A review on prognostic techniques for non-stationary and non-linear rotating systems

Kan, Man Shan; Tan, Andy; Mathew, Joseph

doi:10.1016/j.ymssp.2015.02.016

Cited by 304 publications

(167 citation statements)

References 190 publications

(358 reference statements)

Supporting

Mentioning

153

Contrasting

Order By: Relevance

“…Kan et al [19] correctly identify that non-stationary properties characterise the operating conditions of many rotating machines, including those found in the generation industry. Reasoning about future health in the context of changes of state presents a complex challenge to the prognostics and health monitoring discipline, and this is one of the major problems approached in this paper.…”

Section: Machine Learning In Reliability Engineeringmentioning

confidence: 99%

Machine Learning Model for Event-Based Prognostics in Gas Circulator Condition Monitoring

2017

View full text Add to dashboard Cite

The Strathprints institutional repository (https://strathprints.strath.ac.uk) is a digital archive of University of Strathclyde research outputs. It has been developed to disseminate open access research outputs, expose data about those outputs, and enable the management and persistent access to Strathclyde's intellectual output. Abstract-Gas circulator (GC) units are an important rotating asset used in the Advanced Gas-cooled Reactor (AGR) design, facilitating the flow of CO2 gas through the reactor core. The ongoing maintenance and examination of these machines is important for operators in order to maintain safe and economic generation. GCs experience a dynamic duty cycle with periods of non-steady state behavior at regular refuelling intervals, posing a unique analysis problem for reliability engineers.In line with the increased data volumes and sophistication of available technologies, the investigation of predictive and prognostic measurements has become a central interest in rotating asset condition monitoring. However, many of the state-of-theart approaches finding success deal with the extrapolation of stationary time series feeds, with little to no consideration of more-complex but expected events in the data.In this paper we demonstrate a novel modelling approach for examining refuelling behaviors in GCs, with a focus on estimating their health state from vibration data. A machine learning model was constructed using the operational history of a unit experiencing an eventual inspection-based failure. This new approach to examining GC condition is shown to correspond well with explicit remaining useful life (RUL) measurements of the case study, improving on the existing rudimentary extrapolation methods often employed in rotating machinery health monitoring.

show abstract

Section: Machine Learning In Reliability Engineeringmentioning

confidence: 99%

Machine Learning Model for Event-Based Prognostics in Gas Circulator Condition Monitoring

2017

View full text Add to dashboard Cite

show abstract

“…Roughly speaking, the prognostics approaches for mechanical equipment can be classified as data-driven methods and model-based methods [8]. For data-driven methods, no prior knowledge about systems is needed, and the relationship between the RUL and the historical failure data is constructed with machine learning techniques.…”

Section: Introductionmentioning

confidence: 99%

Bearing Remaining Useful Life Prediction Based on a Nonlinear Wiener Process Model

Wen

Gao

Zhang

2018

Shock and Vibration

View full text Add to dashboard Cite

Prognostic is an essential part of condition-based maintenance, which can be employed to enhance the reliability and availability and reduce the maintenance cost of mechanical systems. This paper develops an improved remaining useful life (RUL) prediction method for bearings based on a nonlinear Wiener process model. First, the service life of bearings is divided into two stages in terms of the working condition. Then a new prognostic model is constructed to reflect the relationship between time and bearing health status. Besides, a variety of factors that cause uncertainties toward the degradation path are considered and appropriately managed to obtain reliable RUL prediction results. The particle filtering is utilized to estimate the degradation state, qualify the uncertainties, and predict the RUL. The experimental studies show that the proposed method has a better performance in RUL prediction and uncertainty management than the exponential model and the linear model.

show abstract

“…Although many techniques have been developed for the fault diagnosis of the ball screw system [13][14][15], RUL prediction of the ball screw system is a remaining challenge. Generally, RUL prediction approaches can be classified into two categories: data-driven techniques, and model-based techniques [16]. For data-driven approaches, the RUL estimation models are established from historical data through machine learning techniques, e.g., artificial neural network [17], support vector machine [18], and neuro-fuzzy systems [19].…”

Section: Introductionmentioning

confidence: 99%

Remaining useful life prediction of the ball screw system based on weighted Mahalanobis distance and an exponential model

Wen¹,

Gao²

2018

J. vibroeng.

View full text Add to dashboard Cite

Abstract. The ball screw system is one of the crucial components of machine tools and predicting its remaining useful life (RUL) can enhance the reliability and safety of the entire machine tool and reduce maintenance costs. Although quite a few techniques have been developed for the fault diagnosis of the ball screw system, forecasting the RUL of the ball screw system is a remaining challenge. To make up for this deficiency, we present a model-based method to predict the RUL of the ball screw system, which consists of two parts: health indicator (HI) construction and RUL prediction. First, we develop a novel HI, weighted Mahalanobis distance (WDMD). Unlike the Mahalanobis distance (MD), which is constructed by fusing original features directly, the WDMD is formed with some selected features only, and the features are weighted before integration. Second, an exponential model is developed to describe the degradation path of the ball screw system. Then, the particle filtering algorithm is employed to combine the WDMD and the degradation model for state estimation and RUL prediction. The proposed approach is verified by a dataset obtained from an experimental system designed for accelerated life tests of the ball screw system. The results show that the WDMD has a more apparent deterioration trend than the MD and the proposed exponential model performs better than both the linear model and the nonlinear model in RUL prediction.

show abstract

A review on prognostic techniques for non-stationary and non-linear rotating systems

Cited by 304 publications

References 190 publications

Machine Learning Model for Event-Based Prognostics in Gas Circulator Condition Monitoring

Machine Learning Model for Event-Based Prognostics in Gas Circulator Condition Monitoring

Bearing Remaining Useful Life Prediction Based on a Nonlinear Wiener Process Model

Remaining useful life prediction of the ball screw system based on weighted Mahalanobis distance and an exponential model

Contact Info

Product

Resources

About