Thesis topic:

Explainable AI in Digital Twin Environments for Industrial Fault Detection

Supervisor: Mubashar Iqbal
- contact: mubashar.iqbal@ut.ee
This thesis focuses on integrating explainable artificial intelligence (XAI) with digital twin technology to improve fault detection in industrial systems. Digital twins, virtual replicas of physical systems, are widely used in industries to monitor and simulate real-time operations. By incorporating XAI models, this research aims to enhance the transparency of AI-driven decision-making processes in detecting faults or anomalies in industrial machinery or processes. Unlike traditional AI, where the decision-making is often opaque, XAI provides human-understandable explanations for the identified issues, helping engineers and operators better interpret the results. This could improve trust and adoption of AI in critical systems by giving users clearer insights into why a specific fault was flagged. This work could also explore the challenges of integrating XAI within complex digital twins, considering computational efficiency and scalability.