Search

Building Information Modelling (BIM) is becoming increasingly prevalent in infrastructure asset management, as it facilitates current management practices. This includes the construction of BIM models for roads, rails, bridges, tunnels etc. Bridges are particularly challenging to digitalize due to their complex geometry. The manual construction of bridge BIM models based on 2D plans is hardly feasible due to the related workload. Given the recent advancements in the field of 3D surveying and artificial intelligence, new possibilities emerge for an automated generation of as‐is bridge BIM models. This paper presents a novel, modular framework for the automatic processing of point clouds into as‐is BIM models, based on a fusion of artificial intelligence and heuristic algorithms. Representative bridge element datasets were provided to train neural network. Trained neural network can identify elements of a bridge, which are further processed using geometric algorithms into surface and solid bridge elements. This result can be additionally enriched with semantic information from existing databases. The final BIM models are exported in the standardized vendor‐free Industry Foundation Classes (IFC) format. [ABSTRACT FROM AUTHOR]

As the global manufacturing industry entered its fourth revolution (4IR, or Industry 4.0), innovations such as robotics, automation, and artificial intelligence are set to take over and improving the global industries. As the number of active industrial robots worldwide is increasing every day in different applications and industries automation continues to create new types of robots with improved utility and function. In the AAC Industry, these innovations already took place for some time in different process phases and applications such as oiling, autoclaves stacking pins, handling, packing, and so forth. Through this research, advantages commonly attributed to automation and robotics include higher production rates and increased productivity, more efficient use of materials, better product quality, improved safety, shorter workweeks for labor, and reduced factory lead times. Especially reduced scrap and waste through improved accuracy, increased efficiency, and operation around the clock could be emphasized. Based on the accumulated experience of WKB Systems GmbH in the field of the forging industry, selected models, real‐life application case studies, and implementation of different robotics in the AAC industry are discussed in this paper. These examples such as linear robots for autoclaves stacking pins, articulated robots for AAC packing and sorting line, and hybrid systems for handling and packing AAC insulation boards are studied in detail. [ABSTRACT FROM AUTHOR]

This paper describes a technological solution for digital condition inspection, which includes the entire process, starting with on‐site image acquisition upto the IFC‐4‐compliant result. In detail, the process includes the following steps: – Digital image recording of the entire object on site– Automated creation of a 3D model from the image data in the form of a textured scatter plot– Generation of a BIM geometry model from the scatter plot– Fully automated damage detection in the original images using AI (accurate to the pixel)– Correct location of the damage on the 3D model as a polyline and linking the damage with the associated damage information in a database (e.g., crack length, crack width, damage area)– Fully automated creation of an IFC‐4 compliant damage model. [ABSTRACT FROM AUTHOR]

The latest successes in AI have been largely driven by a paradigm known as Foundation Models (FMs), large Neural Networks pretrained on massive datasets that thereby acquire impressive transfer learning capabilities to adapt to new tasks. The emerging properties of FMs have unlocked novel tantalizing applications for instance enabling the generation of fluent text and realistic images from text descriptions. The impact of FMs on technical domains like civil engineering is however still in its infancy, owing to a gap between research development and application use cases. This paper aims to help bridge this gap and promote adoption among technical practitioners, specifically in visual inspection applications for civil engineering. For that we analyze the requirements in terms of data availability making particular use cases amenable to the pretraining/fine‐tuning paradigm of FMs, i.e. situations where labeled data is scarce or costly, but unlabeled data is abundant. We then illustrate proof‐of‐concepts workflows using FMs, in visual inspection applications. We hope that our contribution will mark the start of conversations between AI researchers and civil engineers on the potential of FMs to accelerate workflows supporting vision tasks for maintenance inspections and decisions. [ABSTRACT FROM AUTHOR]

