School of Engineering

Machine Health Intelligence

We develop AI solutions that enable machines and infrastructures to understand, monitor, and manage their own health.

By combining data-driven methods with engineering and physics knowledge, we detect anomalies, diagnose faults, and predict future system conditions. Our research helps industrial companies optimize maintenance, improve reliability, and increase operational efficiency across manufacturing, transportation, energy, and other critical infrastructure sectors.

At the heart of our work is the integration of artificial intelligence, physics, and domain expertise to create trustworthy, interpretable, and actionable machine intelligence for real-world industrial applications.

News

Research & Projects

Applied Research Focus

We help organizations improve the reliability, availability, safety and cost-effectiveness of industrial assets and critical infrastructure. By combining engineering expertise, data analytics, and artificial intelligence, we develop practical solutions that address real-world maintenance and operational challenges.

From Operational Challenges to Scalable Solutions

Our expertise covers the full journey from condition monitoring and diagnostics to prognostics, maintenance decision support, and enterprise-scale deployment. Working closely with industry partners, we translate research into value-generating solutions that increase asset lifetime, reduce maintenance costs, and enhanced operational resilience.

Application Areas

Our research is applied across a broad range of industrial sectors where reliability, safety, and operational performance are critical.


Energy Systems.  Monitoring, diagnostics, and prognostics for renewable energy assets, battery storage systems, electrical infrastructure, and nuclear power plants.


Transportation Systems.  Health monitoring and predictive maintenance for aircraft, railways, automotive fleets, maritime systems, and autonomous vehicles.


Manufacturing & Robotics. Intelligent maintenance solutions for production equipment, industrial robots, automated assembly systems, and smart manufacturing environments.
 

Research Areas

Machine Health Intelligence is the core research domain of the group. We develop methods for condition monitoring, fault diagnostics, prognostics, predictive maintenance, and intelligent asset management that enable organizations to understand asset health, anticipate failures, and optimize maintenance interventions throughout the asset lifecycle.

To advance Machine Health Intelligence, our research focuses on three complementary areas:

  • Trustworthy AI. We develop physics-informed machine learning (PIML), reliability-informed deep learning (RIDL), uncertainty quantification, and explainable AI methods to create reliable, interpretable, and trustworthy health monitoring and prognostics systems.

  • Agentic AI.  We investigate AI assistants, multi-agent systems, and knowledge-augmented decision-support frameworks that support engineers and operators in diagnostics, prognostics, and maintenance planning.

  • Resilient Intelligence. Our research explores adaptive monitoring systems, continual learning, autonomous reconfiguration, and resilience-aware decision support to enable systems that can adapt to changing operating conditions, evolving degradation mechanisms, and unexpected disruptions.

Selected Research Partners

MHI collaborates with leading industrial companies, research organizations, and academic institutions to advance the state of the art in machine health intelligence, predictive maintenance, and intelligent asset management.

Teaching

MHI contributes to undergraduate, graduate, and continuing education programs that equip engineers and decision-makers with the knowledge and tools required to monitor, maintain, and optimize the performance of industrial assets and critical infrastructure throughout their lifecycle.

Bachelor

  • Maintenance (MO.INS) 

  • Data-based Decision Support (WIV.DDS) 

  • Traffic System Operations (AVS.TSO) 

  • Anomaly Detection (WPI.AnDet) 

Master

  • Lifecycle Management of Infrastructures (FTP_Life) 

  • Anomaly Detection (AnDet) 

Continuing Education

Team

Team Lead

Senior Lecturers

Research Associates and Assistants

PhD Researchers