Artificial neural network applied on sintered BaTiO3-ceramic density

It is very important to determine microstructure parameters of consolidated ceramic samples, because it opens new frontiers for further microelectronics miniaturization and integrations. Therefore, controlling, predicting and designing the ceramic materials? properties are the objectives in ceramic materials consolidating process, within the science of sintering. In order to calculate the precise values of desired microstructure parameter at the level of the grains? coating layers based on the measurements on the bulk samples, we applied the artificial neural networks, as a powerful mathematical tool for mapping input-output data. Input signals are propagated forward, as well as the adjustable coefficients that contribute the calculated output signal, denoted as error, which is propagated backwards and replaced by examined parameter. In our previous research, we used neural networks to calculate different electrophysical parameters at the nano level of the grain boundary, like relative capacitance, breakdown voltage or tangent loss, and now we extend the research on sintered material?s density calculation. Errors on the network output were substituted by different consolidated samples density values measured on the bulk, thus enabling the calculation of precise material?s density values between the layers. We performed the neural network theoretical experiments for different number of neurons in hidden layers, according to experimental ceramics material?s density of ?=5.4x103[kg/m3], but it opens the possibility for neural networks application within other density values, as well.