Evaluation of One-Class Classifiers for Fault Detection: Mahalanobis Classifiers and the Mahalanobis-Taguchi System

被引:7
作者
Kim, Seul-Gi [1 ]
Park, Donghyun [2 ]
Jung, Jae-Yoon [2 ,3 ]
机构
[1] SK Inc C&C, ICT Digital Sect, Seongnam Si 13558, South Korea
[2] Kyung Hee Univ, Dept Big Data Analyt, Yongin 17104, South Korea
[3] Kyung Hee Univ, Dept Ind & Management Syst Engn, Yongin 17104, South Korea
基金
新加坡国家研究基金会;
关键词
one-class classification; imbalanced classification; fault detection; Mahalanobis distance; Mahalanobis-Taguchi system; smart manufacturing; DIAGNOSIS; SELECTION;
D O I
10.3390/pr9081450
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
Today, real-time fault detection and predictive maintenance based on sensor data are actively introduced in various areas such as manufacturing, aircraft, and power system monitoring. Many faults in motors or rotating machinery like industrial robots, aircraft engines, and wind turbines can be diagnosed by analyzing signal data such as vibration and noise. In this study, to detect failures based on vibration data, preprocessing was performed using signal processing techniques such as the Hamming window and the cepstrum transform. After that, 10 statistical condition indicators were extracted to train the machine learning models. Specifically, two types of Mahalanobis distance (MD)-based one-class classification methods, the MD classifier and the Mahalanobis-Taguchi system, were evaluated in detecting the faults of rotating machinery. Their performance for fault detection on rotating machinery was evaluated with different imbalanced ratios of data by comparing with binary classification models, which included classical versions and imbalanced classification versions of support vector machine and random forest algorithms. The experimental results showed the MD-based classifiers became more effective than binary classifiers in cases in which there were much fewer defect data than normal data, which is often common in the real-world industrial field.
引用
收藏
页数:15
相关论文
共 29 条
[1]  
[Anonymous], 2002, The Mahalanobis-Taguchi Strategy: A Pattern Technology System
[2]   Outliers analysis and one class classification approach for planetary gearbox diagnosis [J].
Bartkowiak, Anna ;
Zimroz, Radoslaw .
9TH INTERNATIONAL CONFERENCE ON DAMAGE ASSESSMENT OF STRUCTURES (DAMAS 2011), 2011, 305
[3]   The chi squared and multinormal distributions [J].
Brereton, Richard G. .
JOURNAL OF CHEMOMETRICS, 2015, 29 (01) :9-12
[4]   Selection Strategy of Vibration Feature Target under Centrifugal Pumps Cavitation [J].
Cao, Ruijia ;
Yuan, Jianping .
APPLIED SCIENCES-BASEL, 2020, 10 (22) :1-13
[5]   SMOTE: Synthetic minority over-sampling technique [J].
Chawla, Nitesh V. ;
Bowyer, Kevin W. ;
Hall, Lawrence O. ;
Kegelmeyer, W. Philip .
2002, American Association for Artificial Intelligence (16)
[6]   Quality inspection of complex-shaped metal parts by vibrations and an integrated Mahalanobis classification system [J].
Cheng, Liangliang ;
Yaghoubi, Vahid ;
Van Paepegem, Wim ;
Kersemans, Mathias .
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 2021, 20 (06) :3075-3091
[7]   On the Influence of Reference Mahalanobis Distance Space for Quality Classification of Complex Metal Parts Using Vibrations [J].
Cheng, Liangliang ;
Yaghoubi, Vahid ;
Van Paepegem, Wim ;
Kersemans, Mathias .
APPLIED SCIENCES-BASEL, 2020, 10 (23) :1-18
[8]   Mahalanobis classification system (MCS) integrated with binary particle swarm optimization for robust quality classification of complex metallic turbine blades [J].
Cheng, Liangliang ;
Yaghoubi, Vahid ;
Van Paepegem, Wim ;
Kersemans, Mathias .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2021, 146
[9]   A novel approach for classifying imbalance welding data: Mahalanobis genetic algorithm (MGA) [J].
El-Banna, Mahmoud .
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2015, 77 (1-4) :407-425
[10]   Data-Driven Approach for Fault Detection and Diagnostic in Semiconductor Manufacturing [J].
Fan, Shu-Kai S. ;
Hsu, Chia-Yu ;
Tsai, Du-Ming ;
He, Fei ;
Cheng, Chun-Chung .
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2020, 17 (04) :1925-1936