Intelligent Control System of Biotechnological Objects with Fuzzy Controller and Noise Filtration Unit

The article presents the study results of the intelligent control systems for biotechnological objects using the example of a greenhouse. A measuring system for effectively study of solar radiation and prediction of possible violations of information was developed. Neural networks were used as a mathematical tool for predicting temperature time series. The information channels of solar radiation were filtered using the Hilbert-Huang transformation. A transformational mathematical filter was developed, which made it possible to significantly increase the accuracy of solar radiation intensity prediction. The optimal weights for the neural network of predicting the time series of solar radiation intensity were determined with the application of the genetic algorithm. The developed vegetable production control system allows ensuring the maximum profit from the products sale and minimizes energy costs by introducing an additional unit of the neural network prediction of external disturbances and to determine control actions using fuzzy controllers.