Abstract
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.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Bifet A, Holmes G, Pfahringer B, Kirkby R, Gavaldà R (2009) New ensemble methods for evolving data streams. In: Proceedings of the 15th ACM SIGKDD International Conference, KDD ’09. ACM, New York, pp 139–148. ISBN 978-1-60558-495-9
Bishop CM (2006) Pattern recognition and machine learning (Information Science and Statistics). Springer, Berlin. ISBN 0387310738
Cerrada M, Sánchez R-V, Li C, Pacheco F, Cabrera D, de Oliveira JV, Vásquez RE (2018) A review on data-driven fault severity assessment in rolling bearings. Mech Syst Signal Process 99:169–196. ISSN 0888-3270. https://doi.org/10.1016/j.ymssp.2017.06.012. http://www.sciencedirect.com/science/article/pii/
Dems~ar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30. ISSN 1532-4435
El-Thalji I, Jantunen E (2015) A summary of fault modelling and predictive health monitoring of rolling element bearings. Mech Syst Signal Process 60-61:252–272. ISSN 0888-3270. https://doi.org/10.1016/j.ymssp.2015.02.008. http://www.sciencedirect.com/science/article/pii/S0888327015000813
Georgoulas G, Nikolakopoulos G (2016) Bearing fault detection and diagnosis by fusing vibration data. In: IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society, pp 6955–6960. https://doi.org/10.1109/IECON.2016.7794118
Harris FJ (1978) On the use of windows for harmonic analysis with the discrete Fourier transform. Proc IEEE 66(1):51–83. ISSN 0018-9219. https://doi.org/10.1109/PROC.1978.10837
Hashemian HM (2011) State-of-the-art predictive maintenance techniques. IEEE Trans Instrum Meas 60:3480–3492
Heng RBW, Nor MJM (1998) Statistical analysis of sound and vibration signals for monitoring rolling element bearing condition. Appl Acoust 53(1):211–226. ISSN 0003-682X. https://doi.org/10.1016/S0003-682X(97)00018-2. http://www.sciencedirect.com/science/article/pii/S0003682X97000182
Holmes MP, Gray AG, Isbell Jr CL (2008) QUIC-SVD: fast SVD using cosine trees. In: Advances in Neural Information Processing Systems 21, Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems, Vancouver, pp 673–680. http://papers.nips.cc/paper/3473-quic-svd-fast-svd-using-cosine-trees
Howard I, Howard IM (1994) Defence Science, Technology Organisation (Australia), Aeronautical, and Maritime Research Laboratory (Australia). A review of rolling element bearing vibration: detection, diagnosis and prognosis / Ian Howard. DSTO Aeronautical and Maritime Research Laboratory Melbourne
Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, Yen N-C, Tung CC, Liu HH (1998) The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc A: Math Phys Eng Sci 454:903–995. https://doi.org/10.1098/rspa.1998.0193
Imaouchen Y, Kedadouche M, Alkama R, Thomas M (2017) A frequency-weighted energy operator and complementary ensemble empirical mode decomposition for bearing fault detection. Mech Syst Signal Process 82:103 – 116. ISSN 0888-3270. https://doi.org/10.1016/j.ymssp.2016.05.009. http://www.sciencedirect.com/science/article/pii/S0888327016300802
Jothilakshmi S, Ramalingam V, Palanivel S (2009) Unsupervised speaker segmentation with residual phase and MFCC features. Expert Syst Appl 36:9799–9804
Kumar S, Goyal D, Dang RK, Dhami SS, Pabla BS (2018) Condition based maintenance of bearings and gears for fault detection – a review. Mater Today: Proc 5(2, Part 1):6128–6137. ISSN 2214-7853. https://doi.org/10.1016/j.matpr.2017.12.219. http://www.sciencedirect.com/science/article/pii/S2214785317332078. 7th International Conference of Materials Processing and Characterization
