20 KB611 KB17 KB200020242012Mazahéri, AlyShabani, Mohsen Ostadštevilka:2letnik:46str. 109-115ISSN:1580-2949COBISSID:929194URN:URN:NBN:SI:doc-UTEIYABSenInštitut za kovinske materiale in tehnologijeMateriali in tehnologijecompositehardnesskompozitmechanical propertiesmehanske lastnostitrdotaThe performance of various artificial neurons interconnections in the modelling and experimental manufacturing of the composites| Predstavitev različnih umetnih nevronskih povezav pri modeliranju in eksperimentalni izdelavi kompozitov|This study reports the performance of different artificial neural network (ANN) training algorithms in the prediction of mechanical properties. First, an experimental investigation was carried out on the mechanical behavior of an A356 composite reinforced with B4C particulates and then an ANN modeling was implemented in order to predict the mechanical properties, including the yield stress, UTS, hardness and elongation percentage. After the preparation of the training set, the neural network was trained using different training algorithms, hidden layers and the number of neurons in hidden layers. The test set was used to check the system accuracy for each training algorithm at the end of the learning. The results show that the Levenberg-Marquardt learning algorithm gave the best prediction for the yield stress, UTS, hardness and elongation percentage of the A356 composite reinforced with B4C particulatesV tem delu smo najprej opredelili mehanske lastnosti, vključno z mejo plastičnosti, natezno trdnostjo, trdoto in raztezkom kompozita A356, ojačenega z delci B4C, in nato uporabili kombinacijo umetne nevronske mreže in metode končnih elementov. Po pripravi trening postavitve je bila nevronska mreža preizkušena z uporabo različnih algoritmov, skritih plasti in števila nevronov v skritih plasteh. Trening postavitev je bila uporabljena za preverjanje natančnosti za vsak algoritem na koncu učenja. Rezultati kažejo, da da Levenberg-Marquardtov učni logaritem najboljšo napoved meje plastičnosti, natezne trdnosti, trdote in raztezka za kompozit A356, ki je ojačen z delci B4CTEXTznanstveno časopisjejournalsSlovenian National E-content AggregatorNational and University Library of SloveniaInštitut za kovinske materiale in tehnologije