16 research outputs found
How large language models and artificial intelligence are transforming civil engineering
No full textLarge language models with artificial intelligence are transforming the way infrastructure projects are planned, executed and managed. Vishak Dudhee and Vladimir Vukovic of V-Lab say they are unlocking unprecedented efficiency and innovation in civil engineering.In civil engineering, where efficiency and precision are paramount, integrating large language models (LLMs) is proving to be a game-changer. These advanced artificial-intelligence (AI) systems are reshaping how infrastructure construction projects are planned, executed and managed, significantly improving productivity and project outcomes.The UK government’s National AI Strategy (HMG, 2021) recognises the immense potential of AI in enhancing resilience, productivity and innovation across various sectors.According to McKinsey (Chui et al., 2023), generative AI and other technologies can potentially automate work activities that currently occupy 60–70% of employee time
Coupling OpenModelica and GenOpt:Guidelines Version 2.1
Full text linkThe guidelines manual describes the steps for coupling Modelica modelling language based simulation environment OpenModelica and genric optimisation program GenOpt
Integration of Building Information Modelling and Augmented Reality for Building Energy Systems Visualisation
Full text linkBuildings consist of numerous energy systems, including heating, ventilation, and air conditioning (HVAC) systems and lighting systems. Typically, such systems are not fully visible in operational building environments, as some elements remain built into the walls, or hidden behind false ceilings. Fully visualising energy systems in buildings has the potential to improve understanding of the systems’ performance and enhance maintenance processes. For such purposes, this paper describes the process of integrating Building Information Modelling (BIM) models with Augmented Reality (AR) and identifies the current limitations associated with the visualisation of building energy systems in AR using BIM. Testing of the concept included creating and superimposing a BIM model of a room in its actual physical environment and performing a walk-in analysis. The experimentation concluded that the concept could result in effective visualisation of energy systems with further development on the establishment of near real-time information
Investigating Potential Alignments between Modelica Standard Library and SAREF Ontologies
No full textSimulation tools based on the Modelica language provide comprehensive modelling and simulation approaches for building energy systems. However, the simulation and optimisation of such systems are data-driven processes, lacking a common understanding of information structure within the process. This paper investigates the possible semantic alignments of the Smart Appliances REFerence (SAREF) ontology and its extension for building domain, SAREF4BLDG, with the Modelica Standard Library (MSL). Using the MSL, a residential heating system has been modelled in OpenModelica, an open-source modelling and simulation environment. Then, SAREF and its extension SAREF4BLDG semantic alignments to the MSL used to create the model have been assessed. A list of alignments has been proposed to expose semantic links for the residential Heating, Ventilation, and Air Conditioning (HVAC) system. Such alignments would allow for the semantic annotation of building energy system models and greater interoperability between modelling environments
Building Information Model Visualisation in Augmented Reality
No full textThe possibility of integrating building information in an Augmented Reality (AR) environment provides an effective solution to all phases of a building's lifecycle. This paper explores the integration of Building Information Modelling (BIM) and AR to effectively visualise building information models in an AR environment and evaluates the currently available AR tools. A BIM model of a selected office room was created and superimposed to the actual physical space using two different AR devices and four different AR applications. The superimposing techniques, accuracy and the level of information that can be visualised were then investigated by performing a walk-through analysis. From the investigation, it can be concluded that model positioning can be inaccurate depending on the superimposing method used and the AR device. Moreover, using the currently available techniques, only static building information can be superimposed and visualised in AR, showing a need to integrate data from Internet of Things (IoT) sensors into the current BIM-AR processes to allow visualisation of accurate and high-quality operational building information. A practical process and method for visualising and superimposing BIM models in an AR environment have been described. Recommendations to improve superimposing accuracy are provided. The assessment of type, quality and level of detail that can be visualised indicates the areas that need improvement to increase the effectiveness of building information's visualisation in AR
Superimposing Building Information Models in Augmented Reality
Full text linkAugmented Reality (AR) can enhance Building Information Modelling (BIM) by allowing architecture, engineering, and construction (AEC) professionals to visualise and refine building models. The possibility of integrating BIM model in AR environment provides an effective solution to all phases of a building’s lifecycle. To visualise digital information in the actual physical environment, BIM models are superimposed to the structure. The techniques used to superimpose the BIM models are either based on reference markers or QR codes, which are occasionally inaccurate. This paper reviews and analyses the BIM model superimposing techniques in AR. To describe and discuss different methods, a BIM model of an office room was generated in Revit and superimposed to the actual physical space using two different AR devices and four different AR applications. From the results obtained, it can be concluded that presented superimposing methods allow for overlaying of digital information, but model positioning can be slightly inaccurate depending on the superimposing method used and AR device. Any inaccuracy while positioning the BIM model reference markers or QR code can lead to inaccurate superimposing of the model. The recommended process and method for superimposing BIM in AR environment is documented
