Please use this identifier to cite or link to this item:
|Title:||Application of artificial intelligence for 3D concrete printing||Authors:||Lim, Megan||Keywords:||Engineering::Mechanical engineering||Issue Date:||2022||Publisher:||Nanyang Technological University||Source:||Lim, M. (2022). Application of artificial intelligence for 3D concrete printing. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/159040||Project:||C022||Abstract:||The construction industry is known to be one of the most labour intensive and time consuming industry which still uses traditional methods for construction. In recent years, research has been ongoing to incorporate technologies like 3D Concrete Printing for construction to overcome the challenges faced by the construction industry which includes time, manpower and costs. However, the usage of 3D Concrete Printing is still facing many challenges as it is only at the initial stage of development and thus hindered its advancement in the industry. Fatal features, such as cracks and rough surface finish on the concrete extrudate, could cause the structure to collapse during printing due to the softness of the concrete material printed. There is a need to be able to identify and rectify these printing imperfections to ensure smooth printing and reliability of the concrete structure. Such fatal features can be identified through Artificial Intelligence by incorporating computer vision of instance segmentation and semantic segmentation for object detection. Mask R-CNN and DeepLabV3+ were models investigated in this report through varying the respective parameters of the models and analysing its effects on the predictions. The results of detection for the 2 models were investigated to obtain a suitable machine learning model with optimized parameters in order to achieve high speed and accurate detection. Through training and optimization of parameters, object detection with relatively high accuracy and speed can be observed.||URI:||https://hdl.handle.net/10356/159040||Schools:||School of Mechanical and Aerospace Engineering||Fulltext Permission:||restricted||Fulltext Availability:||With Fulltext|
|Appears in Collections:||MAE Student Reports (FYP/IA/PA/PI)|
Updated on Sep 23, 2023
Updated on Sep 23, 2023
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.