본 논문은 고장 분류 시스템을 위해 진동 신호로부터 특징 벡터를 자동적으로 추출하는 효과적인 기법을 제안한다. 기존의 멜-주파수 캡스트럼 계수는 진동신호의 노이즈에 민감하여 분류 정확도를 감소시키는 단점이 있다. 이러한 문제를 해결하기 위해 본 논문은 4단계 필터 뱅크로 구성된 스펙트럴 엔벨로프 캡스트럼 계수 분석을 제안하며, 4단계는 (1) 모든 진동 신호의 스펙트럴 엔벨로프를 기술하기 위한 선형 예측 코딩 알고리즘 사용 단계, (2) 일반적인 스펙트럴 모양을 얻기 위해 모든 엔벨로프의 평균화 단계, (3) 평균 엔벨로프와 그 주파수의 최대값을 찾기 위한 기울기 하강 방법 사용 단계, (4) 엔벨로프의 주파수 사이의 거리로부터 계산된 중앙값을 얻는데 사용되는 비 중첩 필터 뱅크 단계로 구성된다. 이4-단계필터뱅크는 특징벡터를 추출하기위해 캡스트럼 계수 계산에 사용된다. 마지막으로 유도전동기의 결함 형태를 구분하기 위해 이러한 특수 파라미터를 사용하는 다중 계층 서포트 벡터 머신을 사용한다. 모의실험 결과, 제안하는 방법은 약 99.65%의 분류 성능을 보이며, 동시에 기존 방법들보다 우수한 성능을 보인다.
본 논문은 고장 분류 시스템을 위해 진동 신호로부터 특징 벡터를 자동적으로 추출하는 효과적인 기법을 제안한다. 기존의 멜-주파수 캡스트럼 계수는 진동신호의 노이즈에 민감하여 분류 정확도를 감소시키는 단점이 있다. 이러한 문제를 해결하기 위해 본 논문은 4단계 필터 뱅크로 구성된 스펙트럴 엔벨로프 캡스트럼 계수 분석을 제안하며, 4단계는 (1) 모든 진동 신호의 스펙트럴 엔벨로프를 기술하기 위한 선형 예측 코딩 알고리즘 사용 단계, (2) 일반적인 스펙트럴 모양을 얻기 위해 모든 엔벨로프의 평균화 단계, (3) 평균 엔벨로프와 그 주파수의 최대값을 찾기 위한 기울기 하강 방법 사용 단계, (4) 엔벨로프의 주파수 사이의 거리로부터 계산된 중앙값을 얻는데 사용되는 비 중첩 필터 뱅크 단계로 구성된다. 이4-단계필터뱅크는 특징벡터를 추출하기위해 캡스트럼 계수 계산에 사용된다. 마지막으로 유도전동기의 결함 형태를 구분하기 위해 이러한 특수 파라미터를 사용하는 다중 계층 서포트 벡터 머신을 사용한다. 모의실험 결과, 제안하는 방법은 약 99.65%의 분류 성능을 보이며, 동시에 기존 방법들보다 우수한 성능을 보인다.
This paper proposes an effective technique that is used to automatically extract feature vectors from vibration signals for fault classification systems. Conventional mel-frequency cepstral coefficients (MFCCs) are sensitive to noise of vibration signals, degrading classification accuracy. To solve ...
This paper proposes an effective technique that is used to automatically extract feature vectors from vibration signals for fault classification systems. Conventional mel-frequency cepstral coefficients (MFCCs) are sensitive to noise of vibration signals, degrading classification accuracy. To solve this problem, this paper proposes spectral envelope cepstral coefficients (SECC) analysis, where a 4-step filter bank based on spectral envelopes of vibration signals is used: (1) a linear predictive coding (LPC) algorithm is used to specify spectral envelopes of all faulty vibration signals, (2) all envelopes are averaged to get general spectral shape, (3) a gradient descent method is used to find extremes of the average envelope and its frequencies, (4) a non-overlapped filter is used to have centers calculated from distances between valley frequencies of the envelope. This 4-step filter bank is then used in cepstral coefficients computation to extract feature vectors. Finally, a multi-layer support vector machine (MLSVM) with various sigma values uses these special parameters to identify faulty types of induction motors. Experimental results indicate that the proposed extraction method outperforms other feature extraction algorithms, yielding more than about 99.65% of classification accuracy.
