A Distributed Approach for Machine Learning in Large Scale Manufacturing Systems
Large scale manufacturing systems are capable to execute manufacturing operations across multiple product batches by coordinating many shop floor actors. Monitoring and processing in real time the information flow from these systems becomes an essential part in optimizing and detecting faults that might affect the production schedule. This paper proposes an architecture that uses big data concepts and map-reduce algorithms to process the information streams in large scale manufacturing systems, focusing on energy consumptions aggregated at various layers. Once the information is aggregated in logical streams and consolidated based on relevant metadata, a neural network is trained and used to learn historical patterns in data on each layer. This novel approach also allows accurate forecasting of the energy consumption patterns during the production cycle by using Long Short Term Memory neural networks. The paper presents a practical example on how map-reduce algorithms can be implemented and how repetitive patterns in energy consumption can be learned.
KeywordsBig data Machine learning LSTM Energy consumption Forecasting Neural networks
This research work has been partially supported by the IBM Faculty Award 2016 Project: Big Data, Analytics and Cloud for Digital Transformation on Manufacturing – DTM, period of execution 2016–2018.
- 2.Kreps, J., Narkhede, N., Rao, J.: Kafka: a distributed messaging system for log processing. In: Proceedings of the NetDB, pp. 1–7 (2011)Google Scholar
- 3.Wang, J., Ma, Y., Zhang, L., Gao, R.X., Wu, D.: Deep learning for smart manufacturing: methods and applications. J. Manuf. Syst. (2018)Google Scholar
- 7.Sutskever, O., Vinyals, Q., Le, V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104–3112 (2014)Google Scholar
- 8.Mikolov, T., Karafiat, M., Burget, L., Cernock, J., Khudanpur, S.: Recurrent neural network based language model. In: INTERSPEECH, pp. 1045–1048 (2010)Google Scholar
- 9.Sundermeyer, M., Schluter, R., Ney, H.: LSTM neural networks for language modeling. In: INTERSPEECH (2010)Google Scholar
- 10.Williams, J.D., Zweig, G.: End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning. arXiv preprint arXiv:1606.01269 (2016)
- 11.Viswanadham, N., Johnson, T.L.: Fault detection and diagnosis of automated manufacturing systems. In: Proceedings of the 27th IEEE Conference on Decision and Control. IEEE (1998)Google Scholar