Artificial Neural Networks Used for Development Prediction of State-of-the-Art Surface Engineering Areas
The paper presents new, possible applications of artificial neural networks in the field of materials science and material engineering in relation to other artificial intelligence methods known and applied in this area. The most recent simulation experiments, the exemplary results of which are presented in this paper, point out that the scope of the existing applications of artificial neural networks can be extended to encompass new areas related to prediction of development of materials treatment and processing technologies. The goal of such research is to focus, intentionally, the areas of future research and investments on the most promising areas likely to yield the highest added value in the future together with mitigating a risk relating to such a process. The computational models created were used for creating multi-variant probabilistic scenarios of future events based on heuristic independent variables acquired in the process of multi-stage expert surveys. Dependencies were determined, in particular, between the probability of occurrence of alternative macro-scenarios of future events and the development of the relevant thematic areas of M1–M7 and P1–P7.
Algirdas V. Valiulis, Olegas Černašėjus and Vadim Mokšin
A. D. Dobrzańska-Danikiewicz et al., "Artificial Neural Networks Used for Development Prediction of State-of-the-Art Surface Engineering Areas", Solid State Phenomena, Vols. 220-221, pp. 785-789, 2015