Neural Networks and Microelectronic Parameters Distribution Measurements depending on Sintering Temperature and Applied Voltage

Abstract

This research is based on the idea to design the interface structure around the grains and thin layers between two grains, as a possible solution for deep microelectronic parameters integrations. The experiments have been based on nano-BaTiO3 powders with Y-based additive. The advanced idea is to create the new observed directions to network microelectronic characteristics in thin films coated around and between the grains on the way to get and compare with global results on the samples. Biomimetic similarities are artificial neural networks which could be original method and tools that we use to map input–output data and could be applied on ceramics microelectronic parameters. This mapping is developed in the manner like signals that are processed in real biological neural networks. These signals are processed by using artificial neurons, which have a simple function to process input signal, as well as adjustable parameter which represents sensitivity to inputs. The integrated network output presents practically the large number of inner neurons outputs sum. This original idea is to connect analysis results and neural networks. It is of the great importance to connect microcapacitances by neural network with the goal to compare the experimental results in the bulk samples measurements and microelectronics parameters. The result of these researches is the study of functional relation definition between consolidation parameters, voltage (U), consolidation sintering temperature and relative capacitance change, from the bulk sample surface down to the coating thin films around the grains.