Remaining Useful Life Estimation of Rotating Machines through Supervised Learning with Non-Linear Approaches
Source abstract
Abstract
Bearings are one of the most common causes of failure for rotating electric machines. Intelligent condition-based monitoring (CbM) can be used to predict rolling element bearing fault modes using non-invasive and inexpensive sensing. Strategically placed accelerometers can acquire bearing vibration signals, which contain salient prognostic information regarding the state of health. Machine learning (ML) algorithms are currently being investigated to accurately predict the health of machines and equipment in real time. This is highly advantageous towards reducing unscheduled maintenance, increasing the operational lifetime, as well as mitigation of the associated health risks caused by catastrophic machine failure. Motivated by this, a robust CbM system is presented for rotating machines that is suitable for various industrial applications. Novel non-linear methods for both feature engineering (one-third octave bands) and wear-state modelling (exponential) are investigated. The paper compares two main types of feature extraction, which are derived from Short-Time Fourier Transform (STFT) and Envelope Analysis (EA). In addition, two types of supervised learning, Support Vector Machines (SVM) and k-Nearest Neighbour (k-NN) are explored. The work is tested and validated on the PRONOSTIA platform dataset, with remaining useful life (RUL) classification results of up to 74.3% and a mean absolute error of 0.08 achieved.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Fault Diagnosis Techniques · Gear and Bearing Dynamics Analysis · Engineering Diagnostics and Reliability
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Engineering, Institute of Technology Carlow, R93 V960 Carlow, Ireland
Funding
Government of Ireland
References (80)
Show source-provided references
1. Kudelina, K., Vaimann, T., Asad, B., Rassõlkin, A., Kallaste, A., and Demidova, G. (2021). Trends and Challenges in Intelligent Condition Monitoring of Electrical Machines Using Machine Learning. Appl. Sci., 11.10.3390/app11062761 ↗
2. Review of condition monitoring of rotating electrical machines10.1049/iet-epa:20070280 ↗
3. Rolling element bearing diagnosis based on singular value decomposition and composite squared envelope spectrum10.1016/j.ymssp.2020.107174 ↗
4. Condition monitoring analysis of rolling element bearing based on frequency envelope10.1016/j.matpr.2020.10.291 ↗
5. Condition monitoring and fault detection in roller bearing used in rolling mill by acoustic emission and vibration analysis10.1016/j.matpr.2021.05.447 ↗
6. Gyftakis, K.N., and Cardoso, A.J.M. (, January 14–17). Reliable Detection of Very Low Severity Level Stator Inter-Turn Faults in Induction Motors. Proceedings of the IECON 2019–45th Annual Conference of the IEEE Industrial Electronics Society, Lisbon, Portugal.10.1109/IECON.2019.8926928 ↗
7. A Survey of Condition Monitoring and Protection Methods for Medium-Voltage Induction Motors10.1109/TIA.2010.2090839 ↗
8. Condition Monitoring and Fault Diagnosis of Electrical Motors—A Review10.1109/TEC.2005.847955 ↗
9. Induction machine drive condition monitoring and diagnostic research—A survey10.1016/S0378-7796(02)00172-4 ↗
10. Saidi, L., and Benbouzid, M. (2021). Prognostics and Health Management of Renewable Energy Systems: State of the Art Review, Challenges, and Trends. Electronics, 10.10.3390/electronics10222732 ↗
11. Chelmiah, E.T., McLoone, V.I., and Kavanagh, D.F. (2020, January 18–21). Remaining Useful Life Estimation of Rotating Machines using Octave Spectral Features. Proceedings of the IECON 2020 the 46th Annual Conference of the IEEE Industrial Electronics Society, Singapore.10.1109/IECON43393.2020.9254950 ↗
12. Lebold, M., and Thurston, M. (2001, January 6–9). Open standards for condition-based maintenance and prognostic systems. Proceedings of the 5th Maintenance and Reliability Conference (MARCON 2001), Gatlinburg, TN, USA.
