Reinforcement learning for dynamic condition-based maintenance of a system with individually repairable components

Yousefi, Nooshin; Tsianikas, Stamatis; Coit, David W.

doi:10.1080/08982112.2020.1766692

Cited by 48 publications

(11 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adsule et al [1], modeled the CBM decision-making problem as a continuous semi-Markov decision process (CSMDP), and applied an RL algorithm. Yousefi et al [9], modeled the CBM decision-making problem as an MDP and also used an RL algorithm. Peng et al [10], modeled the problem of CBM as a continuous Markov decision-making process without discretizing the degradation states under a Gaussian process (GP) and then applied an RL algorithm.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The feedback is usually termed as a reward. The agent's goal (objective) is to maximize cumulative rewards by learning to perform better [7].An MDP usually describes the environment, consisting of a state space, an action space, a reward function, and state transition probabilities.Therefore, MDP for an RL problem has the following components [11,17,9].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An overview of reinforcement learning and deep reinforcement learning for condition-based maintenance

Ghobadi

Haghighi

Safari

2021

IJRRS

View full text Add to dashboard Cite

Condition-based maintenance (CBM) involves making decisions on maintenance based on the actual deterioration conditions of the components. It consists of a chain of states representing various stages of deterioration and a set of maintenance actions. Therefore, condition-based maintenance is a sequential decision-making problem. Reinforcement Learning(RL) is a subfield of Machine Learning proposed for automated decision-making. This article provides an overview of reinforcement learning and deep reinforcement learning methods that have been used so far in condition-based maintenance optimization.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An overview of reinforcement learning and deep reinforcement learning for condition-based maintenance

Ghobadi

Haghighi

Safari

2021

IJRRS

View full text Add to dashboard Cite

show abstract

“…For example, a four‐state MDP has been used to model CBM for multi‐component systems with individual reparable components. The authors have used RL to find an optimal maintenance action for each of the components [3].…”

Section: Literature Reviewmentioning

confidence: 99%

Reinforcement learning for optimal policy learning in condition‐based maintenance

Adsule¹,

Kulkarni²,

Tewari³

2020

IET Collaborative Intelligent Manufacturing

View full text Add to dashboard Cite

“…There have been some research studies that propose distributed dynamic maintenance scheduling where the agents (sub-components) decide about their optimal maintenance individually, such as [2], [30], and [23].…”

Section: Introductionmentioning

confidence: 99%

“…Aissani et al [2] propose a multi-agent maintenance scheduling in a petroleum system using reinforcement learning (RL). RL is also used in [30] to obtain maintenance decisions for sub-components. The authors consider finite discrete values for the degradation state and solve the problem using Q-learning.…”

Section: Introductionmentioning

confidence: 99%

Distributed joint dynamic maintenance and production scheduling in manufacturing systems: Framework based on model predictive control and Benders decomposition

Rokhforoz¹,

Fink²

2020

Preprint

View full text Add to dashboard Cite

Scheduling the maintenance based on the condition, respectively the degradation level of the system leads to improved system's reliability while minimizing the maintenance cost. Since the degradation level changes dynamically during the system's operation, we face a dynamic maintenance scheduling problem.In this paper, we address the dynamic maintenance scheduling of manufacturing systems based on their degradation level. The manufacturing system consists of several units with a defined capacity and an individual dynamic degradation model, seeking to optimize their reward. The units sell their production capacity, while maintaining the systems based on the degradation state to prevent failures. The manufacturing units are jointly responsible for fulfilling the demand of the system. This induces a coupling constraint among the agents. Hence, we face a large-scale mixed-integer dynamic maintenance scheduling problem. In order to handle the dynamic model of the system and large-scale optimization, we propose a distributed algorithm using model predictive control (MPC) and Benders decomposition method. In the proposed algorithm, first, the master problem obtains the maintenance scheduling for all the agents, and then based on this data, the agents obtain their optimal production using the distributed MPC method which employs the dual decomposition approach to tackle the coupling constraints among the agents. The effectiveness of the proposed method is investigated on a case study.

show abstract

Reinforcement learning for dynamic condition-based maintenance of a system with individually repairable components

Cited by 48 publications

References 33 publications

An overview of reinforcement learning and deep reinforcement learning for condition-based maintenance

An overview of reinforcement learning and deep reinforcement learning for condition-based maintenance

Reinforcement learning for optimal policy learning in condition‐based maintenance

Distributed joint dynamic maintenance and production scheduling in manufacturing systems: Framework based on model predictive control and Benders decomposition

Contact Info

Product

Resources

About