SOME ARTIFICIAL NEURAL-NETWORK APPLICATIONS TO GREENHOUSE ENVIRONMENTAL-CONTROL

A review is presented of several potentially useful applications of ar tificial neural networks (NN) to greenhouse climate control. Subjects covered are: Quasi-steady-state modelling, reduction (compression) of input and state vectors, NNs used as difference equations and replacin g controllers (algorithms or humans) with NNs. In this context the str ength of NNs is their flexibility to adapt to non-linear and non-physi cal data. Their main disadvantage is that their proper training requir es large multi-dimensional sets of data to reduce the risk of extrapol ation. Therefore, minimizing the dimensionality of the problem (both i nput and state vectors) becomes of paramount importance. Bottleneck NN s may be used for this purpose. (C) 1997 Elsevier Science B.V.