AI-enabled Digital Twins for Cyber-Physical Systems

Shaukat Ali
Simula Research Lab

Given that operational cyber-physical systems (CPS) produce continuous data, a complementary approach to building digital twins is learning digital twin models with machine learning techniques and providing functionalities such as predictions and anomaly detection.
The talk will present our recent works on learning digital twins from historical data and continuous updates of digital twins with continuous data from operational CPS. Various machine learning techniques were applied, such as generative adversarial networks, curriculum learning, and transfer learning to learn digital twins. The digital twins were built for use cases from the transportation domain and water distribution/treatment plants focusing on anomaly detection and waiting time predictions.
Finally, the talk will present the research directions which we are following for building AI-enabled digital twins

Speaker bio: Shaukat Ali is a Chief Research Scientist and Head of the Department at Simula Research Laboratory, Norway. His research focuses on devising novel methods for the Verification and Validation of Cyber-Physical Systems. He has been involved in several basic research, research-based innovation, and innovation projects in the capacity of PI/Co-PI related to testing, search-based software engineering, model-based system engineering, and, recently on, quantum software engineering. Shaukat has been on the program committees of several international conferences (e.g., FSE, ICSE, MODELS, ICST, GECCO, SSBSE) and also served as a reviewer for several software engineering journals (e.g., TSE, IST, SOSYM, JSS, TEVC).

Recording