Abstract
Purpose
The global interest of develo** monitoring system is increasing due to the continuous challenges in reliability and accuracy. Automatic fault detection and diagnosis of rotating machinery play an important role for the high efficiency and reliability of modern industrial systems. The key point of having high accurate automatic model for fault detection and diagnosis is obtaining defect features and choosing a representative approach for the model.
Methods
In this paper, a model is developed based on Mel Frequency Cepstral Coefficients (MFCC) and gammatone cepstral coefficients (GTCC) that are computed for the input signal frames. Additionally, two global representations (feature concatenation and feature statistics) are adopted to feed Support Vector Machine (SVM) and a temporal representation is used with Long Short-Term Memory (LSTM) and Echo State Network (ESN) classification models. To generalize the proposed model, the experiments are evaluated based on two different datasets (PHM09 and DDS), where the PHM09 contains samples of helical and spur gears while the DDS contains samples from parallel and plenary gearboxes.
Results
The results show that the proposed SVM model based on feature concatenation can effectively detect faults from gears and outperforms the other existing methods in the state-of-the-art studies.
Conclusion
Base on the result of this paper, a global representation by concatenating frame-based features outperforms global statistical and time-series feature representations.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00768-6/MediaObjects/42417_2022_768_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00768-6/MediaObjects/42417_2022_768_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00768-6/MediaObjects/42417_2022_768_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00768-6/MediaObjects/42417_2022_768_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00768-6/MediaObjects/42417_2022_768_Fig5_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00768-6/MediaObjects/42417_2022_768_Fig6_HTML.png)
Similar content being viewed by others
Availability of Data and Material
Both datasets (PHM09 and DDS) utilized during the current study are available in public. The PHM09 and DDS dataset can be found on (Public Data Sets - PHM Society) and (GitHub - cathysiyu/Mechanical-datasets) respectively.
Code Availability
The implementation of the concat-SVM and other models will be send upon request.
Change history
05 December 2022
A Correction to this paper has been published: https://doi.org/10.1007/s42417-022-00805-4
References
Hai Y, Tsui KL and Zuo MJ (2021) Gear crack level classification based on multinomial logit model and cumulative link model. In: Proceeding of IEEE 2012 Progn. Syst. Heal. Manag. Conf. PHM-2012. https://doi.org/10.1109/PHM.2012.6228904
Li B, Zhang PL, Wang ZJ, Mi SS, Liu DS (2011) Application of S transform and morphological pattern spectrum for gear fault diagnosis. Proc Inst Mech Eng Part C J Mech Eng Sci 225(12):2963–2972. https://doi.org/10.1177/0954406211408781
Hartono D, Halim D, Roberts GW (2019) Gear fault diagnosis using the general linear chirplet transform with vibration and acoustic measurements. J Low Freq Noise Vib Act Control 38(1):36–52. https://doi.org/10.1177/1461348418811717
Tao Y, Wang X, Sanchez RV, Yang S, Bai Y (2019) Spur gear fault diagnosis using a multilayer gated recurrent unit approach with vibration signal. IEEE Access 7:56880–56889. https://doi.org/10.1109/ACCESS.2019.2914181
Li H, Zhang Y, Zheng H (2009) Gear fault detection and diagnosis under speed-up condition based on order cepstrum and radial basis function neural network. J Mech Sci Technol 23(10):2780–2789. https://doi.org/10.1007/s12206-009-0730-8
Cabrera JV, Sancho D, Li F, Cerrada C, Sánchez M, Pacheco RV, de Oliveira F (2017) Automatic feature extraction of time-series applied to fault severity assessment of helical gearbox in stationary and non-stationary speed operation. Appl Soft Comput J 58:53–64. https://doi.org/10.1016/j.asoc.2017.04.016
Ismail Fawaz H, Forestier G, Weber J, Idoumghar L, Muller PA (2019) Deep learning for time series classification: a review. Data Min Knowl Discov 33(4):917–963. https://doi.org/10.1007/s10618-019-00619-1
Wang J, Zhao R, Wang D, Yan R, Mao K, Shen F (2017) Machine health monitoring using local feature-based gated recurrent unit networks. IEEE Trans Ind Electron 65(2):1539–1548. https://doi.org/10.1109/TIE.2017.2733438
Chen L, Liu L, He M and Liu D (2019) Gearbox fault diagnosis based on VMD and acoustic emission technology. In: I2MTC 2019 - 2019 IEEE Int. Instrum. Meas. Technol. Conf. Proc., vol. 2019-May, pp 1–6. https://doi.org/10.1109/I2MTC.2019.8826954.
