Data-Driven Control and Learning Systems

Any industry processes, aerospace systems, transportation systems, power grid systems, etc. are becoming more and more complex. Modeling the accurate physical models for these plants using first principles may be impossible or infeasible. Even if their physical models are available, they may be too complex to be tractable for controller design, system monitoring, performance evaluation, etc. However, huge amounts of measured process data can easily be collected due to the well developed information technology, both in the form of stored historical data from prior measurements and on-line data in real time during process runs. Thus, it would be very significant if we can make full use of those on-line or off-line process data to directly design controller, predict and assess system states, evaluate performance, make decisions, perform real-time optimization, and conduct fault diagnosis. For this reason, the establishment and development of data-driven control (DDC) theory and methodology are the urgent issues both in theory and applications.