages of bearings to predict the RUL distribution of different degradation stages. Zhang T et al [ 17 ] extracted the average multi-scale morphological gradient power spectrum information entropy of rolling bearings and then used Hodrick Prescott trend filtering to process HI to construct a smooth HI. Qian et al [ 18 ] and Liu et al [ 19 ] used the optimization algorithm to update the physical model parameters so as to realize the bearing RUL prediction.…”

RUL prediction method for rolling bearing using convolutional denoising autoencoder and bidirectional LSTM

“…Currently, accurate RUL prediction for rolling bearings to achieve later maintenance decisions has been a popular research topic in recent years [7], and the existing models for RUL prediction can be broadly classified into two categories: model-based approaches and data-driven approaches [8]. The model-based approach is to establish a RUL prediction model through the knowledge of the degradation mechanism of the bearing [9].…”