Zamanian AH, Ohadi A (2016) Gearbox fault detection through PSO exact wavelet analysis and SVM classifier. Arxiv E-prints. https://doi.org/10.13140/RG.2.1.4983.3442
Yu J, Zhou X (2020) One-dimensional residual convolutional autoencoder based feature learning for gearbox fault diagnosis. IEEE Trans Ind Informatics 16(10):6347–6358. https://doi.org/10.1109/TII.2020.2966326
Eyben F, Wöllmer M and Schuller B (2009) OpenEAR—introducing the Munich open-source emotion and affect recognition toolkit. In: Proceeding—2009 3rd International Conference of Affected Computer Intelligence Interact. Work. ACII 2009. https://doi.org/10.1109/ACII.2009.5349350
Isermann R (1993) Fault diagnosis of machines via parameter estimation and knowledge processing-Tutorial paper. Automatica 29(4):815–835. https://doi.org/10.1016/0005-1098(93)90088-B
Edwards S, Lees AW, Friswell MI (1998) Fault diagnosis of rotating machinery. Shock Vib Digest 30(1):4–13. https://doi.org/10.1177/058310249803000102
Luo RC, Wang H (2018) Diagnostic and prediction of machines health status as exemplary best practice for vehicle production system. IEEE Veh Technol Conf 2018(Augus):1–5. https://doi.org/10.1109/VTCFall.2018.8690710
Chen B, Li Y, Zeng N, He W (2019) Fractal lifting wavelets for machine fault diagnosis. IEEE Access 7:50912–50932. https://doi.org/10.1109/ACCESS.2019.2908213
Kumar P, Hati AS (2020) Review on machine learning algorithm based fault detection in induction motors. Arch Comput Methods Eng. https://doi.org/10.1007/s11831-020-09446-w
Zeng C, Su H, Li Y, Guo J, Yang C (2021) An approach for robotic leaning inspired by biomimetic adaptive control. IEEE Trans Ind Informatics 8(3):1479–1488
Zeng N, Qiu H, Wang Z, Liu W, Zhang H, Li Y (2018) A new switching-delayed-PSO-based optimized SVM algorithm for diagnosis of Alzheimer’s disease. Neurocomputing 320:195–202. https://doi.org/10.1016/j.neucom.2018.09.001
Gaikwad SK, Gawali BW, Yannawar P (2010) A review on speech recognition technique. Int J Comput Appl 10(3):16–24. https://doi.org/10.5120/1462-1976
Lei J, Liu C, Jiang D (2019) Fault diagnosis of wind turbine based on long short-term memory networks. Renew Energy 133:422–432. https://doi.org/10.1016/j.renene.2018.10.031
Abdul ZK, Al-Talabani A, Abdulrahman AO (2016) A new feature extraction technique based on 1D local binary pattern for gear fault detection. Shock Vib. https://doi.org/10.1155/2016/8538165
Zhang J, Jiang Q, Chang F (2018) Fault diagnosis method based on MFCC fusion and SVM. 2018 IEEE Int Conf Inf Autom ICIA 2018(August):1617–1622. https://doi.org/10.1109/ICInfA.2018.8812417
Benkedjouh AM, Chettibi T, Saadouni Y (2018) Gearbox fault diagnosis B based on mel-frequency cepstral coefficients and support vector machine. Springer International Publishing
Abdul ZK, Al-Talabani AK, Ramadan DO (2020) A hybrid temporal feature for gear fault diagnosis using the long short term memory. IEEE Sens J 23:14444–14452. https://doi.org/10.1109/jsen.2020.3007262
Yang HB, Zhang JA, Chen LL, Zhang HL, Liu SL (2019) Fault diagnosis of reciprocating compressor based on Cconvolutional neural networks with multisource raw vibration signals. Math Prob Eng. https://doi.org/10.1155/2019/6921975
**g L, Zhao M, Li P, Xu X (2017) A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox. Measurement 111(July):1–10. https://doi.org/10.1016/j.measurement.2017.07.017
Shao S, McAleer S, Yan R, Baldi P (2019) Highly accurate machine fault diagnosis using deep transfer learning. IEEE Trans Ind Informatics 15(4):2446–2455. https://doi.org/10.1109/TII.2018.2864759
Saufi SR, Bin Ahmad ZA, Leong MS, Lim MH (2020) Gearbox fault diagnosis using a deep learning model with limited data sample. IEEE Trans Ind Informatics 16(10):6263–6271. https://doi.org/10.1109/TII.2020.2967822
Tang S, Yuan S, Zhu Y (2020) Convolutional neural network in intelligent fault diagnosis toward rotatory machinery. IEEE Access. https://doi.org/10.1109/ACCESS.2020.2992692
Tang S, Zhu Y, Yuan S (2022) Intelligent fault diagnosis of hydraulic piston pump based on deep learning and Bayesian optimization. ISA Trans 129:555–563. https://doi.org/10.1016/j.isatra.2022.01.013
He W, Chen B, Zeng N, Zi Y (2018) Sparsity-based signal extraction using dual Q-factors for gearbox fault detection. ISA Trans 79:147–160. https://doi.org/10.1016/j.isatra.2018.05.009
Staszewski WJ, Tomlinson GR (1994) Application of the wavelet transform to fault detection in a spur gear. Mech Syst Signal Process 8(3):289–307. https://doi.org/10.1006/mssp.1994.1022
Rizos PF, Aspragathos N, Dimarogonas AD (1990) Identification of crack location and magnitude in a cantilever beam from the vibration modes. J Sound Vib 138(3):381–388. https://doi.org/10.1016/0022-460X(90)90593-O
Zhao B, Cheng C, Peng Z, Dong X, Meng G (2020) Detecting the early damages in structures with nonlinear output frequency response functions and the CNN-LSTM model. IEEE Trans Instrum Meas 69(12):9557–9567. https://doi.org/10.1109/TIM.2020.3005113
** S, Wang X, Du L, He D (2021) Evaluation and modeling of automotive transmission whine noise quality based on MFCC and CNN. Appl Acoust 172:107562. https://doi.org/10.1016/j.apacoust.2020.107562
Sharma V, Parey A (2016) A review of gear fault diagnosis using various condition indicators. Procedia Eng 144:253–263. https://doi.org/10.1016/j.proeng.2016.05.131
Tiwari V (2010) MFCC and its applications in speaker recognition. Int J Emerg Technol 1(1):19–22
Andrew PRS, Geib F, Kuo CC, Gawecki M, Tsau ES, Kang JW (2014) MFCC and celp to detect turbine engine faults. US Patent 8,655,571, 18 Feb 2014
Adiga A, Magimai M and Seelamantula CS (2013) Gammatone wavelet cepstral coefficients for robust speech recognition. In: IEEE Reg. 10 Annu. Int. Conf. Proceedings/TENCON. https://doi.org/10.1109/TENCON.2013.6718948.
