Industrial AI Enabled Prognostics for High-speed Railway Systems

Abstract

The vision of pervasive applications of artificial intelligence (AI) and the fact that hardware is becoming more portable and computationally powerful has encouraged the development of industrial AI. High-speed railway (HSR) transportation is an area of focus for industrial AI, since it demands maximized safety, reliability, availability, and minimized cost. Given the system complexity, the predictive maintenance for high-speed railway could hardly sustain with a raw experience-based system. This paper presents a framework for industrial AI enabled PHM system for HSR, which creates cyber twins of physical key subsystems and components to improve the condition transparency and decision efficiency. Enabled by advanced signal processing and machine learning with domain insights on historical data, cyber twins monitor real-time performance and predict potential faults to prevent unexpected downtime and support optimized decisions. Instead of performing analytics with large amount of raw data on the cloud, the cyber railway transportation system leverages the advantage of edge computing for real-time feature extraction and anomaly detection. The proposed framework introduces the general approach of implementing industrial AI. The paper also discusses the key methods of data-driven solutions for selected critical subsystems.