The growing need for automation in construction requires seamless integration of Building Information Modeling (BIM) and robotics. This study examines how BIM-based planning supports automating structural shell construction using a cable-driven parallel robot (CDPR). A six-phase methodology—covering data identification, classification, standardization, attribution, export, and validation—was tested through a use case. The approach ensures accurate embedding of geometric, material, and structural properties in the BIM model and their transfer to the robotic system via the Industry Foundation Classes (IFC) standard. Findings show that BIM-based automation enhances precision, boosts productivity, and helps address labor shortages in construction.
Demolition remains the dominant practice at the end-of-life stage, primarily due to its immediate economic advantages. Transitioning from demolition to deconstruction requires a shift in focus toward meeting customers' needs in the second-hand market. Therefore, the present study proposes a customer-centric deconstruction assessment model to enhance deconstruction planning. The research followed a three-stage methodology: (i) analyzing the attributes of existing deconstruction models; (ii) identifying the requirements of potential customers; and (iii) developing a knowledge graph model. The proposed model, which focused specifically on wood-based products, demonstrated its practical applicability by effectively matching products with suitable customers across five test scenarios.
IFC data has become the general building information standard for collaborative work in the construction industry. However, IFC data can be very complicated because it allows for multiple ways to represent the same product information. In this research, we utilise the capabilities of LLMs to parse the IFC data with Graph Retrieval-Augmented Generation (Graph-RAG) technique to retrieve building object properties and their relations. We will show that, despite limitations due to the complex hierarchy of the IFC data, the Graph-RAG parsing enhances generative LLMs like GPT-4o with graph-based knowledge, enabling natural language query-response retrieval without the need for a complex pipeline..
Extracting shareable knowledge concerning design-related issues from construction project documentation enables the assessment of design quality and, more broadly, improvement across the industry. This study proposes a solution to automate information extraction from inspection reports in construction industry processes, with a specific focus on those produced by design reviews often conducted before the tendering phase. The approach is based on LLMs, prompt engineering, and few-shot learning. We evaluated three LLMs (GPT-4o, Mistral, and Llama 3) across four-shot scenarios, assessing their performance, computational cost, and time. Results show that GPT-4o achieved the highest performance while ranking second in computational cost and time.
The Architecture, Engineering, Construction, and Operation (AECO) sector needs to shift from linear to Circular Economy to address environmental challenges and promote sustainability. This study critically assesses the Level(s) framework through two-part methodology: (1) procedural analysis of Macro-Objective 2 ("resource efficient and circular material life cycle") and its indicators, and (2) a simplified numerical case-study. It integrates the Level of Information Need (LOIN) to define Information Requirements revealing gaps in automation and precision. Findings highlight the need for digital tools and standardized data flows to improve circularity assessments. The study provides actionable insights for refining Level(s) implementation and stakeholder collaboration.
Accurate indoor temperature prediction models are essential for smart building control systems. Gaussian Process Regression (GPR) is widely used due to its prediction accuracy and error guarantees. However, real-life applications face challenges, including GPR’s poor scalability with large datasets and the manual selection of input features. This study employs LoG-GP, a distributed GPR method, for continuous model updating and fast predictions.The wrapper method is used for sensitivity analysis to identify optimal input features for various building types. A metadata-driven workflow is proposed to automate feature selection and dataset retrieval, achieving computationally efficient, accurate, and adaptable models tested on new buildings.
Regeneration, which aims at climate positivity, is not yet considered in building production research, let alone implemented in praxis (except isolated cases). In this paper, we start investigating its potential in building production, especially focusing on the relevant human-data interactions (HDI) around building processes. We therefore review the recent literature on regeneration and HDI within urban planning, architectural design, and business model innovation, and use the phenomena construction methodology to conceptualize basic HDI dimensions in regenerative building production. Our results show that HDI can be crucial for transforming building production processes and management, as well as upskilling labor, towards regeneration.
In construction projects, frequent changes to time planning result from unforeseen events, impacting both timing and scope of information exchanges (IE). Currently, IE planning and production planning are performed independently with limited integration between the two, leading to inefficiencies when changes are needed. This study proposes a unified approach facilitating Level of Information Need (LOIN) to systematically identify and link to required IEs for the production phase. The mapping was co-developed with and evaluated by industry professionals to ensure practical relevance. Integrating LOIN-driven IE mapping into production planning enhances responsiveness to schedule changes by providing structured guidelines for information delivery.
Achieving high-level fire safety performances in building design requires addressing complex challenges to safeguard occupants. This paper presents a BIM-integrated framework for validating building fire safety designs, combining fire simulations tools to assess occupant safety, quantified through a KPI. The KPI facilitates results’ visualization within the BIM environment, enabling even the identification of critical areas. The framework has been tested on a pilot case, to demonstrate its ability to assess compliance with fire safety objectives and to enhance design flexibility. This approach bridges simulation and design processes, providing stakeholders with actionable insights to validate and improve building fire safety strategies.
An international, standardised product catalogue format representing parametric and variable product data, simplifying their exchange and integration, is to be developed. We map product data requirements in IFC files by leveraging lessons from existing national standards to enhance their parametric modelling capabilities. Using a case study, we evaluate the implementation of property value dependencies and valid combinations using a product catalogue example. Significant is the extension of data linking and value calculation in IFC, which integrates control structures. Of the three proposed implementation approaches, we favour the code-based solution to support the integration of parametrics in IFC for different applications.
