Original scientific paper

Metallurgical productions fault detection method based on RESLSTM-CNN model

Z. J. Chen ; School of Computer Science and Software Engineering, University of Science and Technology Liaoning, China
J. Zhao ; School of Computer Science and Software Engineering, University of Science and Technology Liaoning, China
M. A. Liu ; School of Computer Science and Software Engineering, University of Science and Technology Liaoning, China

Abstract

Timely detection of abnormal working conditions and accurate diagnosis of abnormal working conditions are of great research significance to ensure the safe and stable operation of metallurgical production processes and to avoid losses caused by faults. In this paper, it propose a residual long and short-term memory network and convolutional neural network (RESLSTM-CNN) model for fault detection in metallurgical production processes bearing fault detection with an accuracy of 98,92 %.

Keywords

metallurgical production; fault; detection; bearing; method network model

Hrčak ID:

290073

URI

https://hrcak.srce.hr/290073

Publication date:

3.4.2023.

Visits: 912 *