Amid global climate change challenges, the construction industry faces an urgent  transition from a linear production model to a Circular Economy (CE). Initiatives  and recommendations in Dutch transition roadmaps and literature predominantly  focus on ensuring a future circular built environment, while lacking concrete actions on leveraging the existing assets for reuse. Dutch CE roadmap timelines  and interventions are developed based on Material Flow Analysis (MFA) studies with highly uncertain data input, this uncertainty impacts either environment or  economy with inaccurate interventions on the CE-transition. Secondly, the Replacement & Renovation (R&R) task of civil structures poses a threat for the  industry due to the limitations of capital, contractor capacity, and material  resources required to facilitate this peak. There is currently a lack of centrally  stored high-quality physical asset data available at public organisations. This data is essential in effectively managing the decommissioning peak and reduces risk for reuse realization. Lastly, Asset Management (AM) is transitioning towards a 3D-centralised strategy in line with Building Information Modelling (BIM) and  digital twins, while existing assets are still in 2D with often incomplete and  fragmented data documentation. Consequently, a large data quality gap is forming between new and existing assets. This led to the research question: How can centrally stored, quantified, and visualised asset data of existing infrastructure impact the CE-transition, bridge R&R-task efficiency, and AM practices? An upgrade towards 3D-BIM is required for existing assets to bridge this data gap. In doing so, facilitate higher quality- and more accessible asset specific  information that can be used in reusability scanning and structural assessments,  material quantification for CE-transition roadmap accuracy, and numerous AM  benefits. The costs for upgrading the existing assets using manual modelling or  3D scanning technology are currently too large to justify. An opportunity was  identified for modelling 3D-BIM of existing beam & slab bridges from 2D drawings using a modular approach to Parametric Engineering, aiming to reduce the investment threshold, and accelerating the digitization transition. Preliminary testing executed by the author showed a potential for 50-80% reduction in modelling efforts compared to conventional modelling practices with a volume  accuracy of >97%. The prototype calls for further development, validation, and similar efforts for other infrastructure types. The tool also showed potential for 3D structural & reusability assessments, reinforcement approx., and ptioneering & circularity scoring for the design phase. To put the tool’s use in perspective, a roadmap towards 3D centralized AM and a reuse economy was developed for AM.

Various tasks in the construction industry are tedious due to the high amount of repetition or time-consuming nature. In recent years Deep Learning within computer vision has made it possible to automate various tasks using images. The Hoofdvaarweg Lemmer-Delfzijl has been assessed using images and a pointcloud. The images were being worked with two employees over a month. This is time-consuming and there are a lot of images to go through. Our project statement is thus: Develop a tool using computer vision techniques to reliably detect problematic corrosion on piling sheet within 4-5 months to understand what the state is of this topic for asset managers. We first start with an analysis in which we looked at the existing the literature, the data, the existing methods and how Witteveen+Bos is assessing the images. We then set the requirements to which the algorithm should adhere to. Literature study has shown that most models, with data-sets of above 3000 images, achieve above 90% for both accuracy and mean average precision. Afterwards we start writing the algorithm and model testing various model structures as part of the synthesis procedure. The models are variating in structures, filters, depth, and augmentation. We created a classifier, of four and six classes, and an object detection algorithm and conducted various evaluation techniques. The four-class classifier performed better than the six-class classifier. This could be due to the six-class classifier being made up of less data, classes that are vague, parts of the data showing imbalance problems. An object detection algorithm was created to detect dimensional features to estimate the height above water and distance of the bumps. To convert the pixel distance to actual distance, we trained the model to detect a reference object. The object detector performed well, but did not meet the requirements we set. The dimension estimation provided can only provide a rough estimation. This may be the result of not every image, in the training set, contained a reference object. Creating the data-set was a tedious task and our data-set with two classes, took around eight hours to finish training. We can conclude that for image classification, the structure of the model and the trainable parameters play a role. The object detector can count elements, but the predicted bounding box is sometimes larger than expected. Some recommendations are to increase data and classes. A robust feasibility for Witteveen+Bos regarding AI. Repurposing the algorithm for progress monitoring and exploring the interoperability between software relevant for the manager.

The Architecture, Engineering, and Construction (AEC) industry is undergoing digital transformation to improve project performance and Building Information Modelling (BIM) is helping to achieve this objective. BIM is a comprehensive digital representation of a built facility with great information depth. BIM fosters collaboration across the construction supply chain however the benefits of collaboration are realised only in a relatively small number of BIM-enabled projects. Poor collaboration continues to be one of the major risks affecting BIM-enabled projects with misunderstandings, misinterpretation of data and increased rework. This is especially high in the design phase of construction projects because of the high BIM usage. This research aims to explore the most critical barrier to collaboration in BIM teams in the design phase of infrastructure projects and provide strategies to avoid the barrier in future projects. The most critical barrier in this research is defined as “the main issue that causes the occurrence of problems resulting in undesired outcomes”. For this objective, the case-study method is preferred. Three large infrastructure projects are studied and interviews were conducted with BIM teams to identify the barriers to collaboration in BIM teams. The data collected are analysed by comparing among cases and with literature. Why questions were asked until the main issue that led to the occurrence of problems is found. From the analysis, it is found that lack of guidelines and standards is the most critical barrier to collaboration in BIM teams in the design phase of infrastructure projects. To avoid this problem in future projects, the existing BIM-based design process is improved to work with ISO19650 standards along with strategies to achieve better results. To enable better collaboration in BIM teams, the process is automated using Business Process Management (BPM) software. The proposed strategies are validated with BIM teams for applicability in practice. To conclude, the proposed strategies help in solving the lack of guidelines and standards. It improves the BIM-based design process in infrastructure projects and leads to achieving better collaboration in BIM teams. This research benefits researchers as well as BIM teams. Researchers can validate the proposed strategies in real-life projects and BIM teams can improve their work practices by implementing the proposed strategies.