A simulated neural system (ANNs) for micro-hardnessof nano-crystalline titanium dioxide

Abstract

In this article, nano-crystalline titanium dioxide has been modeled by artificial neural networks (ANN) and resilient back-propagation (Rprop) training algorithm. For this purpose, composite hardness (H c ), yield stress (σ y ), and film hardness (H f ) have been collected at different dwell time (t), temperature (T) and relative indentation depth (β). ANN was trained on the available experimental data. Many runs were tried to achieve good performance. Simulation results and predicted values were compared with the corresponding experimental data. This comparison shows that neural networks are very powerful in modeling the nano-crystalline titanium dioxide experimental data with very low percentage of error. Mathematical formula describes the relation between inputs (t, T, β) and outputs (H c , σ y , H f ) obtained based on ANNs. Finally, this article showed that ANNs are very successful tools in modeling and are able to pursue the experimental data with a high exactness.