Publications
Strength Lab AI: A Mixture-of-Experts Deep Learning Approach for Limit State Analysis and Design of Monolithic and Laminate Structures made of Glass
The demand for transparent building envelopes, particularly glass facades, is rising in modern architecture. These facades are expected to meet multiple objectives, including aesthetic appeal, durability, quick installation, transparency, and both economic and...
Physics-Informed Neural Networks for Nonlinear Analysis of Reinforced Concrete Beams
Reinforced concrete (RC) beams are a common structural component in buildings and bridges and play a pivotal role in design and verification processes. Current structural computations often rely on linear elastic analyses which potentially yield overly conservative...
SOUNDLAB AI Tool-Machine learning for sound insulation value predictions
Modern architecture promotes a high demand for transparent building envelopes. Typically, glass façades are designed under a variety of objectives, one of which is to meet sound insulation requirements. Reliable and fairly accurate estimation of the sound insulation...
Aktive Partner statt passive Elemente–die Zukunft von Branchensoftware im Bauwesen
Die Entwicklung muss folglich in Richtung von KI-basierten Assistenzsystemen für das Bauwesen gehen, welche als intelligente Partner einerseits eine Kommunikation in Form von Texten, Grafiken und Zahlen bieten, andererseits aber einen hohen Grad an Interaktion mit...
Digitale Transformation im Bauwesen–Grundlagen zur künstlichen Intelligenz und deren Anwendung im Wohnungsbau
Dieser Beitrag führt die im Mauerwerk-Kalender 2022 begonnene Reihe zur digitalen Transformation der Planung im Bauwesen weiter. Dazu werden mit Hinblick auf die Anwendung im Wohnungsbau zunächst relevante Grundlagen der digitalen Transformation des Bauwesens in...
Entwicklung einer synthetischen Datenpipeline zum domänen-spezifischen Lernens eines neuronalen Netzes im Bauwesen [in progress]
OPUS 4 | Entwicklung einer synthetischen Datenpipeline zum domänen-spezifischen Lernens eines neuronalen Netzes im Bauwesen [in progress] Deutsch Login Open Access Home Search Browse Publish FAQ Entwicklung einer synthetischen Datenpipeline zum domänen-spezifischen...
Explainable Domain-Specific Artificial Intelligence for Bridge Engineering and Design
The use of artificial intelligence (AI) is currently being discussed and evaluated across the board in research and pray tice in all industries. This paper first provides the necessary background knowledge on general AI and then elaborates the necessity of developing...
Improved Perception of AEC Construction Details via Immersive Teaching in Virtual Reality
This work proposes, implements and tests an immersive framework upon Virtual Reality (VR) for comprehension, knowledge development and learning process assisting an improved perception of complex spatial arrangements in AEC in comparison to the traditional 2D...
Scientific Machine and Deep Learning Investigations of the Local Buckling Behaviour of Hollow Sections
The recent advent of Machine and Deep Learning (ML/DL) increased interest among applicability of data‐driven methods to design and verification in structural civil engineering concerned, specifically with members made of steel within this paper. Scientific ML (SciML)...
Artificial intelligence-finite element method-hybrids for efficient nonlinear analysis of concrete structures
Realistic structural analyses and optimisations using the non-linear finite element method are possible today yet suffer from being very time-consuming, particularly in case of reinforced concrete plates and shells. Hence such investigations are currently dismissed in...
The in-plane expansion of fractured thermally pre-stressed glass panes:-An equivalent temperature difference model for engineering glass design
The present paper is concerned with deriving simplified design equations and charts for modelling in-plane expansion of fractured thermally pre-stressed soda-lime-silica glass panes using the method of equivalent temperature differences (ETD) together with a thermal...
Mixed Reality Applications for Teaching Structural Design
Teaching structural engineering is a core part of education in every undergraduate civil engineering program. The content in these kinds of lectures is demanding advanced analytical thinking and abstract perception. Previous research showed the little level of using...
SoundLab AI-Machine learning for sound insulation value predictions of various glass assemblies
Modern architecture promotes a high demand for transparent building envelopes and especially glass facades. Commonly, facades are designed to fulfill a multitude of objectives such as superior aesthetic appearance, a higher degree of weathering reliability, quick...
Design Space Exploration and Explanation via Conditional Variational Autoencoders in Meta-model-based Conceptual Design of Pedestrian Bridges
For conceptual design, engineers rely on conventional iterative (often manual) techniques. Emerging parametric models facilitate design space exploration based on quantifiable performance metrics, yet remain time-consuming and computationally expensive. Pure...
