A Discrete Partially Observable Markov Decision Process Model for the Maintenance Optimization of Oil and Gas Pipelines

Abstract

Corrosion is one of the major causes of failure in pipelines for transporting oil and gas products. To mitigate the impact of this problem, organizations perform different maintenance operations, including detecting corrosion, determining corrosion growth, and implementing optimal maintenance policies. This paper proposes a partially observable Markov decision process (POMDP) model for optimizing maintenance based on the corrosion progress, which is monitored by an inline inspection to assess the extent of pipeline corrosion. The states are defined by dividing the deterioration range equally, whereas the actions are determined based on the specific states and pipeline attributes. Monte Carlo simulation and a pure birth Markov process method are used for computing the transition matrix. The cost of maintenance and failure are considered when calculating the rewards. The inline inspection methods and tool measurement errors may cause reading distortion, which is used to formulate the observations and the observation function. The model is demonstrated with two numerical examples constructed based on problems and parameters in the literature. The result shows that the proposed model performs well with the added advantage of integrating measurement errors and recommending actions for multiple-state situations. Overall, this discrete model can serve the maintenance decision-making process by better representing the stochastic features.

A Corrosion Maintenance Model Using Continuous State Partially Observable Markov Decision Process for Oil and Gas Pipelines

“…Yinka-Banjo, et al [19] discussed the application of unmanned vehicles as an inspection tool and implemented MDP as a maintenance optimization model. Compare, et al [8] and Wari, et al [7] demonstrated the implementation of the POMDP for two different optimization problems. Compare, et al [8] optimized maintenance action along with some economic analysis for gas transmission networks.…”

“…Compare, et al [8] optimized maintenance action along with some economic analysis for gas transmission networks. Wari, et al [7] focused on the maintenance action considering partially observed states with ILI inspection errors. Most Markov-based maintenance optimization models assumed that the deterioration state of the pipeline could be accurately observed.…”

“…In practice, accurate observation is challenging due to the dynamic nature of corrosion and the inherent error of inspection methods. Wari, et al [7] addressed this problem by formulating a discrete state partially observable Markov decision process (DSPOMDP) model that considers observational errors and inaccuracies. This study extends the DSPOMDP approach by formulating the state as a continuous function to integrate the uncertainty without any discretization step.…”

“…The MP has been adopted for modeling the pipeline corrosion process to predict the rate of degradation or failure [1][2][3][4]. Extensions of this method, such as the Markov decision process (MDP) and partially observable Markov decision process (POMDP), have also been implemented to integrate maintenance operation optimization with corrosion degradation process formulation as well as deterioration rate (failure) prediction [5][6][7][8]. In these Markov-based approaches, maintenance operations (actions) considered only the current deterioration state and not the event that led it.…”

Bridging POMDPs and Bayesian decision making for robust maintenance planning under model uncertainty: An application to railway systems

“…Only few papers deal with the POMDP inference, which poses a challenge in itself, while best practices are not generally available. Papakonstantinou and Shinozuka (2014a); Song, Zhang, Shafieezadeh, and Xiao (2022); Wari, Zhu, and Lim (2023) propose methods to estimate the state transition probability matrix for deterioration processes, but without demonstrating inference on the transition matrices associated with maintenance actions. Guo and Liang (2022) propose methods to estimate both the transition and the observation models, but do not consider model uncertainty and the implementation examples do not involve real-world data but only simulated ones.…”