Data Model For Information Research Articles

Balancing performance and cost of LLMs in a multi-agent framework for BIM data retrieval

ABSTRACT This study explores strategies for optimizing the use of large language models (LLMs) in Building Information Modeling (BIM) data retrieval. BIM data retrieval plays a crucial role in enhancing the efficiency and effectiveness of building management and construction processes. Utilizing LLMs can significantly improve data accessibility, reduce retrieval time, and support better decision-making. We propose a method to match queries of varying complexity with suitable LLMs within a multi-agent system (MAS) to balance accuracy and computational costs. We evaluated three commonly used LLMs (GPT-3.5 Turbo, GPT-4o, and GPT-4 Turbo) and found that GPT-4o strikes a good balance between performance and cost. By encoding and clustering query statements, we effectively classified query difficulty levels and matched them with appropriate models. Our tests showed that the multi-agent system with the planner mechanism reduced costs by nearly 31% while maintaining the same accuracy compared to systems without the mechanism.

Enabling personalized smart tourism with location-based social networks.

With the rapid advance of mobile internet, communication technology and the Internet of Things (IoT), the tourism industry is undergoing unprecedented transformation. Smart tourism offers users personalized and customized services for travel planning and recommendations. Location-based social networks (LBSNs) play a crucial role in smart tourism industry by providing abundant data sources through their social networking attributes. However, applying LBSNs to smart tourism is a challenge due to the need to deal with complex multi-source information modeling and tourism data sparsity. In this article, to fully harness the potential of LBSNs using deep learning technologies, we propose an knowledge-driven personalized recommendation method for smart tourism. Representation learning techniques can effectively modeling the contextual information (e.g., time, space, and semantics) in LBSNs, while the data augmentation strategy of contrastive learning techniques can explore user personalized travel behaviors and alleviate data sparsity. To demonstrate the effectiveness of the proposed approach, we conducted a case study on trip recommendation. Furthermore, the patterns of human mobility are revealed by exploring the effect of contextual data and tourist potential preferences.

Integrating Building Information Modelling and Artificial Intelligence in Construction Projects: A Review of Challenges and Mitigation Strategies

Artificial intelligence (AI), including machine learning and decision support systems, can deploy complex algorithms to learn sufficiently from the large corpus of building information modelling (BIM) data. An integrated BIM-AI system can leverage the insights to make smart and informed decisions. Hence, the integration of BIM-AI offers vast opportunities to extend the possibilities of innovations in the design and construction of projects. However, this synergy suffers unprecedented challenges. This study conducted a systematic literature review of the challenges and constraints to BIM-AI integration in the construction industry and categorise them into different taxonomies. It used 64 articles, retrieved from the Scopus database using the PRISMA protocol, that were published between 2015 and July 2024. The findings revealed thirty-nine (39) challenges clustered into six taxonomies: technical, knowledge, data, organisational, managerial, and financial. The mean index score analysis revealed financial (µ = 30.50) challenges are the most significant, followed by organisational (µ = 23.86), and technical (µ = 22.29) challenges. Using Pareto analysis, the study highlighted the twenty (20) most important BIM-AI integration challenges. The study further developed strategic mitigation maps containing strategies and targeted interventions to address the identified challenges to the BIM-AI integration. The findings provide insights into the competing issues stifling BIM-AI integration in construction and provide targeted interventions to improve synergy.

3D object recognition using deep learning for automatically generating semantic BIM data

The successful reuse of Building Information Model (BIM) data is reliant on the use of clearly defined objects. File formats such as the Industry Foundation Classes (IFC) along with classification systems offer approaches to standardising semantic BIM data. Inconsistent application of these standards during BIM authoring results in objects that are unable to be reused across systems. This research proposes a Machine Learning (ML) based alternative for detecting objects and enriching BIM data based on geometrical representations of objects to support interoperability across systems throughout the supply chain. First, an existing dataset of training and test data is modified to correspond with predefined data types from the IFC schema. Second, a convolutional deep belief network is implemented and applied on new testing data from the National BIM Library to identify 3D objects and enabling semantic enrichment of BIM data. Finally, the testing is extended to four real-world industry BIM models. The findings show that the geometric data from emerging BIM object libraries can be used to search and retrieve objects within industry BIM models based on geometric rather than semantic data.

