Big Data Analytics Based Optimisation for Enriched Process Planning: A Methodology
2017 (English)In: Manufacturing Systems 4.0 – Proceedings of the 50th CIRP Conference on Manufacturing Systems, Elsevier, 2017, Vol. 63, p. 161-166Conference paper, Published paper (Refereed)
Abstract [en]
To improve flexibility and accurateness of the optimisation in machining, this paper presents a big data analytics based optimisation method for enriched process planning in the concept of which cutting condition and cutting tool are optimised together and simultaneously. Within the context, the machining factors (workpiece, machining requirement, machine tool, machining process and machining result etc.) are concerned and represented by data attributes. In case that, the new machining resource, new materials and new machining tools etc., can be represented by a group of parameters, so that each machining cases can be treated by data regardless of the relevant experiments, which can enhance practicality and flexibility of potential application in real industry. Also a hybrid method combining neural networks (NN), analytic hierarchy process (AHP), and evolution based algorithm (EBA) or swarm intelligence based algorithm (SIBA) is proposed. NN based model is trained by the big data to improve the accurateness of each single objective, AHP is employed for multi-objective, and EBA or SBA is used to execute the optimising calculation.
Place, publisher, year, edition, pages
Elsevier, 2017. Vol. 63, p. 161-166
Series
Procedia CIRP, ISSN 2212-8271 ; 63
Keywords [en]
Big data analytics, cutting parameter optimisation, enriched process planning, tool optimisation
National Category
Production Engineering, Human Work Science and Ergonomics
Identifiers
URN: urn:nbn:se:kth:diva-214646DOI: 10.1016/j.procir.2017.03.090ISI: 000418465500027Scopus ID: 2-s2.0-85028667638OAI: oai:DiVA.org:kth-214646DiVA, id: diva2:1142522
Conference
50th CIRP Conference on Manufacturing Systems, CIRP CMS 2017, Taichung City HallTaichung, Taiwan, 3 May 2017 through 5 May 2017
Note
QC 20170919
2017-09-192017-09-192018-01-16Bibliographically approved