Article
Computer Science, Interdisciplinary Applications
Ahmad Al Hanbali, Haitham H. Saleh, Omar G. Alsawafy, Ahmed M. Attia, Ahmed M. Ghaithan, Awsan Mohammed
Summary: The upcoming industrial revolution 4.0, based on the internet of things and prescriptive analytics, paves the way for the spread of continuously monitored condition-based maintenance (CBM) in the industry. In CBM implementations, the impact of spare parts quality, lead-time, and inspection errors on maintenance cost and system availability must be considered. A new maintenance model is proposed to incorporate these factors along with different cost factors and optimize the degradation level at which spare parts are ordered.
COMPUTERS & INDUSTRIAL ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
Baokui Yang, Xiaosheng Si, Hong Pei, Jianxun Zhang, Huiqing Li
Summary: This study proposes a joint maintenance strategy considering the uncertainty of the number of imperfect maintenance activities for nonlinear degraded equipment. It linearizes the nonlinear degradation data and constructs a degradation model under the influence of imperfect activities. The number of maintenances is calculated, and decision variables are optimized to minimize cost.
Article
Engineering, Industrial
Meimei Zheng, Hongqing Ye, Dong Wang, Ershun Pan
Summary: Efficient coordination in maintenance scheduling and spare parts management can reduce overall operational costs for companies. Balancing response times and prices from multiple suppliers is key in further reducing operational costs. A joint condition-based maintenance and spare parts provisioning policy can significantly reduce expected costs by as much as 42% in a multi-unit system with dual sourcing.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Article
Computer Science, Interdisciplinary Applications
Pieterjan Dendauw, Thomas Goeman, Dieter Claeys, Koen De Turck, Dieter Fiems, Herwig Bruneel
Summary: Condition-based maintenance strategy is proposed to significantly reduce operational costs by implementing preventive maintenance at critical levels, avoiding costly downtimes due to stock-outs. The study establishes a numerical procedure for selecting optimal base-stock and critical level thresholds, showing that the proposed critical level policy can indeed lead to substantial cost savings compared to traditional base-stock policies.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Mathematics
Ernesto Armando Pacheco-Velazquez, Manuel Robles-Cardenas, Saul Juarez Ordonez, Abelardo Ernesto Damy Solis, Leopoldo Eduardo Cardenas-Barron
Summary: This article presents a heuristic method to determine the optimal inventory level for spare parts, aiming to minimize total costs. The research offers a valuable decision-making framework based on two parameters, providing a quick and reliable estimation for practitioners.
Article
Mathematics
Xiaoyue Wang, Jingxuan Wang, Ru Ning, Xi Chen
Summary: In order to respond to emergencies in a timely manner, it is crucial to have appropriate maintenance and spare parts inventory strategies for emergency engineering equipment considering demand priorities. Existing studies rarely consider the impact of urgency degree and demand priorities on the service order of the equipment. This study establishes a joint optimization model to bridge these research gaps.
Article
Engineering, Industrial
Xiaohong Zhang, Haitao Liao, Jianchao Zeng, Guannan Shi, Bing Zhao
Summary: The study focuses on optimal condition-based opportunistic maintenance and spare parts provisioning policies for a two-unit system experiencing continuous deterioration. A state space partitioning approach is proposed to analyze the requirements and actions for different maintenance types. The explicit representations of stationary probability densities and numerical solutions are used to obtain the optimal joint strategy.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Review
Management
Cerag Pince, Laura Turrini, Joern Meissner
Summary: Forecasting spare parts demand has been a challenging issue for many companies, and has received considerable attention over the past fifty years. This paper provides a critical review and quantitative analysis of current literature on spare parts demand forecasting methods, offering detailed insights into when and why particular forecasting methods should be preferred.
OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE
(2021)
Article
Computer Science, Artificial Intelligence
Vincent F. Yu, Nabila Yuraisyah Salsabila, Nurhadi Siswanto, Po-Hsun Kuo
Summary: The research proposes a joint optimization model for managing spare parts inventory and planned maintenance to balance inventory cost and spare parts availability. The study shows that the independent policy results in lower cost than the aggregate policy, and the proposed Genetic Algorithm performs efficiently for large-scale problems.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Information Systems
Shengang Hao, Jun Zheng, Jie Yang, Haipeng Sun, Quanxin Zhang, Li Zhang, Nan Jiang, Yuanzhang Li
Summary: This paper studies the joint optimization of condition-based maintenance (CBM) policy and spare components inventory for multi-component systems. An improved deep reinforcement learning algorithm based on the stochastic policy and actor-critic framework is proposed. Experimental results show that the proposed algorithm outperforms other benchmark algorithms in terms of time performance and system cost.
