Session: 03-12 Metals: Simulation, Modeling, and Training II

Paper Number: 94202

94202 - A Framework of Multisource Data Integration and Analytics for Direct Energy Deposition Additive Manufacturing (Ded-Am) 

As one of the most representative additive manufacturing (AM) categories, direct energy deposition (DED)-AM has high importance and never failed to attract people's attention in the last decade. Typical DED AM generally consists of server stages including design, path planning, part building and post-processing. This can generate a large amount of data from various data sources including system and process monitoring sensors. For industry 4.0 it is necessary to guarantee a traceable and stable production process, and multisource data in DED-AM needs to be acquired and managed. However, there is still a lack of guidance on data research for DED-AM. This paper reviews the state-of-the-art of data-driven research and proposes a framework focusing on DED-AM multisource data. An overview of DED-AM data fusion including data selection, collection, integration, and analytics for assisting AM research to realise the best approach for DED-AM data processing will be given. Based on the proposed framework, a case study is then demonstrated, in which a monitoring and control platform is introduced for a wire arc additive manufacturing (WAAM) system. This is a commercial WAAM system, including hardware and software, which was designed and developed by WAAM3D Limited. The monitoring and control platform collects and integrates data from the system manipulator, power source, various process monitoring sensors and part design information. All the sensing data is selected based on process and material knowledge which can be used for further data analytics. Furthermore, a full digital footprint of the manufactured part is generated, with part quality control is provided by the platform.

Presenting Author: Jian Qin Cranfield University

Presenting Author Biography: Determined to experience high-value manufacturing, especially Metal Additive Manufacturing, Dr. Qin joined Cranfield University as a research fellow Welding Engineering and Laser Process centre in 2019. He is currently working on AM system integration, process monitoring and controlling, and advanced data analytics. He obtained his MSc degree in Mechatronics from the University of Bath in 2014. Then, he joined Cardiff University for his PhD in the High-value manufacturing research group at the School of Engineering in 2015, focusing on the research area of system monitoring, processing controlling and manufacturing informatics for additive manufacturing.

Authors: