Possibilities of application of artificial neural networks for biological and nonconventional materials
Nalazite se na CroRIS probnoj okolini. Ovdje evidentirani podaci neće biti pohranjeni u Informacijskom sustavu znanosti RH. Ako je ovo greška, CroRIS produkcijskoj okolini moguće je pristupi putem poveznice www.croris.hr
izvor podataka: crosbi !

Possibilities of application of artificial neural networks for biological and nonconventional materials (CROSBI ID 664598)

Prilog sa skupa u zborniku | sažetak izlaganja sa skupa | međunarodna recenzija

Basan, Robert ; Marohnić, Tea ; Franulović, Marina Possibilities of application of artificial neural networks for biological and nonconventional materials // Proceedings of the First International Conference on Materials, Mimicking and Manufacturing from and for the Bio Application. Milano: Politecnico di Milano, 2018, 110, 1

Podaci o odgovornosti

Basan, Robert ; Marohnić, Tea ; Franulović, Marina

engleski

Possibilities of application of artificial neural networks for biological and nonconventional materials

As very flexible and versatile statistical models artificial neural networks (ANNs) are increasingly used in various areas of human activity for solving various types of problems such as weather forecasting, pattern recognition in medical findings, signal processing, risk assessment etc. One of their many applications is also function approximation i.e. identification of unknown relationship between input data (predictor variables) and target data (dependent variables). Unlike conventional methods for function approximation, such as regression analysis, ANNs “learn-by-example” meaning that they can model more complex relationships between inputs and targets and are thus often used in estimation of complex materials’ behavior and properties. Materials commonly involved are metallic materials – steels, aluminum alloys and others. Genel (2004), Ghajar et al. (2011) and Marohnic (2017) applied ANNs for estimation of cyclic stress- strain and strain-life fatigue properties of steels. However, ANNs are also successfully applied to other material groups - Yousef et al. (2011) used ANNs for prediction of tensile curves and mechanical properties of pure polyethylene PE, pure propylene PP and their blends while Shen et al. (2004) developed an ANN based constitutive model for rubber material. The need for developing new materials with ever better properties is constantly present nowadays and the inspiration is often found in nature’s materials or biological tissues. Since the results of experiments on material behavior of such materials are relatively scarce or difficult to obtain (ethical problems), it could be of great importance to develop a smart system based on ANNs that could be sufficiently accurate in predicting such materials behavior and reduce the need for experimental characterization. This is of great importance when it comes to testing biological tissues. Current work is oriented towards investigations of existing uses of ANNs in such applications for which extensive literature review is underway in order to determine best-practices and also to acquire required data which could be used in development of initial ANN-based models.

biological tissues ; material behavior ; artificial neural networks ; estimation

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

Podaci o prilogu

110

2018.

objavljeno

Podaci o matičnoj publikaciji

Vergani, Laura ; Guagliano, Mario

Milano: Politecnico di Milano

Podaci o skupu

predavanje

27.06.2018-29.06.2018

Milano, Italija

Povezanost rada

Strojarstvo