Utilizing convolutional autoencoders for anomaly detection and drill bit damage assessment in rotary percussion drilling

• Autorzy: Senjoba Lesego , Ikeda Hajime , Toriya Hisatoshi , Adachi Tsuyoshi , Kawamura Youhei

Identyfikatory

DOI

10.46873/2300-3960.1456

• Języki publikacji: EN

Abstrakty

EN

Monitoring drill bit wear during drilling improves operational efficiency. Wear in drill bits is influenced by factors related to drilling parameters and rock properties and can be categorized into types based on the cause of failure. Several studies have used machine learning to detect drill bit wear, mainly using classification models. However, these models require an extensive amount of data that includes different possible drill bit failures. This presents a challenge as acquiring data is difficult due to the scarcity of anomalies. This study introduces a novel approach utilizing convolutional autoencoders (CAE) for both anomaly detection and drill bit damage assessment within rotary percussion drilling. The proposed CAE model was trained on the vibrations of normal data, learning to accurately reconstruct input patterns. A dual threshold was set based on the reconstruction errors of the validation data, serving as a criterion to distinguish between normal and anomalous data. An innovative method for assessing drill bit degradation was developed, utilizing reconstruction errors and thresholds. These findings highlight the significance of adopting advanced machine learning techniques to optimize drilling performance and enhance operational efficiency within the mining field.

Słowa kluczowe

EN

anomaly detection; condition monitoring; autoencoders; drill bit failure; Creative Commons

PL

wykrywanie anomalii; monitorowanie stanu; autoenkodery; awaria wiertła; Creative Commons

• Wydawca: Elsevier ; Główny Instytut Górnictwa
• Czasopismo: Journal of Sustainable Mining
• Rocznik: 2025
• Tom: Vol. 24, iss. 2
• Strony: 282--298
• Opis fizyczny: Bibliogr. 41 poz.

Twórcy

autor

Senjoba Lesego

• Graduate School of International Resource Sciences, Akita University, 1-1 Tegata Gakuenmachi, Akita 010-8502, Japan

• https://orcid.org/0000-0003-2277-0025

autor

Ikeda Hajime

• Graduate School of International Resource Sciences, Akita University, 1-1 Tegata Gakuenmachi, Akita 010-8502, Japan

• https://orcid.org/0000-0002-0863-5583

autor

Toriya Hisatoshi

• Graduate School of International Resource Sciences, Akita University, 1-1 Tegata Gakuenmachi, Akita 010-8502, Japan

• https://orcid.org/0000-0001-6753-5681

autor

Adachi Tsuyoshi

• Graduate School of International Resource Sciences, Akita University, 1-1 Tegata Gakuenmachi, Akita 010-8502, Japan

• https://orcid.org/0000-0003-0556-7527

autor

Kawamura Youhei

• Division of Sustainable Resources Engineering, Faculty of Engineering, Hokkaido University, Kita 13, Nishi 8, Kita-Ku, Sapporo 060- 8628, Japan

