Open AccessFaults Detection and Classification under Variable Condition Using Intrinsic Time - Scale Decomposition and Neural Network
Author(s) -
Saidani Djama Leddine,
Rahmoune Chamceddine,
R. Zenasni
Publication year - 2021
Publication title -
journal européen des systèmes automatisés/journal européen des systèmes automaitsés
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.16
H-Index - 20
eISSN - 2116-7087
pISSN - 1269-6935
DOI - 10.18280/jesa.540513
Subject(s) - multilayer perceptron , fault (geology) , pattern recognition (psychology) , root mean square , artificial neural network , nonlinear system , vibration , perceptron , computer science , rotor (electric) , artificial intelligence , rotation (mathematics) , control theory (sociology) , engineering , acoustics , physics , mechanical engineering , control (management) , quantum mechanics , seismology , electrical engineering , geology
Misalignment and unbalance are a common fault occurring in the rotor system. A new approach for detecting misalignment and unbalance problems combining the intrinsic time - scale decomposition (ITD), the root mean square (RMS) and perceptron multilayer network (MLP) is proposed in this paper. Vibration signals of normal condition, misalignment horizontal, misalignment vertical and unbalance with different level are collected under different speed. ITD, nonlinear analysis of signals, was applied to decompose the vibration signals into 8 proper rotation components. The RMS values of 8 components are calculated and using as features vector. Last, the perceptron multilayer network was used for fault identification and classification. The proposed approach accurately classified and detection of unbalance and misalignment; the average accuracy achieved is 97.99%.