ASSET LIFE PREDICTION USING MULTIPLE DEGRADATION INDICATORS AND FAILURE EVENTS: A CONTINUOUS STATE SPACE MODEL APPROACH

作者：Zhou Yifan^*; Ma Lin; Mathew Joseph; Sun Yong; Wolff Rodney

来源：Maintenance and Reliability, 2009, (4): 72-81.

• Asset life prediction
• Degradation model
• Expectation-Maximisation algorithm
• State space model

Two practical issues are involved in asset life prediction using degradation indicators: (1) identifying uncertain failure thresholds of degradation indicators and (2) fusing multiple degradation indicators extracted from condition monitoring data. The state space degradation model provides an effective approach to address these two issues. However, existing research on the state space degradation model largely adopts a discrete time or states assumption which requires equal inspection intervals or discretising continuous degradation indicators. To remove the discrete time and states assumptions, this paper proposes a Gamma-based state space model. The Gamma process has a monotonically increasing property that is consistent with the irreversible degradation processes of engineering assets within a single maintenance cycle. The monotonically increasing property also makes the establishment of the likelihood function more straightforward when failure times are considered In this paper, parameter estimation and lifetime prediction algorithms for the Gamma-based state space model are developed. In addition, an effectiveness evaluation approach for indicators in degradation modelling is established. The proposed Gamma-based state space model and algorithms are validated using both simulated data and afield dataset from a liquefied natural gas company.

• 出版日期2009