Lin J, Chen Q (2013) Fault diagnosis of rolling bearings based on multifractal detrended fluctuation analysis and Mahalanobis distance criterion. Mech Syst Signal Process 38(2):515–533. https://doi.org/10.1016/j.ymssp.2012.12.014
Michie D, Spiegelhalter DJ, Taylor CC, Campbell J (eds) (1994) Machine learning, neural and statistical classification. Ellis Horwood, Upper Saddle River. ISBN 0-13-106360-X
Muda L, Begam M, Elamvazuthi I (2010) Voice recognition algorithms using mel frequency cepstral coefficient (mfcc) and dynamic time warping (dtw) techniques. CoRR, arXiv:http://arXiv.org/abs/1003.4083. http://dblp.uni-trier.de/db/journals/corr/corr1003.html#abs-1003-4083
Okoh C, Roy R, Mehnen J (2017) Predictive maintenance modelling for through-life engineering services. Procedia CIRP 59:196–201. ISSN 2212-8271. https://doi.org/10.1016/j.procir.2016.09.033. http://www.sciencedirect.com/science/article/pii/S2212827116309726. Proceedings of the 5th International Conference in Through-life Engineering Services Cranfield University, 1st and 2nd November 2016
Poularikas AD (2010) Transforms and applications primer for engineers with examples and MATLAB®;. Electrical Engineering Primer Series. CRC Press, Boca Raton. ISBN 9781420089325. https://books.google.pt/books?id=fgrdgTm45X4C
Rai Akhand, Upadhyay SH (2016) A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings. Tribol Int 96(Complete):289–306. https://doi.org/10.1016/j.triboint.2015.12.037
Rai Akhand, Upadhyay SH (2017) Bearing performance degradation assessment based on a combination of empirical mode decomposition and k-medoids clustering. Mech Syst Signal Process 93(Complete):16–29. https://doi.org/10.1016/j.ymssp.2017.02.003
Read J, Bifet A, Holmes G, Pfahringer B (2012) Scalable and efficient multi-label classification for evolving data streams. Mach Learn 88(1-2):243–272. ISSN 0885-6125
Saruhan H, Sandemir S, Çiçek A, Uygur I (2014) Vibration analysis of rolling element bearings defects. J Appl Res Technol 12(3):384–395. https://doi.org/10.1016/s1665-6423(14)71620-7
Tabrizi AA, Garibaldi L, Fasana A, Marchesielo S (2014) Ensemble empirical mode decomposition (EEMD) and Teager-Kaiser Energy Operator (TKEO) based damage identification of roller bearings using one-class support vector machine. In: Cam VLx, Mevel L, Schoefs F (eds) EWSHM - 7th European Workshop on Structural Health Monitoring. https://hal.inria.fr/hal-01022990. IFFSTTAR, Inria, Université de Nantes, Nantes
Wang Y-H, Yeh C-H, Young H-WV, Hu K, Lo M-T (2014) On the computational complexity of the empirical mode decomposition algorithm. Physica A: Stat Mech Appl 400(Complete):159–167. https://doi.org/10.1016/j.physa.2014.01.020
Zhou X, Garcia-Romero D, Duraiswami R, Espy-Wilson C, Shamma S (2011) Linear versus mel frequency cepstral coefficients for speaker recognition. In: 2011 IEEE Workshop on Automatic Speech Recognition Understanding, pp 559–564. https://doi.org/10.1109/ASRU.2011.6163888
Acknowledgments
The authors would like to thank the reviewers for the careful reading and constructive feedback on the material presented in this article.
Funding
This work is co-financed by the ERDF – European Regional Development Fund through the Operational Programme for Competitiveness and Internationalization - COMPETE 2020 under the PORTUGAL 2020 Partnership Agreement, and through the Portuguese National Innovation Agency (ANI) as a part of project ADIRA I4.0 with reference POCI-01-0247-FEDER-017922.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Sousa, R., Antunes, J., Coutinho, F. et al. Robust cepstral-based features for anomaly detection in ball bearings. Int J Adv Manuf Technol 103, 2377–2390 (2019). https://doi.org/10.1007/s00170-019-03597-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-019-03597-2