Spectrum Skeletonization: A New Method for Acoustic Signal Feature Extraction

Vibration Analysis Tests (VAT) and Acoustic Emission tests (AE) are used in several industrial applications. Many of them perform analysis in the frequency domain. Peaks in the power density spectrum hold relevant information about acoustic events. In this paper we propose a novel method for feature extraction of vibration samples by analyzing the shape of their auto power spectrum density function. The approach uses skeletonization techniques in order to find the hierarchical structure of the spectral peaks. The proposed method can be applied as a preprocessing step for spectrum analysis of vibration signals.

[1]  Rafael C. González,et al.  Digital image processing, 3rd Edition , 2008 .

[2]  Jason Weston,et al.  A user's guide to support vector machines. , 2010, Methods in molecular biology.

[3]  Zicheng Guo,et al.  Parallel thinning with two-subiteration algorithms , 1989, Commun. ACM.

[4]  Gilles Bertrand,et al.  Two-Dimensional Parallel Thinning Algorithms Based on Critical Kernels , 2008, Journal of Mathematical Imaging and Vision.

[5]  Gabor POR,et al.  Developing an Acoustic Emission Measuring System Based on Modular High Speed Data Acquisition Devices , 2012 .

[6]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[7]  Fulei Chu,et al.  VIBRATION SIGNAL ANALYSIS AND FEATURE EXTRACTION BASED ON REASSIGNED WAVELET SCALOGRAM , 2002 .

[8]  M. Couprie.  Note on fifteen 2 D parallel thinning algorithms , 2006 .

[9]  Morioka Toshihiko,et al.  Studies on the loose part evaluation technique , 1985 .

[10]  B. Samanta,et al.  ARTIFICIAL NEURAL NETWORK BASED FAULT DIAGNOSTICS OF ROLLING ELEMENT BEARINGS USING TIME-DOMAIN FEATURES , 2003 .

[11]  Milan Sonka,et al.  Quantitative analysis of pulmonary airway tree structures , 2006, Comput. Biol. Medicine.

[12]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[13]  M. Fatih Demirci,et al.  Many-to-Many Matching under the l1 Norm , 2009, ICIAP.

[14]  Hamid GHADERI,et al.  Automobile Independent Fault Detection based on Acoustic Emission Using FFT , 2011 .

[15]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[16]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[17]  Szilveszter Pletl,et al.  Identification of the Place and Materials of Knocking Objects in Flow Induced Vibration , 2011, Acta Cybern..

[18]  Stéphane Mallat,et al.  A Wavelet Tour of Signal Processing, 2nd Edition , 1999 .

[19]  Jason Weston,et al.  Support vector machines for multi-class pattern recognition , 1999, ESANN.

[20]  Péter Kardos,et al.  Order-independent sequential thinning in arbitrary dimensions , 2011, ICSIPA 2011.

[21]  Bo Wang,et al.  Skeleton Graph Matching Based on Critical Points Using Path Similarity , 2009, ACCV.

[22]  T. Y. Kong,et al.  Topological Algorithms for Digital Image Processing , 1996 .

[23]  Lin Ma,et al.  Vibration feature extraction techniques for fault diagnosis of rotating machinery : a literature survey , 2003 .

[24]  Longin Jan Latecki,et al.  Path Similarity Skeleton Graph Matching , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Kaleem Siddiqi,et al.  Medial Representations: Mathematics, Algorithms and Applications , 2008 .

[26]  Kil To Chong,et al.  Vibration Signal Analysis for Electrical Fault Detection of Induction Machine Using Neural Networks , 2007 .

[27]  Péter Kardos,et al.  An Order-Independent Sequential Thinning Algorithm , 2009, IWCIA.

[28]  Dr. Jeno.  INTEGRATION OF FAULT DIAGNOSTIC TECHNOLOGIES INTO A COMPLEX CONDITION MONITORING SYSTEM AND ITS PRACTICAL RESULTS , 2008 .

[29]  Wolf-Joachim Fischer,et al.  Signal-Based Feature Extraction and SOM based Dimension Reduction in a Vibration Monitoring Microsystem , 2001, WSOM.

[30]  Kien A. Hua,et al.  Many-to-Many Skeletal-Graphs Matching Approach to Shape Recognition , 2004 .

[31]  Albrecht Rüdiger,et al.  Spectrum and spectral density estimation by the Discrete Fourier transform (DFT), including a comprehensive list of window functions and some new at-top windows , 2002 .

[32]  J. Tang,et al.  Feature extraction and selection based on vibration spectrum with application to mill load modeling , 2011, 2011 International Symposium on Advanced Control of Industrial Processes (ADCONIP).

[33]  T.H.J.J. van der Hagen,et al.  A comparison of three time-domain anomaly detection methods , 1996 .