Incremental novelty detection and fault identification scheme applied to a kinematic chain under non-stationary operation

被引：8

作者：

Carino, J. A. ^{[1
]}

Delgado-Prieto, M. ^{[1
]}

Zurita, D. ^{[1
]}

Picot, A. ^{[2
]}

Ortega, J. A. ^{[1
]}

Romero-Troncoso, R. J. ^{[3
]}

机构：

[1] Tech Univ Catalonia, MCIA Res Ctr, Terrassa, Spain

[2] Univ Tolouse, Lab Plasma & Convers Energie, Toulouse, France

[3] Autonomous Univ Queretaro, HSPdigital, San Juan Del Rio, Mexico

来源：

ISA TRANSACTIONS | 2020年 / 97卷

关键词：

Condition monitoring; Data-driven modelling; Fault diagnosis; Non-stationary operation; Novelty detection; DIAGNOSIS; MECHANISM;

D O I：

10.1016/j.isatra.2019.07.025

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Classical methods for monitoring electromechanical systems lack two critical functions for effective industrial application: management of unexpected events and the incorporation of new patterns into the knowledge database. This study presents a novel, high-performance condition-monitoring method based on a four-stage incremental learning approach. First, non-stationary operation is characterised using normalised time-frequency maps. Second, operating novelties are detected using multivariate kernel density estimators. Third, the operating novelties are characterised and labelled to increase the knowledge available for subsequent diagnosis. Fourth, operating faults are diagnosed and classified using neural networks. The proposed method is validated experimentally with an industrial camshaft-based machine under a variety of operating conditions. (C) 2019 ISA. Published by Elsevier Ltd. All rights reserved.

引用

页码：76 / 85

页数：10

共 30 条

[1] FDI based on Artificial Neural Network for Low-Voltage-Ride-Through in DFIG-based Wind Turbine [J].