Connor Walker

PhD topic: Data-driven Intelligent Alarm Systems (DIAS) for Offshore Wind Maintenance

Connor Walker is developing advanced alarm processing systems for Offshore Wind Turbines using statistical methodology to improve Machine Learning accuracy. His current research focuses on how Large Language Models (LLMs) can be utilised to interpret alarm sequences and predict maintenance procedures, whilst ensuring LLM safety in the SafeLLM project.

 

Publications:

• Walker, C,. Rothon, C,. Aslansefat, K,. Papadopoulos, Y,. & Dethlefs, N. (2022). A Deep Learning Framework for Wind Turbine Repair Action Prediction Using Alarm Sequences and Long Short-Term Memory Algorithms. In the 8th International Symposium on Model-Based Safety Assessment (IMBSA2022).

• Walker, C,. Rothon, C,. Aslansefat, K,. Papadopoulos, Y,. & Dethlefs, N. (2024). Using Large Language Models to Recommend Repair Actions for Offshore Wind Maintenance. Manuscript in preparation.

• Walker, C,. Rothon, C,. Aslansefat, K,. Papadopoulos, Y,. & Dethlefs, N. (2024). Safety Monitoring for Large Language Models: A Case Study of Offshore Wind Maintenance. In the Proceedings of the 32nd Safety-Critical Systems Symposium (SSS2024).

 

Useful Links

 

• LinkedIn

​

Achievements

​

• Award: Computer Science Research Away Day​

• Authored two conference papers and made significant contributions to the SafeLLM project.

​

Research Interest

​

• Large Language Models

• SafeML

• Safe AI

• Offshore Wind & Renewable Energy

​