Real-Time Monitoring of Automation Processes with Applications to Cyber Security

Potential supervisors: 
Description: 

Motivation

Cyber-physical automation processes operating in critical infrastructure typically involve expensive and safety-critical equipment and machinery. Oftentimes, these systems have real-time availability and uptime requirements, which makes unexpected failures of sensitive machines highly costly and in some cases dangerous to society. Real-time monitoring of industrial assets and automation processes to detect deviations from a baseline behavior is an effective way of ensuring optimal operation and resilience to cyber-attacks. In this master thesis, the students will work with imagery and sensory data from a real industrial process and apply state-of-art anomaly-detection methods.

Challenges & Expected Outcome

Imagery and sensory data collected from industrial processes requires challenging and innovative pre-processing approaches to make it representative and suitable for iterative anomaly-detection algorithms. The expected outcome of this thesis is to investigate the feasibility and efficacy of real-time monitoring of automation processes through temporal process data to ensure optimal and safe operation.

Date range: 
September, 2020 to June, 2021