| Summary: | Statistics demonstrate that public transportation plays a significant role in people’s movement in metropolises. However, transit systems are aging and are facing rising maintenance costs. Technologies such as Condition-Based Maintenance (CBM) could be used in order to monitor performance conditions of transportation and industrial assets in real-time to detect when and what maintenance is required. CBMs could help to identify risk scenarios in real-time, enhance reliability, reduce call out costs, increase productivity, and better asset functioning visibility. Since the high volume of maintenance data is generated from the different source, managing assets conditions with traditional inspection system such as planned maintenance (PM) is impossible. Therefore, providing a comprehensive performance management program is essential. My research is motivated by interesting challenges increasing from the growing size, variety, and complexity of maintenance data in CBM systems. This paper presents a knowledge-based approach of CBM using streaming big data analysis (SBDA) in order to solve real-time big data management, storage and computation challenges and predictive data analytics in CBM systems. This platform could detect changes in asset’s behavior before they stop.
|
|---|