NEURAL NETWORK CONTROL SYSTEM OF VD-400 VACUUM DEAERATOR
P.P. Alekseev, I.A. Sherbatov
Astrakhan State Technical University, Str. Tatishchev, 16, Astrakhan, Astrakhan region
Keywords: вакуумный деаэратор, многослойные нейронные сети, обучение и моделирование нейронных сетей, линейная функция, vacuum deaerator, multilayered neural networks, training and modeling of neural networks, linear function
Abstract
The article considers the algorithms, applied in program realization of a neural network control system of concentration of oxygen of deaerated water. The analysis of the VD-400vacuum deaerator as the object of control is carried out. Control and perturbation actions, as well as adjustable parameters of VD-400 are revealed. The special attention is paid to the software, creating models of the feedforward multilayered neural networks with live training. Interfaces of training and modeling are shown. The general scheme of control of the VD-400 vacuum deaerator is presented.
|