This paper proposes an effective technique that is used to automatically extract feature vectors from vibration signals for fault classification systems. Conventional mel-frequency cepstral coefficients (MFCCs) are sensitive to noise of vibration signals, degrading classification accuracy. To solve this problem, this paper proposes spectral envelope cepstral coefficients (SECC) analysis, where a 4-step filter bank based on spectral envelopes of vibration signals is used: (1) a linear predictive coding (LPC) algorithm is used to specify spectral envelopes of all faulty vibration signals, (2) all envelopes are averaged to get general spectral shape, (3) a gradient descent method is used to find extremes of the average envelope and its frequencies, (4) a non-overlapped filter is used to have centers calculated from distances between valley frequencies of the envelope. This 4-step filter bank is then used in cepstral coefficients computation to extract feature vectors. Finally, a multi-layer support vector machine (MLSVM) with various sigma values uses these special parameters to identify faulty types of induction motors. Experimental results indicate that the proposed extraction method outperforms other feature extraction algorithms, yielding more than about 99.65% of classification accuracy.
* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.
제안 방법
To evaluate the effectiveness of the proposed extraction method for additive white Gaussian noise signals, we train MLSVM with features extracted from original signals and measure the classification accuracy using test data including additive white Gaussian noise. The more severely noise attacks, the more overlapping feature vectors are generated.
To identify optimal sigma values set with feature vectors extracted from both noiseless and noise attacked vibration signals by using the proposed SECC analysis, we measured the classification performance with σ values in the range of 0.3 to 2.
이론/모형
For early detection and classification of faults in induction motors, this paper proposed a robust feature extraction method that is cepstral coefficients based on the spectral envelope. Thes cepstral coefficients well reflected vibration signals with and without noise of induction motors.
When more than two classes are present, there are several approaches that evolve around 2-class case. In this study, we utilize an one-against-all (OAA) method to consider more than two classes of feature vectors. It constructs k SVM models where k is number of classes.
8, 10-12], but they are sensitive to noise, which degrades classification accuracy. To solve this problem, this paper proposes a robust feature extraction method, called spectral envelope cepstral coefficients analysis (SECC), where a 4-step filter bank based on spectral envelopes is used: (1) a linear predictive coding (LPC) algorithm to specify spectral envelopes of all faulty vibration signals, (2) averaging all envelopes to get general spectra shape, (3) a gradient descent method to find maxima and minima of the average envelope and its frequencies, (4) a non-overlapped filter bank to have centers calculated from distances between valley frequencies of the envelope. This filter bank is then used in cepstral coefficients computation to generate feature vectors.
참고문헌 (23)
A. M. Da Silva, R. J. Povinelli, N.A.O. Demerdash, "Induction Machine Broken Bar and Stator Short-Circuit Fault Diagnostics Based on Three-Phase Stator Current Envelopes," IEEE Transaction on Industrial Electronics, Vol. 55, pp. 1310-1318, 2008.
C.-H. Hwang, Y,-M. Kim, C.-H. Kim, J.-M. Kim, "Fault Detection and Diagnosis of Induction Motors using LPC and DTWMethods," Journal of the Korea Society of Computer and Information, Vol. 16, No. 3, pp. 141-147, 2011.
C.-H. Hwang, M. Kang, J.-M. Kim, "A Study on Robust Feature Vector Extraction for Fault Detection and Classification of Induction Motor in Noise Circumstance," Journal of the Korea Society of Computer and Information, Vol. 16, No. 12, pp. 187-196, 2011.
P. A. Laggan, "Vibration Monitoring," IEE Colloquium on Understanding Your Condition Monitoring, pp. 1-11, 1999.
H. Han, S. Cho, and U. Chong, "Fault Diagnosis System Using LPC Coefficients and Neural Network," Proc. of International Forum on Strategic Technology, pp. 87-90, 2010.
