Search

Three-dimensional (3D) printing, or additive manufacturing (AM), is a production can be utilised to fabricate 3D shapes from a simulated file. This technology has gained global popularity in the construction industry since 2014 due to its wide range of applications. AM promotes a more automated, innovative, flexible, and sustainable construction method, making it an integral part of the Construction Industry 4.0. However, there need to be more detailed studies regarding the effectiveness of AM as the future direction in the construction industry. This paper investigates the application of the finite element method (FEM) in assessing 3D-printed structures to get insight into the performance of these structures. Three leading 3D-printed structures were selected, including Dubai Future Foundation in the United Arab Emirates, Apis Cor house in Russia and PERI house in Germany. Structural and thermal analyses, including linear static, natural frequency, spectral response, and steady state heat, were performed using Strand7 to assess the effectiveness of AM in construction and the reliability of FEM in analysing 3D-printed structures. Although there are limited standards and regulations for 3D-printed structures in most countries, it was concluded that 3D-printed structures presented a similar strength to traditional ones. Moreover, FEM can be used to provide a reasonable analysis of the performance of these structures, while complying with the relevant standards. This paper presents a novel numerical procedure to assess the performance of small-scale 3D-printed structures under various mechanical and thermal loadings by checking against the relevant standards. [ABSTRACT FROM AUTHOR]

A new application of neurocomputing for data approximation and classification is introduced to process data in a wireless sensor network. For this purpose, a simplified dynamic sliding backpropagation algorithm is implemented on a wireless sensor network for transportation applications. It is able to approximate temperature and humidity in sensor nodes. In addition, two architectures of "radial basis function" (RBF) classifiers are introduced with probabilistic features for data classification in sensor nodes. The applied approximation and classification algorithms could be used in similar applications for data processing in embedded systems. [ABSTRACT FROM AUTHOR]