13. A new method for the estimation of bearing health state and remaining useful life based on the moving average cross-correlation of power spectral density10.1016/j.ymssp.2020.106617 ↗
14. A multi-time scale approach to remaining useful life prediction in rolling bearing10.1016/j.ymssp.2016.06.031 ↗
15. Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network
16. Chelmiah, E.T., McLoone, V.I., and Kavanagh, D.F. (2020, January 6–9). Wear State Estimation of Rolling Element Bearings using Support Vector Machines. Proceedings of the 2020 15th IEEE International Conference on Signal Processing (ICSP), Beijing, China.10.1109/ICSP48669.2020.9321007 ↗
17. Condition monitoring and fault diagnosis of induction motors: A review10.1007/s11831-018-9286-z ↗
18. State-of-the-Art Predictive Maintenance Techniques10.1109/TIM.2010.2047662 ↗
19. Unsupervised neural-network-based algorithm for an on-line diagnosis of three-phase induction motor stator fault10.1109/TIE.2006.888790 ↗
20. Prognosis of bearing acoustic emission signals using supervised machine learning10.1109/TIE.2017.2767551 ↗
21. Residual Life Prediction of Rotating Machines Using Acoustic Noise Signals10.1109/TIM.2012.2212508 ↗
22. Kavanagh, D.F., Scanlon, P., and Boland, F. (April, January 31). Envelope analysis and data-driven approaches to acoustic feature extraction for predicting the remaining useful life of rotating machinery. Proceedings of the 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, Las Vegas, NV, USA.10.1109/ICASSP.2008.4517936 ↗
23. Static air-gap eccentricity fault diagnosis using rotor slot harmonics in line neutral voltage of three-phase squirrel cage induction motor10.1016/j.ymssp.2016.07.016 ↗
24. Measurement and analysis of instantaneous torque and angular velocity variations of a low speed two stroke diesel engine10.1016/j.ymssp.2014.04.016 ↗
25. Gear wear monitoring by modulation signal bispectrum based on motor current signal analysis10.1016/j.ymssp.2017.02.037 ↗
26. A new method of accurate broken rotor bar diagnosis based on modulation signal bispectrum analysis of motor current signals10.1016/j.ymssp.2014.05.017 ↗
27. A General Framework for Aliasing Corrections of Inductive Oil Debris Detection Based on Artificial Neural Networks10.1109/JSEN.2020.2994458 ↗
28. The combined use of vibration, acoustic emission and oil debris on-line monitoring towards a more effective condition monitoring of rotating machinery10.1016/j.ymssp.2010.11.007 ↗
29. Thermography-Based Methodology for Multifault Diagnosis on Kinematic Chain10.1109/TII.2018.2816925 ↗
30. Infrared thermography for condition monitoring—A review10.1016/j.infrared.2013.03.006 ↗
31. A new method for the estimation of the instantaneous speed relative fluctuation in a vibration signal based on the short time scale transform10.1016/j.ymssp.2008.07.001 ↗
32. Time-frequency vibration analysis for the detection of motor damages caused by bearing currents10.1016/j.ymssp.2015.12.008 ↗
33. Hebda-Sobkowicz, J., Zimroz, R., Pitera, M., and Wyłomańska, A. (2020). Informative frequency band selection in the presence of non-Gaussian noise—A novel approach based on the conditional variance statistic with application to bearing fault diagnosis. Mech. Syst. Signal Process., 145.10.1016/j.ymssp.2020.106971 ↗
34. Liu, H., Li, L., and Ma, J. (2016). Rolling Bearing Fault Diagnosis Based on STFT-Deep Learning and Sound Signals. Shock Vib., 2017.10.1155/2016/6127479 ↗
35. Non-stationary signal processing for bearing health monitoring10.1504/IJMR.2006.010701 ↗
36. A simple and fast guideline for generating enhanced/squared envelope spectra from spectral coherence for bearing fault diagnosis10.1016/j.ymssp.2018.12.055 ↗
37. Time-Varying and Multiresolution Envelope Analysis and Discriminative Feature Analysis for Bearing Fault Diagnosis10.1109/TIE.2015.2460242 ↗
38. A new procedure for using envelope analysis for rolling element bearing diagnostics in variable operating conditions10.1016/j.ymssp.2012.09.014 ↗
