Neural daylight control system

The paper describes the design, the implementation of a neural controller used in an automatic daylight control system. The automatic lighting control system (ALCS) attempt to maintain constant the illuminance at the desired level on working plane even if the daylight contribution is variable. Therefore, the daylight will represent the perturbation signal for the ALCS. The mathematical model of process is unknown. The applied structure of control need the inverse model of process. For this purpose it was used other artificial neural network (ANN) which identify the inverse model of process in an on-line manner. In fact, this ANN identify the inverse model of process + the perturbation signal. In this way the learning signal for neural controller has a better accuracy for the present application.