Abstract
Effective diagnosis of the gear damage stages is critical for the industries to reduce unexpected failures and maximise life utilisation. In geared systems, pitting is one of the most common failure modes observed, which originates from the surface/subsurface cracks. The gear damage levels were classified using seeded defect data instead of naturally progressed in the reported works. It is difficult to simulate a natural pitting failure on the gear tooth using an artificial process. As implemented in prior experimental studies involving seeded defects, a sudden change in the gear pitting area may not occur in practice. This study presents an ensemble decision tree-based random forest (RF) classifier methodology for the online classification of gear damage stages under natural pitting progression. A health indicator (HI) termed CCR (i.e. correlation coefficient of residual vibration signal) is extracted using a raw vibration signal to represent the pitting progression in spur gears. The exact relationship between the HI and gear tooth degradation stages is crucial during the implementation of the classifier model. Hence, a binary segmentation (BS) methodology identifies the relationship between HI and gear health stages (i.e. healthy, initial pitting, medium pitting and severe pitting). The output of BS methodology is used for classifier model training, and later based on the trained model, gear pitting severity levels were estimated for a newly installed gear. The performance of the proposed framework (i.e. combining BS and RF methodology) is validated through six accelerated runs to failure gear pitting experiments.
Similar content being viewed by others
References
Sharma V (2021) A review on vibration-based fault diagnosis techniques for wind turbine gearboxes operating under nonstationary conditions. J Inst Eng Ser C 102(2):507–523. https://doi.org/10.1007/S40032-021-00666-Y/FIGURES/6
Kundu P, Darpe AK, Kulkarni MS (2020) A review on diagnostic and prognostic approaches for gears. Struct Health Monit 0(0):1–41. https://doi.org/10.1177/1475921720972926
Saravanan N, Ramachandran KI (2010) Incipient gear box fault diagnosis using discrete wavelet transform (DWT) for feature extraction and classification using artificial neural network (ANN). Expert Syst Appl 37(6):4168–4181. https://doi.org/10.1016/j.eswa.2009.11.006
Seo Y, Kim S, Kim B, Lee S, Kim J (2014) Classification of damage for planetary gear of wind turbine simulator, in Internoise. 249(5): 3119–3125
Yang D, Liu Y, Li S, Li X, Ma L (2015) Gear fault diagnosis based on support vector machine optimized by artificial bee colony algorithm. Mech Mach Theory 90:219–229. https://doi.org/10.1016/j.mechmachtheory.2015.03.013
Liu Z, Guo W, Tang Z, Chen Y (2015) Multi-sensor data fusion using a relevance vector machine based on an ant colony for gearbox fault detection. Sensors 15(9):21857–21875. https://doi.org/10.3390/s150921857
Saravanan N, Siddabattuni VNSK, Ramachandran KI (2010) Fault diagnosis of spur bevel gear box using artificial neural network (ANN), and proximal support vector machine (PSVM). Appl Soft Comput J 10(1):344–360. https://doi.org/10.1016/j.asoc.2009.08.006
Liu Z, Zuo MJ, Xu H (2013) Fault diagnosis for planetary gearboxes using multi-criterion fusion feature selection framework. Proc Inst Mech Eng Part C J Mech Eng Sci. 227(9):2064–2076. https://doi.org/10.1177/0954406212468407
Lei Y, Zuo MJ, He Z, Zi Y (2010) A multidimensional hybrid intelligent method for gear fault diagnosis. Expert Syst Appl 37:1419–1430. https://doi.org/10.1016/j.eswa.2009.06.060
Han T, Jiang D, Zhao Q, Wang L, Yin K (2018) Comparison of random forest, artificial neural networks and support vector machine for intelligent diagnosis of rotating machinery. Trans Inst Meas Control 40(8):2681–2693. https://doi.org/10.1177/0142331217708242
