Dr. Alfredo Núñez Vicencio – Intelligent Railway Infrastructure
Railways are the backbone of transportation, and their role in a greener future is undeniable. But to fully unlock their potential, we need a smarter, more resilient, and autonomous railway system. My research focuses on Intelligent Railway Infrastructure, where I equip railways with the abilities to perceive-decide-learn, transforming them into self-improving systems. In short, I develop the brains of a railway system by considering the railway infrastructure as a living being from where each of our methodologies contributes to creating its digital brain.
Our research considers theoretical developments inspired by actual challenges in practice. We apply solutions working with industrial partners to real railway networks, from high-speed rail to metro systems, freight corridors, and rural railways. Moreover, the methodologies we develop inspire cross-industry solutions in power grids, roads, and logistics networks.
Furthermore, my work is in the interface between railway engineering/railway infrastructure and different research areas such as computational intelligence (neural networks, fuzzy logic, and evolutionary computation), structural health monitoring, maintenance of engineering structures, control of railway systems, asset management of transportation infrastructures, big data, and optimization.
See Our Research in Action
🎥 Watch how our measurement train gathers real-time data using advanced sensing technologies.
📍 Explore our research campaign in Sweden-Norway, where we test AI-driven railway monitoring in the field.
Perception: Seeing and Understanding the Railway in Real-Time
To ensure safety and efficiency, railway infrastructure needs to monitor its condition autonomously. My research focuses on:
- Multi-sensor fusion from fixed and mobile sensors
- Crowd-sourced data for real-time monitoring
- Big data analytics for predictive assessments
- Detecting track defects using AI-powered sensing
- Fusing satellite, drone, and train-based data
- Developing real-time performance indicators
Decision: Optimizing Maintenance and Operations
Railway maintenance involves large-scale decision problems, which I address using:
- Optimization algorithms for maintenance scheduling
- Robust optimization to account for uncertainties
- Multi-objective models balancing cost, efficiency, and safety
- Enhancing maintenance planning to reduce disruptions
- AI-driven predictions for track wear and optimization
- Decision-support tools for infrastructure investment
Learning: Railways That Adapt and Improve
A truly intelligent railway system must learn from past experiences. My work applies AI to:
- Detect infrastructure defects beyond human capability
- Transfer knowledge between railway networks
- Simulate future scenarios using digital twins
- AI-driven defect detection in tracks and catenary
- Simulation-based infrastructure performance testing
- Reinforcement learning for operational improvements