Automated quality control of vacuum insulated glazing by convolutional neural network image classification
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 glazing units of equivalent performance. The VIG is a double-pane configuration with a...
Künstliche Intelligenz–multiskale und cross‐domäne Synergien von Raumfahrt und Bauwesen
Dieser Beitrag führt zunächst in die digitale Transformation (dT) des Bauwesens sowie künstliche Intelligenz (KI), maschinelles und tiefes Lernen ein. Zur Erzielung eines begrifflichen und semantischen Verständnisses werden wesentliche Grundlagen zu KI‐Algorithmen,...
SOUNDLAB AI Tool–Machine Learning zur Bestimmung des bewerteten Schalldämmmaßes
Die moderne Architektur strebt nach transparenten Gebäudehüllen und insbesondere nach nachhaltigen und bauphysikalisch adäquaten Glasfassaden. Typischerweise werden Glasfassaden entworfen, um eine Vielzahl von Zielen zu erfüllen, eines davon sind die Anforderungen an...
Statistische Charakterisierung der Druckzonentiefe vorgespannter Gläser
Infolge variierender Produktionsbedingungen erfolgt der thermische Vorspannprozess von Gläsern nicht vollständig homogen. Daraus entstehen lokale Unterschiede in den Eigenspannungen. Um die statistischen Verteilungen von charakterisierenden Größen des...
Digitale Transformation im Bauwesen – Von der Theorie zur Anwendung
Dieser Beitrag führt zunächst in die digitale Transformation (DT) des Bauwesens und deren wesentliche Methoden wie BIM, digitaler Zwilling etc. ein. Zur Erzielung eines begrifflichen und semantischen Verständnisses werden die Definitionen zudem an...
Erklärbare domänenspezifische Künstliche Intelligenz im Massiv‐und Brückenbau
Der Einsatz von Künstlicher Intelligenz (KI) wird derzeit flächendeckend in Forschung und Praxis aller Branchen diskutiert und evaluiert. Dieser Beitrag vermittelt zunächst das notwendige Hintergrundwissen zur allgemeinen KI und erarbeitet dann die Notwendigkeit der...
NTAB0: Design Priors for AI-Augmented Generative Design of Network Tied-Arch-Bridges
Projects in the Architecture, Engineering and Construction (AEC) industry inherit a great complexity due to a tremendous amount of design parameters, multiple objectives, and many involved stakeholders. Especially in the conceptual design stage of bridges, an...
Mixture-of-Experts-Ensemble Meta-Learning for Physics-Informed Neural Networks
Partial Differential Equations (PDEs) arise in natural and engineering sciences to model reality and allow for numerical assessment of these phenomena. Classical numerical solutions for PDEs rely on discretisations such as eg the finite or spectral element method...
Badania eksperymentalne i analizy numeryczne hipersprężystości folii PVB
[1] Kraus, MA, i M. Niederwald. Uogólniona metoda kolokacji z wykorzystaniem macierzy sztywności w kontekście teorii lepkosprężystości liniowej (Generalized collocation method using Stiffness matrices in the context of the Theory of Linear viscoelasticity (GUSTL))....
Immersive Teaching of AEC Construction Details using Virtual Reality
Designing basic construction details of buildings is a fundamental part in the course of educating students of architecture and civil engineering during their first year. To meet current challenges in education, this research is concerned with investigating the...
Numerical analysis of experimentally tested frame corners with opening moments using the Compatible Stress Field Method (CSFM)
The critical parts of structures are typically discontinuity regions, where abrupt changes in geometry occur or large concentrated loads are applied. In engineering practice the verification of the ultimate limit stage of such discontinuity regions employs...
Statistische Charakterisierung der Verteilung der Druckzonentiefe vorgespannter Gläser
Due to varying production conditions, the thermal tempering process of glass is not fully homogeneous. This results in local differences in the residual stresses. In order to determine the statistical distributions of characterizing quantities of the residual stress...
Statistische Charakterisierung der Verteilung der Druckzo-nentiefe vorgespannter Gläser
Due to varying production conditions, the thermal tempering process of glass is not fully homogeneous. This results in local differences in the residual stresses. In order to determine the statistical distributions of characterizing quantities of the residual stress...
Adé ETAG 002–A Eurocode‐compliant design concept for silicone adhesive joints
Hyperelastic adhesives such as structural silicones have excellent properties for bonding brittle materials like glass. They typically have a low modulus of elasticity, high elongation at break and good adhesion to many materials such as glass, stainless steel and...
