考量車組劣化特性之軌道車輛預測性檢修排程

Abstract

軌道車輛是鐵道系統中最昂貴的資產之一，因此，車輛運用效率是實務中追求的重要目標。隨著運輸需求高漲，再加上既有的人力以及資源限制，如何適當進行車輛資產運用，並同時兼顧系統的營運可靠度，為鐵路營運上相當重要的研究課題。實務作業中，營運者在決定時刻表後即需規劃車輛運用路徑，以滿足營運及檢修的需求，並產生車輛調配計畫。目前實務上檢修排程多採用固定時隔的「週期性檢修」策略，所有車輛皆一體適用相同的檢修標準，檢修排程因此無法考量不同車輛的可靠度，包含車輛使用狀態是否影響其調配過程與檢修安排等，且實務操作尚仰賴人工操作，難以達到車輛系統之最佳運用與效率。隨著檢修管理系統的建置，所有元件的檢修歷程均能完整記錄，進而推導出劣化模式，協助營運者建立更好的趨勢分析及預測模式。本研究提出一套最佳化架構，協助營運者以「預測性檢修」策略，以最小化檢修成本、車輛失效所造成的營運損失成本為目標，並考量基於各車輛的劣化模式、人力、檢修容量等資源限制，產生更能充分反映各車輛特性之調配計畫。本研究成果可支援營運者在兼顧車輛可靠度與檢修成本的情況下，研擬合乎車輛特性之較佳車輛調配計畫。

The efficiency of trainset utilization is an important objective pursued in practice. Trainset assignment plan including the assignment of utilization paths and maintenance tasks. Previous studies have adopted the fixed periodic maintenance (PM) strategy; however, the difference in the reliability of trainset is not considered. Maintenance planners have to manually adjust utilization and maintenance tasks on the basis of experience. Consequently, this study proposes an optimization process for assigning trainset to utilization paths and maintenance tasks in accordance with the predictive maintenance strategy (PdM) with trainset-specific degradation models. Results of the empirical study demonstrate that the developed process with PdM can assign utilization paths and schedule maintenance tasks to each trainset efficiently and reduce the total cost compared with the PM-only strategy. Adopting this process can help planners improve the efficiency and reliability of trainset utilization.