A new concept for large additive manufacturing in construction: tower crane-based 3D printing controlled by deep reinforcement learning
ISSN: 1471-4175
Article publication date: 31 January 2023
Issue publication date: 9 January 2024
Abstract
Purpose
Most of the 3D printing machines do not comply with the requirements of on-site, large-scale multi-story building construction. This paper aims to propose the conceptualization of a tower crane (TC)-based 3D printing controlled by artificial intelligence (AI) as the first step towards a large 3D printing development for multi-story buildings. It also aims to overcome the most important limitation of additive manufacturing in the construction industry (the build volume) by exploiting the most important machine used in the field: TCs. It assesses the technology feasibility by investigating the accuracy reached in the printing process.
Design/methodology/approach
The research is composed of three main steps: firstly, the TC-based 3D printing concept is defined by proposing an aero-pendulum extruder stabilized by propellers to control the trajectory during the extrusion process; secondly, an AI-based system is defined to control both the crane and the extruder toolpath by exploiting deep reinforcement learning (DRL) control approach; thirdly the proposed framework is validated by simulating the dynamical system and analysing its performance.
Findings
The TC-based 3D printer can be effectively used for additive manufacturing in the construction industry. Both the TC and its extruder can be properly controlled by an AI-based control system. The paper shows the effectiveness of the aero-pendulum extruder controlled by AI demonstrated by simulations and validation. The AI-based control system allows for reaching an acceptable tolerance with respect to the ideal trajectory compared with the system tolerance without stabilization.
Originality/value
In related literature, scientific investigations concerning the use of crane systems for 3D printing and AI-based systems for control are completely missing. To the best of the authors’ knowledge, the proposed research demonstrates for the first time the effectiveness of this technology conceptualized and controlled with an intelligent DRL agent.
Practical implications
The results provide the first step towards the development of a new additive manufacturing system for multi-storey constructions exploiting the TC-based 3D printing. The demonstration of the conceptualization feasibility and the control system opens up new possibilities to activate experimental research for companies and research centres.
Keywords
Acknowledgements
Funding: The current research is Funded by the European Union – European Social Fund – PON Research and Innovation 2014–2020.
Authors’ contributions: Original Idea Conceptualization F.P.; Research Conceptualization and design F.P., V.S; Formalization of the novel 3D construction printing system V.S., N.P.; Study of the building construction technology V.S.; Methodology F.P.; Software F.P.; Validation F.P., V.S.; Formal analysis F.P., M.F.; Result discussion F.P., V.S.; Finding supervision V.S., F.P., A.M., M.F., J.A.; Research supervision, V.S., N.P., A.M., M.F., J.A.; Investigation F.P., V.S.; Visualization F.P., V.S., N.P.; Writing-original draft F.P., V.S.; Writing-review and editing F.P., V.S., N.P., A.M., M.F., J.A.
All authors have read and agreed to the published version of the manuscript.
Citation
Parisi, F., Sangiorgio, V., Parisi, N., Mangini, A.M., Fanti, M.P. and Adam, J.M. (2024), "A new concept for large additive manufacturing in construction: tower crane-based 3D printing controlled by deep reinforcement learning", Construction Innovation, Vol. 24 No. 1, pp. 8-32. https://doi.org/10.1108/CI-10-2022-0278
Publisher
:Emerald Publishing Limited
Copyright © 2022, Emerald Publishing Limited