Experimental investigation and Mohr‐Coulomb plasticity modeling of glass fragments from pre‐stressed glass panes
The numerical treatment of the residual load-bearing behaviour of laminated glasses (LG) is currently a much-noticed topic, although there are only few approaches for an accurate representation of the experimentally observed behaviour. If one tries to characterize the...
Connecting Artificial Intelligence and Structural Glass Engineering–Overview, Potentials and Case Studies
This paper introduces the Artificial Intelligence (AI) technology to structural glass engineering and glass industry audience. The first part of the paper is concerned with lying nomenclature and theory foundation of AI and its subclasses of Machine and Deep Learning...
Multi-objective loss balancing for physics-informed deep learning
Physics Informed Neural Networks (PINN) are algorithms from deep learning leveraging physical laws by including partial differential equations (PDE) together with a respective set of boundary and initial conditions (BC / IC) as penalty terms into their loss function....
Konstitutive Modellierung der Bruchfragmente thermisch vorgespannter Gläser innerhalb der Plastizitätstheorie–Experiment und Numerik
Die numerische Modellierung des Tragverhaltens von Verbundglas (VG) im vollständig gebrochenen Zustand ist hochaktuell. Allerdings gibt es dafür derzeit nur wenige Simulationsansätze. Neben den Eigenschaften der polymeren Zwischenschicht und der Adhäsion zwischen Glas...
The In-plane Expansion of Fractured Thermally Pre-stressed Glass Panes
The present paper is concerned with deriving simplified design equations and charts for modeling in-plane expansion of fractured thermally pre-stressed glass panes using the method of equivalent temperature differences (ETD) together with a thermal expansion analogy...
Automated Quality Control of Vacuum Insulated Glazing by Convolutional Neural Network Image Classification
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 glazing units of equivalent performance. The VIG is a double-pane configuration with a...
Deep Learning based method for the prediction of the buckling resistance of SHS and RHS
This paper proposes a data-driven and deep learning based model for the prediction of the buckling load of square and rectangular hollow sections (SHS and RHS) based on Finite Element Method (FEM) results of the local buckling effects. The data was elaborated during...
Struct-MRT: Immersive Learning and Teaching of Design and Verification in Structural Civil Engineering using Mixed Reality
Our goal is to transform traditional paper-based instruction into an immersive lesson. This paper presents the conception, workflow and deployment of two MR applications for verification of typical yet geometrically complex structural members: a reinforced concrete...
Semi‐probabilistische Bemessung tragender Silikonverklebungen mit Teilsicherheitsbeiwerten
Zur Dimensionierung geklebter Silikonbauteile wird gemäß ETAG 002 ein globaler Sicherheitsbeiwert von 6 gefordert. Die Hintergründe dieses Sicherheitsfaktors sind nicht näher bekannt, allerdings gelten neben materiellen Unsicherheiten auch Modellierungsfehler infolge...
Simulation von Verbundsicherheitsglas aus Einscheibensicherheitsglas im gebrochenen Zustand
Die numerische Behandlung des Resttragfähigkeitsverhaltens von Verbundgläsern (VG) stellt aktuell ein vielbeachtetes Thema dar, obwohl derzeit nur wenige Ansätze für eine zutreffende Abbildung des experimentell beobachteten Verhaltens existieren. Dieser Beitrag...
Semantic segmentation with deep learning: Detection of cracks at the cut edge of glass
In this paper, artificial intelligence (AI) will be applied for the first time in the context of glass processing. The goal is to use an algorithm based on artificial intelligence to detect the fractured edge of a cut glass in order to generate a so-called mask image...
Experimental and numerical investigations on glass fragments: shear-frame testing and calibration of Mohr–Coulomb plasticity model
The numerical treatment of the residual load-bearing behavior of laminated glasses (LG) in the post-fractured state is highly topical. Nevertheless, currently only few numerical approaches for an accurate representation of the experimentally observed behavior are...
Semi-probabilistic design of silicone adhesive joints: A Eurocode-compliant approach using the finite element method
This paper deals with the application of the semi-probabilistic design concept (Level I, DIN EN 1990) for structural silicone adhesives. First, background information on the safety theory and the general framework of the Eurocode for the derivation of partial material...
Statistische Charakterisierung der Verteilung der Druckzonentiefe vorgespannter Gläser
Due to varying production conditions, the thermal tempering process of glass is not fully homogeneous. This results in local differences in the residual stresses. In order to determine the statistical distributions of characterizing quantities of the residual stress...