Optimal maintenance scheduling under uncertainties using Linear Programming-enhanced Reinforcement Learning

Hu, Jueming; Wang, Yuhao; Pang, Yutian; Liu, Yongming

doi:10.1016/j.engappai.2021.104655

Cited by 21 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All classes of optimization problems related to industrial activities in general and organization-planned operations, including production and maintenance, more particularly, know an extensive application of mathematical programming as a discipline of operational research. Indeed, mathematical programming methods such as linear programming, non-linear programming, integer programming, and dynamic programming are widely used to assist operations management in making decisions relating to assembly line configuration [24]; to support decision-making in optimizing maintenance [25][26][27][28]; in addition to aiding decision-making in optimizing manufacturing planning or even strategic capacity planning in manufacturing [29][30][31][32], transport, and supply chain problems [33,34], control plans in manufacturing [35], safety in manufacturing [36], and many other activities in the industry. Moreover, the recent mathematical programming literature has long recognized the centric role of mathematical programming methods in maximizing production in diverse areas, notably the petroleum industry (e.g., [18], small mechanical-based industry (e.g., [19], and energy (e.g., [20,21].…”

Section: Methodsmentioning

confidence: 99%

Systems Theory and Evidence‐Based Decision‐Making as Keys for Arbitrating between Optimal Production and Efficient Maintenance: A Case Study

Hallioui

Herrou

Santos

et al. 2022

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

Organizations in the 21st century operate in evolving and highly competitive environments—such environments are catalysts for deviation in organization-planned operations, including production and maintenance. The differences between maintenance and production, in general, are well known, given the several studies found in the literature regarding industrial engineering. However, the differences between maintenance and production are becoming less significant as a result of increased understanding of the systemic approach to organizations where the whole matters more than the sum of the parts. The aim of this study was to maximize the productivity of a manufacturing factory by applying mathematical programming methods while simultaneously considering the requirements of efficient maintenance. A case study is used to show how systems theory can be used as the basis for evidence-based decision-making in a factory manufacturing line in Morocco. Despite the potential for conflict between optimal production objectives and efficient maintenance in high-performance factories, the four-month case application suggests that systems theory is a key for arbitration. Research implications are presented along with future research directions.

show abstract

Section: Methodsmentioning

confidence: 99%

Systems Theory and Evidence‐Based Decision‐Making as Keys for Arbitrating between Optimal Production and Efficient Maintenance: A Case Study

Hallioui

Herrou

Santos

et al. 2022

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

show abstract

“…In this stage, the quality of the impure fractions is inspected, and the usable fractions are utilized as fertilizers. In this process, the unusable fractions disposed of biogas have a volumetric fertilizer yield rate of about 8% [58]. Furthermore, since demand and recycling cannot be predicted, it is crucial to incorporate the uncertainties of parameters into biomass supply chains due to possible changes in climatic parameters that often challenge the extraction of biomass resources.…”

Section: Problem Statementmentioning

confidence: 99%

Biogas Reverse Supply Chain Network Design based on Biomass Quality Levels using Robust Programming and Benders decomposition approach

Hamidieh,

Akhgari

2024

Scientia Iranica

View full text Add to dashboard Cite

Today, renewable energy generation infrastructures are increasingly developed due to reduced fossil fuel resources and increased energy consumption. In this respect, a biogas supply chain has a high potential to generate energy. This paper aims to design a bi-objective biogas supply chain network for power and fertilizer generation. A mixed-integer linear programming (MILP) model was developed for the multi-level biogas supply chain with biomass input under different parameter uncertainties. A stochastic-robust programming approach was adopted to cope with the intrinsic uncertainties of such value chains. Realistic uncertainty modeling allowed for adjusting the conservatism level for a trade-off between performance and robustness. The adopted stochastic-robust programming pathway not only diminished the optimality fluctuations and provided a reasonable allocation space for uncertainties but also enhanced network flexibility and alleviated decision-making risks. Finally, the model was solved using the Benders decomposition (BD) algorithm. This research obtained more efficient and effective solutions by enhancing the Benders cuts based on previously generated solutions and Pareto optimal cuts. The implemented algorithm converged to the optimal solution at a reasonable rate.

show abstract

“…The maintenance framework is proposed to be solved as an optimization problem that aims to minimize the maintenance costs subject to certain constraints such as a threshold of the failure probability. We plan to incorporate a reinforcement learning method (Hu, Wang, Pang, & Liu, 2022) for maintenance scheduling.…”

Section: Remaining Workmentioning

confidence: 99%

Information Fusion and Data Augmentation for Risk-based Maintenance Optimization of Hydrogen Gas Pipelines

Kethamukkala,

Liu

2023

PHM_CONF

View full text Add to dashboard Cite

Demand for energy is increasing every year and hydrogen is being seen as a good alternative to conventional natural gas. The current focus is on the use of existing pipeline infrastructure for the transport of hydrogen gas, and it is necessary for us to ensure the safe and efficient operation of the pipeline infrastructure given the risks posed by hydrogen. Pipeline integrity management is critical for hydrogen transport and there are knowledge gaps for the impact of hydrogen on the pipeline integrity and operational considerations, thus hindering the pipeline operators from adopting hydrogen into their networks. To realize the concept of transporting hydrogen through existing pipeline systems, it is necessary to have reliable risk assessment and maintenance optimization frameworks in place. A Bayesian network methodology is proposed to fuse information from multiple sources obtained by multimodality diagnosis of pipe materials and Bayesian updating will be incorporated to reduce the uncertainty arising from different random variables. Risk assessment of the pipeline systems will be carried out based on the posterior distributions of the random variables. Given the predicted risk level, we then propose a risk-based maintenance optimization framework to minimize the maintenance costs while ensuring the safe operation of the pipeline systems.

show abstract

Optimal maintenance scheduling under uncertainties using Linear Programming-enhanced Reinforcement Learning

Cited by 21 publications

References 37 publications

Systems Theory and Evidence‐Based Decision‐Making as Keys for Arbitrating between Optimal Production and Efficient Maintenance: A Case Study

Systems Theory and Evidence‐Based Decision‐Making as Keys for Arbitrating between Optimal Production and Efficient Maintenance: A Case Study

Biogas Reverse Supply Chain Network Design based on Biomass Quality Levels using Robust Programming and Benders decomposition approach

Information Fusion and Data Augmentation for Risk-based Maintenance Optimization of Hydrogen Gas Pipelines

Contact Info

Product

Resources

About