Cerrada M, Zurita G, Cabrera D, Sánchez RV, Artés M, Li C (2016) Fault diagnosis in spur gears based on genetic algorithm and random forest. Mech Syst Signal Process 70–71:87–103. https://doi.org/10.1016/j.ymssp.2015.08.030
Chen Z, Li C, Sánchez RV (2015) Multi-layer neural network with deep belief network for gearbox fault diagnosis. J Vibroengineering 17(5):2379–2392
Chen Z, Chen X, Li C, Sanchez RV, Qin H (2017) Vibration-based gearbox fault diagnosis using deep neural networks. J Vibroengineering 19(4):2475–2496. https://doi.org/10.21595/jve.2016.17267
Sun W, Yao B, Zeng N, Chen B, He Y, Cao X, He W (2017) An intelligent gear fault diagnosis methodology using a complex wavelet enhanced convolutional neural network. Materials (Basel) 10(7):790. https://doi.org/10.3390/ma10070790
Rafiee J, Arvani F, Harifi A, Sadeghi MH (2007) Intelligent condition monitoring of a gearbox using artificial neural network. Mech Syst Signal Process 21(4):1746–1754. https://doi.org/10.1016/j.ymssp.2006.08.005
Cheng G, Cheng YL, Shen LH, Qiu JB, Zhang S (2013) Gear fault identification based on Hilbert-Huang transform and SOM neural network. Meas J Int Meas Confed 46(3):1137–1146. https://doi.org/10.1016/j.measurement.2012.10.026
Jolandan SG, Mobli H, Ahmadi H, Omid M, Mohtasebi SS (2012) Fuzzy-rule-based faults classification of gearbox tractor. WSEAS Trans Appl Theor Mech 7(2):69–82
Wang W, Kanneg D (2009) An integrated classifier for gear system monitoring. Mech Syst Signal Process 23(4):1298–1312. https://doi.org/10.1016/j.ymssp.2008.10.006
Wang W, Ismail F, Golnaraghi F (2004) A neuro-fuzzy approach to gear system monitoring. IEEE Trans Fuzzy Syst 12(5):710–723. https://doi.org/10.1109/TFUZZ.2004.834807
Wang W (2008) An intelligent system for machinery condition monitoring. IEEE Trans Fuzzy Syst 16(1):110–122. https://doi.org/10.1109/TFUZZ.2007.896237
Fan Q, Ikejo K, Nagamura K, Kawada M, Hashimoto M (2014) Gear damage diagnosis and classification based on support vector machines. J Adv Mech Des Syst Manuf 8(3). https://doi.org/10.1299/jamdsm.2014jamdsm0021
Zhang C, Peng Z, Chen S, Li Z, Wang J (2018) A gearbox fault diagnosis method based on frequency-modulated empirical mode decomposition and support vector machine. Proc Inst Mech Eng Part C J Mech Eng Sci 232(2):369–380. https://doi.org/10.1177/0954406216677102
Qu J, Liu Z, Zuo MJ, Huang H-Z (2011) Feature selection for damage degree classification of planetary gearboxes using support vector machine. Proc Inst Mech Eng Part C J Mech Eng Sci 225(9):2250–2264. https://doi.org/10.1177/0954406211404853
Fan Q, Zhou Q, Wu C, Guo M (2017) Gear tooth surface damage diagnosis based on analyzing the vibration signal of an individual gear tooth. Adv Mech Eng 9(6):1–14. https://doi.org/10.1177/1687814017704356
Liu Z, Zuo MJ, Qu J, Xu H (2011) Classification of gear damage levels in planetary gearboxes, in IEEE International Conference on Computational Intelligence for Measurement Systems and Applications Proceedings, 86–90. https://doi.org/10.1109/CIMSA.2011.6059913
Zhao X, Zuo MJ, Liu Z, Hoseini MR (2013) Diagnosis of artificially created surface damage levels of planet gear teeth using ordinal ranking. Meas J Int Meas Confed 46(1):132–144. https://doi.org/10.1016/j.measurement.2012.05.031
Cheng Z, Hu N, Gu F, Qin G (2011) Pitting damage levels estimation for planetary gear sets based on model simulation and grey relational analysis. Trans Can Soc Mech Eng 35(3):403–417
Kundu P, Darpe AK, Kulkarni MS (2019) A correlation coefficient based vibration indicator for detecting natural pitting progression in spur gears. Mech Syst Signal Process 129:741–763. https://doi.org/10.1016/j.ymssp.2019.04.058
Killick R, Eckley P, Eckley IA, Lecturer S (2012) Optimal detection of changepoints with a linear computational cost, Accessed: Sep. 12, 2017. [Online]. Available: https://arxiv.org/pdf/1101.1438.pdf