Concrete is a mass commodity with more than approx. 250 Mio. batches of concrete being produced every year in Europe alone. Despite this enormous repetition rate, both the quality inspection of the concrete raw materials as well as of the mixed concrete are still primarily batch‐based, relying on manual processes, thus hindering the application of modern process control schemes. The reasons for this lack are on the one hand to be seen in the lack of suitable sensor technologies and on the other hand in missing control algorithms. The paper at hand gives an overview on the current state of the art sensor technologies for both raw material as well as concrete properties measurement. Further, it outlines a pathway towards an online concrete process control. [ABSTRACT FROM AUTHOR]

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 den Schallschutz. Eine zuverlässige Abschätzung der Schalldämmeigenschaften beliebiger Glasaufbauten ist aufgrund der Komplexität experimenteller Tests oder numerischer Simulationen zeitaufwendig und kostenintensiv. Daher wird in dieser Arbeit ein maschineller Lern‐Ansatz zur Prädiktion der akustischen Eigenschaften beliebiger Glasaufbauten vorgestellt. SOUNDLAB AI Tool – Machine learning for the determination of the weighted sound Insulation Value. Modern architecture strives for transparent building envelopes and, in particular, for sustainable and physically adequate glass facades. Typically, glass facades are designed to meet a variety of objectives, one of which is to satisfy sound insulation requirements. Reliable estimation of the sound insulation properties of arbitrary glass assemblies is time consuming and costly due to the complexity of experimental tests or numerical simulations. Therefore, this paper presents a machine learning approach for predicting the acoustic properties of various glass setups. [ABSTRACT FROM AUTHOR]

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 (ML/DL), elaborating the specific needs and requirements for the application in a structural glass context. A subsequent section explores applications of AI for different subjects within the production and quality assessment of glass products as well as the design, verification and monitoring of facades and glass structures. This paper presents successfully conducted industry projects by the authors, which are: supervised ML for material parameter identification of polymeric interlayers used in laminated glass, the prediction of sound insulation properties of insulation glass units and glass laminates and the application of computer vision DL methods to image classification of the Pummel test. A visionary outlook highlights how to use AI for future generative design and verification of glass structures for rapid collaborative prototyping. The summary and conclusion section wraps up the main findings for the applicability and impact of AI for the presented structural glass research and industry problems. This paper shows, that already by today in many cases AI, data, software and computing resources are already in place to successfully implement and conduct AI projects in the glass industry and structural glass engineering practice. [ABSTRACT FROM AUTHOR]

In Zukunft werden beim Fassadenentwurf neben den Anforderungen an die Funktion als thermohygrische Barriere, dem Sonnenschutz und ansprechend‐ästhetischem Design weitere Punkte zum Nutzerkomfort oder der ‐interaktion mit der Fassade im Fokus stehen. Dieser Beitrag zeigt auf, wie innovative adaptive Steuerungen der Fassade unter Verwendung von Künstlicher Intelligenz (KI) konzipiert werden, um die sich ergebende Mehrzieloptimierung zu bewältigen, indem Modelle der KI mit dem digitalen Zwilling der Fassade zu einem cyber‐physikalischen Regelkreis mit Benutzer‐Feedback verbunden werden. Am Beispiel der Fassade des sich im Bau befindlichen Glass Competence Center der TU Darmstadt wird ein derartiges Fassadensystem vorgestellt. Applications and Potentials of Artificial Intelligence to Building Envelopes. Modern facades act as barrier against environmental influences but have to fulfill additional demands on functionality and appealing design. In future however, the design of facades will not only focus on the mentioned aspects but will have to account for user comfort and interaction with the facade. Hence, this article investigates the conceptual design of innovative adaptive control systems for facades using Artificial Intelligence (AI) in order to cope with the arising multi‐objective optimization problem. Models of AI are combined with a digital twin of the facade to form a cyber‐physical control loop with user feedback. Using the facade of the Glass Competence Center of the Technical University of Darmstadt as an example, such an intelligent and adaptive facade system is presented within this paper. [ABSTRACT FROM AUTHOR]