• https://orcid.org/0000-0003-4103-762X

Bibliografia

• [1] Tian J, Fan C, Zhang T, Zhou Y. Rock breaking mechanism in percussive drilling with the effect of high frequency torsional vibration. Energy Sources, Part A Recovery, Util Environ Eff 2022 Mar 31;44(1):2520e34.
• [2] Gomez MP, Hey AM, Ruzzante JE, D’Attellis CE. Tool wear evaluation in drilling by acoustic emission. Phys Procedia 2010 Jan;3(1):819e25.
• [3] Katiyar PK, Maurya R, Singh PK. Failure behavior of cemented tungsten carbide materials: a case study of mining drill bits. J Mater Eng Perform 2021 Aug;30(8):6090e106.
• [4] Kawamura Y, Jang H, Hettiarachchi D, Takarada Y, Okawa H, Shibuya T. A case study of assessing button bits failure through wavelet transform using rock drilling induced noise signals [cited 2021 Aug 22] J Powder Metall Min [Internet] 2017;6(1):162. Available from: https://www. omicsgroup.org/journals/a-case-study-of-assessing-button-bits-failure-through-wavelet-transformusing-rock-drilling-induced-noise-signals-2168-9806-1000162.php?aid=86987.
• [5] Iqbal M, Madan AK. CNC machine-bearing fault detection based on convolutional neural network using vibration and acoustic signal. J Vib Eng Technol 2022 Jul;10(5):1613e21.
• [6] Jantunen E. A summary of methods applied to tool condition monitoring in drilling. Int J Mach Tool Manufact 2002 Jul; 42(9):997e1010.
• [7] Li Y, Wang J, Shan Y, Wang C, Hu Y. Measurement and analysis of downhole drill string vibration signal. Appl Sci 2021 Dec 3;11(23):11484.
• [8] Da Silva Arantes J, Da Silva Arantes M, Frohlich HB, Siret L, Bonnard R. A novel unsupervised method for anomaly detection in time series based on statistical features for industrial predictive maintenance. Int J Data Sci Anal 2021 Oct; 12(4):383e404.
• [9] Qin M, Wang K, Pan K, Sun T, Liu Z. Analysis of signal characteristics from rock drilling based on vibration and acoustic sensor approaches. Appl Acoust 2018 Nov;140:275e82.
• [10] Rafezi H, Hassani F. Drilling signals analysis for tricone bit condition monitoring. International Journal of Mining Science and Technology 2021;31:187e95. https://doi.org/10. 1016/j.ijmst.2020.12.025.
• [11] Bello O, Teodoriu C, Yaqoob T, Oppelt J, Holzmann J, Obiwanne A. Application of artificial intelligence techniques in drilling system design and operations: a state of the art review and future research pathways. In: All days [Internet]. Lagos, Nigeria: SPE International; 2016 [cited 2021 Aug 22]. p. SPE-184320-MS. Available from: https://onepetro.org/ SPENAIC/proceedings/16NAIC/All16NAIC/Lagos,% 20Nigeria/192754.
• [12] Jung D, Choi Y. Systematic review of machine learning applications in mining: exploration, exploitation, and reclamation. Minerals 2021 Jan 31;11(2):148.
• [13] Rafezi H, Hassani F. Drill bit wear monitoring and failure prediction for mining automation. International Journal of Mining Science and Technology 2023;33:289e96. https://doi. org/10.1016/j.ijmst.2022.10.006.
• [14] Senjoba L, Sasaki J, Kosugi Y, Toriya H, Hisada M, Kawamura Y. One-dimensional convolutional neural network for drill bit failure detection in rotary percussion drilling. Mining 2021 Nov 12;1(3):297e314.
• [15] Zhou C, Paffenroth RC. Anomaly detection with robust deep autoencoders [cited 2023 Nov 8]. In: Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining [Internet]. Halifax NS Canada: ACM; 2017. p. 665e74. Available from: https://dl.acm.org/doi/10. 1145/3097983.3098052.
• [16] Kang HS, Choi YS, Yu JS, Jin SW, Lee JM, Kim YJ. Hyperparameter tuning of OC-SVM for industrial gas turbine anomaly detection. Energies 2022 Nov 21;15(22):8757.
• [17] Fernandez-Francos D, Martinez-Rego D, Fontenla-Romero O, Alonso-Betanzos A. Automatic bearing fault diagnosis based on one-class n-SVM. Comput Ind Eng 2013 Jan;64(1):357e65.
• [18] Miele ES, Bonacina F, Corsini A. Deep anomaly detection in horizontal axis wind turbines using Graph Convolutional Autoencoders for Multivariate Time series. Energy AI 2022 May;8:100145.
• [19] Son J, Kim C, Jeong M. Unsupervised learning for anomaly detection of electric motors. Int J Precis Eng Manuf 2022 Apr; 23(4):421e7.
• [20] Saufi SR, Isham MF, Ahmad ZA, Hasan MDA. Machinery fault diagnosis based on a modified hybrid deep sparse autoencoder using a raw vibration time-series signal. J Ambient Intell Hum Comput 2023 Apr;14(4):3827e38.
