Deep fusion for energy consumption prediction in additive manufacturing

Hu, Fu, Qin, Jian, Li, Yixin, Liu, Ying ORCID: https://orcid.org/0000-0001-9319-5940 and Sun, Xianfang ORCID: https://orcid.org/0000-0002-6114-0766 2021. Deep fusion for energy consumption prediction in additive manufacturing. Presented at: 54th CIRP Conference on Manufacturing Systems (CMS 2021), Virtual, 22-24 September 2021. 54th CIRP CMS 2021 - Towards Digitalized Manufacturing 4.0. Procedia CIRP , vol.104 Elsevier, pp. 1878-1883. 10.1016/j.procir.2021.11.317

PDF - Accepted Post-Print Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (462kB)

Abstract

Owing to the increasing trend of additive manufacturing (AM) technologies being employed in the manufacturing industry, the issue of AM energy consumption attracts attention in both industry and academia. The energy consumption of AM systems is affected by various factors. These factors involve features with different dimensions and structures which are hard to tackle in the analysis. In this work, a data fusion approach is proposed for energy consumption prediction based on CNN-LSTM (convolutional neural network and long short-term memory) model. A case study was conducted on an SLS system by using the proposed methodology, achieving the RMSE of 8.143 Wh/g in prediction.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Engineering
Publisher:	Elsevier
ISSN:	2212-8271
Date of First Compliant Deposit:	15 July 2021
Date of Acceptance:	13 July 2021
Last Modified:	28 Nov 2022 13:15
URI:	https://orca.cardiff.ac.uk/id/eprint/142559

Citation Data

Cited 4 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item