39. Lkurtogram Guided Adaptive Empirical Wavelet Transform and Purified Instantaneous Energy Operation for Fault Diagnosis of Wind Turbine Bearing10.1109/TIM.2021.3123218 ↗
40. Yoo, Y., and Baek, J.G. (2018). A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network. Appl. Sci., 8.10.3390/app8071102 ↗
41. Fault Diagnosis of a Rolling Bearing Using Wavelet Packet Denoising and Random Forests10.1109/JSEN.2017.2726011 ↗
42. Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics10.1016/j.jsv.2005.03.007 ↗
43. An Adaptive Optimized TVF-EMD Based on a Sparsity-Impact Measure Index for Bearing Incipient Fault Diagnosis
44. Chelmiah, E.T., and Kavanagh, D.F. (2021, January 13–16). Hilbert Marginal Spectrum for Failure Mode Diagnosis of Rotating Machines. Proceedings of the IECON 2021–47th Annual Conference of the IEEE Industrial Electronics Society, Online.10.1109/IECON48115.2021.9589472 ↗
45. Condition Monitoring of Machines Using Fused Features from EMD-Based Local Energy with DNN10.1109/JSEN.2019.2927754 ↗
46. Multivariate empirical mode decomposition and its application to fault diagnosis of rolling bearing10.1016/j.ymssp.2016.03.010 ↗
47. A data-driven method to enhance vibration signal decomposition for rolling bearing fault analysis10.1016/j.ymssp.2016.02.067 ↗
48. Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals10.1016/j.apacoust.2014.08.016 ↗
49. Moshrefzadeh, A. (2021). Condition monitoring and intelligent diagnosis of rolling element bearings under constant/variable load and speed conditions. Mech. Syst. Signal Process., 149.10.1016/j.ymssp.2020.107153 ↗
50. A vibration-based method for contact pattern assessment in straight bevel gears10.1016/j.ymssp.2018.10.002 ↗
51. K-nearest neighbors based methods for identification of different gear crack levels under different motor speeds and loads: Revisited10.1016/j.ymssp.2015.10.007 ↗
52. Liu, X., and Li, H. (2019, January 24–26). A New Method of Fault Diagnosis in Rolling Bearings. Proceedings of the 2019 fourth International Conference on Mechanical, Control and Computer Engineering (ICMCCE), Hohhot, China.10.1109/ICMCCE48743.2019.00036 ↗
53. Zhong, Y.X., Fan, H.L., Lu, J.P., Pang, L., and Li, Y.F. (2018, January 16–19). Research on Fault Diagnosis of Rolling Bearing Based on Wavelet Packet Transform and IPSO-SVM. Proceedings of the 2018 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), Bangkok, Thailand.10.1109/IEEM.2018.8607276 ↗
54. Rolling bearing fault detection and diagnosis based on composite multiscale fuzzy entropy and ensemble support vector machines10.1016/j.ymssp.2016.09.010 ↗
55. Bearing Health Monitoring Based on Hilbert–Huang Transform, Support Vector Machine, and Regression10.1109/TIM.2014.2330494 ↗
56. Li, X., Elasha, F., Shanbr, S., and Mba, D. (2019). Remaining Useful Life Prediction of Rolling Element Bearings Using Supervised Machine Learning. Energies, 12.10.3390/en12142705 ↗
57. A new intelligent bearing fault diagnosis method using SDP representation and SE-CNN10.1109/TIM.2019.2956332 ↗
58. Deep Convolutional Transfer Learning Network: A New Method for Intelligent Fault Diagnosis of Machines With Unlabeled Data10.1109/TIE.2018.2877090 ↗
59. Mao, W., He, J., Tang, J., and Li, Y. (2018). Predicting remaining useful life of rolling bearings based on deep feature representation and long short-term memory neural network. Adv. Mech. Eng., 10.10.1177/1687814018817184 ↗
60. Lee, J., Qiu, H., Yu, G., and Lin, J. (2007). Rexnord Technical Services. Bearing Data Set, IMS, University of Cincinnati, NASA Ames Prognostics Data Repository.
61. A Hybrid Prognostics Approach for Estimating Remaining Useful Life of Rolling Element Bearings10.1109/TR.2018.2882682 ↗
62. Nectoux, P., Gouriveau, R., Medjaher, K., Ramasso, E., Chebel-Morello, B., Zerhouni, N., and Varnier, C. (2020, January 8–10). PRONOSTIA: An experimental platform for bearings accelerated degradation tests. Proceedings of the IEEE International Conference on Prognostics and Health Management, Detroit, MI, USA.
