Performance Improvement of Feature-Based Fault Classification for Rotor System

다국어 초록 (Multilingual Abstract)

For the management of rotating machines, machine learning (ML) has been researched with the use of feature parameters that have physical and statistical meanings of vibration signals. Genetic algorithm (GA) and principal component analysis (PCA) are the algorithms used for the selection or extraction process of the features; equipment condition. This study proposes a new method to maximize the advantages of the extraction and selection algorithms, thereby improving the fault classifi cation performance. The proposed method is estimated in a variety of equipment conditions by selecting and extracting the eff ective features for status classifi cation. To evaluate the performance of the fault classifi cation through feature selection and extraction of the ML, a comparative analysis with the proposed method and the original method is also performed. With Lab-scale gearbox, several types of fault tests are conducted, and seven diff erent fault types of equipment conditions, including the normal status, are simulated. The results of the experiments show that, the performance of classifi cation of GA for feature selection is 85%, while PCA for feature extraction is 53%. The performance result of the proposed method for fault classifi cation is 95%, meaning that the performance of fault diagnosis is more effi cient in terms of discriminative learning than the original method. Therefore, the proposed method with feature extraction and selection algorithm can improve the fault classifi cation performance by 10% and more for fault diagnosis through ML.

참고문헌 (Reference)

1 김현중, "특징에 따른 기어박스 결함의 진동신호 분석" 한국소음진동공학회 27 (27): 419-424, 2017

2 김정민, "배관 균열 및 밸브 개폐에 따른 진동과 음향방출의 특징 분석" 한국소음진동공학회 27 (27): 857-862, 2017

3 김현중, "기어박스 결함 유형에 따른 고장진단을 위한 특징 분석" 한국소음진동공학회 27 (27): 312-317, 2017

4 정덕영, "기어 이 파손 정도에 따른 진동신호의 특징기반 경향 감시" 한국소음진동공학회 29 (29): 199-205, 2019

5 안병현, "가스터빈 고장 진단을 위한 기계 학습과 유전 알고리즘을 이용한특징 분석" 한국정밀공학회 35 (35): 163-167, 2018

6 Trendafi lova, I., "Vibration-based damage detection in an aircraft wing scaled model using principal component analysis and pattern recognition" 313 : 560-566, 2008

7 Yang, H., "Vibration feature extraction techniques for fault diagnosis of rotating machinery: A literature survey" 2003

8 Preuveneers, D., "The intelligent industry of the future: A survey on emerging trends, research challenges and opportunities in Industry 4.0" 9 : 287-298, 2017

9 Rekimoto, J., "The information cube: Using transparency in 3D information visualization" 1993

10 Shao, R., "The fault extraction and classifi cation of gear using principal component analysis and kernel principal component analysis based on the wavelet packet transform" 54 : 118-132, 2014

11 Saitta, L., "Support-vector networks" 20 : 273-297, 1995

12 Widodo, A., "Support vector machine in machine condition monitoring and fault diagnosis" 21 : 2560-2574, 2007

13 김동현, "Smart Machining Process Using Machine Learning: A Review and Perspective on Machining Industry" 한국정밀공학회 5 (5): 555-568, 2018

14 Lee, J., "Service innovation and smart analytics for Industry 4.0 and big data environment" 16 : 3-8, 2014

15 Parker, J. R., "Rank and response combination from confusion matrix data" 2 : 113-120, 2001

16 De Jong, K., "Learning with genetic algorithms : An overview" 3 (3): 121-138, 1988

17 Jeong, H. D., "Industrial artifi cial intelligence" 27 (27): 3-7, 2017

18 Jack, L. B., "Genetic algorithms for feature selection in machine condition monitoring with vibration signals" 147 : 205-212, 2000

19 Leardi, R., "Genetic algorithms as strategy for feature selection" 6 : 267-281, 1992

20 Vafaie, H., "Genetic algorithms as a tool for feature selection in machine learning" 1992

21 Goldberg, D. E., "Genetic algorithm and machine learning" 3 (3): 95-99, 1988

22 Samanta, B., "Gear fault detection using artifi cial neural networks and support vector machines with genetic algorithms" 18 : 625-644, 2004

23 김정섭, "Development of Data-Driven In-Situ Monitoring and Diagnosis System of Fused Deposition Modeling (FDM) Process Based on Support Vector Machine Algorithm" 한국정밀공학회 5 (5): 479-486, 2018

24 Nacib, L., "Detecting gear tooth cracks using cepstral analysis in gearbox of helicopters" 5 : 139-145, 2013

25 하정민, "Degradation Trend Estimation and Prognostics for Low Speed Gear Lifetime" 한국정밀공학회 19 (19): 1099-1105, 2018

26 Samanta, B., "Artifi cial neural network based fault diagnostics of rolling element bearings using time-domain features" 17 : 317-328, 2003

27 Widodo, A., "Application of nonlinear feature extraction and support vector machines for fault diagnosis of induction motor" 33 (33): 241-250, 2007

28 Lindasay, I. S., "A tutorial on principal components analysis"

29 Randall, R. B., "A history of Cepstrum analysis its application to mechanical problems" 97 : 3-19, 2016

30 신인선, "A Framework for Prognostics and Health Management Applications toward Smart Manufacturing Systems" 한국정밀공학회 5 (5): 535-554, 2018