Estimating Remaining Useful Life for Railway Rolling Stock

(AI Factory /RAILWAY)

Goal

To enhance maintenance planning and decision-making processes through the development and implementation of AI-based analytical tools tailored for High-Value Components (HVCs).

Project status and results

The primary aim of this project is to develop an AI-based analytical tool tailored for High-Value Components (HVCs), such as wheel pairs and brakes. This tool will enable predictive capabilities crucial for spare parts planning, capacity planning, and scheduling maintenance activities and workshops.

By developing an analytical tool grounded in data-driven insights, the study aims to empower stakeholders with the ability to forecast maintenance needs accurately. With a focus on ensuring inventory and resource availability, the research seeks to optimize maintenance processes, thereby facilitating smoother operations and efficient resource utilization.

This study utilized metrics like MTBF, Utilization Rate, and Availability to forecast maintenance needs.

It analyzed high-utilization components and overdue maintenance timelines.

It identified components like “Drivpaket (Powerpack)” for improved scheduling due to high utilization rate.

It predicted Next Maintenance Dates for preventive planning.

Through informed decision-making enabled by the analytical tool, the research aspires to enhance the efficiency and effectiveness of asset management practices. Ultimately, the goal is to minimize downtime and maximize the lifespan of critical assets, thereby contributing to improved operational performance and cost-effectiveness in industrial contexts.