Goran Andonovski, Edwin Lughofer, and Igor Škrjanc
Fuzzy cloud-based predictive functional control (FCPFC), Robust evolving cloud-based controller (RECCo), chemical reactor CSTR
The objective of this paper was to present a performance comparison between a new fuzzy (cloud-based) predictive functional control (FCPFC) and the Robust Evolving Cloud-based controller (RECCo). Both methods use the same type of fuzzy cloud-based system (the same antecedent part). The clouds are used for partitioning the data space and dealing with the non-linearity of the processes. In case of FCPFC the fuzzy cloud-based model is used to identify the process model while the control signal is analytically calculated to minimize some criterion. In case of RECCo algorithm the clouds are used to identify the operating region and the control signal is adapted in online manner. The controllers were tested on a second order nonlinear, locally oscillating, chemical process CSTR (Continuous Stirred Tank Reactor). The performance and control effort of the methods were compared according to several criteria. The results show that the proposed controller FCPFC has slightly faster response but longer settling time than the RECCo controller.