The scour phenomenon around piles is regarded as one of the main causes of serious damages to the pile‐supported structures such as bridges, jetties, wind turbines, and offshore platforms threatening their stability and sustainability in the long term. Thus, accurate forecast of scouring is vital for the design and operation of these structures. In this paper, three artificial intelligence‐based techniques including support vector regression, artificial neural network and random forest were applied to predict the local scour depth around pile groups. An experimental dataset is collected and used to construct the machine learning‐based models. The sediment number, shields parameter spacing, Keulegan‐Carpenter number and pile Reynolds number were used as input variables for the model development. Results assessment indicate that the artificial neural network model anticipated the highest performance among the three machine learning based models, with coefficient of determination of 0.97, and root mean square error of 0.15. [ABSTRACT FROM AUTHOR]

In the era of internet and robots, sophisticated devices and real‐time simulation, the construction sector remains highly dependent on manual labor which is also the main source of delays, lack of quality, and human injuries. The rapid development in technological areas such as mechatronics, computers, sensors, programming, human interfaces and artificial intelligence (AI) – offers huge potential for modern applications. Nowadays, additive manufacturing is rapidly growing, and it could offer efficient solutions for steel construction since it can be executed in any shape and scale. There are a few solutions in additive manufacturing technologies, which can process materials and produce components. However, there is a gap in the market for capacity to link the processed material conditions and characteristics to the production parameters in real‐time. Real‐time and cognitive re‐planning of the process parameters becomes significantly important when components with large‐scale and complex shapes are considered. This paper presents a summary of existing technologies for automatic construction process, it identifies the critical issues which hamper the adoption of new technologies in construction and describes an additive manufacturing solution currently being implemented. [ABSTRACT FROM AUTHOR]

In the era of internet and robots, sophisticated devices and real‐time simulation, the construction sector remains highly dependent on manual labor which is also the main source of delays, lack of quality, and human injuries. The rapid development in technological areas such as mechatronics, computers, sensors, programming, human interfaces, and artificial intelligence offers huge potential for modern applications. Nowadays, additive manufacturing is rapidly growing, and it could provide efficient solutions for steel construction since it can be executed in any shape and scale. There are a few solutions in additive manufacturing technologies, which can process materials and produce components. However, there is a gap in the market for capacity to link the processed material conditions and characteristics to the production parameters in real‐time. Real‐time and cognitive re‐planning of the process parameters becomes significantly important when components with large‐scale and complex shapes are considered. In steel construction, material should comply with strict requirements in terms of its strength and ductility. Hence, it is necessary to characterize the material properties before their application in construction. This paper presents material characterization for WAAM fabricated steel coupons, considering different directions with respect to the deposition direction. [ABSTRACT FROM AUTHOR]

Designing thin‐walled structural members is a complex process due to the possibility of multiple instabilities. This study aimed to develop machine learning algorithms to predict the buckling behavior of thin‐walled channel elements under axial compression or bending. The algorithms were trained using feed‐forward multi‐layer Artificial Neural Networks (ANNs), with the input variables including the cross‐sectional dimensions, the thickness, the presence and location of intermediate stiffeners, and the element length. The output data included the elastic critical buckling load or moment, as well as a modal decomposition of the buckled shape into the pure buckling mode categories: local, distortional and global buckling. The Finite Strip Method (FSM) and the Equivalent Nodal Force Method (ENFM) were used to prepare the sample output for training. To ensure the accuracy of the developed algorithms, the ANN models were subjected to a K‐fold cross‐validation technique and featured optimized hyperparameters. The results showed that the trained algorithms had a remarkable accuracy of 98% in predicting the elastic critical buckling loads and modal decomposition of the critical buckled shapes. [ABSTRACT FROM AUTHOR]

Artificial intelligence based models, namely using machine learning techniques, have been widely used in different engineering fields, providing accurate, easy‐to‐apply and fast assessment tools to predict the mechanical behaviour. These models not only can be used to increase the inference about the mechanical phenomena of a certain problem but also, for example, allow to quantify the capacity of steel beams, as studied in this work. For that purpose, different models were developed and trained using machine learning algorithms, and it is demonstrated that the capacity predicted by these models surpass the accuracy given by existing analytical models, when using the results obtained with the finite element method as the baseline. [ABSTRACT FROM AUTHOR]

Copyright of CE/Papers is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)