63. Lee, J., and Jiang, J. (2019, January 3–6). Time Series Multi-Channel Convolutional Neural Network for Bearing Remaining Useful Life Estimation. Proceedings of the 2019 IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE), Yunlin, Taiwan.10.1109/ECICE47484.2019.8942782 ↗
64. Khamoudj, C.E., Tayeb, F.B., Benatchba, K., and Benbouzid, M. (2019, January 14–17). Induction Machines Bearing Failures Detection and Diagnosis using Variable Neighborhood Search. Proceedings of the IECON 2019–45th Annual Conference of the IEEE Industrial Electronics Society, Lisbon, Portugal.10.1109/IECON.2019.8927697 ↗
65. Enabling Health Monitoring Approach Based on Vibration Data for Accurate Prognostics10.1109/TIE.2014.2327917 ↗
66. (2015). Acoustics—Preferred Reference Values for Acoustical and Vibratory Levels (Standard No. ISO 1683:2015).
67. Boashash, B. (2016). Chapter 9—Noise Analysis and Random Processes in the (t,f) Domain. Time-Frequency Signal Analysis and Processing, Academic Press. [2nd ed.].
68. Caesarendra, W., and 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. Machines, 5.10.3390/machines5040021 ↗
69. Wu, B., Li, W., and Qiu, M.Q. (2017). Remaining Useful Life Prediction of Bearing with Vibration Signals Based on a Novel Indicator. Shock Vib., 2017.10.1155/2017/8927937 ↗
70. Dynamic Programming10.1126/science.153.3731.34 ↗
71. Zhou, Z., Mo, J., and Shi, Y. (2017, January 13–16). Data imputation and dimensionality reduction using deep learning in industrial data. Proceedings of the 2017 third IEEE International Conference on Computer and Communications (ICCC), Chengdu, China.10.1109/CompComm.2017.8322951 ↗
72. Performance of a Classifier Based on Time-Domain Features for Incipient Fault Detection in Inverter Drives10.1109/TII.2018.2854885 ↗
73. Meng, L., Miao, W., and Chunguang, W. (2010, January 11–12). Research on SVM Classification Performance in Rolling Bearing Diagnosis. Proceedings of the 2010 International Conference on Intelligent Computation Technology and Automation, Changsha, China.10.1109/ICICTA.2010.747 ↗
74. Shi, R., Ngan, K.N., and Li, S. (2014, January 27–30). Jaccard index compensation for object segmentation evaluation. Proceedings of the 2014 IEEE International Conference on Image Processing (ICIP), Paris, France.10.1109/ICIP.2014.7025904 ↗
75. Niwattanakul, S., Singthongchai, J., Naenudorn, E., and Wanapu, S. (2013, January 13–15). Using of Jaccard coefficient for keywords similarity. Proceedings of the International Multiconference of Engineers and Computer Scientists, Hong Kong, China.
76. Predictive modeling for US commercial building energy use: A comparison of existing statistical and machine learning algorithms using CBECS microdata10.1016/j.enbuild.2017.12.031 ↗
77. Medar, R., Rajpurohit, V.S., and Rashmi, B. (2017, January 17–18). Impact of Training and Testing Data Splits on Accuracy of Time Series Forecasting in Machine Learning. Proceedings of the 2017 International Conference on Computing, Communication, Control and Automation (ICCUBEA), Pune, India.10.1109/ICCUBEA.2017.8463779 ↗
78. Sutrisno, E., Oh, H., Vasan, A.S.S., and Pecht, M. (2012, January 17–18). Estimation of remaining useful life of ball bearings using data driven methodologies. Proceedings of the 2012 IEEE Conference on Prognostics and Health Management, Denver, CO, USA.10.1109/ICPHM.2012.6299548 ↗
79. Extended Kalman filtering for remaining-useful-life estimation of bearings10.1109/TIE.2014.2336616 ↗
80. A model-based method for remaining useful life prediction of machinery10.1109/TR.2016.2570568 ↗