BIM-based task planning method for wheeled-legged rebar binding robot

ABSTRACT Building Information Modeling (BIM) data has the advantages of high quality, operability, and parametric capabilities. In recent years, the application of BIM in construction planning for building robots has been increasing. Task planning for rebar binding is an important aspect of construction, and there is a growing trend of using robots to improve the accuracy and efficiency of binding operations. However, the complex and dynamic construction site environment poses significant challenges for task planning in rebar binding. Therefore, this paper proposes a new BIM-based task planning method for a wheeled-legged rebar binding robot, which can quickly generate an optimal task sequence. Firstly, an initial set of rebar intersection points is generated based on BIM data. Then, considering the execution dead zone of the robot and the variable workspace of the binding mechanism, the rebar intersection points set is decomposed and filtered using morphological opening operations. Finally, a constrained genetic algorithm is employed to sort the set of task points. Simulation and real-world experiments were conducted using a wheeled-legged rebar binding robot as the research subject. The results demonstrate that, compared to manual planning, the average binding efficiency is approximately 1500 points per hour, which is 1.97 times higher than manual operation. This validates the applicability and effectiveness of the proposed method.

Narrating Serranos Bridge Evolution in Valencia (1500–2022) Using Historic Building Information Modelling and Historical Data

The city of Valencia (Spain) is famous for its Gothic bridges, built in the 16th century. Today, the bridges no longer cross over the Turia River but have become walkways over one of the most extensive gardens in Europe. One of these bridges is the Serranos Bridge, the oldest bridge in the city and for centuries, it was the only one that existed. This research narrates the evolution of the historical changes related to this bridge, using Historic Building Information Modelling (HBIM) technology. The Serranos Bridge (and related Serranos Towers) were recorded with the help of terrestrial laser scanning, and parametric 3D modelling was followed after scan-to-HBIM. By referring to historical documents and traces from the past, the height of the historic wall of the city was obtained and used to recreate the urban footprint of the area. In addition, the details of the historical bridge components and the subsequent volumetric changes were reconstructed through HBIM. This investigation shows that there is a common symbol in the historical bridges of Valencia, called Casilicium, of which no traces can be identified in the present bridge. The effective integration of historical data, geomatics and HBIM can be used to understand the past and its complex transformation over six centuries with unprecedented expectations.

Research and application of OPC UA-based digital twin smoke alarm calibration workshop information model.

Aiming at the problems of data integration and information sharing in the calibration workshop of smoke alarm, combining OPC Unified Architecture (OPC UA) and digital twin technology, the OPC UA based digital twin smoke alarm calibration workshop information network framework is proposed. Using OPC UA information modeling technology, a digital workshop information model for smoke alarm calibration was constructed, and the static attribute set, process attribute set, and functional component set of the workshop were defined in detail. Taking the smoke box as an example, the information model construction was instantiated, and data collection and transmission were carried out with the digital twin model of the smoke box, achieving the implementation mapping between the twin model and physical entities. The results show that based on the proposed OPC UA information model, the interconnection and intercommunication of data at all levels of the digital twin smoke alarm calibration workshop can be achieved, and the workshop can be visualized, digitized, and flexible.

Integration of building information modeling and big data processing technologies

Integration of building information modeling and big data processing technologies

Embedding Mātauranga Māori in Architectural Education

The School of Architecture at Unitec | Te Pūkenga has developed a te reo Māori kuputaka (glossary). This resource is included in the first-year Bachelor of Architectural Studies content to help embed mātauranga Māori in pedagogy. The initiative reflects the determination on the part of Te Whare Wānanga o Wairaka Unitec | Te Pūkenga and the School of Architecture to honour te Tiriti o Waitangi (the Treaty of Waitangi) and meet programme aims. This bicultural approach mirrors professional practice: in Ōtautahi Christchurch, after the 2011 earthquake, Indigenous sustainable practices were successfully integrated during the rebuild in collaboration with Ngāi Tahu and local hapū Ngāi Tūāhuriri; in Tāmaki Makaurau Auckland, Te Aranga Māori Design Principles recognise the authority of mana whenua and ensure Indigenous values are incorporated in the design of the built environment. Frameworks for the integration of te ao Māori sustainable values into Building Information Modelling (BIM) data are currently being developed to become a nationwide resource expanding and enriching the New Zealand BIM Handbook. Including specific architectural vocabulary in te reo Māori sensitises all involved in the course to the interaction and layering of languages. The poetic and resonant qualities of te reo equivalents of English terms enrich the discussion of a more existential significance of architecture’s concepts, components and acts. Cases in point are ‘āputa whai take’ – ‘purposeful gap/space’; ‘nōhanga hāneanea’ – ‘comfortable habitat/ergonomics’; and ‘whare kiato’ – ‘compact house/tiny home’. This additional layer of meaning reflects our bicultural circumstances. In addition, the kuputaka introduces tikanga Māori in terms such as ‘tapu’ – ‘sacred, set apart’ – and ‘noa’ – ‘common, ordinary’ – as well as ‘iwi’, hapū’ and other essential components of te ao Māori.Introducing mātauranga Māori and a te reo Māori kuputaka creates foundations that successive years of architectural study can build on – this provides our graduates with essential skills and the instruments to engage effectively within professional practice and to shape our environment.

