The neural network analysis of optical glasses transmittance

The attention is devoted to the active and passive optical fibres of the suitable glasses. Because of high structural sensitivity of optical transmittance to glass composition we present sophisticated solution of experimental data evaluation to obtain way directly predict the proper glass composition-transmitance relation. In the paper we present application of artificial neural network (ANN) on relation between glass composition versus optical transmittance of the chosen glass systems of Sb₂O₃ - PbCl₂ and Sb₂O₃ - PbO - M₂O, where M was Na, K and Li, respectively. The developed neural model predicts optical transmittance with sufficiently small error (7%). Neural networks are able to simulate dependences which can be hardly solved by classic methods of statistic data evaluation and they are able to express more complex relations than these methods.