Abstract
Detection of surface defects in high-pressure aluminum die castings is of paramount importance for maintaining product quality. Visual inspection by humans is time-consuming and subject to errors and oversights. A machine vision system has been set up to capture part surface images in this work. Afterimage quality enhancement using standard transformations and filtering Regions of Interest were defined in the areas where defects are expected to appear. Noise elimination extended edge extraction followed. Corresponding descriptors were employed to identify statistical features associated with defective parts. An advanced learning process has been developed to classify parts as defective or normal, based on Feedforward Artificial Neural Networks (ANNs), which were compared to typically used Support Vector Machines. Different combinations of descriptors were tried as input to determine the best four ANNS, which were used as an ensemble to enhance robustness at overall positive recognition rates of the order of 90% despite the restricted dataset.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Mery, D., Jaeger, T., Dieter, F.: A review of methods for automated recognition of casting defects. Insight-wigst. Northhampton 44(7), 428–436 (2002)
Singh, S., Kaur, M.: Machine vision system for automated visual inspection of tile’s surface quality. IOSR J. Eng. 2, 429–432 (2012)
Luo, Q., et al.: Automated visual defect classification for flat steel surface: a survey. IEEE Trans. Instrum. Meas. 69, 9329–9349 (2020). https://doi.org/10.1109/TIM.2020.3030167
Jia, H., Murphey, Y.L., Shi, J., Chang, T.-S.: An intelligent real-time vision system for surface defect detection. In: Proceedings of the 17th International Conference on Pattern Recognition, pp. 239–242. Cambridge (2004). https://doi.org/10.1109/ICPR.2004.1334512
López, F., Valiente, J.M., Prats, J.M., Ferrer, A.: Performance evaluation of soft color texture descriptors for surface grading using experimental design and logistic regression. Pattern Recogn. 41, 1761–1772 (2008). https://doi.org/10.1016/j.patcog.2007.09.011
Ng, H.: Automatic thresholding for defect detection. Pattern Recogn. Lett. 27, 1644–1649 (2006). https://doi.org/10.1016/j.patrec.2006.03.009
Gamage, P., Xie, S.Q.: A real-time vision system for defect inspection in cast extrusion manufacturing process. In: Proceedings of the 14th International Conference on Mechatronics and Machine Vision in Practice (IEEE), pp. 240–245 (2007). https://doi.org/10.1109/MMVIP.2007.4430750
Wakaf, Z., Jalab, H.A.: Defect detection based on extreme edge of defective region histogram. J. King Saud Univ.-Comput. Inf. Sci. 30, 33–40 (2018). https://doi.org/10.1016/j.jksuci.2016.11.001
Galan, U., Orta, P., Kurfess, T., Ahuett-Garza, H.: Surface defect identification and measurement for metal castings by vision system. Manuf. Lett. 15, 5–8 (2018). https://doi.org/10.1016/j.mfglet.2017.12.001
Kowal, J., Sioma, A.: Surface defects detection using a 3D vision system. In: Proceedings of the 2012 13th International Carpathian Control Conference, ICCC 2012 (IEEE), pp. 382–387 (2012). https://doi.org/10.1109/CarpathianCC.2012.6228672
Lei, W., Shen, Y.: Design of machine vision applications in detection of defects in high-speed bar copper. In: Proceedings of the International Conference on E-Product E-Service and E-Entertainment (Henan), pp. 1–4 (2010)
Hanzaei, S.H., Afshar, A., Barazandeh, F.: Automatic detection and classification of the ceramic tiles’ surface defects. Pattern Recogn. 66, 174–189 (2017). https://doi.org/10.1016/j.patcog.2016.11.021
Nielsen, D.R., Pitchumani, R.: Control of flow in resin transfer molding with real-time preform permeability estimation. Polym. Compos. 23, 1087–1110 (2002). https://doi.org/10.1002/pc.10504
Pastor-Lopez, I., Santos, I., Santamarıa-Ibirika, A., Salazar, M., De-la-Pena-Sordo, J.G., Bringas, P.: Machine-learning-based surface defect detection and categorisation in high-precision foundry. In: Proceedings of the 2012 7th IEEE Conference on Industrial Electronics and Applications, pp. 1359–64 (2012). https://doi.org/10.1109/ICIEA.2012.6360934
Pastor-Lopez, I., Santos, I., De-la-Pena-Sordo, J., Salazar, M., Santamarıa-Ibirika, A., Bringas, P.G.: Collective classification for the detection of surface defects in automotive castings. In: Proceedings of the IEEE 8th Conference on Industrial Electronics and Applications, pp. 941–946 (2013). https://doi.org/10.1109/ICIEA.2013.6566502
Pastor-Lopez, I., Santos, I., De-la-Pena-Sordo, J., Garcıa-Ferreira, I., Zabala, A.G., Bringas, P.G.: Enhanced image segmentation using quality threshold clustering for surface defect categorisation in high precision automotive castings. In: Herrero, Á., et al. (eds.) SOCO’13-CISIS’13-ICEUTE’13, pp. 191–200. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-01854-6_20
Le, X., Mei, J., Zhang, H., Zhou, B., Xi, J.: A learning-based approach for surface defect detection using small image datasets. Neurocomputing 408, 112–120 (2020). https://doi.org/10.1016/j.neucom.2019.09.107
Nguyen, T.P., Choi, S., Park, S.-J., Park, S.H., Yoon, J.: Inspecting method for defective casting products with convolutional neural network (CNN). Int. J. Precis. Eng. Manuf.-Green Technol. 8(2), 583–594 (2020). https://doi.org/10.1007/s40684-020-00197-4
Jain, S., Seth, G., Paruthi, A., Soni, U., Kumar, G.: Synthetic data augmentation for surface defect detection and classification using deep learning. J. Intell. Manuf. 33, 1–14 (2020). https://doi.org/10.1007/s10845-020-01710-x
Tsai, D.M., Fan, S.K.S., Chou, Y.H.: Auto-annotated deep segmentation for surface defect detection. IEEE Trans. Instr. Meas. 70, 5011410 (2021). https://doi.org/10.1109/TIM.2021.3087826
Walkington, W.G.: Die Casting Defects - Causes and Solutions. Wheeling, North American die Casting Association (NADCA) (2007)
Acknowledgment
Vioral SA is gratefully acknowledged for providing castings and consultation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Papagianni, Z., Vosniakos, GC. (2022). Surface Defects Detection on Pressure Die Castings by Machine Learning Exploiting Machine Vision Features. In: Ivanov, V., Trojanowska, J., Pavlenko, I., Rauch, E., Peraković, D. (eds) Advances in Design, Simulation and Manufacturing V. DSMIE 2022. Lecture Notes in Mechanical Engineering. Springer, Cham. https://doi.org/10.1007/978-3-031-06025-0_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-06025-0_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06024-3
Online ISBN: 978-3-031-06025-0
eBook Packages: EngineeringEngineering (R0)