GGLCM: A Real-time Early Anomaly Detection Method for Mechanical Vibration Data with Missing Labels

Yu, Hu; Che, Xiaoyu; Zhang, Chao; Zhu, Rupeng; Chen, Weifang

doi:10.2478/msr-2025-0019

Abstract

Early anomaly detection plays a central role in the scientific maintenance of mechanical equipment. Although the application is limited by weak monitoring, it encounters the problem of missing labels. To overcome this challenge, the Gramian gray level co-occurrence matrix (GGLCM) analysis method is proposed, which includes three phases: first, the time-series are input into the Gramian angular field (GAF) in real time for signal dimension reconstruction. Second, the gray level co-occurrence matrix (GLCM) is applied to the reconstructed signal. Since the GAF preserves the dependencies in the time-series, the limitation of missing labels is significantly weakened. Third, a continuous alarm mechanism is developed for reliable detection. Finally, the GGLCM is verified by actual vibration datasets of overloaded bearings.

References

Cao, H., Zhou, K., Chen, X., Zhang, X. (2017). Early chatter detection in end milling based on multi-feature fusion and 3σ criterion. The International Journal of Advanced Manufacturing Technology, 92 (9), 4387–4397. https://doi.org/10.1007/s00170-017-0476-x
Search in Google Scholar Back to article
Climente-Alarcon, V., Antonino-Daviu, J. A., Strangas, E. G., Riera-Guasp, M. (2015). Rotor-bar breakage mechanism and prognosis in an induction motor. IEEE Transactions on Industrial Electronics, 62 (3), 1814–1825. https://doi.org/10.1109/TIE.2014.2336604
Search in Google Scholar Back to article
Zhang, J., Xu, Z., Wang, J., Zhao, J., Din, Z., Cheng, M. (2021). Detection and discrimination of incipient stator faults for inverter-fed permanent magnet synchronous machines. IEEE Transactions on Industrial Electronics, 68 (8), 7505–7515. https://doi.org/10.1109/TIE.2020.3009563
Search in Google Scholar Back to article
Rojas, G. A., Quiroga Rubiano, E. L., Caratar Chaux, J. F., Pinedo Jaramillo, C. R., Garcia Melo, J. I. (2017). Supervisory system for fault detection and diagnosis in drinking water treatment plants using fuzzy engine. IEEE Latin America Transactions, 15 (11), 2071–2076. https://doi.org/10.1109/TLA.2017.8070410
Search in Google Scholar Back to article
Xu, X., Yan, X., Sheng, C., Yuan, C., Xu, D., Yang, J. (2020). A belief rule-based expert system for fault diagnosis of marine diesel engines. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 50 (2), 656–672. https://doi.org/10.1109/TSMC.2017.2759026
Search in Google Scholar Back to article
De Angelo, C. H., Bossio, G. R., Giaccone, S. J., Valla, M. I., Solsona, J. A., Garcia, G. O. (2009). Online model-based stator-fault detection and identification in induction motors. IEEE Transactions on Industrial Electronics, 56 (11), 4671–4680. https://doi.org/10.1109/TIE.2009.2012468
Search in Google Scholar Back to article
Wang, Q., Jin, T., Mohamed, M. A., Chen, T. (2020). A minimum hitting set algorithm with prejudging mechanism for model-based fault diagnosis in distribution networks. IEEE Transactions on Instrumentation and Measurement, 69 (7), 4702–4711. https://doi.org/10.1109/TIM.2019.2951866
Search in Google Scholar Back to article
Wu, P., Ferrari, R. M. G., Liu, Y., van Wingerden, J.-W. (2021). Data-driven incipient fault detection via canonical variate dissimilarity and mixed kernel principal component analysis. IEEE Transactions on Industrial Informatics, 17 (8), 5380–5390. https://doi.org/10.1109/TII.2020.3029900
Search in Google Scholar Back to article
Wang, B., Lei, Y., Li, N., Li, N. (2020). A hybrid prognostics approach for estimating remaining useful life of rolling element bearings. IEEE Transactions on Reliability, 69 (1), 401–412. https://doi.org/10.1109/TR.2018.2882682
Search in Google Scholar Back to article
Mao, W., Chen, J., Liang, X., Zhang, X. (2020). A new online detection approach for rolling bearing incipient fault via self-adaptive deep feature matching. IEEE Transactions on Instrumentation and Measurement, 69 (2), 443–456. https://doi.org/10.1109/TIM.2019.2903699
Search in Google Scholar Back to article
Ni, X., Yang, D., Zhang, H., Qu, F., Qin, J. (2023). Time-series transfer learning: An early stage imbalance fault detection method based on feature enhancement and improved support vector data description. IEEE Transactions on Industrial Electronics, 70 (8), 8488–8498. https://doi.org/10.1109/TIE.2022.3229351
Search in Google Scholar Back to article

GGLCM: A Real-time Early Anomaly Detection Method for Mechanical Vibration Data with Missing Labels

Abstract

Paradigm

My account