Evolving rules-based control

An approach to control non-linear objects based on evolving Rule-based (eR) models is presented in the paper. Fuzzy rules, representing the structure of the controller are generated based on data collected during the process of control using newly introduced technique for on-line identification of Takagi-Sugeno type of fuzzy rule-based models. Initially, the process is supposed to be controlled for few time steps by any other conventional type of controller (P, PID or a fuzzy one with a fixed structure determined off-line). Then, in on-line mode the output of the plant under control (including its dynamic) and the respective control signal applied has been memorised and stored. These data has been used to train in a non-iterative way the eR model representing the fuzzy controller, which aim is to control the plant at a given set point. The indirect adaptive control approach has been used in combination with the newly introduced on-line identification technique based on unsupervised learning of antecedent and consequent parts separately. This approach exploits the quasi-linear nature of Takagi-Sugeno models and builds-up the control rule-base structure and adapts it in on-line mode. The method is illustrated with an example from air-conditioning systems, though it has wider potential applications.