This project aimed to support the detection of risky excavation operations based on historical datasets of damages in the Netherlands. Jiarong Li developed, using XGBoost, a data-driven model that predicted the likelihood of damage occurring in an excavation polygon. The Dutch agency Kadaster uses such polygons to exchange data on utility locations between network owners and excavator operators.
The machine learning model had a satisfactory performance with an AUC-ROC score of 0.821 and a balanced accuracy of 0.743.
Read More
This study aims to predict the likelihood of overshooting costs in utility streetworks projects, using historical project data and open datasets.
Read More
The Smart Utility Registration project explored the generation and the processing of 3D models of open trenches where new utilities were constructed. The method developed to generate 3D models facilitates the location and registration process of underground utilities. This brings the philosophy closer by to collect “from the Trench and store it directly in GIS”.
Read More
This study focuses on translating the underground spatial impact of redevelopments in public space, related to heat transition, electric grid upgrading, and climate resilience.
Read More
Utility lines can be extracted from point clouds to support further 3D modelling and mapping. Doing this manually is time consuming, Jorn Kruiper investigated how to use machine learning for this task.
Read More
Therefore, Dutch law (WIBON) mandates practitioners to reduce the uncertainty in the information about the subsurface situation through the process of utility surveying. One of the most promising non-disruptive methods is the Ground Penetrating Radar (GPR). GPR is a geophysical method that uses electromagnetic waves to investigate the subsurface. This study aims to explore, explain and support the decision making between trial trenches and GPR as a utility surveying method by developing, implementing and evaluating a Decision Support Tool.
Read More
To scale up city district heating construction projects, processes need to be developed and reliable. Currently teams largely rely on experience and improvisation, making them skilled in troubleshooting, but less efficient in planning and anticipating disruptions. This thesis has explored anticipation and containment through the lens of HRO
Read More
Smart Utility Registration aims to develop a method for scanning trench data in more automated ways. It mobilizes off-the-shelf (preferably open sources) technologies to register deployed cables/pipelines. Currently, this process is laborious and involves many different workers, while new technology might enable direct registration by the jobsite crew.
Read More
Utiilty construction projects make the transition from being supported by only 2D towards 3D information models. Currently, however, no means exists to support the specification of both semantic as visual information for such networks. The goal of this study therefore to develop a Level of Development (LOD)-framework to support this emerging practice.
Read More
This project ran from 2019-2021 and resulted in a prototype Decision Support System, which provides decision-makers with insight in the optical fiber deployment process as well as the results of operational changes they may wish to make
Read More
This project developed a roadmap that captures developments that influence subsurface vocational education, and a prototype e-learning training for field workers that intend to apply the ground penetrating radar for utility mapping (which is a tool that is not applied in the Netherlands at standard practice).
Read More
This project is aims to validate the developed CityGML Utility ADE Operations and Maintenance data model. To this end Federico encoded the UML diagram (concept model) and implemented this as relational database tables in a PostGreSQL and PostGIS environment.
Read More
This study explores the state-of-practice in 3D modelling at a mid-sized Utility Contractor.
Read More
Collaboration with Australian Pipeline Sector. Assessing the feasibility and effectiveness of pipeline intrusion avoidance solutions and providing context-specific decision support for selection.
Read More
Although the advent of GPR started in the field of geoscience, it is gradually utilized in civil engineering disciplines. GPR data quality depends on various software, hardware, and other factors. The main aim of the project is to develop a GPR validation method to find out under what condition it can successfully detect specific types of utility and what is the accuracy, reliability, and repeatability.
Read More
Traditionally, sewer inspections are conducted by direct access to the pipes, and where possible by visual inspections. In addition to being a tedious and cumbersome job, visual inspections do not always deliver the desired results. In the TISCALI project, research is being done to more efficient and less error prone inspection methods.
Read More
In the project IMKL 2.0, four showcases have been developed to show how the data that is gathered according to the new IMKL2.1 protocol can be used for visualising uncertainties and risks.
Read More
With the introduction of cleaner fuels for vehicles and the arrival of electric cars, also a need for the accompanying charging infrastructure has come into existence. At this moment, charging facilities are mostly placed in the shape of a charging point. Placement often happens after a private e-driver asks for it. With the increasing amount of electric cars, the question if the current method will still work in the future. The goal of this research has therefore been: to develop a future-proof, universally applicable method for the development of charging infrastructure for electric cars in small and medium-sized municipalities in urban areas.
Read More
While digging test trenches is relatively conventional, is the reasoning concerning the locations mostly implicit, unclear en not documented. This project is about improving the decision process for the selection of the locations of test trenches.
Read More