"4"^^ . . . . "27360" . . "ingots, model, neural networks, prediction, steel"@en . . . "Recent Researches in Engineering and Automatic Control" . "2011-12-10+01:00"^^ . "Jan\u010D\u00EDkov\u00E1, Zora" . "Prediction of Forging Ingots Defects Using Neural Networks" . . "RIV/61989100:27360/11:86080579" . "4"^^ . "At some types of ingots technological deviations exhibit by defects, which occur as late as in the process of forging. Prediction of such defects would enable a fast intervention and thus reducing costs for the reparation. Statistically was proven, that the defects are not caused by exceeding of any measured parameter in the production. However, they are caused by an unsuitable combination of more parameters. In such case artificial intelligence elements can be successfully applied. A multilayer artificial neural network was used for the prediction of defective ingots. Results, which were reached at prediction with neural network, are very interesting. In some cases even 100% accordance occurred." . . "Puerto De La Cruz, Tenerife" . "Ru\u017Eiak, Ivan" . "Frydr\u00FD\u0161ek, Karel" . "Prediction of Forging Ingots Defects Using Neural Networks"@en . . "Prediction of Forging Ingots Defects Using Neural Networks"@en . . . "Neuvedeno" . . "5"^^ . "Ko\u0161tial, Pavol" . . . . "[6E7396D56B4B]" . . . "RIV/61989100:27360/11:86080579!RIV12-MPO-27360___" . "978-1-61804-057-2" . "WSEAS Press" . . . "Val\u00ED\u010Dek, Jan" . "Prediction of Forging Ingots Defects Using Neural Networks" . . "222721" . "P(FR-TI3/818)" . "Ru\u017Eiak, Ivan" . . "At some types of ingots technological deviations exhibit by defects, which occur as late as in the process of forging. Prediction of such defects would enable a fast intervention and thus reducing costs for the reparation. Statistically was proven, that the defects are not caused by exceeding of any measured parameter in the production. However, they are caused by an unsuitable combination of more parameters. In such case artificial intelligence elements can be successfully applied. A multilayer artificial neural network was used for the prediction of defective ingots. Results, which were reached at prediction with neural network, are very interesting. In some cases even 100% accordance occurred."@en .