F. V. Nelwamonodo and T. Marwala, "Fault Detection Using Gaussian Mixture Models, Mel-Frequency Cepstral Coefficients and Kurtosis," IEEE International Conference on Systems, Man and Cybernetics, pp. 290-295, 2006.
T. Boukra and A. Lebaroud, "Classification on Induction Machine Faults," International Multi-Conference on Systems and Devices, pp. 1-6, 2007.
F. Li, G. Meng, L. Ye, and P. Chen, "Wavelet Transform-Based Higher-Order Statistics for Fault Diagnosis in Rolling Element Bearings," Journal of Vibration and Control, Vol. 14, pp. 1691-1709, 2008.
H. Ocak, K. A. Loparo, "Estimation of the Running Speed and Bearing Defect Frequencies of an Induction Motor from Vibration Data," Mechanical Systems and Signal Processing, Vol. 18, pp. 515-533, 2004.
F. V. Nelwamonodo, T. Marwala, and U. Mahola, "Early Classifications of Bearing Faults Using Hidden Markov Models, Gaussian Mixture Models, Mel-Frequency Cepstral Coefficients and Fractals," Journal of Innovative Computing, Information and Control, Vol. 2, pp. 1281-1299, 2006.
M. Ge, G. C. Zhang, and Y. Yu, "Feature Extraction from Energy Distribution of Stamping Processes Using Wavelet Transform," Journal of Vibration and Control, Vol. 8, pp. 1323-1032, 2002.
K. M. Silva, B. A. Souza, N. S. D. Brito, "Fault Detection and Classification in Transmission Lines Based on Wavelet Transform and ANN," IEEE Trans. on Power Delivery, Vol. 21, pp. 2058-2063, 2006.
B.-S. Yang, T. Han, and W.W. Hwang, "Fault Diagnosis of Rotating Machinery based on Multi-Class Support Vector Machines," Journal of Mechanical Science and Technology, Vol. 19, No. 3, pp. 845-858, 2005.
B. -S. Yang, D.S Lim, and J.L. An, "Vibration Diagnostic System of Rotating Machinery using Artificial Neural Network and Wavelet Transform," Proc. of 13th Intl. Congress on COMADEM, pp. 12-20, 2000.
A. Widodo, B.-S. Yang, and T. Han, "Combination of Independent Component Analysis and Support Vector Machine for Intelligent Faults Diagnosis of Induction Motors," Expert System with Application, Vol. 32, pp. 299-312, 2007.
A. Widodo, B. -S. Yang, T. Han, and D. J. Kim, "Fault Diagnosis of Induction Motor using Independent Component Analysis and Multi-Class Support Vector Machine," Proceedings of the 11th Asia-Pacific Vibration Conference, pp. 144-149, 2005.
S. Poyhonen, Support Vector Machine Based Classification in Condition Monitoring of Induction Motors, Thesis Presented at Helsinki University of Technology, 2004.
M. Deriche, "Bearing Fault Diagnosis Using Wavelet Analysis," International Conference on Computers, Communication and Signal Processing with Special Track on Biomedical Engineering, pp. 197-201, 2005.
N. Mehla and R. Dahiya, "An Approach of Condition Monitoring of Induction Motor Using MCSA," International Journal of Systems Applications, Engineering and Development, Vol. 1, pp. 13-17, 2007.
R. O. Duda, P. E. Hart, and D. G. Stock, Pattern Classification, Wiley, New York, 2001.
T. Han, B.-S. Yang, and Z.-J. Yin, "Feature-based Fault Diagnosis System of Induction Motors using Vibration Signal," Journal of Quality in Maintenance Engineering, Vol. 13, No. 2, pp. 163-175, 2007.
T. H. Park, Introduction to Signal Processing: Computer Musically Speaking, World Scientific, Singapore, 2010.
M. Kang, N. Nguyen, Y. Kim, C. Kim, and J. Kim, "Feature Vector Extraction and Classification Performance Comparison According to Various Settings of Classifiers for Fault Detection and Classification of Induction Motor," J. of Acoustical Society of Korea, Vol. 30, No. 8, pp. 446-460, Dec. 2011.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.