Minimizing Cost of Multi-Component Preventive Maintenance Models with Simultaneous Determination of Maintenance Periods and Maintenance Activities

本研究目的乃針對多元件系統，建構一個使維修總成本最小化的週期性非完美預防維修最佳化模式，並建立適當的限制條件，以滿足實務上對系統性能的基本需求，其中維修策略的制定將同時決定系統中個別元件最適的維修週期與每一個維修時間點上最適的維修活動，所考量的維修活動包括：不實施任何預防維修活動、保養、維修及置換等四種，另外當元件發生失效時，則實施最小修復（minimal repair）的矯正性維修，使元件功能回復至失效前的狀態，從而建立一個非完美維修最佳化模式，來決定最適的維修策略。本研究以粒子群（Particle Swarm Optimization, PSO）演算法具有概念簡單、實作容易且搜尋速度快等優點的基礎下，建構一個適合同時求解維修週期與維修活動的維修策略之改良型粒子群演算法（Improved PSO, IPSO），其中必須克服典型PSO之粒子僅適用於求解維修週期之連續型問題的移動機制，包括：重新定義粒子速度的更新機制與位置更新的機制等。此外，本研究建立一種調整機制，解決落入不可行解區域的問題，可以提高IPSO的搜索效能。另外，IPSO演算法之搜尋參數值的制定，導入實驗設計法中的反應曲面法（Response Surface Methodology, RSM），經由有系統的實驗規劃與實驗據解析，適配建立維修總成本與搜尋參數間的反應曲面模式，從而決定搜尋參數的最佳設定值，以利求解成效。最後以一個模擬案例及一個文獻的例子驗證IPSO求解多元件預防維修最佳化模式的有效性。

關鍵字

預防維修；多元件系統；粒子群最佳化演算法

並列摘要

This study aims at developing a repairable system that can be used to establish a multi-component preventive maintenance (MCPM) model in which the total maintenance cost is optimized by determining the maintenance period and maintenance activities simultaneously. Constraints are added to fulfill the practical system requirements. The maintenance activities involved in the established MCPM model include no action, mechanical service, repair, and replacement. When the components fail, corrective maintenance with minimal repair is implemented. To efficiently solve the established MCPM model, this study proposes an improved particle swarm optimization (IPSO) algorithm utilizing the superiority of the easy concept, simple implementation, and rapid searching ability of a conventional particle swarm optimization (PSO). A hybrid particles moving algorithm is developed to enable simultaneous optimization of the maintenance periods and maintenance activities. The IPSO extends the practicability of the conventional PSO originally designed to solve an optimization problem with continuous decision variables. In addition, this study establishes an adjustment mechanism addressing the issue of particles falling into the infeasible solution, owing to its random search mechanism which results in the inability of the particles to approach the global optimum. The adjustment mechanism can enhance the exploring ability of the IPSO. A simulated case and a case from past literature are used to verify the accuracy of the established MCPM model and the efficacy of the IPSO algorithm.

並列關鍵字

preventive maintenance ； multi-component system ； particle swarm optimization

參考文獻

Caldeira Duarte, J. A.,Craveiro, J. C. T. A.,Trigo, T. P.(2006).Optimization of the preventive maintenance plan of a series components system.International Journal of Pressure Vessels and Piping.83(4),244-248.

Google Scholar

El-Gallad, A. I.,El-Hawary, M. E.,Sallam, A. A.(2001).Swarming of intelligent particles for solving the nonlinear constrained optimization problem.Engineering Intelligent Systems for Electrical Engineering and Communications.9(3),155-163.

Google Scholar

He, S.,Wu, Q. H.,Wen, J. Y.,Saunders, J. R.,Paton, R. C.(2004).A particle swarm optimizer with passive congregation.Biosystems.78(1-3),135-147.

Google Scholar

Hu, X.,Eberhart, R.(2002).Solving constrained nonlinear optimization problems with particle swarm optimization.Proceedings of 6th World Multiconference on Systemics, Cybernetics and Informatics (SCI 2002).203-206.