Browse > Article

Rejection Scheme of Nearest Neighbor Classifier for Diagnosis of Rotating Machine Fault  

Choe, Yeong-Il (Dept.of Mechanical Engineering, Graduate School of Chonnam National Universityisy)
Park, Gwang-Ho (Dept.of Mechanical Engineering, Graduate School of Chonnam National Universityisy)
Gi, Chang-Du (Dept.of Mechanical Engineering, Chonnam National Universityisy)
Publication Information
Journal of the Korean Society for Precision Engineering / v.19, no.3, 2002 , pp. 52-58 More about this Journal
Abstract
The purpose of condition monitoring and fault diagnosis is to detect faults occurring in machinery in order to improve the level of safety in plants and reduce operational and maintenance costs. The recognition performance is important not only to gain a high recognition rate bur a1so to minimize the diagnosis failures error rate by using off effective rejection module. We examined the problem of performance evaluation for the rejection scheme considering the accuracy of individual c1asses in order to increase the recognition performance. We use the Smith's method among the previous studies related to rejection method. Nearest neighbor classifier is used for classifying the machine conditions from the vibration signals. The experiment results for the performance evaluation of rejection show the modified optimum rejection method is superior to others.
Keywords
Pattern Recognition; Nearest Neighbor Classifier; Rejection Scheme; Recognition Rate; Error Rate; Reject Rate; Rotating Machine;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 S. J. Smith and M. O. Bourgoing, 'Handwritten Character Classfication using Nearest Neighbor in Large Database,' IEEE Trans. on PAMI, Vol. 16, No. 9, pp. 915-919, 1994   DOI   ScienceOn
2 김창구, 박광호, 기창두, '회전기계 고장 진단에 적용한 인공신경망과 통계적 패턴인식 기법의 비교 연구,' 한국정밀공학회지, 제 16 권 제 12 호, pp. 119-125, 1999
3 H. Mizutani, 'Discriminative Learning for Minimum Error and Minimum Reject Classification,' proceedings of the 14th International Conference on Pattern Recognition, Kawasaki, Japan, Vol. 1, pp. 136-140, 1998
4 M. Golfarelli and D. Mario, 'On the Error-reject Trade-off in Biometric Verification Systems,' IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 19, No. 7, pp. 786-796, 1997   DOI   ScienceOn
5 W. Gersch, T. Brotherton and S.Braun, 'Nearest Neighbor-Time Series Analysis Classification of Faults in Rotating Machinery,' Transactions of the ASME, Vol. 105, pp. 178-184, 1983   DOI
6 J. T. Renwick, 'Vibration Analysis - A Proven Technique as a Predictive Maintenance Tool,' IEEE Trans. on Industry Applications, Vol. 21, pp. 324-332, 1985   DOI   ScienceOn
7 J. Mathew and J. Alfreds, 'The Condition Monitoring of Rolling Element Bearings Using Vibration Anlaysis,' Journal of Vibration, Acoustics, Stress and Reliability in Design, Vol. 106, pp. 447-453, 1996
8 C. K. Mechefske and J. Mathew, 'Fault Detection and Diagnosis in Low Speed Rolling Element Bearings Part II: The Use of Neatest Neighbour Classification,' Mechanical Systems and Signal Processing, Vol. 6, No. 4, pp. 309-316, 1992   DOI   ScienceOn
9 Singiresu Rao, Engineering Optimization, Wiley Inter-science, 1996
10 배용채, '터빈이상 진동의 자동 진단 시스템에 관한 연구,' 전남 대학교 대학원 박사학위 논문, 1995
11 Morton Nadler anf Eric P.Smith, Pattern Recognition Engineering, Wiley Inter-science, 1993
12 이정철, '고정도 스펙트럼 해석법에 의한 회전기계의 이상진단에 관한 연구,' 한양 대학교 대학원 박사학위논문, 1995