The work described herein discusses the case-study implementation of low-cost, vibration-based technologies for the assessment of roadway networks at point and street level, using smartphone sensors and participatory sensing. The utilized technology aims for (1) the provision of a low-cost, yet accurate, alternative to high-priced specialized equipment for assessing roadways, and (2) the continuous sourcing of data by use of participatory sensing. The study utilized two hybrid cars serving as probe-vehicles, about two hours of roadway surveying, and about 600K sensor-collected datapoints. The underlying spatiotemporal data analysis is utilized for the prioritization of O&M actions by municipalities and bus operators.
Manual creation of as-built models for Finite Element Method (FEM) analysis is labour-intensive and error-prone, hindering effective reuse of building structures. SCAN-to-FEM technology automates the capture and analysis of building stock, lacking efficient methods for converting point cloud or photogrammetry data into analytical FEM models of skeleton structures. This paper introduces Scan2Beams, a framework for transforming 3D photogrammetry data of industrial buildings into parametric structural meshes of the load-bearing structure. Validated through a use case, Scan2Beams enables integration of point cloud data into structural analysis workflows and eliminates manual modelling. Future research includes automated joint behavior recognition and retrofitting suggestions.
Bridges are associated with extensive data throughout their lifecycle, particularly during design and operational phases. Existing bridge data is stored in various national and international databases. This data can consist of geometric parameters, structural details, and environmental conditions and is often available in non-machine-readable varying file formats. These inconsistencies hinder performance evaluations and AI applications. Ontologies based on the Web Ontology Language (OWL) could offer a solution for harmonizing this data. This paper proposes an ontology-driven approach that integrates open-source data for advanced semantic querying, enhancing consistency and enabling the potential of informed decision-making in bridge design through a harmonized, machine-interpretable model.
Heating and cooling account for 50% of the EU's energy consumption, with over 70% sourced from fossil fuels. Decarbonizing residential heating by electrifying systems presents challenges such as increased demand and grid instability. Energy storage systems (ESSs) offer a solution, but tools for selecting optimal ESSs at the neighborhood scale are lacking. This paper introduces a decision-support method that evaluates ESSs using dynamic neighborhood-level energy demand simulation. A case study in Eindhoven, Netherlands, demonstrates how this approach helps stakeholders make informed decisions, enhancing grid stability and promoting effective energy storage integration for residential decarbonization.
With the increasing frequency of extreme weather events such as typhoons, the stability and resilience of the inter-city population mobility network is facing serious challenges. The study shows that the typhoon had a significant impact on the characteristics and patterns of the population mobility network in the YRD. First, during the typhoon, the network size and density decreased, long-distance mobility decreased and showing the characteristics of “small world”. Second, after the typhoon landfall, the population inflow to the central city dropped significantly. Then, network connectivity declines during the typhoon, but modularity increases.
Manual classification of Bill of Quantities in construction procurement is labor-intensive and error-prone, limiting efficiency in bidding and contract management. No structured datasets for BOQ classification exist in the literature, limiting automation routes. To address this, we present a labeled dataset of BOQ tasks from Portuguese public procurement contracts, structured for multilabel classification. Synthetic augmentation using GPT-4o Mini and cosine similarity-based batching mitigated class imbalance, expanding training data to 23,542 examples per fold (3 folds). This dataset, provides a Portuguese construction corpus and enables Artificial Intelligence-driven BOQ task classification, fostering procurement automation and expanding automation routes in construction contract analysis.
Monitoring and predicting indoor PM2.5 levels is critical for ensuring healthy indoor environments. However, the integration of real-time data acquisition and instant PM2.5 forecasting within digital twin systems remains underdeveloped in practical applications. This study presents a CNN-BiLSTM hybrid model for forecasting indoor PM2.5 concentrations over a 72-hour horizon. In a real-world case study, the model achieved a root mean square error (RMSE) of 4.884 μg/m3 and a Mean Absolute Error (MAE) of 4.092 μg/m3. The integration of the model into a digital twin platform demonstrates its potential to enhance indoor air quality management through real-time, data-driven interventions.
The creation of BIMs of existing structures has been widely researched, yet mainly covering visible components. For a structural assessment of concrete components, the steel reinforcement contained in the component is as important as the outer dimensions. Ground penetrating radar (GPR) can be used for steel reinforcement imaging. This study will propose a methodology to align 3D reinforcement data with a BIM model, provide a 3D reconstruction of the rebar and present it in an open BIM format. The method will be rigorously evaluated on the basis of two concrete test samples with known location and diameter of the reinforcement.
This paper proposes a socio-technical approach for the development and implementation of Construction Digital Twins (CDTs), extending beyond the dominant technocentric perspective. Grounded in insights from an industrial case study, this paper conceptualises CDTs as socio-technical systems, emphasising the interplay among people, process and technology across six proposed lifecycle stages of CDTs: Define, Design, Implement, Assess, Refine and Decommission. The paper also examines human-CDT interactions during the implementation phase, highlighting their mutual influence and the unique requirements posed by the dynamic, socially complex and unpredictable nature of construction projects.