Qi J, Wang D, Xu J and Tejedor J (2013) Bottleneck features based on gammatone frequency cepstral coefficients. In: Proceeding of Annual Conference of International Speech Communication of Associations interspeech, no. August, pp 1751–1755
Farhat NH (1992) Photonit neural networks and learning mathines the role of electron-trap** materials. IEEE Expert Syst Appl 7(5):63–72. https://doi.org/10.1109/64.163674
Al-Talabani A, Sellahewa H and Jassim SA (2015) Emotion recognition from speech: tools and challenges. In: Mobile multimedia/image processing, security, and applications 2015, vol. 9497, p 94970N
**e W, Wang J, **ng C, Guo S, Guo M, Zhu L (2021) Variational autoencoder bidirectional long and short-term memory neural network soft-sensor model based on batch training strategy. IEEE Trans Ind Informatics 17(8):5325–5334. https://doi.org/10.1109/TII.2020.3025204
Jaeger H, Haas H (2004) Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science (80–) 304(5667):78–80. https://doi.org/10.1126/science.1091277
Dai J, Venayagamoorthy GK and Harley RG (2009) An introduction to the echo state network and its applications in power system. In: 2009 15th International conference of intelligent system application to power system. ISAP ’09, no. 2, pp 1–7. https://doi.org/10.1109/ISAP.2009.5352913
Validated C (2021) What is an intuitive explanation of Echo State Networks?. Stack Exchange Network. https://stats.stackexchange.com/q/261735 (accessed Nov. 19, 2021)
Bianchi FM, Scardapane S, Lokse S, Jenssen R (2021) Reservoir computing approaches for representation and classification of multivariate time series. IEEE Trans Neural Netw Learn Syst 32(5):2169–2179. https://doi.org/10.1109/TNNLS.2020.3001377
Shao S, Member S, Mcaleer S, Yan R, Member S (2018) Highly-accurate machine fault diagnosis using deep transfer learning. IEEE Trans Ind Informatics. https://doi.org/10.1109/TII.2018.2864759
The Prognostics and Health Management Society (2009) 2009 PHM challenge competition data set. https://phmsociety.org/public-data-sets/ (accessed Oct 25, 2021)
Lei Y, Kong D, Lin J, Zuo MJ (2012) Fault detection of planetary gearboxes using new diagnostic parameters. Meas Sci Technol. https://doi.org/10.1088/0957-0233/23/5/055605
Tong C, Wang Y, Tian Y, Yu C (2018) Dynamic reliability analysis of gear vibration response with random parameters. No Icectt. https://doi.org/10.5220/0006968502410245
Ibrahim H, Loo CK, Alnajjar F (2021) Speech emotion recognition by late fusion for bidirectional reservoir computing with random projection. IEEE Access 9:122855–122871. https://doi.org/10.1109/ACCESS.2021.3107858
Amarnath M, Praveen Krishna IR (2014) Local fault detection in helical gears via vibration and acoustic signals using EMD based statistical parameter analysis. Meas J Int Meas Confed 58(December):154–164. https://doi.org/10.1016/j.measurement.2014.08.015
Wu C, Jiang P, Ding C, Feng F, Chen T (2019) Intelligent fault diagnosis of rotating machinery based on one-dimensional convolutional neural network. Comput Ind 108:53–61. https://doi.org/10.1016/j.compind.2018.12.001
Acknowledgements
The authors wish to thank the Erbil Polytechnic University, the Koya University and charmo University.
Funding
Not applicable.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
The original online version of this article was revised: The last affiliation was not correct.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Abdul, Z.K., Al-Talabani, A.K. Highly Accurate Gear Fault Diagnosis Based on Support Vector Machine. J. Vib. Eng. Technol. 11, 3565–3577 (2023). https://doi.org/10.1007/s42417-022-00768-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42417-022-00768-6