Application of Neural Networks and Expert Systems in a hierarchical approach to the intelligent greenhouse control

Abstract

A novelty methodology based on the hierarchical combination of neural networks and expert systems is proposed in a centralized approach for the intelligent greenhouse control. The knowledge-based system is in charge of carrying out the determination of PH land value, composition, carbonic anhydride artificial atmosphere, external and internal temperature, wind and humidity measurements. From the results obtained, and by means of a neural network developed and trained for this application, the land quality is evaluated. On the other hand, the expert system, apart from supervising the system function and implementing fault tolerance mechanisms, performs the opportune actions in function of the results obtained by the neural network and others variables directly controlled by the expert system, in order to maintain the optimum microclimate and land composition. Satisfactory results have been obtained in the application of this approach to different quality lands and climatic conditions.