Applying more intelligent algorithms in the process computers that control the greenhouse climate and irrigation may help growers to optimize crop growth and yields as well as save energy. A greenhouse process computer has been developed with an architecture that allows for easy implementation of custom algorithms without risk to control continuity. The system in question was demonstrated by implementing a transpiration model that predicts actual crop transpiration from greenhouse climate measurements. In addition, the process computer was connected to a system that calculates the transpiration rate from the rooting substrate weight, irrigation supply, drainage water and crop weight. The transpiration model was calibrated and validated with historical data from the weighing system collected at a Dutch commercial greenhouse from April to May 2014. Then, the model was implemented in the process control computer at commercial nurseries in The Netherlands and Texas USA, respectively. It can be assumed that the model predicts the transpiration rate of a healthy and productive crop. Therefore, suboptimal cropperformance is indicated when the measured transpiration rate is less than predicted. In the time period when the tests were conducted, the crops exhibited both low transpiration rates at midday and reduced transpiration rates due to insufficient irrigation. On those occasions, the process computer generated an alarm in order to warn the grower that a problem had occurred. This study demonstrates that additional intelligence, such as simulation models, when implemented in a greenhouse process computer and combined with the appropriate measurements, can automatically alert the grower of potentially damaging conditions, e.g. reduced crop performance or a system malfunction in the greenhouse. The developed architecture will facilitate the design of new generation computer controls that take advantage of increasing knowledge of crop-functioning and other greenhouse processes.