Data-driven control and learning has been developed quickly both in theory and applications recently. The deep involvement of information science in practical processes poses enormous challenges to the existing control science and engineering due to their size, distributed nature and complexity. Modeling these processes accurately using first principles or identification is almost impossible although these plants produce huge amount of operation data in every moment. The high-tech hardware/software and the cloud computing enable us to perform complex real-time computation, which makes implementation of data-driven control and method for these complex practical plants possible. It would be very significant if we can learn the systems’ behaviors, discover the relationship of system variables by making full use of on-line or off-line process data, to directly design controller, predict and assess system states, make decisions, perform real-time optimization and conduct fault diagnosis.
Call for paper
Draft paper submission deadline：2017-12-20
Draft paper acceptance notification：2018-03-01
Abstract submission deadline：2017-12-20
Final paper submission deadline：2018-03-31