HYBRID NEURAL NETWORKS IN CONTINUOUS PRODUCTION CONTROL

Baryshnikova Elena Sergeevna, Krylosova Nataliya Yurievna

The article considers the problem of continuous production control on the example of technological process of sheet glass production. The information about the object is presented in the form of expert evaluations in natural language. To maintain the stability of complex continuous technological processes, a model based on fuzzy neural network is proposed, combining the apparatus of artificial neural networks and fuzzy logic mechanisms. A hybrid algorithm is used to train the network. Since the network training is a continuous process, the proposed model will be adapted to the changing parameters of production, which will allow to use this network on other similar technological lines to maintain the stability of their work.

Keywords:fuzzy neural network, control system, continuous production.