Maintenance policy: degradation laws versus hidden Markov model availability indicator

Abstract

Today, maintenance strategies and their analyses remain a worrying problem for companies. Socio-economic stakes depending on the competitiveness of each strategy are more than ever linked to the activity and quality of maintenance interventions. A series of specific events can eventually warn the expert of an imminent breakdown. This study aims at understanding such a signature thanks to hidden Markov models. For that purpose, two methods for damage level estimation of a maintained system are proposed. The first consists in using non-parametric and semi-parametric degradation laws (which will be used as references). The second method consists in using a Markovian approach. All proposals are illustrated on two studies corresponding to two real industrial situations (a continuous system for food processing and moulded products in aluminium alloys for the automotive industry).

Choosing the optimal intervention method to reduce human-related machine failures

“…But there is no mention of human-related factors either. Neither with the work of Vrignat et al (2012) nor with Castanier et al (2003) is there a deeper focus on the specific causes of degeneration. All causes leading to machine degeneration are combined together.…”

“…Peng and Dong (2011) use a Markov chain approach for uptime prediction. Vrignat, Avila, Duculty, and Kratz (2012), discuss an approach, where they draw observations from the process to generate an availability indicator to be used by a DM to plan actions dynamically. The authors also mention the PHM as a tool.…”

Homogeneous Continuous-Time, Finite-State Hidden Semi-Markov Modeling for Enhancing Empirical Classification System Diagnostics of Industrial Components

“…Multistate degradation modeling has been receiving considerable attention for supporting dynamic maintenance paradigms based on condition monitoring (CM), such as condition-based maintenance and predictive maintenance (examples in References [1][2][3][4]). In fact, multistate models describe the degradation evolution more realistically than binary models, as the evolution of many degradation processes proceed in successive phases characterized by different physical degradation mechanisms.…”

“…Furthermore, the classification performance of the ECS is assumed to be known. Hence, the resulting degradation model is framed as a hidden semi-Markov process [4,[37][38][39][40] with known misclassification probabilities.…”

Maintenance policy performance assessment in presence of imprecision based on Dempster–Shafer Theory of Evidence

“…Stochastic Flowgraphs [25] and Hidden Markov Models [35] (both based on the Maximum Likelihood Estimation method) have been proposed to estimate the unknown parameters of the stochastic model of the maintained component, when some field data are missing (e.g., [26], [43]). Fuzzy Logic ( [47]) has been applied to address the cases in which the lack of knowledge concerns both the degradation model of a component and its parameters (e.g., [1]- [3], [27]).…”