SCAN-TO-BIM method and analysis of measurement accuracy on the example of a historic church

Building information modeling (BIM) data for existing buildings based on scans and point clouds acquired from terrestrial laser scanning (TLS) is the basis of the Scan-to-BIM methodology and is becoming common practice. However, work on the accuracy of the resulting model is still desired. The article discusses the possibility of developing a BIM model of a historical building, based on data obtained by terrestrial laser scanning. The subject of the study was the church in Posada Rybotycka (Poland). The mapping reliability studies included PointCab and ReCap point cloud processing, 3D modeling of the object using Revit software, and analysis of the accuracy of distance measurements made by TLS with data obtained from measurements made with traditional methods: total station and laser rangefinder. Based on the conducted research, the possibility of using the BIM with TLS data in the process of reconstructing the geometry of a historic building was evaluated. The results of the study showed that the convergence of the 3D model geometry with the actual course of the structure depends on the development methodology, i.e. the accuracy of 3D data acquisition, the registration process, the filtering procedure, or the parametric structural modeling method used.

Robust Watermarking Algorithm for Building Information Modeling Based on Element Perturbation and Invisible Characters

With the increasing ease of building information modeling data usage, digital watermarking technology has become increasingly crucial for BIM data copyright protection. In response to the problem that existing robust watermarking methods mainly focus on BIM exchange formats and cannot adapt to BIM data, a novel watermarking algorithm specifically designed for BIM data, which combines element perturbation and invisible character embedding, is proposed. The proposed algorithm first calculates the centroid of the enclosing box to locate the elements, and establishes a synchronous relationship between the element coordinates and the watermarked bits using a mapping mechanism, by which the watermarking robustness is effectively enhanced. Taking into consideration both data availability and the need for watermark invisibility, the algorithm classifies the BIM elements based on their mobility, and perturbs the movable elements while embedding invisible characters within the attributes of the immovable elements. Then, the watermark information after dislocation is embedded into the data. We use building model and structural model BIM data to carry out the experiments, and the results demonstrate that the signal-to-noise ratio and peak signal-to-noise ratio before and after watermark embedding are both greater than 100 dB. In addition, the increased information redundancy accounts for less than 0.15% of the original data., which means watermark embedding has very little impact on the original data. Additionally, the NC coefficient of watermark extraction is higher than 0.85 when facing attacks such as translation, element addition, element deletion, and geometry–property separation. These findings indicate a high level of imperceptibility and robustness offered by the algorithm. In conclusion, the robust watermarking algorithm for BIM data fulfills the practical requirements and provides a feasible solution for protecting the copyright of BIM data.

Investigating the Impact of Augmented Reality and BIM on Retrofitting Training for Non-experts.

Augmented Reality (AR) tools have shown significant potential in providing on-site visualization of Building Information Modeling (BIM) data and models for supporting construction evaluation, inspection, and guidance. Retrofitting existing buildings, however, remains a challenging task requiring more innovative solutions to successfully integrate AR and BIM. This study aims to investigate the impact of AR+BIM technology on the retrofitting training process and assess the potential for future on-site usage. We conducted a study with 64 non-expert participants, who were asked to perform a common retrofitting procedure of an electrical outlet installation using either an AR+BIM system or a standard printed blueprint documentation set. Our findings indicate that AR+BIM reduced task time significantly and improved performance consistency across participants, while also decreasing the physical and cognitive demands of the training. This study provides a foundation for augmenting future retrofitting construction research that can extend the use of AR+BIM technology, thus facilitating more efficient retrofitting of existing buildings. A video presentation of this article and all supplemental materials are available at https://github.com/DesignLabUCF/SENSEable/_RetrofittingTraining.