INFORMATION SCIENCES
(2023)
Review
Engineering, Industrial
Alessandra Cantini, Mirco Peron, Filippo De Carlo, Fabio Sgarbossa
Summary: Configuring supply chains is crucial for the success of spare parts retailers. This paper introduces a new methodology called SP-LACE, which reviews the configuration of spare parts supply chains and evaluates their economic benefits. The results indicate that SP-LACE provides economic benefits and ensures high service levels, overcoming the limitations of existing literature methodology.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2023)
Review
Green & Sustainable Science & Technology
Shuai Zhang, Kai Huang, Yufei Yuan
Summary: The importance of spare parts inventory management is gaining attention, particularly in the pursuit of sustainability. Research in this area is mainly divided into two categories, focusing on spare parts characteristics and research methodologies, and emphasizing supply chain structures and analytical techniques.
Article
Engineering, Multidisciplinary
Shuyuan Gan, Xinzhou Zhang, Lan Chen
Summary: An innovative maintenance policy is proposed for an efficient production system, involving spare parts ordering, production quality, and buffer inventory. Monte Carlo simulation and enumerative search are used to determine cost-effective spare parts ordering and maintenance policies to minimize production cycle cost. Numerical examples show that spare parts should be ordered late in situations with high buffer inventory costs.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART O-JOURNAL OF RISK AND RELIABILITY
(2022)
Article
Engineering, Industrial
Jiachen Shi, Heraldo Rozas, Murat Yildirim, Nagi Gebraeel
Summary: Service supply chain models often suffer significant losses due to conservatism in maintenance and spare part management. However, conservatism alone cannot protect against unexpected consequences without a better understanding of risks. Risk scenarios such as asset failure and inventory shortage are frequently observed. Advances in IoT technology enable accurate prediction of these risk factors, driving dynamic decision models for more efficient maintenance and replenishment actions. This study proposes a unified framework that optimizes condition-based maintenance and inventory decisions using IoT data, considering the interplay between maintenance, spare parts inventory, and asset reliability.
Article
Engineering, Marine
Evanthia Kostidi, Nikitas Nikitakos, Iosif Progoulakis
Summary: The study investigated the application of 3D printing technology in the spare part supply chain, identifying company objectives and employee skills as key factors affecting successful implementation, providing guidance for the successful implementation of additive manufacturing in the maritime industry.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2021)
Article
Engineering, Industrial
Alp Akcay, Engin Topan, Geert-Jan van Houtum
Summary: The study examines randomly failing high-precision machine tools in a discrete manufacturing setting, developing a Markov decision model to determine when to inspect or retire a tool in order to maximize total expected reward. Implementation using real-world maintenance logs at a Philips shaver factory demonstrates that the value of the optimal policy can be substantial compared to current practice.
Article
Engineering, Manufacturing
Bram Westerweel, Rob Basten, Jelmar den Boer, Geert-Jan van Houtum
Summary: This study explores the benefits of on-site printing of spare parts in remote geographic locations with intermittent spare parts supply and fixed interval replenishment. By considering emergency supply options and modeling replenishment decisions, it is found that on-site 3D printing leads to significant operational cost savings and increased asset availability compared to expediting. These results have implications for organizations operating in remote locations, such as the mining and offshore industry.
PRODUCTION AND OPERATIONS MANAGEMENT
(2021)
Article
Engineering, Industrial
Douniel Lamghari-Idrissi, Rob Basten, Geert-Jan van Houtum
Summary: This study investigates spare parts service contracts for capital goods and introduces a flexible-time contract as a solution, proving its advantages through simulation and a Markov decision process.
Article
Management
Thijs Nicolaas Schouten, Rommert Dekker, Mustafa Hekimoglu, Ayse Sena Eruguz
Summary: This paper introduces a new model for maintenance optimization in offshore wind turbine maintenance, which addresses time-varying costs. The authors extend the standard maintenance policies and prove that the optimal maintenance policy under time-varying costs is a time-dependent strategy. They also present linear programming models for parameter optimization. By applying these models, they demonstrate significant cost savings in maintenance planning.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2022)
Article
Management
Ipek Dursun, Alp Akcay, Geert-Jan Van Houtum
Summary: The study focuses on applying an age-based replacement policy in a system with a finite lifespan to preventively replace a critical component before failure. It considers the decision maker's belief on the existence of a weak population and builds an optimal policy that balances the trade-off between cost and learning the true population type.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2022)
Article
Management
S. Voorberg, W. van Jaarsveld, R. Eshuis, G. J. van Houtum
Summary: Component maintenance, repair and overhaul are conducted under long-term service agreements. Service providers need to make accurate estimations of contract values to win contracts and make profits. Therefore, collecting attributes from multiple sources to improve knowledge about specific contracts is crucial. This paper introduces a model for optimal information acquisition and a specific model refinement for quotation optimization. Three heuristic policies with different levels of dynamism are proposed. Fixing the order in which attributes are retrieved has a small impact on profit, while fixing the number of attributes has worse consequences.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2023)
Editorial Material
Operations Research & Management Science
Frank P. A. Coolen, Tahani Coolen-Maturi, Geert-Jan van Houtum
APPLIED STOCHASTIC MODELS IN BUSINESS AND INDUSTRY
(2023)
Article
Engineering, Industrial
Ipek Dursun, Alp Akcay, Geert-Jan Van Houtum
Summary: This study considers multiple single-component systems with a known finite lifespan and investigates the optimal replacement policy to minimize cost. Expert opinions are used to estimate the component lifetime distribution, while uncertainty regarding population heterogeneity is resolved through data pooling. Numerical experiments demonstrate significant cost reduction through data pooling.
