Advancing Chipboard Milling Process Monitoring through Spectrogram-Based Time Series Analysis with Convolutional Neural Network using Pretrained Networks

• Autorzy: Kurek Jarosław , Szymanowski Karol , Chmielewski Leszek , Orłowski Arkadiusz

Identyfikatory

DOI

10.22630/MGV.2023.32.2.5

• Języki publikacji: EN

Abstrakty

EN

This paper presents a novel approach to enhance chipboard milling process monitoring in the furniture manufacturing sector using Convolutional Neural Networks (CNNs) with pretrained architectures like VGG16, VGG19, and RESNET34. The study leverages spectrogram representations of time-series data obtained during the milling process, providing a unique perspective on tool condition monitoring. The efficiency of the CNN models in accurately classifying tool conditions into distinct states (‘Green’, ‘Yellow’, and ‘Red’) based on wear levels is thoroughly evaluated. Experimental results demonstrate that VGG16 and VGG19 achieve high accuracy, however with longer training times, while RESNET34 offers faster training at the cost of reduced precision. This research not only highlights the potential of pretrained CNNs in industrial applications but also opens new avenues for predictive maintenance and quality control in manufacturing, underscoring the broader applicability of AI in industrial automation and monitoring systems.

Słowa kluczowe

EN

convolutional neural networks; CNN; vgg16; vgg19; resnet34; tool state monitoring; chipboard milling

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2023
• Tom: Vol. 32, No. 2
• Strony: 89--108
• Opis fizyczny: Bibliogr. 21 poz., rys., tab.

Twórcy

autor

Kurek Jarosław

• Institute of Information Technology, Warsaw University of Life Sciences - SGGW, Warsaw, Poland

• https://orcid.org/0000-0002-2789-4732

autor

Szymanowski Karol

• Institute of Wood Sciences and Furniture, Warsaw University of Life Sciences - SGGW, Warsaw, Poland

• https://orcid.org/0000-0003-0383-0897

autor

Chmielewski Leszek

• Institute of Information Technology, Warsaw University of Life Sciences - SGGW, Warsaw, Poland

• https://orcid.org/0000-0002-9725-2479

autor

Orłowski Arkadiusz

• Institute of Information Technology, Warsaw University of Life Sciences - SGGW, Warsaw, Poland

• https://orcid.org/0000-0002-6755-1830

Bibliografia

• [1] Gao M., Qi D., Mu H., and Chen J.: A transfer residual neural network based on ResNet-34 for detection of wood knot defects. Forests, 12(2), 2021. doi:10.3390/f12020212.
• [2] Iakubovskii P. (qubvel). Classification models Zoo - Keras (and TensorFlow Keras). https://github.com/qubvel/classification_models, 2023. [Accessed: 2023-12-01].
• [3] Iskra P.and Hernández R. E.: Toward a process monitoring and control of a cnc wood router: Development of an adaptive control system for routing white birch. Wood and Fiber Science, 42(4):523-535, 2010. https://wfs.swst.org/index.php/wfs/article/view/567.
• [4] A. Jegorowa, J. Górski, J. Kurek, and M. Kruk. Initial study on the use of support vector machine (SVM) in tool condition monitoring in chipboard drilling. European Journal of Wood and Wood Products, 77(5):957–959, 2019. doi:10.1007/s00107-019-01428-5.
• [5] Jegorowa A., Górski J., Kurek J., and Kruk M.: Use of nearest neighbors (K-NN) algorithm in tool condition identification in the case of drilling in melamine faced particleboard. Maderas: Ciencia y Tecnologia, 22(2):189-96, 2020. doi:10.4067/S0718-221X2020005000205.
• [6] Jegorowa A., Kurek J., Antoniuk I., Dołowa W., Bukowski M., et al. Deep learning methods for drill wear classification based on images of holes drilled in melamine faced chipboard. Wood Science and Technology, 55(1):271-293, 2021. doi:10.1007/s00226-020-01245-7.
• [7] Kuo R. J.: Multi-sensor integration for on-line tool wear estimation through artificial neural networks and fuzzy neural network. Engineering Applications of Artificial Intelligence, 13(3):249-261, 2000. doi:10.1016/S0952-1976(00)00008-7.
• [8] Kurek J., Antoniuk I., Górski J., Jegorowa A., Świderski B., et al. Classifiers ensemble of transfer learning for improved drill wear classification using convolutional neural network. Machine Graphics & Vision, 28(1/4):13-23, 2019. doi:10.22630/MGV.2019.28.1.2.
• [9] Kurek J., Antoniuk I., Górski J., Jegorowa A., Świderski B., et al. Data augmentation techniques for transfer learning improvement in drill wear classification using convolutional neural network. Machine Graphics and Vision, 28(1/4):3-12, 2019. doi:10.22630/MGV.2019.28.1.1.
• [10] Kurek J., Antoniuk I., Świderski B., Jegorowa A., and Bukowski M.: Application of siamese networks to the recognition of the drill wear state based on images of drilled holes. Sensors (Switzerland), 20(23):1-16, 2020. doi:10.3390/s20236978.
• [11] Kurek J., Świderski B., Jegorowa A., Kruk M., and Osowski S.: Deep learning in assessment of drill condition on the basis of images of drilled holes. In: Eighth International Conference on Graphic and Image Processing (ICGIP 2016), vol. 10225, pp. 375-381. SPIE, 2017. doi:10.1117/12.2266254.
• [12] Mascarenhas S. and Agarwal M.: A comparison between VGG16, VGG19 and ResNet50 architecture frameworks for image classification. In: 2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON), vol. 1, pp. 96-99, 2021. doi:10.1109/CENTCON52345.2021.9687944.
• [13] matplotlib.pyplot.specgram - matplotlib 3.5.1 documentation. https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.specgram.html, 2023. [Accessed: 15-11-2023].
• [14] Osowski S., Kurek J., Kruk M., Górski J., Hoser P., et al. Developing automatic recognition system of drill wear in standard laminated chipboard drilling process. Bulletin of the Polish Academy of Sciences: Technical Sciences, pp. 633-640, 2016. doi:10.1515/bpasts-2016-0071.
• [15] Panda S. S., Singh A. K., Chakraborty D., and Pal S. K.: Drill wear monitoring using back propagation neural network. Journal of Materials Processing Technology, 172(2):283-290, 2006. doi:10.1016/j.jmatprotec.2005.10.021.
• [16] SciPy.interpolate.interpld - scipy v1.8.0 reference guide. https://docs.scipy.org/doc/scipy/reference/generated/scipy.interpolate.interp1d.html, 2023. [Accessed: 15-11-2023].
• [17] Simonyan K. and Zisserman A.: Very deep convolutional networks for large-scale image recognition. arXiv, 2015. ArXiv.1409.1556. doi:10.48550/arXiv.1409.1556.
• [18] Szwajka K. and Trzepieciński T.: Effect of tool material on tool wear and delamination during machining of particleboard. Journal of Wood Science, 62(4):305-315, 2016. doi:10.1007/s10086-016-1555-6.
• [19] tf.keras.applications.vgg16.vgg16. https://www.tensorflow.org/api_docs/python/tf/keras/applications/vgg16/VGG16. [Accessed: 2023-12-01].
• [20] tf.keras.applications.vgg19.vgg19. https://www.tensorflow.org/api_docs/python/tf/keras/applications/vgg19/VGG19. [Accessed: 2023-12-01].
• [21] Wei W., Y.Li, Xue T., S.Tao, Mei C., et al. The research progress of machining mechanisms in milling wood-based materials. BioResources, 13(1):2139-2149, 2018. doi:10.15376/biores.13.1.Wei.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).