engleski

ESTIMATION OF WEAR BEHAVIOUR IN ACID SOLUTION OF DENTAL CERAMICS BY NEURAL NETWORK

This research investigated the wear behaviour of dental ceramics in acid solution (10-3 mol dm-3 HCl) at temperature of 50 oC. The experiments were conducted on four samples of dental ceramics: feldspatic ceramic, hydrothermal ceramic, bijeli valjčić and žuti valjčić. The resistent of samples of dental ceramics to wear was estimated by the mass change of dental samples after contact with 10-3 mol dm-3 HCl, and measurements of the mass concentration of eluted Na+, K+, Ca2+, Si4+ and Al3+ ions. The measurements were made at time interval of 1, 2, 3, 6 and 12 months. The concentrations of Na+, K+ and Ca2+ were determined by ion chromatography (IC) and that of Si4+ and Al3+ by UV/VIS spectrometry. For the subject issue, using experimental data, the feedforward backpropagation neural network for estimation of wear behaviour of dental ceramics has been modelled. The results of 1, 2 and 12 months time interval measurements were used for the training 13-20-5 model of neural network. Comparison of experimental data and data obtained by estimation (results of 3 and 6 months interval time) of neural network shows that applied network model provides very good estimation of wear behaviour of dental ceramics with high correlation coefficient (R) and low sum of squared error (SSE) between measurement and estimated output values.

dental ceramics; acid; neural network

nije evidentirano