Diagnostic system of sintering process

E. G. Egorova, A. A. Musaev

St. Petersburg Institute for Informatics and Automation of RAS

Abstract: The complexity of a sintering process in an iron- and steel-making plant always tends to create a problem in monitoring and supervision system. This issue reviews the approach of implementing of the two level neuronet model. The neural network with normal and faulty event is executed on the data collected from the experiment. The upper level network is used for the detection of faulty machine and lower level networks are executed the identification of the abnormal situations.

Keywords: Diagnostics, fault, artificial neural network, sintering process.

UDC: 62-501.12

PACS: 81.20.Ev

MSC: 62M45

Received: 18.06.2012