G.A. van Nederveen
Please Note
14 records found
1
Purpose – This study aims to automate the visual inspection of piling sheets in water channel construction using artificial intelligence (AI). By employing image classification and object detection techniques, the research focuses on extracting and analysing geometric features to enhance the accuracy and efficiency of the inspection process. It also addresses key challenges associated with the unique characteristics of construction materials and the limited variability of available inspection datasets. Design/methodology/approach – Convolutional neural networks (CNNs) with varying complexities are employed for image classification, across four and six classes, and for object detection of piling sheets in water channel environments. A dataset provided by Witteveen + Bos is preprocessed to generate training sets, and the CNN architectures are optimized for enhanced performance. The accuracy and efficiency of the proposed models are evaluated and compared against traditional manual inspection methods. Findings – The AI-driven approach significantly reduces processing time, evaluating 40, 000 images in just 11.9 h, compared to approximately one month using manual assessment. The 4-class classification model achieves an accuracy of 96%, while the 6-class model attains 72%. The object detection model produces a mean average precision (mAP) of 79%. These results meet the performance standards set by the Dutch company Witteveen + Bos, which demonstrate the effectiveness of AI in automating the inspection of piling sheets. Originality/value – This study introduces a novel AI-based approach for assessing piling sheets, demonstrating substantial improvements over traditional inspection methods. It introduces a systematic evaluation of various CNN architectures and hyperparameters to optimize the models specifically for piling sheet inspection rather than relying on off-the-shelf solutions. The use of CNNs for both image classification and object detection adheres to relevant Dutch engineering standards. Notably, the reduction in processing time, from one month to around 12 h, represents a major advancement in the efficiency of civil engineering inspections.
IMAP-WFO
A holistic optimization tool for bottom fixed offshore wind farm design and control
Facing circular transition challenges, building circularity should be evaluated in the early design phase to reduce the risks of circular and environmental performance problems found in later project phases. However, due to the current design workflow, such practice is hindered because there is not enough information to evaluate building circularity in detail in the early design phases. An improved workflow to emphasize circularity more in the early design phase is thus needed. This research explores the current workflow and designs an improved workflow by developing an automated decision support system to assess early design phase building circularity with limited available information, aiming to improve the working efficiency and efficacy. This automated system helps in data-driven decision-making by integrating different data sources and presenting the calculated results interactively with business intelligence interfaces. The interfaces involve different types of evaluations based on the data availability in both schematic design and detail design sub-phases. It also visualizes the data quality and future scenarios. This system has been designed based on interviews and literature studies, and verified and validated with practitioners. This study serves as a starting point to rethink the workflow to improve circularity with currently available technology.
...
This paper evaluates experiences with applying a linked data approach for coping with the many challenges for information management in asset management from the perspective of National Road Authorities (NRAs). As influential players, NRAs are often the initiators of innovation in the civil infrastructure sector. In this paper we focus on specifying the information standards applied by NRAs, using a hybrid, semantically enhanced linked data approach. The linked data approach originates from the World Wide Web Consortium and can be used for modelling, storing, linking and retrieving road data; integrating existing asset management software applications and giving rise to new innovative software functionalities. It is called a ‘hybrid’ approach because it also incorporates and reuses existing non-linked data information standards originating from the worlds of Building Information Modelling (BIM), Geospatial Information Systems (GIS) and Systems Engineering (SE).
Understanding effects of BIM on collaborative design and construction
An empirical study in China
In principle, Building Information Modelling (BIM) should provide a basis for infrastructure information management during the whole life-cycle. In practice however, the use of BIM is normally limited to the design and construction phases. It seems that the use of BIM information in other life-cycle stages requires significant changes in the way BIM models are developed. In order to explore this issue, three different approaches for integration of BIM and life cycle information management are discussed, illustrated by three projects: London Crossrail, the EU-project V-Con and an experimental project at Volker.