Abstract
In order to ensure high productivity and quality in industrial production, early identification of tool wear is needed. Within the context of Industry 4.0, we integrate wear monitoring of solid carbide milling and drilling cutters automatically into the production process. Therefore, we propose to analyze wear types with image instance segmentation using Mask R-CNN with feature pyramid and bounding box regression. Our approach is able to recognize the five most important wear types: flank wear, crater wear, fracture, built-up edge and plastic deformation. While other methods use image classification and classify only one wear type for each image, our model is able to detect multiple wear types. Over 35 models with different hyperparameter settings were trained on 5,000 labeled images to establish a reliable classifier. The results show up to 82.03% accuracy and benefit for overlapping wear types, which is crucial for using the model in production.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
MAPAL Fabrik für Präzisionswerkzeuge Dr. Kress KG, URL: https://www.mapal.com/.
References
Abdulla, W.: Mask R-CNN for Object Detection and Segmentation (2017). https://github.com/matterport/Mask_RCNN
Cuš, F., Župerl, U.: Real-time cutting tool condition monitoring in milling. Strojniski Vestnik 57, 142–150 (2011). https://doi.org/10.5545/sv-jme.2010.079
D’Addona, D.M., Teti, R.: Image data processing via neural networks for tool wear prediction. Procedia CIRP 12, 252–257 (2013). https://doi.org/10.1016/j.procir.2013.09.044
Dutta, A., et al.: VGG Image Annotator (VIA) (2019). http://www.robots.ox.ac.uk/~vgg/software/via/
Erdik, T., şen, Z.: Prediction of tool wear using regression and ANN models in end-milling operation a critical review. Int. J. Adv. Manuf. Tech. 37, 765–766 (2008). https://doi.org/10.1007/s00170-008-1758-0
e.V., D.: DIN 4000–82. Beuth Verlag GmbH (2011)
e.V., D.: DIN 4000–81. Beuth Verlag GmbH (2012)
Fernández-Robles, L., et al.: Machine-vision-based identification of broken inserts in edge profile milling heads. RCIM 44, 276–283 (2017). https://doi.org/10.1016/j.rcim.2016.10.004
García-Ordás, M.T., et al.: Tool wear monitoring using an online, automatic and low cost system based on local texture. MSSP 112, 98–112 (2018). https://doi.org/10.1016/j.ymssp.2018.04.035
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE ICCV, pp. 1440–1448 (2015). arXiv: 1504.08083
Girshick, R., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. CoRR, pp. 580–587 (2013). arXiv: 1311.2524
He, K., et al.: Mask R-CNN. CoRR, pp. 2980–2988 (2017). arXiv: 1703.06870
IDS Imaging Development Systems GmbH: iDS UI-1460SE (2020). https://de.ids-imaging.com/store/ui-1460se.html
International Organization for Standardization: ISO 8688–1. ISO, 1st edn. (1989)
International Organization for Standardization: ISO 8688–2. ISO, 1st edn. (1989)
Kong, D., et al.: Gaussian process regr. for tool wear pred. MSSP 104, 556–574 (2018). https://doi.org/10.1016/j.ymssp.2017.11.021
Lin, T.Y., et al.: Microsoft COCO. In: ECCV, pp. 740–755 (2014). arXiv: 1405.0312
M-Service & Geräte Peter Müller e.K.: Bedienungsanleitung Modell CV-KLQ-LED-9 (2016). https://www.m-service.de/seiten/d/downloads_d_only/d_Bedienungsanleitung_CV-KLQ-LED.pdf
MAPAL Fabrik für Präzisionswerkzeuge Dr. Kress KG: Kompetenz Vollbohren mit Vollhartmetall, PKD und Wechselkopf-Systemen (2020). https://www.mapal.com/de/produkte/vollbohren-aufbohren-senken/vollbohren/
Mikołajczyk, T., et al.: Neural network approach for automatic image analysis of cutting edge wear. MSSP 88, 100–110 (2017). https://doi.org/10.1016/j.ymssp.2016.11.026
Pfeifer, T., Wiegers, L.: Reliable tool wear monitoring by optimized image and illumination control in machine vision. Measurement 28(3), 209–218 (2000). https://doi.org/10.1016/S0263-2241(00)00014-2
Shi, X., Wang, X., Jiao, L., Wang, Z., Yan, P., Gao, S.: A real-time tool failure monitoring system based on cutting force analysis. Int. J. Adv. Manuf. Technol., 2567–2583 (2017). https://doi.org/10.1007/s00170-017-1244-7
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015). arXiv: 1409.1556
Sukeri, M., et al.: Wear detection of drill bit by image-based technique. IOP Conf. Ser. Mat. Sci. Eng. 328 (2018). https://doi.org/10.1088/1757-899X/328/1/012011
Thakre, A.A., et al.: Measurements of tool wear parameters using machine vision system. Model. Simul. Eng. 2019, 1–9 (2019). https://doi.org/10.1155/2019/1876489
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Dalferth, J., Winkelmann, S., Schwenker, F. (2020). Using Mask R-CNN for Image-Based Wear Classification of Solid Carbide Milling and Drilling Tools. In: Schilling, FP., Stadelmann, T. (eds) Artificial Neural Networks in Pattern Recognition. ANNPR 2020. Lecture Notes in Computer Science(), vol 12294. Springer, Cham. https://doi.org/10.1007/978-3-030-58309-5_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-58309-5_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58308-8
Online ISBN: 978-3-030-58309-5
eBook Packages: Computer ScienceComputer Science (R0)