Using of neuron net models for statistic analysis and control of glass ribbon formation on the tin melt

A technique for constructing and applying models on artificial neural networks for analyzing and regulating the mode of forming a glass ribbon on a tin melt is considered. The technique provides for the creation of models on neural networks describing the dependence of the glass property indicators on the regime and controlled input variables, as well as the development of an algorithm for adjusting the regime variables depending on the thickness of the glass strip produced, taking into account changes in controlled disturbances. Tab. 3, ill. 1, bibliography: 3 titles.