All Issue

2021 Vol.34, Issue 1 Preview Page

Research Paper

Fault Classification Model Based on Time Domain Feature Extraction of Vibration Data

진동 데이터의 시간영역 특징 추출에 기반한 고장 분류 모델

Seung-il Kim1
,
Yoojeong Noh2†
,
Young-jin Kang3
,
Sunhwa Park4
,
Byungha Ahn5
김 승일1
,
노 유정2†
,
강 영진3
,
박 선화4
,
안 병하5
1Graduate Student, School of Mechanical Engineering, Pusan National University, Busan, 46241, Korea
2Associate Professor, School of Mechanical Engineering, Pusan National University, Busan, 46241, Korea
3Research Institute of Mechanical Engineering, Pusan National University, Busan, 46241, Korea
4Senior Researcher, H&A Research Center, LG Electronics, Changwon, 51554, Korea
5Chief Researcher, H&A Research Center, LG Electronics, Changwon, 51554, Korea
1부산대학교 기계공학부 대학원생
2부산대학교 기계공학부 부교수
3부산대학교 기계기술연구원 연구원
4LG전자 H&A연구소 선임연구원
5LG전자 H&A연구소 연구위원
*yoonoh@pusan.ac.kr
28 February 2021. pp. 25-33
PDF XML Citation
Abstract

With the development of machine learning techniques, various types of data such as vibration, temperature, and flow rate can be used to detect and diagnose abnormalities in machine conditions. In particular, in the field of the state monitoring of rotating machines, the fault diagnosis of machines using vibration data has long been carried out, and the methods are also very diverse. In this study, an experiment was conducted to collect vibration data from normal and abnormal compressors by installing accelerometers directly on rotary compressors used in household air conditioners. Data segmentation was performed to solve the data shortage problem, and the main features for the fault classification model were extracted through the chi-square test after statistical and physical features were extracted from the vibration data in the time domain. The support vector machine (SVM) model was developed to classify the normal or abnormal conditions of compressors and improve the classification accuracy through the hyperparameter optimization of the SVM.

Keywords
fault diagnosis
twin rotary compressor
health index
intersection area
data augmentation
support vector machine (SVM)

머신러닝 기법의 발달과 함께 기계에서 발생하는 다양한 종류(진동, 온도, 유량 등)의 데이터를 활용하여 기계의 상태를 진단하고 이상 탐지 및 비정상 분류 연구도 활발히 진행되고 있다. 특히 진동 데이터를 활용한 회전 기계의 상태 진단은 전통적인 기계 상태 모니터링 분야로 오랜 기간 동안 연구가 진행되었고, 연구 방법 또한 매우 다양하다. 본 연구에서는 가정용 에어컨에 사용되는 로터리 압축기에 가속도계를 직접 설치하여 진동 데이터를 수집하는 실험을 진행하였다. 데이터 부족 문제를 해결하기 위해 데이터 분할을 수행하였으며, 시간 영역에서의 진동 데이터로부터 통계적, 물리적 특징들을 추출한 후, Chi-square 검증을 통해 고장 분류 모델의 주요 특징을 추출하였다. SVM(Support Vector Machine) 모델은 압축기의 정상 혹은 이상 유무를 분류하기 위해 개발되었으며, 파라미터 최적화를 통해 분류 정확도를 개선하였다.

