This paper presents an integrated framework for improving the reliability, safety, and sustainability of high speed rail stations through the combination of AI powered predictive maintenance and piezoelectric energy harvesting, with a specific focus on the HS2 network. The proposed approach uses Internet of Things sensing, edge and cloud analytics, and machine learning models to monitor critical station assets and provide early warning of degradation, while footfall based piezoelectric floor systems recover energy to support selected lighting and resilience functions. A whole system perspective is adopted, covering technical architecture, maintenance workflow integration, economic appraisal, cyber security, data governance, and phased deployment strategy, with scenario based analysis used to illustrate potential operational and energy benefits. The framework provides a credible foundation for pilot validation and future smart station deployment across the United Kingdom rail network.
Samuel Mbakara John (Thu,) studied this question.