direct expansion, air conditioning, on-line, adaptive control, artificial neural network
An on-line adaptive artificial neural network (ANN)-based controller has been developed for an experimental DX A/C system. It controls the indoor air temperature and humidity simultaneously by varying the compressor speed and supply fan speed in a space served by the experimental DX A/C system. The ANN-based direct inverse control (DIC) strategy was adopted in the development of the controller and the specialized training method was used to on-line update an ANN-based model and an inverse model used in the controller. The controllability tests including the command following test and the disturbance rejection test were carried out using the experimental DX A/C system, and the test results showed that the on-line adaptive ANN-based controller developed was able to control indoor air dry-bulb temperature and wet-bulb temperature outside the operating conditions within which the models were trained, with a high control accuracy.