키워드
고장진단
트윈 로터리 압축기
건전성지표
교차면적
데이터 증대
서포트벡터머신
References
1
Caesarendra, W., Tjahjowidodo, T. (2017) A Review of Feature Extraction Methods in Vibration-Based Condition Monitoring and Its Application for Degradation Trend Estimation of Low- Speed Slew Bearing, Mach., 5(4), p.21. 10.3390/machines5040021
2
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P. (2002) SMOTE: Synthetic Minority Over-Sampling Technique, J. Artif. Intell. Res., 16, pp.321~357. 10.1613/jair.953
3
Choi, J. (2020) PHM Practice-Case Study for Industrial Digitization: PHM Core Basic, Korea Society for Prognostics & Health Management, Seoul, South Korea, p.29.
4
Cortes, C., Jackel, L.D., Chiang, W.P. (1995) Limits on Learning Machine Accuracy Imposed by Data Quality, In Advances in Neural Information Processing Systems, pp.239~246.
5
Jahromi, A., Piercy, R., Cress, S., Service, J., Fan, W. (2009) An Approach to Power Transformer Asset Management using Health Index, IEEE Electr. Insul. Mag., 25(2), pp.20~34. 10.1109/MEI.2009.4802595
6
Jović, A., Brkić, K., Bogunović, N. (2015) A Review of Feature Selection Methods with Applications, 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), pp.1200~1205. 10.1109/MIPRO.2015.7160458
7
Kang, Y.J., Hong, J., Lim, O.K., Noh, Y. (2017) Reliability analysis using parametric and nonparametric input modeling methods, J. Comput. Struct. Eng. Inst. Korea, 30(1), pp.87~94. 10.7734/COSEIK.2017.30.1.87
8
Kang, Y.J., Noh, Y., Lim, O.K. (2018) Kernel Density Estimation with Bounded Data, Struct. & Multidiscip. Optim., 57(1), pp.95~113. 10.1007/s00158-017-1873-3
9
Kim, Y.S., Lee, D.H., Kim, S.K. (2010) Fault Classification for Rotating Machinery using Support Vector Machines with Optimal Features Corresponding to Each Fault Type, Trans. Korean Soc. Mech. Eng. A, 34(11), pp.1681~1689. 10.3795/KSME-A.2010.34.11.1681
10
Ko, J.U., Jung, J.H., Kim, M., Kong, H.B., Youn, B.D. (2018) Noise Robust Fault Diagnosis Technique to Simultaneously Learn Classification and Denoising, In Proceedings of The Korean Soc. of Mech. Eng. (KSME), pp.165~167.
11
Lee, S.H., Ryu, S.M., Jeong, W.B. (2012) Vibration Analysis of Compressor Piping System with Fluid Pulsation, J. Mech. Sci. & Technol., 26(12), pp.3903~3909. 10.1007/s12206-012-0891-8
12
Lim, D.S., Yang, B.S., An, B.H., Tan, A., Kim, D.J. (2003) Condition Classification for Small Reciprocating Compressors Using Wavelet Transform and Artificial Neural Network, J. Korea Soc. Power Syst. Eng., 7(2), pp.29~35.
13
Sano, K., Mitsui, K. (1984) Analysis of Hermetic Rolling Piston Type Compressor Noise, and Countermeasures, Int. Compress. Eng. Conf., p.460.
14
Saxena, V., Chowdhury, N., Devendiran, S. (2013) Assessment of Gearbox Fault Detection using Vibration Signal Analysis and Acoustic Emission Technique, J. Mech. & Civil Eng., 7(4), pp.52~60. 10.9790/1684-0745260
15
Son, M.J., Jung, S.W., Hwang, E.J. (2019) A Deep Learning Based Over-Sampling Scheme for Imbalanced Data Classification, KIPS Trans. Softw. & Data Eng., 8(7), pp.311~316.
16
Son, Y., Ha, J., Lee, J. (2015) An Experimental Study on the Noise Source Identification of Rotary Compressor, Trans. Korea Soc. Noise & Vib. Eng., 25(11), pp.723~730. 10.5050/KSNVE.2015.25.11.723
17
Son, Y., Ha, J., Lee, J. (2017) The Noise Identification and Reduction of a Twin Rotary Compressor, Trans. Korea Soc. Noise & Vib. Eng., 27(3), pp.306~311. 10.5050/KSNVE.2017.27.3.306
18
Stockwell, D.R., Peterson, A.T. (2002) Effects of Sample Size on Accuracy of Species Distribution Models, Ecol. Model., 148(1), pp.1~13. 10.1016/S0304-3800(01)00388-X
19
Verstraete, D., Ferrada, A., Droguett, E.L., Meruane, V., Modarres, M. (2017) Deep Learning Enabled Fault Diagnosis using Time-Frequency Image Analysis of Rolling Element Bearings, Shock & Vib., 2017. 10.1155/2017/5067651
20
Wang, G., Kang, W., Wu, Q., Wang, Z., Gao, J. (2018) Generative Adversarial Network (GAN) based Data Augmentation for Palmprint Recognition, Digital Image Computing: Techniques and Applications (DICTA), pp.1~7. 10.1109/DICTA.2018.8615782
21
Yang, H.B., Zhang, J.A., Chen, L.L., Zhang, H.L., Liu, S.L. (2019) Fault Diagnosis of Reciprocating Compressor based on Convolutional Neural Networks with Multisource Raw Vibration Signals, Math. Probl. Eng., 2019. 10.1155/2019/6921975
Information
  • Publisher :Computational Structural Engineering Institute of Korea
  • Publisher(Ko) :한국전산구조공학회
  • Journal Title :Journal of the Computational Structural Engineering Institute of Korea
  • Journal Title(Ko) :한국전산구조공학회 논문집
  • Volume : 34
  • No :1
  • Pages :25-33
  • Received Date : 2020-11-18
  • Revised Date : 2020-12-10
  • Accepted Date : 2020-12-11
  • DOI :https://doi.org/10.7734/COSEIK.2021.34.1.25
Journal Informaiton Journal of the Computational Structural Engineering Institute of Korea Journal of the Computational Structural Engineering Institute of Korea
Online Submission
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close