Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Data analytics for energy consumption of digital manufacturing systems using Internet of Things method

Qin, Jian, Liu, Ying and Grosvenor, Roger 2017. Data analytics for energy consumption of digital manufacturing systems using Internet of Things method. Presented at: IEEE International Conference on Automation Science and Engineering, Xi'an, China, 20-23 August 2017.

[img]
Preview
PDF
Download (759kB) | Preview

Abstract

The topic of ‘Industry 4.0’ has become increasingly popular in manufacturing and academia since it was first published. Under this trending topic, researchers and companies have pointed out many related capabilities required by current manufacturing systems, such as automation, interoperability, consciousness, and intelligence. To achieve these capabilities, data is considered the vitally important connecting media that integrates different manufacturing objects and activities. Additionally, sustainability is one of the most important research areas of Industry 4.0. Although modern digital manufacturing systems are becoming increasingly automated, the issue of sustainability still attracts attention, and is related to many processing factors that are present in a wide variety of systems. As a result, defining the energy consumption behaviour of digital manufacturing systems and discovering more efficient usage methods has been established as a crucial research target. In this paper, data analysis methods are proposed to facilitate better understanding and prediction of the energy consumption of digital production processes under an Internet of Things (IoT) framework. A Selective Laser Sintering (SLS) system is applied as a case study, in which a variety of real-time raw data is collected within machine logs from this ongoing Additive Manufacturing (AM) system. The machine data logs are combined with the product layout data and analysed using three data analysis techniques: linear regression, the decision tree method and the Back-propagation Neural Network method. The future work is introduced in order to complete this research.

Item Type: Conference or Workshop Item (Paper)
Date Type: Completion
Status: Unpublished
Schools: Engineering
Subjects: T Technology > TS Manufactures
Related URLs:
Last Modified: 27 May 2019 23:51
URI: http://orca.cf.ac.uk/id/eprint/102082

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics