Multi-objective loss balancing for physics-informed deep learning

R Bischof, M Kraus - arXiv preprint arXiv:2110.09813, 2021 - arxiv.org
Physics-Informed Neural Networks (PINN) are algorithms from deep learning leveraging
physical laws by including partial differential equations together with a respective set of …

The impact of industry 4.0 concepts and technologies on different phases of construction project lifecycle: a literature review

J Menegon, LCP da Silva Filho - Iranian Journal of Science and …, 2023 - Springer
With the advent of the fourth Industrial Revolution, sensors, machines, tools, and intelligent
systems became connected and can interact with each other along the production chain …

Deciphering the non-linear impact of Al on chemical durability of silicate glass

K Damodaran, JM Delaye, AG Kalinichev, S Gin - Acta Materialia, 2022 - Elsevier
The role of Al in aluminosilicate glasses remains somewhat a mystery: at low concentrations,
it increases the resistance to hydrolysis of the glass, whereas at high concentrations an …

Active, passive and cyber-physical adaptive façade strategies: a comparative analysis through case studies

J Böke, PR Denz, N Suwannapruk… - Journal of Facade Design …, 2022 - jfde.eu
In view of the required energy savings in the building sector, there is an urgent need for
innovative and sustainable solutions to increase the performance of building envelopes …

Predicting Nanobinder‐Improved Unsaturated Soil Consistency Limits Using Genetic Programming and Artificial Neural Networks

AM Ebid, LI Nwobia, KC Onyelowe… - … Intelligence and Soft …, 2021 - Wiley Online Library
Unsaturated soils used as compacted subgrade, backfill, or foundation materials react
unfavorably under hydraulically bound environments due to swell and shrink cycles in …

Online prediction of automotive tempered glass quality using machine learning

A Khdoudi, N Barka, T Masrour, I El-Hassani… - … International Journal of …, 2023 - Springer
This study explores the application of machine learning algorithms for supporting complex
product manufacturing quality through a focus on quality assurance and control. We aim to …

Automated quality control of vacuum insulated glazing by convolutional neural network image classification

H Riedel, S Mokdad, I Schulz, C Kocer… - Automation in …, 2022 - Elsevier
Vacuum insulated glazing (VIG) is a highly thermally insulating window technology, which
boasts an extremely thin profile and lower weight as compared to gas-filled insulated …

Data-driven process mining framework for risk management in construction projects

A Khodabakhshian, FR Cecconi - IOP Conference Series: Earth …, 2022 - iopscience.iop.org
Construction Projects are exposed to numerous risks due to their complex and uncertain
nature, threatening the realization of the project objectives. However, Risk Management …

Fabrication, physical and machine learning density prediction techniques of newly B2O3–ZnO–BaO–PtO2 glasses

NAM Alsaif, MM Ahmed, H Al-Ghamdi… - Optical Materials, 2023 - Elsevier
New glass samples with chemical formula (50-x) B 2 O 3–25ZnO–25BaO-xPtO 2 (0 (Pt-
0.0)≤ x≤ 1 (Pt-1.0) mol%) have been fabricated for first time using the traditional technique …

SoundLab AI-Machine learning for sound insulation value predictions of various glass assemblies

M Drass, MA Kraus, H Riedel, I Stelzer - Glass Structures & Engineering, 2022 - Springer
Modern architecture promotes a high demand for transparent building envelopes and
especially glass facades. Commonly, facades are designed to fulfill a multitude of objectives …