Title: Rotating machinery fault diagnosis using a quadratic neural unit

Authors: Ricardo Rodríguez-Jorge; Laura Sánchez-Pérez; Jiri Bila; Jiří Škvor

Addresses: Faculty of Science, Jan Evangelista Purkyně University, Ústí nad Labem, Czech Republic ' Instituto de Ingeniería y Tecnología, Universidad Autónoma de Ciudad Juárez, Ciudad Juárez, Chihuahua, México ' Department of Instrumentation and Control Engineering, Czech Technical University in Prague, Prague, Czech Republic ' Faculty of Science, Jan Evangelista Purkyně University, Ústí nad Labem, Czech Republic

Abstract: In this work, a quadratic neural unit was implemented for rotating machinery fault diagnoses of an industrial machine, where the input data that were used were taken from a vibration test on an alternating current motor. The data that were obtained from the vibrometre were the frequency and the average of the vibration, which were previously trained and input into the neural unit. The output of this unit was a value that can be used to categorize the severity level of an engine, according to the severity table provided by the norm ISO 10816 for industrial machines.

Keywords: quadratic neural unit; industrial machine; predictive maintenance; vibration test; alternating current motor.

DOI: 10.1504/IJGUC.2022.124403

International Journal of Grid and Utility Computing, 2022 Vol.13 No.2/3, pp.309 - 319

Received: 09 Dec 2020
Accepted: 02 Sep 2021
Published online: 26 Jul 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article