Robust cepstral-based features for anomaly detection in ball bearings

This paper proposes the linear frequency cepstral coefficients as highly discriminative features for anomaly detection in ball bearings using vibration sensor data. These features are based on cepstral analysis and are capable of encoding the patterns of a spectral magnitude profile. Incipient damages on bearings can grow rapidly under normal use resulting in vibration and harsh noise. If left undetected, this damage will worsen, leading to high maintenance costs or even injury. Multiple interferences in an industrial environment contaminate the signal, making it a challenge to correctly identify the bearings’ condition. Many studies have attempted to overcome this issue at the signal level. However, the discriminative capacity of the current vibration signal features is still vulnerable to interference, which motivates this work. In order to demonstrate the benefits of these features, we (1) show that they are computationally efficient and suitable for real-time incremental training; (2) conduct discriminative analysis by evaluating the separability performance and comparing it with the state of the art; and (3) test the robustness of the proposed features under noise interference, which is ideal for use in the harsh operating conditions of industrial machinery. The data was obtained from a laboratory workbench setting that reproduces bearing fault scenarios. Results show that the proposed features are fast, competitive when compared to state-of-the-art features, and resilient to high levels of interference. Despite the higher performance when using the quadratic model, the proposed features remain highly discriminative when used with several other discriminant function.

[1]  George Nikolakopoulos,et al.  Bearing fault detection and diagnosis by fusing vibration data , 2016, IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society.

[2]  Yung-Hung Wang,et al.  On the computational complexity of the empirical mode decomposition algorithm , 2014 .

[3]  Idriss El-Thalji,et al.  A summary of fault modelling and predictive health monitoring of rolling element bearings , 2015 .

[4]  Luigi Garibaldi,et al.  Ensemble empirical mode decomposition (EEMD) and Teager-Kaiser energy operator (TKEO) based damage identification of roller bearings using one-class support vector machine. , 2014 .

[5]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[6]  Hashem M. Hashemian,et al.  State-of-the-Art Predictive Maintenance Techniques* , 2011, IEEE Transactions on Instrumentation and Measurement.

[7]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[8]  Sanjay H Upadhyay,et al.  Bearing performance degradation assessment based on a combination of empirical mode decomposition and k-medoids clustering , 2017 .

[9]  Geoff Holmes,et al.  Scalable and efficient multi-label classification for evolving data streams , 2012, Machine Learning.

[10]  J. Lin,et al.  Fault diagnosis of rolling bearings using multifractal detrended fluctuation analysis and Mahalanobis distance criterion , 2012, 18th International Conference on Automation and Computing (ICAC).

[11]  Marc Thomas,et al.  A Frequency-Weighted Energy Operator and complementary ensemble empirical mode decomposition for bearing fault detection , 2017 .

[12]  Sanjay H Upadhyay,et al.  A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings , 2016 .

[13]  Diego Cabrera,et al.  A review on data-driven fault severity assessment in rolling bearings , 2018 .

[14]  Mohd Jailani Mohd Nor,et al.  Statistical analysis of sound and vibration signals for monitoring rolling element bearing condition , 1998 .

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

[16]  Rajkumar Roy,et al.  Predictive Maintenance Modelling for Through-Life Engineering Services , 2017 .

[17]  Adem Çiçek,et al.  Vibration Analysis of Rolling Element Bearings Defects , 2014 .

[18]  Vennila Ramalingam,et al.  Unsupervised speaker segmentation with residual phase and MFCC features , 2009, Expert Syst. Appl..

[19]  Alexander G. Gray,et al.  QUIC-SVD: Fast SVD Using Cosine Trees , 2008, NIPS.

[20]  Daniel Garcia-Romero,et al.  Linear versus mel frequency cepstral coefficients for speaker recognition , 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

[21]  Sanjay Kumar,et al.  Condition based maintenance of bearings and gears for fault detection – A review , 2018 .

[22]  F. Harris.  On the use of windows for harmonic analysis with the discrete Fourier transform , 1978, Proceedings of the IEEE.

[23]  Geoff Holmes,et al.  New ensemble methods for evolving data streams , 2009, KDD.