A Two-Stage Data-Driven-Based Prognostic Approach for Bearing Degradation Problem

Yu, Wenbin; Peng, Yizhen; Ye, Zi; Jin, Xiaohang; Tsui, Kwok Leung

doi:10.1109/tii.2016.2535368

Cited by 270 publications

(117 citation statements)

References 37 publications

Supporting

Mentioning

113

Contrasting

Order By: Relevance

“…Therefore, in the normal stage, we do not conduct the updating process, while in the degradation stage we incorporate the model developed in Section 3.2 and the vibration signals to track the health status and perform RUL prediction. Besides, prognostics based on the health stage division can improve the estimation accuracy and reduce the computational cost [46,47]. Hence, the operational process of the bearing is divided into two stages according to the method described in Section 3.1.…”

Section: Experimental Setup and Datamentioning

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

Section: Experimental Setup and Datamentioning

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

show abstract

“…Time domain and frequency domain analyses are traditional methods for extracting features from vibration signals. Wang et al [11] extracted 14 time domain features using statistics such as root mean square, mean, variance, and crest factor to denoise the raw signal and capture the degradation trend. Time domain features are suitable for stationary signals.…”

Section: Introductionmentioning

confidence: 99%

A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network

Yoo¹,

Baek²

2018

Applied Sciences

130

View full text Add to dashboard Cite

Abstract:In data-driven methods for prognostics, the remaining useful lifetime (RUL) is predicted based on the health indicator (HI). The HI detects the condition of equipment or components by monitoring sensor data such as vibration signals. To construct the HI, multiple features are extracted from signals using time domain, frequency domain, and time-frequency domain analyses, and which are then fused. However, the process of selecting and fusing features for the HI is very complex and labor-intensive. We propose a novel time-frequency image feature to construct HI and predict the RUL. To convert the one-dimensional vibration signals to a two-dimensional (2-D) image, the continuous wavelet transform (CWT) extracts the time-frequency image features, i.e., the wavelet power spectrum. Then, the obtained image features are fed into a 2-D convolutional neural network (CNN) to construct the HI. The estimated HI from the proposed model is used for the RUL prediction. The accuracy of the RUL prediction is improved by using the image features. The proposed method compresses the complex process including feature extraction, selection, and fusion into a single algorithm by adopting a deep learning approach. The proposed method is validated using a bearing dataset provided by PRONOSTIA. The results demonstrate that the proposed method is superior to related studies using the same dataset.

show abstract

“…These models are built and used for the identification or development of a degradation parameter, which is trended towards the failure . The model‐based approach has not attracted much attention as the practical solution for industry application because any model is developed specifically for a given component . The data‐driven approach was developed to overcome limitations of the model‐based method.…”

Section: Introductionmentioning

confidence: 99%

“…17 The model-based approach has not attracted much attention as the practical solution for industry application because any model is developed specifically for a given component. 18 The data-driven approach was developed to overcome limitations of the model-based method. The data-driven approach attempts to derive models directly or indirectly from operating and condition data, instead of making models based on system physics.…”

Section: Introductionmentioning

confidence: 99%

Reliability modelling with redundancy—A case study of power generation engines in a wastewater treatment plant

Jolfaei

Jin

Linden

et al. 2019

Quality & Reliability Eng

View full text Add to dashboard Cite

Power generators are critical assets in wastewater treatment plants (WWTPs) in Australia and many countries. Better managing the lifetime, minimising failures, improving reliability and availability, and reducing operating and maintenance costs of the power generation assets are still challenging topics for water utilities. This case study aims to develop power generation system reliability and availability modelling considering redundancy to minimise operation and maintenance costs. The two‐parameter Weibull model was used to assess system reliability and availability to power generation engines in WWTPs. The Kaplan‐Meier method (a time‐driven estimation technique) and the log beta‐Weibull model (which is suitable for modelling censored and uncensored data) were used to analyse and validate the modelling results. Shape and scale parameters of the Weibull models were estimated by maximising the log‐likelihood function using non‐linear optimisation. Hazard and reliability functions were calculated using the Weibull model. Results using two‐parameter Weibull, Kaplan‐Meier, and log beta‐Weibull models display low reliability and high hazard rate over time, which was associated with spark plug failure due to a suboptimal start and stop operation strategy.

show abstract

A Two-Stage Data-Driven-Based Prognostic Approach for Bearing Degradation Problem

Cited by 270 publications

References 37 publications

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

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

A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network

Reliability modelling with redundancy—A case study of power generation engines in a wastewater treatment plant

Contact Info

Product

Resources

About