Cyber-Physical System and Big Data-Enabled Scheduling Optimization for Sustainable Machining
- 472 Downloads
Modern manufacturing is challenged by customized, high-variety and low-volume job orders, dynamic ambient working conditions in shop floors, and stricter requirements on sustainability. Data-driven approach for manufacturing planning, control, and management will be a new research trend to tackle the challenge. In this research, based on in-process monitoring on energy consumption of machining processes and data analytics technologies, an innovative Cyber-physical system (CPS) and Big Data-enabled scheduling optimization system for sustainable computer numerical control (CNC) machining has been developed. This system is augmented with intelligent mechanisms for enhancing adaptability to condition dynamics in machining shop floors. The system consists of scheduling and re-scheduling functions. For scheduling, an artificial neural networks (ANNs)-based algorithm has been designed to establish energy models of components machined in a shop floor according to current working conditions of CNC machines. Based on the energy models, a fruit fly optimization (FFO) algorithm has been applied to generate a multi-objective optimized schedule. For re-scheduling, another ANNs-based algorithm has been developed to monitor the energy consumption of components during machining in real time. Scheduling optimization will be triggered to generate an updated schedule if there are significantly varying working conditions and re-scheduling adjustments are necessary. The system has been validated through deployment into a European machining company and industrial case studies to demonstrate technical innovations and the great potential of applicability in practice.
KeywordsCyber-physical system Big Data Energy efficiency Scheduling optimization
This research was carried out as a part of the Smarter and Cloudflow projects which are supported by the European Commission 7th Framework Programme under the grant agreement PEOPLE-2013-IAPP-610675 and FP7-2013-NMP-ICT-FOF- 609100.
- 15.Salido, M., Escamilla, J., Barber, F., & Giret, A. (2016). Rescheduling in job-shop problems for sustainable manufacturing systems. Journal of Cleaner Production (online).Google Scholar
- 16.Dai, J., Huang, J., Huang, S., Huang, B., & Liu, Y. (2011). HiTune: Dataflow-based performance analysis for big data cloud. In Proceedings of the 2011 USENIX ATC (pp. 87–100). Berkeley.Google Scholar
- 18.Loshin, D. (2014). Big data analytics. Burlington, NJ: Morgan Kaufmann Pub.Google Scholar
- 19.Noor, A. (2013). Putting big data to work. ASME Mechanical Engineering, 32–37.Google Scholar
- 20.Prabhu, N. (2013). Design and construction of an RFID-enabled infrastructure. Florida: CRC Press.Google Scholar
- 25.Li, W. D., Ong, S. K., & Nee, A. Y. C. (2006). Integrated and collaborative product development environment—Technologies and implementation. Singapore: World Scientific Publisher.Google Scholar
- 26.Mausser, H. (2006). Normalization and other topics in multi-objective optimization. In Proceedings of the Fields–MITACS Industrial Problems Workshop (pp. 59–101).Google Scholar
- 28.Mayer-Schonberger, V., & Cukier, K. (2013). Big data: A Revolution that will transform how we live. Boston: Houghton Miffin Harcourt Publishing Company.Google Scholar