• [21] Li Z, Li J, Wang Y, Wang K. A deep learning approach for anomaly detection based on SAE and LSTM in mechanical equipment. Int J Adv Manuf Technol 2019 Jul;103(1e4): 499e510.
• [22] Jang H. Effects of overused top-hammer drilling bits [cited 2022 Apr 21] IMST [Internet] 2019 Sep 25;01(2). Available from: https://juniperpublishers.com/imst/IMST.MS.ID.555558.php.
• [23] Dumler J, Faatz S, Friedrich M, Dopper F. Automatic time series segmentation and clustering for process monitoring in series production. Procedia CIRP 2023;118:602e7.
• [24] Oberst U. The fast fourier transform. SIAM J Control Optim 2007 Jan;46(2):496e540.
• [25] El-Wardany TI, Gao D, Elbestawi MA. Tool condition monitoring in drilling using vibration signature analysis. Int J Mach Tool Manufact 1996 Jun;36(6):687e711.
• [26] Li W, Zhu Z, Jiang F, Zhou G, Chen G. Fault diagnosis of rotating machinery with a novel statistical feature extraction and evaluation method. Mech Syst Signal Process 2015 Jan; 50e51:414e26.
• [27] Heng RBW, Nor MJM. Statistical analysis of sound and vibration signals for monitoring rolling element bearing condition. Appl Acoust 1998 Jan;53(1e3):211e26.
• [28] Maaten LVD, Geoffrey H. Visualizing data using t-SNE. Mach Learn Res 2008;9:2579e605.
• [29] Linderman GC, Steinerberger S. Clustering with t-SNE, provably. SIAM Journal on Mathematics of Data Science 2019 Jan;1(2):313e32.
• [30] Masci J, Meier U, Ciresan D, Schmidhuber J. Stacked convolutional auto-encoders for hierarchical feature extraction [cited 2023 Nov 7]. In: Honkela T, Duch W, Girolami M, Kaski S, editors. Artificial neural networks and machine learning e ICANN 2011 [Internet]. Berlin, Heidelberg: Springer Berlin Heidelberg; 2011. p. 52e9 (Lecture Notes in Computer Science; vol. 6791). Available from: http://link. springer.com/10.1007/978-3-642-21735-7_7.
• [31] Gong D, Liu L, Le V, Saha B, Mansour MR, Venkatesh S, et al. Memorizing normality to detect anomaly: memory-augmented deep autoencoder for unsupervised anomaly detection [cited 2023 Nov 8]. In: 2019 IEEE/CVF international conference on computer vision (ICCV) [Internet]. Seoul, Korea (South): IEEE; 2019. p. 1705e14. Available from: https://ieeexplore.ieee.org/document/9010977/.
• [32] Chow JK, Su Z, Wu J, Tan PS, Mao X, Wang YH. Anomaly detection of defects on concrete structures with the convolutional autoencoder. Adv Eng Inform 2020 Aug;45: 101105.
• [33] Ahmad S, Styp-Rekowski K, Nedelkoski S, Kao O. Autoencoder-based condition monitoring and anomaly detection method for rotating machines [Internet]. arXiv 2021 [cited 2023 Oct 17]. Available from: http://arxiv.org/abs/2101.11539.
• [34] Guo X, Liu X, Zhu E, Yin J. Deep clustering with convolutional autoencoders [. In: Liu D, Xie S, Li Y, Zhao D, El-Alfy ESM, editors. Neural information processing [Internet]. Cham: Springer International Publishing; 2017. cited 2023 Oct 17]. p. 373e382. (Lecture Notes in Computer Science; vol. 10635). Available from: http://link.springer.com/10.1007/978-3-319-70096-0_39.
• [35] Tatachar AV. Comparative assessment of regression models based on model. Evaluation Metrics 2021;8(9).
• [36] Chen S, Guo W. Auto-encoders in deep learningda review with new perspectives. Mathematics 2023 Apr 7;11(8):1777.
• [37] Liu FT, Ting KM, Zhou ZH. Isolation forest [cited 2023 Nov 7]. In: 2008 eighth IEEE international conference on data mining [Internet]. Pisa, Italy: IEEE; 2008. p. 413e22. Available from: http://ieeexplore.ieee.org/document/4781136/.
• [38] Amer M, Goldstein M, Abdennadher S. Enhancing one-class support vector machines for unsupervised anomaly detection [cited 2023 Nov 7]. In: Proceedings of the ACM SIGKDD workshop on outlier detection and description [Internet]. Chicago Illinois: ACM; 2013. p. 8e15. Available from: https:// dl.acm.org/doi/10.1145/2500853.2500857.
• [39] Fawcett T. An introduction to ROC analysis. Pattern Recognit Lett 2006 Jun;27(8):861e74.
• [40] Zeng-Chang Qin. ROC analysis for predictions made by probabilistic classifiers [cited 2023 Nov 16]. In: 2005 international conference on machine learning and cybernetics [Internet], 5. Guangzhou, China: IEEE; 2005. p. 3119e24. Available from: http://ieeexplore.ieee.org/document/ 1527478/.
• [41] Sridhar AV, Prasad BS, Mouli KVVNRC. Evaluation of tool performance and wear through vibration signature analysis in drilling of IS3048 steel. J Eng Appl Sci 2021 Dec