Application of BIM technology in the reinforcement and renovation of existing building inspection projects

PurposeDue to the characteristics of visualization, simulation, information integrity, and flexibility, Building Information Modeling (BIM) technology would be widely applied in every stage of construction projects. MethodThe existing building structure inspection methods used in this article included safety inspection of existing buildings, applicability inspection of existing buildings, and durability inspection of existing buildings. In visual collaborative design, a project information data model was established based on BIM, and the real-time information dynamics of the building information model were mastered through the sharing and updating of local files. The “reinforcement family” established in this article was mainly composed of beams, columns, walls, etc. In order to achieve widespread applicability of reinforcement families, it was necessary to select family templates based on lines or faces that were not limited by the host when creating reinforcement families. ResultThe implementation plan of the building renovation in this article had an annual power consumption of 1260476.5KW·h. ConclusionWhile reducing costs and risks, BIM technology brought higher efficiency, higher quality, and more sustainable development opportunities to the construction industry.

Innovation and exploration of construction project management based on BIM platform of big data

Abstract The study of BIM engineering management platforms based on big data is conducive to improving the status quo of traditional construction engineering and providing new ideas to realize the innovation of construction engineering project management. This paper takes construction engineering project management as the research object, based on the BIM platform of big data, and understands the current difficulties and key points of safety management by investigating and analyzing the status of construction engineering project management and BIM the application status of the platform. Secondly, we make full use of building information model data standards, including: IFC standards, IDM standards, and MVD standards, to analyze building information model data standards. Finally, the data establishment practice is carried out based on the foundation BIM construction model that satisfies the 300 LOD level for the model components. The results satisfy the consistency test, and the weight coefficients are considered to be reasonably assigned. According to the judgment matrix to calculate the weights, the matrix is normalized by column, and the weights of each index are obtained as 0.6377, 0.2580, 0.1034, 0.1790, 0.1130, respectively. This paper is based on big data BIM technology application and construction process safety management activities, which can realize the information management of the whole project construction, strengthen the benefits of construction project safety management, and provide collaboration of all parties to provide a favorable sharing platform.

Integration of Building Information Modeling (BIM) and Big Data in China: Recent Application and Future Perspective

The integrated application of building information modeling (BIM) and big data (BD) has received widespread attention, and has been involved in smart construction sites, construction project management, and construction project budgeting. Nevertheless, research on the integrated implementation of BIM and BD in China mainly concentrates on a project stage or profession, the exploration of technology integration mostly focuses on the theoretical level, and the research distribution is scattered. As such, the intention of this paper is to reveal the research history of BIM and BD in China, as well as to study the research methodologies and research fields for a more thorough knowledge of the BIM and BD research and development status in the Chinese construction sector, which adopts a mixed research method that uses a quantitative research via two analytical software tools, i.e., CiteSpace version of 6.1.R6 and the Statistical Analysis Toolkit on line edition for Informetrics software packages, to conduct a macro bibliometric analysis on BIM and BD research in the China National Knowledge Infrastructure database, and provides a follow-up micro qualitative research with content analysis. To ensure the comprehensiveness of the research, the core articles of the topic in the web of science database have been sorted out and analyzed for fully understanding the development of BIM and BD in the field of Chinese construction, resulting in identifying the current research hotspots and trends in China. The results suggest that the popular research keywords on BIM and BD in China since the year 2015 have mainly been focused on informatization, the internet of things, and rail transportation. Three fruitful research themes in BIM and BD research in China have been identified, including smart construction, smart operation, and bridge informatization.

Application of Data-Driven Building Information Modeling in the Visual Simulation of Disease Transmission and Route with Pipeline System

Currently, preventing epidemics is an extremely critical global topic. Using present data to quickly conduct virus simulations is a difficult but interesting problem, especially when real situations are difficult to experimentally demonstrate. In the past, most studies have used package software for disease transmission simulation, but this approach is limited by availability and software cost. Therefore, we propose a visual simulation of disease transmission using building information modeling data and a 3D model using Unity. The results show that the proposed method can effectively predict the probability and route of disease transmission; it also verifies that the vertical pipeline on the floor plane is conducive to the spread of the virus (90%), and disease transmission on the plane gradually expands outward from the starting room and has a higher probability of spreading (80%) from the opposite room. In addition, a vertical pipeline was simulated using a toilet exhaust air ventilation pipeline, from which it can be observed that the adjacent floors have a higher diffusion probability (70%). It has also been confirmed that distance is the primary factor affecting disease transmission. This framework may provide designers and managers further protection against the spread of future epidemics.

The Evaluation Algorithm of English Teaching Ability Based on Big Data Fuzzy K-Means Clustering

In response to the problem of inaccurate classification of big data information in traditional English teaching ability evaluation algorithms, this paper proposes an English teaching ability estimation algorithm based on big data fuzzy K-means clustering. Firstly, the article establishes a constraint parameter index analysis model. Secondly, quantitative recursive analysis is used to evaluate the capabilities of big data information models and achieve entropy feature extraction of capability constrained feature information. Finally, by integrating big data information fusion and K-means clustering algorithm, the article achieves clustering and integration of indicator parameters for English teaching ability, prepares corresponding teaching resource allocation plans, and evaluates English teaching ability. The experimental results show that using this method to evaluate English teaching ability has good information fusion analysis ability and improves the accuracy of teaching ability evaluation and the efficiency of teaching resource application.

