Abstract
Today the integration of Artificial Intelligence (AI) solutions is part of the strategy in the industrial environment. We focus on anomaly detection in the framework of manufacturing electronic cards manufacturing under mass production conditions (24/7). Early anomaly detection is critical to avoid defects. Researches and applications of anomaly detection techniques in the industry have been published but when they face production constraints success is not guaranteed. Today’s manufacturing systems are complex and involve different behaviors. We propose and evaluate a new realistic methodology for detecting conditional anomalies that could be successfully implemented in production. The proposed solution is based on Variational Autoencoders (VAEs) which provide interesting scores under the near real-time constraints of the production environment. The results have been thoroughly evaluated and validated with the support of expert process engineers.
Supported by Continental Powertrain SAS France.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Hao, W.: Solder joint defect classification based on ensemble learning. Solder. Surf. Mt. Technol. 29, 06 (2017)
Acciani, G., Brunetti, G., Fornarelli, G.: A multiple neural network system to classify solder joints on integrated circuits. Int. J. Comput. Intell. Res. 2, 337–348 (2006)
Hao, W., Xianmin, Z., Yongcong, K., Gaofei, O., Hongwei, X.: Solder joint inspection based on neural network combined with genetic algorithm. Optik 124(20), 4110–4116 (2013)
Song, J.-D., Kim, Y.-G., Park, T.-H.: SMT defect classification by feature extraction region optimization and machine learning. Int. J. Adv. Manuf. Technol. 101, 1303–1313 (2018)
Jiang, J., Cheng, J., Tao, D.: Color biological features-based solder paste defects detection and classification on printed circuit boards. IEEE Trans. Componen. Packag. Manuf. Technol. 2(9), 1536–1544 (2012)
Tsai, D., Huang, C.: Defect detection in electronic surfaces using template-based Fourier image reconstruction. IEEE Trans. Componen. Packag. Manuf. Technol. 9(1), 163–172 (2019)
Jabbar, E., Besse, P., Loubes, J.M., Roa, N.B., Merle, C., Dettai, R.: Supervised learning approach for surface-mount device production. In: Nicosia, G., Pardalos, P., Giuffrida, G., Umeton, R., Sciacca, V. (eds.) LOD 2018. LNCS, vol. 11331, pp. 254–263. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-13709-0_21
Kim, D., Koo, J., Kim, H., Kang, S., Lee, S.H., Kang, J.T.: Rapid fault cause identification in surface mount technology processes based on factory-wide data analysis. Int. J. Distrib. Sens. Netw. 15(2), 1550147719832802 (2019)
Riddle, M.E.: Solder paste measurement: a yield improvement strategy that helps improve profits. SMT Express (2004)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)
Xu, H., et al.: Unsupervised anomaly detection via variational auto-encoder for seasonal KPIs in web applications. In: Champin, P.-A., Gandon, F.L., Lalmas, M., Ipeirotis, P.G., (eds.) WWW, pp. 187–196. ACM (2018)
Chollet, F., et al.: Keras (2015). https://keras.io
Abadi, M., et al.: TensorFlow: Large-scale machine learning on heterogeneous systems. Software available from tensorflow.org (2015)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Masters, D., Luschi, C.: Revisiting small batch training for deep neural networks. CoRR, abs/1804.07612 (2018)
Avati, A.: Evaluation metrics, April 2019. http://cs229.stanford.edu/section/evaluation_metrics.pdf
Acknowledgments
This work is supported by Continental Powertrain France. Special thanks goes to Minds team members: Nathalie Barbosa Roa, Alain Le Grand and Jean-Noël Tomasini.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Jabbar, E., Besse, P., Loubes, JM., Merle, C. (2019). Conditional Anomaly Detection for Quality and Productivity Improvement of Electronics Manufacturing Systems. In: Nicosia, G., Pardalos, P., Umeton, R., Giuffrida, G., Sciacca, V. (eds) Machine Learning, Optimization, and Data Science. LOD 2019. Lecture Notes in Computer Science(), vol 11943. Springer, Cham. https://doi.org/10.1007/978-3-030-37599-7_59
Download citation
DOI: https://doi.org/10.1007/978-3-030-37599-7_59
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37598-0
Online ISBN: 978-3-030-37599-7
eBook Packages: Computer ScienceComputer Science (R0)