Superimposing Building Information Models in Augmented Reality
Full text linkAugmented Reality (AR) can enhance Building Information Modelling (BIM) by allowing architecture, engineering, and construction (AEC) professionals to visualise and refine building models. The possibility of integrating BIM model in AR environment provides an effective solution to all phases of a building’s lifecycle. To visualise digital information in the actual physical environment, BIM models are superimposed to the structure. The techniques used to superimpose the BIM models are either based on reference markers or QR codes, which are occasionally inaccurate. This paper reviews and analyses the BIM model superimposing techniques in AR. To describe and discuss different methods, a BIM model of an office room was generated in Revit and superimposed to the actual physical space using two different AR devices and four different AR applications. From the results obtained, it can be concluded that presented superimposing methods allow for overlaying of digital information, but model positioning can be slightly inaccurate depending on the superimposing method used and AR device. Any inaccuracy while positioning the BIM model reference markers or QR code can lead to inaccurate superimposing of the model. The recommended process and method for superimposing BIM in AR environment is documented
Decision Support in Algorithm Selection for Generic Optimisation
Full text linkThis paper presents the development of an algorithm-selection framework supported by a new intuitive user interface for the generic optimisation tool, GenOpt. The framework consists of an algorithm-selection flowchart to help identify relevant algorithms depending on the nature of the problem, followed by an algorithm-selection matrix which evaluates the algorithms’ suitability based on the user requirements. The algorithm selection framework acts as a decision support system to allow the user to select the most appropriate and effective optimisation algorithm for a given problem. Such a procedure improves decision-making, limits the algorithm selection errors and helps the user to achieve solutions closer to the Pareto optimum. The selection framework is supported by a user interface, developed in C++ and compatible with GenOpt, that allows users who do not have prior coding knowledge to use GenOpt successfully. The developed interface presents the user with the most relevant optimisation algorithms from those available in the programme. It allows the user to easily modify algorithmic variables in a user-friendly environment. The novelty of the approach is reflected in the built-in knowledge and intelligence in the pre-selection of optimisation algorithms, which are tailored to specific user-defined problems. This, consequently, improves the overall optimisation results by allowing the user to better understand the optimisation algorithm and its variables
Building Sensory Information in Augmented Reality: A Conceptual Framework
No full textThe Augmented Reality (AR) technology is rapidly evolving and presents a new innovative approach to overlay and visualise digital information in real physical environments. In construction, the use of AR technology is currently limited to the visualisation of static building information. This paper analyses the AR market trends and the current innovations in AR technologies and explores the possibility of visualising the dynamic building information through the integration of Internet of Things (IoT) sensors and Building Information Modelling (BIM). A conceptual framework for integrating BIM and sensory information for visualisation in head-mounted devices has been demonstrated. The availability of sensory information allows the user to visualise the new dimension in AR. Such a paradigm may lead to a new AR app that can expand the use of AR for sustainable and energy-efficient decision-making
Decision Support in Algorithm Selection for Generic Optimisation
Full text linkThis paper presents the development of an algorithm-selection framework supported by a new intuitive user interface for the generic optimisation tool, GenOpt. The framework consists of an algorithm-selection flowchart to help identify relevant algorithms depending on the nature of the problem, followed by an algorithm-selection matrix which evaluates the algorithms’ suitability based on the user requirements. The algorithm selection framework acts as a decision support system to allow the user to select the most appropriate and effective optimisation algorithm for a given problem. Such a procedure improves decision-making, limits the algorithm selection errors and helps the user to achieve solutions closer to the Pareto optimum. The selection framework is supported by a user interface, developed in C++ and compatible with GenOpt, that allows users who do not have prior coding knowledge to use GenOpt successfully. The developed interface presents the user with the most relevant optimisation algorithms from those available in the programme. It allows the user to easily modify algorithmic variables in a user-friendly environment. The novelty of the approach is reflected in the built-in knowledge and intelligence in the pre-selection of optimisation algorithms, which are tailored to specific user-defined problems. This, consequently, improves the overall optimisation results by allowing the user to better understand the optimisation algorithm and its variables