Killick R, Fearnhead P, Eckley IA (2012) Optimal detection of changepoints with a linear computational cost. J Am Stat Assoc 107(500):1590–1598. https://doi.org/10.1080/01621459.2012.737745
Kundu P, Darpe AK, Kulkarni MS (2020) Gear pitting severity level identification using binary segmentation methodology. Struct Control Health Monit 27(3):e2478 (1-20). https://doi.org/10.1002/stc.2478
James G, Witten D, Tibshirani R, Hastie T (2013) An introduction to statistical learning with applications in R, 2nd edn. Springer
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning, 2nd edn. Springer
Han H, Guo X, Yu H (2016) Variable selection using mean decrease accuracy and mean decrease Gini based on random forest. In: 2016 7th IEEE international conference on software engineering and service science (icsess) 219–224. https://doi.org/10.1109/ICSESS.2016.7883053
Kundu P, Darpe AK, Kulkarni MS (2020) An ensemble decision tree methodology for remaining useful life prediction of spur gears under natural pitting progression. Struct Health Monit 19(3):854–872. https://doi.org/10.1177/1475921719865718
Kundu P, Kulkarni MS, Darpe AK (2021) A hybrid prognosis approach for life prediction of gears subjected to progressive pitting failure mode. J Intell Manuf 1–22. https://doi.org/10.1007/S10845-021-01852-6/FIGURES/14
Tao H, Wang P, Chen Y, Stojanovic V, Yang H (2020) An unsupervised fault diagnosis method for rolling bearing using STFT and generative neural networks. J Franklin Inst 357(11):7286–7307. https://doi.org/10.1016/J.JFRANKLIN.2020.04.024
Tao H, Cheng L, Qiu J, Stojanovic V (2022) Few shot cross equipment fault diagnosis method based on parameter optimization and feature mertic. Meas Sci Technol 33(11):115005. https://doi.org/10.1088/1361-6501/AC8368
Wu J, Zhao Z, Sun C, Yan R, Chen X (2020) Few-shot transfer learning for intelligent fault diagnosis of machine. Measurement 166:108202. https://doi.org/10.1016/J.MEASUREMENT.2020.108202
Funding
The authors were financially supported by the Aeronautics Research and Development Board, D.R.D.O., Government of India (project grant no. ARDB/01/1071913/M/I), and SERB, Government of India (project grant no. SB/S9/Z-16/2016-UALBERTA-IV (2018–19)).
Author information
Authors and Affiliations
Contributions
Pradeep Kundu: data collection, methodology, experiment, result analysis and original draft writing. Ashish K. Darpe: methodology, review and editing. Makarand S. Kulkarni: methodology, review, and editing. Ming J. Zuo: methodology.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix Calculation of residual vibration signal
Appendix Calculation of residual vibration signal
After TSA implementation, the obtained gear vibration signal only contains frequencies that are synchronous with gear rotation, i.e. rotational speed, GMF and its harmonics and sidebands, as shown in Fig. 12. The gear considered in this example has ten teeth and a rotational speed of 10 Hz (i.e. GMF = 10 × 10 = 100 Hz). The residual vibration signal is estimated by removing the shaft rotational frequency, GMF and its harmonics from the raw vibration signal and only extracting the sidebands from the signal, as shown in Fig. 12. The following steps are followed to estimate the residual vibration signal.
-
Perform time synchronous averaging of raw vibration signal in the time domain.
-
Convert the TSA signal in the frequency domain and remove the shaft rotation frequency, GMF and its harmonics.
-
This filtered signal obtained in the frequency domain is converted back to the time domain and is termed a residual vibration signal.
Rights and permissions
About this article
Cite this article
Kundu, P., Darpe, A.K., Kulkarni, M.S. et al. Online damage severity level classification in gears under natural damage progression. Int J Adv Manuf Technol 124, 1–20 (2023). https://doi.org/10.1007/s00170-022-10428-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-022-10428-4