Enhanced Deep Learning Approaches for Diagnosing Drilling Machine Failures Using Gramian Angular Field and Markov Transition Field Encoding

Aroui  Tarek; Dorbez  Fradj

doi:10.6180/jase.202509_28(9).0004

Enhanced Deep Learning Approaches for Diagnosing Drilling Machine Failures Using Gramian Angular Field and Markov Transition Field Encoding

Aroui Tarek^1,2This email address is being protected from spambots. You need JavaScript enabled to view it. and Dorbez Fradj¹

¹Université de Sousse, Ecole Nationale d’Ingénieurs de Sousse (ENISo), 4054, Sousse, Tunisia

²Université de Sfax, Ecole Nationale d’ingénieurs de Sfax (ENIS), Laboratoire des Sciences et Techniques de l’Automatiques et de l’informatique industrielle (LabSTA), 3038, Sfax, Tunisia

Received: July 10, 2024
Accepted: November 5, 2024
Publication Date: December 7, 2024

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202509_28(9).0004

In theeraofIndustry4.0, applyingdeeplearningmodelsforanalyzingsensordatainmachineryisafundamental step toward developing predictive maintenance strategies. Deep learning models can automatically learn complex patterns and features from sensor data, making them highly effective in identifying early signs of faults or anomalies in machinery. This capability is often beyond the reach of traditional analysis methods (e.g., statistical features), which may miss subtle or non-linear patterns. By identifying these issues early, deep learning models enable proactive scheduling of maintenance activities, reducing unplanned downtime and preventing catastrophic failures. This study adopts a specific approach by focusing on diagnosing failures in the VALMETABdrilling machine. We use sound signals captured by AudioBox iTwo Studio microphones as our primary data source. The dataset, which includes 134 sounds categorized into Anomaly and Normal classes, is augmented using advanced techniques. We then employ the Markov Transition Field and the Gramian Angular Field encoding methods to represent the sound signals as images. These encoded images are subsequently used to train two deep-learning models with distinct architectures: ResNet50 and InceptionV3. The study’s results are promising, affirming the efficacy of our approach in detecting and diagnosing failures in drilling machines.

Keywords: VALMETABdrilling machine; Gramian Angular Field; Markov Transition Field; ResNet50; InceptionV3

[1] R. R. Shubita, A. S. Alsadeh, and I. M. Khater, (2023) “Fault Detection in Rotating Machinery Based on Sound Signal Using Edge Machine Learning" IEEE Access 11: 6665–6672. DOI: 10.1109/ACCESS.2023.3237074.
[2] A. Kothuru, S. P. Nooka, and R. Liu, (2018) “Appli cation of audible sound signals for tool wear monitor ing using machine learning techniques in end milling" The International Journal of Advanced Manufac turing Technology 95(9-12): 3797–3808. DOI: 10.1007/s00170-017-1460-1.
[3] S.-Y. Shih, F.-K. Sun, and H.-y. Lee, (2019) “Temporal pattern attention for multivariate time series forecasting" MachineLearning 108(8-9): 1421–1441. DOI: 10.1007/s10994-019-05815-0.
[4] T. Mian, A. Choudhary, and S. Fatima, (2022) “An efficient diagnosis approach for bearing faults using sound quality metrics" Applied Acoustics 195: 108839. DOI: 10.1016/j.apacoust.2022.108839.
[5] J. Yao, C. Liu, H. Wang, and D. Jiang, (2022) “A low frequency fault detection method for low-speed planetary gearbox based on acoustic signals" Applied Acoustics 195: 108838. DOI: 10.1016/j.apacoust.2022.108838.
[6] Y. E. Karabacak, (2024) “Intelligent milling tool wear estimation based on machine learning algorithms" Jour nal of Mechanical Science and Technology 38(2): 835–850. DOI: 10.1007/s12206-024-0131-z.
[7] Y. Tagawa, R. Maskeli¯unas, and R. Damaševiˇcius, (2021) “Acoustic Anomaly Detection of Mechanical Fail ures in Noisy Real-Life Factory Environments" Electron ics 10(19): 2329. DOI: 10.3390/electronics10192329.
[8] T. Tran and J. Lundgren, (2020) “Drill Fault Diagnosis Based on the Scalogram and Mel Spectrogram of Sound Signals Using Artificial Intelligence" IEEE Access 8: 203655–203666. DOI: 10.1109/ACCESS.2020.3036769.
[9] M.T.NguyenandJ.H.Huang,(2021)“Fault detection in water pumps based on sound analysis using a deep learning technique" Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering: 095440892110393. DOI: 10. 1177/09544089211039304.
[10] M.YurdakulandS.Tasdemir.AcousticSignalAnalysis with Deep Neural Network for Detecting Fault Diagnosis in Industrial Machines. Version Number: 1. 2023. DOI: 10.48550/ARXIV.2312.01062.
[11] V. Nasir, J. Cool, and F. Sassani, (2019) “Intelligent Machining Monitoring Using Sound Signal Processed With the Wavelet Method and a Self-Organizing Neural Network" IEEE Robotics and Automation Letters 4(4): 3449–3456. DOI: 10.1109/LRA.2019.2926666.
[12] T. Tran, N. T. Pham, and J. Lundgren, (2022) “A deep learning approach for detecting drill bit failures from a small sound dataset" Scientific Reports 12(1): 9623. DOI: 10.1038/s41598-022-13237-7.
[13] T. Tran, S. Bader, and J. Lundgren. “An artificial neural network-based system for detecting machine failures using a tiny sound dataset: A case study”. In: 2022 IEEE International Symposium on Multime dia (ISM). Italy: IEEE, 2022, 163–168. DOI: 10.1109/ISM55400.2022.00036.
[14] Y.Han,B.Li,Y.Huang,andL.Li,(2023)“Bearingfault diagnosis method based on Gramian angular field and ensemble deep learning" Journal of Vibroengineering 25(1): 42–52. DOI: 10.21595/jve.2022.22796.
[15] Z. WangandT.Oates. “Encoding time series as im ages for visual inspection and classification using tiled convolutional neural networks”. In: Workshops at the twenty-ninth AAAI conference on artificial intelli gence. 2015.
[16] Z. WangandT.Oates. Imaging Time-Series to Improve Classification and Imputation. arXiv:1506.00327 [cs]. 2015.
[17] K. He, X. Zhang, S. Ren, and J. Sun. “Deep Resid ual Learning for Image Recognition”. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA: IEEE, 2016, 770–778. DOI: 10.1109/CVPR.2016.90.
[18] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna. “Rethinking the Inception Architecture for Computer Vision”. In: 2016 IEEE Conference on Com puter Vision and Pattern Recognition (CVPR). Las Ve gas, NV, USA: IEEE, 2016, 2818–2826. DOI: 10.1109/CVPR.2016.308.
[19] F. Melo. “Receiver Operating Characteristic (ROC) Curve”. en. In: Encyclopedia of Systems Biology. Ed. by W. Dubitzky, O. Wolkenhauer, K.-H. Cho, and H. Yokota. New York, NY: Springer New York, 2013, 1818–1823. DOI: 10.1007/978-1-4419-9863-7_242.