INTERNATIONAL JOURNAL OF PRODUCTION ECONOMICS
(2022)
Article
Engineering, Industrial
Halit Metehan Dilaver, Alp Akcay, Geert-Jan van Houtum
Summary: In the maritime industry, obligatory inspections and maintenance operations on moving assets are conducted based on calendar time and usage-based deterioration respectively. Synchronizing these operations to avoid unnecessary dry-dockings is a common approach, but determining the optimal timing and synchronization remains a crucial question. This real-life problem is formulated as a mixed integer linear programming model, which demonstrates that integrated planning can save up to 28.5% of the total cost.
INTERNATIONAL JOURNAL OF PRODUCTION ECONOMICS
(2023)
Article
Management
Erhun Ozkan, Geert-Jan van Houtum
Summary: This study focuses on the inventory and repair scheduling decisions of a maintenance service provider for repairable capital goods. The objective is to minimize the long-run average inventory holding, back-order, and emergency repair costs. The study formulates the repairable network as a closed queueing system and solves a Brownian control problem to derive an optimal decision rule.
OPERATIONS RESEARCH
(2023)
Article
Business
Fiona Sloothaak, Alp Akcay, Geert-Jan van Houtum, Matthieu van der Heijden
Summary: In this study, we propose a continuous-time model to optimize the upgrade decisions of a system during the fixed lifetime of the asset. The model considers important factors such as increasing functionality requirements, age-dependent maintenance costs, a predetermined overhaul plan, and the lifetime of the asset. We analyze the optimal upgrade policy under different cost functions and propose a dynamic programming approach for cases with penalties for upgrading outside an overhaul. Surprisingly, more overhauls may lead to a smaller number of upgrades under the optimal policy.
Article
Operations Research & Management Science
Joni Driessen, Joost de Kruijff, Joachim Arts, Geert-Jan van Houtum
Summary: This article investigates the design problem of line replaceable units (LRUs) and proposes two solving methods using set partitioning and binary linear programming. It considers the costs of replacement, downtime, and purchase/repair, and examines the effects of parameters on the model's outcome.
NAVAL RESEARCH LOGISTICS
(2023)
Article
Engineering, Industrial
Ragnar Eggertsson, Rob Basten, Geert-Jan van Houtum
Summary: This study focuses on the inspection and maintenance planning of capital goods, taking into account the imprecise observations and their dependence on the environment. Through the example of HVAC maintenance on trains, it is demonstrated that an environment-dependent policy can lead to cost savings.
Proceedings Paper
Computer Science, Theory & Methods
Joan Stip, Lois Aerts, Geert-Jan van Houtum
Summary: To minimize costs and meet service level agreements, Original Equipment Manufacturers (OEMs) use spare parts planning models to determine optimal base stock levels at their warehouses. However, there is often a deviation between the expected and realized performance of these optimized stock levels. In order to evaluate this performance and identify root causes for the gap, a digital twin has been developed. This digital twin has helped one semiconductor industry OEM, ASML, create a feedback loop to learn from past results and close the gap between expected and realized performance.
2022 WINTER SIMULATION CONFERENCE (WSC)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Nikki Theeuwes, Geert-Jan Van Houtum, Yingqian Zhang
Summary: This paper presents a case study conducted in a Dutch EMS region to improve ambulance dispatching. By enhancing the current dispatch policy with redispatching and reevaluation policies, the on-time performance of highly urgent ambulance requests was improved by 0.77% points, which is equivalent to adding seven weekly ambulance shifts.
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2021: APPLIED DATA SCIENCE TRACK, PT IV
(2021)
Article
Engineering, Industrial
Xubo Yue, Raed Al Kontar, Ana Maria Estrada Gomez
Summary: This article presents a federated data analytics approach for linear regression models, utilizing hierarchical modeling and information sharing to handle data distributed across different devices. It provides uncertainty quantification, variable selection, hypothesis testing, and fast adaptation to new data.