Abstract
Manufacturing systems contain a large number of parameters, and a proper configuration of parameters is very important to ensure the stability of product quality. Traditional configuration methods rely heavily on manual tuning, which is labor-intensive, time-consuming, and poor performance. In this paper, we propose to build deep learning models on the vast amount of industrial data collected by IIoT devices for automatic configuration tuning. In order to address key challenges such as high data redundancy, limited device capacity, latency-sensitivity, and system heterogeneity, we propose a two-level federated deep learning framework. We first extract representative features from redundant data, and reduce network traffic and latency through joint training on plants and the cloud. Timely configuration tuning is made through local models of plants, and the tuning accuracy is improved through the global model in the cloud. We have deployed and evaluated the performance of the proposed model in real-world smart manufacturing systems, and the experimental results confirm its effectiveness.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bonawitz, K., et al.: Towards federated learning at scale: system design. arXiv preprint arXiv:1902.01046 (2019)
Bui, K.N., Jung, J.J.: ACO-based dynamic decision making for connected vehicles in IoT system. IEEE Trans. Ind. Inf. 15(10), 5648–5655 (2019)
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724–1734 (2014)
Dai, H.N., Wang, H., Xu, G., Wan, J., Imran, M.: Big data analytics for manufacturing internet of things: opportunities, challenges and enabling technologies. Enterp. Inf. Syst. 1–25 (2019)
He, L., Bian, A., Jaggi, M.: COLA: decentralized linear learning. In: Advances in Neural Information Processing Systems, pp. 4536–4546 (2018)
Koren, Y., Gu, X., Guo, W.: Choosing the system configuration for high-volume manufacturing. Int. J. Prod. Res. 56, 476–490 (2018)
La Feperdomo, I., Beruvides, G., Quiza, R., Haber, R.E., Rivas, M.: Automatic selection of optimal parameters based on simple soft-computing methods: a case study of micromilling processes. IEEE Trans. Ind. Inf. 15(2), 800–811 (2019)
Lin, Y., Zhang, Y., Lin, I., Chang, C.: Predicting logistics delivery demand with deep neural networks. In: International Conference Industrial Technology and Management (2018)
Liu, L., Zhang, J., Song, S.H., Letaief, K.B.: Client-edge-cloud hierarchical federated learning. arXiv: Networking and Internet Architecture (2019)
Lu, Y., Huang, X., Dai, Y., Maharjan, S., Zhang, Y.: Blockchain and federated learning for privacy-preserved data sharing in industrial IoT. IEEE Trans. Ind. Info. 16(6), 4177–4186 (2020)
McMahan, B., Moore, E., Ramage, D., Hampson, S., y Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics, pp. 1273–1282 (2017)
Ren, R., Hung, T., Tan, K.C.: A generic deep-learning-based approach for automated surface inspection. IEEE Trans. Syst. Man Cybern. 48(3), 929–940 (2018)
Tao, F., Cheng, J., Qi, Q., Zhang, M., Zhang, H., Sui, F.: Digital twin-driven product design, manufacturing and service with big data. Int. J. Adv. Manufact. Technol. 94(9), 3563–3576 (2018)
Wang, J., Ma, Y., Zhang, L., Gao, R.X., Wu, D.: Deep learning for smart manufacturing: methods and applications. J. Manufact. Syst. 48, 144–156 (2018)
Wang, J., Sun, Y., Zhang, W., Thomas, I., Duan, S., Shi, Y.: Large-scale online multitask learning and decision making for flexible manufacturing. IEEE Trans. Ind. Inf. 12(6), 2139–2147 (2016)
Yang, Q., Liu, Y., Chen, T., Tong, Y.: Federated machine learning: concept and applications. ACM Trans. Intell. Syst. Tech. (TIST) 10(2), 1–19 (2019)
Yin, B., Yin, H., Wu, Y., Jiang, Z.: FDC: a secure federated deep learning mechanism for data collaborations in the internet of things. IEEE Internet Things J. 1 (2020)
Zhang, G., Spaak, A., Martinez, C., Lasko, D.T., Zhang, B., Fuhlbrigge, T.A.: Robotic additive manufacturing process simulation - towards design and analysis with building parameter in consideration. In: International Conference on Automation Science and Engineering, pp. 609–613 (2016)
Zhang, X., Chen, X., Liu, J.K., Xiang, Y.: DeepPAR and DeepDPA: privacy preserving and asynchronous deep learning for industrial IoT. IEEE Trans. Ind. Inf. 16(3), 2081–2090 (2020)
Zhang, X., et al.: Cross-dataset time series anomaly detection for cloud systems. In: USENIX Annual Technical Conference, pp. 1063–1076 (2019)
Zheng, P., et al.: Smart manufacturing systems for industry 4.0: conceptual framework, scenarios, and future perspectives. Front. Mech. Eng. 13(2), 137–150 (2018)
Acknowledgment
The work described in this paper was supported by the National Natural Science Foundation of China (61802003, 61872006), and the Anhui Innovation Program for Overseas Students.
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
Zhang, Y., Li, X., Zhang, P. (2020). Real-Time Automatic Configuration Tuning for Smart Manufacturing with Federated Deep Learning. In: Kafeza, E., Benatallah, B., Martinelli, F., Hacid, H., Bouguettaya, A., Motahari, H. (eds) Service-Oriented Computing. ICSOC 2020. Lecture Notes in Computer Science(), vol 12571. Springer, Cham. https://doi.org/10.1007/978-3-030-65310-1_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-65310-1_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-65309-5
Online ISBN: 978-3-030-65310-1
eBook Packages: Computer ScienceComputer Science (R0)