Managing a greenhouse complex using the synergetic approach and neural networks

Abstract

The paper considers the use of artificial neural networks in order to synthesize intelligent systems governed by a synergetic control law. It has been shown that so far all the studied objects and, therefore, control laws, have been considered linear, or have been treated to reduce them to such, thereby compromising their certain features. However, as evidenced by practice, actual objects are mostly nonlinear. Consideration of such objects with an attempt of their linearization leads to that the important characteristics of the entire process are lost. A greenhouse complex is mostly composed of such nonlinear objects of control. A greenhouse, as well as each process separately, are not exception. We have proposed basic provisions to the synergistic approach related to the systems synthesis task. The synergistic synthesis of control law has been shown for a greenhouse complex under conditions of non-controlling changes in the technological parameters and external disturbances. The applied mathematical apparatus of fuzzy logic enables the implementation of fuzzy control. It manifests itself particularly positively under conditions when the processes are difficult to analyze by using conventional quantitative methods. As well as when the acquired information about the object is substandard, inaccurate, or ambiguous. This is exactly the type of information received for analysis and its subsequent use when growing vegetables at greenhouse complexes. We have proposed an algorithm to synthesize a neuro-network controller for a greenhouse complex based on the predefined synergetic control law. The algorithm is based on the performance of the synergistic controller that simulates values for temperature and humidity from an artificial neural network following our training it. A feature of the proposed integrated approach to the synthesis of an intelligent control system for a greenhouse complex is a combination of the principle of unification of the processes of self-organization and training a neural network at a preliminary stage. Such a combination ensures further stable functioning of the system aimed to intelligently control the cultivation of vegetable produce.