On-line modeling of air temperature system in a naturally ventilated greenhouse

Linear auto-regression moving average with extra input (ARMAX) model for air temperature system in a naturally ventilated greenhouse was developed. Outside air temperature, relative humidity, global solar radiation and wind speed were used as disturbing input variables of the model, while inside temperature was used as output variable of the model. Based on energy and mass flows equations, statistic hypothesis test and model fits analysis were used together to select the model structure, and gradually oblivious recursive extended least squares (RELS) method was adopted to identify the model parameters on line. Moreover, an intelligent supervisory segment was devised to monitor and fix problems appearing during the on-line modeling process. Experiments were carried out in a greenhouse to validate the model. It is concluded that ARMAX model with 4 input variables could be able to describe and predict the air temperature in the greenhouse reasonably well.