Dynamic maintenance model for a repairable multi-component system using deep reinforcement learning

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

doi:10.1080/08982112.2021.1977950

Cited by 33 publications

(11 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mahmoodzadeh et al [11], proposed the CBM optimal policy using an RL algorithm for gas pipelines. Yousefi et al [6] presented a DRL method to provide a new dynamic maintenance model for a degrading repairable system subject to degradation and random shocks. Zhang et al [12] proposed a novel and flexible CBM model based on a custom DRL for multicomponent systems with dependent competing risks.…”

Section: Literature Reviewmentioning

confidence: 99%

“…RL is a subfield of ML focusing on Artificial Intelligence (AI) which deals with learning from repeated interactions with an environment [6]. A learner (decision maker) is called an agent who interacts with the environment by performing specific actions and receiving feedback from the environment [7].…”

Section: Introductionmentioning

confidence: 99%

“…Z. Dehghani Ghobadi, F. Haghighi, A. Safari acting upon in its interactions with the environment, such as SARSA [7], whereas the off-policy methods can learn or improve a policy that is different from the one that the agent is using to take action in the environment such as Q-learning [10,12], Deep Q-learning [6,13] and SMART [1]. With off-policy methods, the experience of other agents interacting with the environment can also be used to find the optimal policy.…”

mentioning

confidence: 99%

“…The gradient-based methods can be used to improve parameterized policies, and the non-gradient-based method is applied to optimize less complicated policies. More details about the classification of RL algorithms can be found in [6].…”

mentioning

confidence: 99%

See 3 more Smart Citations

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%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

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

“…With the continuous development of deep learning algorithms, the application of deep learning in maintenance strategies is also increasing. Yousefi N [38] used deep reinforcement learning methods to provide a new dynamic maintenance model for degraded repairable systems subject to degradation and random shocks. Rodriguez MLR [30] proposed a new multi-intelligence approach to learn maintenance strategies executed by technicians under the uncertainty of multiple machine failures.…”

Section: Introductionmentioning

confidence: 99%

Research on preventive maintenance strategy of Coating Machine based on dynamic failure rate

Gu¹,

Nie²,

Han³

et al. 2023

Eksploatacja i Niezawodność – Maintenance and Reliability

View full text Add to dashboard Cite

In this paper, a dynamic preventive maintenance strategy is proposed for the problem of high maintenance cost rate due to excessive maintenance caused by unreasonable maintenance threshold setting when complex electromechanical equipment maintenance strategy is formulated. Increasing failure rate factor and decreasing service age factor are introduced to describe the evolution rules of failure rate during the maintenance of the coating machine, and the BP-LSTM (BP-Long Short Term Memory Network, BP-LSTM) model is combined to predict the failure rate of the coating machine. A Dynamic preventive maintenance Model (DM) that relies on dynamic failure rate thresholds to classify the three preventive maintenance modes of minor, medium and major repairs is constructed. A dynamic preventive maintenance strategy optimization process based on Genetic-Particle Swarm Optimization (GPSO) algorithm with the lowest cost rate per unit time in service phase is built to solve the difficult problem of dynamic failure rate threshold finding. Based on the historical operating data of the coating machine, a case study of the dynamic preventive maintenance strategy of the coating machine was conducted to verify the effectiveness of the model and the developed maintenance strategy proposed in this paper. The results show that the maintenance strategy developed in this paper can ensure better economy and applicability.

show abstract

Deep reinforcement learning for resilient microgrid expansion planning with multiple energy resource

Pang

Zhou

Tsianikas

et al. 2022

Quality & Reliability Eng

Self Cite

View full text Add to dashboard Cite

Microgrid has attracted more and more attention to provide backup power for customers in the case of power grid outages. Microgrid expansion planning is significant to handle the increasing customer demand and to enhance power resilience. Current research about long‐term microgrid expansion planning rarely if ever considered the uncertainties associated with energy storage and power generation units, for example, battery cycle degradation. These factors have important influence on the performance of microgrid expansion planning in reality. In this paper, a long‐term microgrid expansion planning model with multiple energy resource is presented. Deep reinforcement learning method is used to obtain the cost‐effective microgrid expansion policies to enhance power resilience. In the case study, optimal microgrid expansion planning is achieved based on the proposed model. The impacts of battery degradation and resilience constraint on microgrid expansion policy optimization are also investigated. The simulation results prove the effectiveness of the proposed method on economic and resilient microgrid expansion planning.

show abstract

Dynamic maintenance model for a repairable multi-component system using deep reinforcement learning

Cited by 33 publications

References 32 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

Research on preventive maintenance strategy of Coating Machine based on dynamic failure rate

Deep reinforcement learning for resilient microgrid expansion planning with multiple energy resource

Contact Info

Product

Resources

About