Research on speed control of high-speed trains based on hybrid modeling

With the continuous improvement of train speed, the automatic driving of trains instead of driver driving has become the development direction of rail transit in order to realize traffic automation. The application of single modeling methods for speed control in the automatic operation of high-speed trains lacks exploration of the com-bination of train operation data information and physical model, resulting in low system modeling accuracy, which impacts the effectiveness of speed control and the operation of high-speed trains. To further increase the dynamic modeling accuracy of high-speed train operation and the high-speed train's speed control effect, a high-speed train speed control method based on hybrid modeling of mechanism and data drive is put forward. Firstly, a model of the high-speed train's mechanism was created by analyzing the train's dynamics. Secondly, the improved kernel-principal component regression algorithm was used to create a data-driven model using the actual opera-tion data of the CRH3 (China Railway High-speed 3) high-speed train from Huashan North Railway Station to Xi'an North Railway Station of "Zhengxi High-speed Railway," completing the mechanism model compensation and the error correction of the speed of the actual operation process of the high-speed train, and realizing the hybrid modeling of mechanism and data-driven. Finally, the prediction Fuzzy PID control algorithm was devel-oped based on the natural line and train characteristics to complete the train speed control simulation under the hybrid model and the mechanism model, respectively. In addition, analysis and comparison analysis were conduct-ed. The results indicate that, compared to the high-speed train speed control based on the mechanism model, the high-speed train speed control based on hybrid modeling is more accurate, with an average speed control error reduced by 69.42%. This can effectively reduce the speed control error, improve the speed control effect and oper-ation efficiency, and demonstrate the efficacy of the hybrid modeling and algorithm. The research results can provide a new ideal of multi-model fusion modeling for the dynamic modeling of high-speed train operation, further improve control objectives such as safety, comfort, and efficiency of high-speed train operation, and pro-vide a reference for automatic driving and intelligent driving of high-speed trains.

PRESERVATION THROUGH DIGITIZATION - STANDARDIZATION IN DOCUMENTATION OF BUILD CULTURAL HERITAGE USING CAPTURING REALITY TECHNIQUES AND HERITAGE/HISTORIC BIM METHODOLOGY

Abstract. Building Information Modelling (BIM) is an established approach in the construction industry that enables efficient collaboration between stakeholders and facilitates project management. However, when it comes to historical buildings, the application of BIM can be demanding due to the complex nature of these projects. Although BIM Uses in the construction sector are well-documented (Penn State University, 2013) and we are surrounded by amazing technologies, we do not yet have standardized international workflows on how to use those state-of-the-art techniques with Cultural Heritage Assets (Bruno and Roncella, 2019). Standardizing Cultural Heritage (CH) metric documentation and Heritage/Historic Building Information Modeling (HBIM) is challenging since each CH asset needs different information throughout the whole life cycle of the monument - both their physical and non-physical attributes, such as historical and cultural characteristics. Additionally, every work carried out on CH, such as knowledge acquisition, restoration, adaptation, etc., requires specific data inputs. Although there are guidelines books that offer some general proposals, they represent the maximum effort towards standardization. As a result, the field of HBIM has emerged as a relatively new area of scientific research that focuses on the digital representation of CH assets.This research aims to develop a working method and templates for procurement workflow standardization that will facilitate the documentation of historic buildings and heritage assets in coordination with relevant historic preservation authorities for the BIM use case - asset register. The use of various measurement methods, the registration of captured point clouds, and the transfer of geometry to a BIM-compliant 3D information model and sustainable data storage are important aspects of this project.

Design of Secondary Circuit Visualization System for UHVDC Converter Stations

For the problems of complicated work content and error-prone workload of secondary circuits, a three-dimensional visualization method is proposed for the visualization and management of the physical circuits of the control and protection system of the converter station based on digital twin technology. The system can be used to improve the work efficiency of operation and maintenance personnel by constructing a secondary circuit information data model, generating corresponding data through artificial intelligence image recognition and manual review of secondary circuit drawings and schematics, and performing accurate corresponding circuit data analysis and 3D visualization management of the secondary physical circuits of control and security equipment, which can visualize the circuit information of control and security equipment in the station from outside to inside at multiple levels and multiple dimensions.