This framework proves an autonomous decision-making system that organically links inspection data with maintenance regulations by transforming static, manual-labor-centered maintenance workflows into intelligent automated models and increases the efficiency of railway infrastructure management while providing a scalable technical foundation for overall asset management of future smart-city infrastructure.
Abstract
Modern railway maintenance is transitioning toward a condition-based maintenance system to stably operate the core infrastructure of sustainable smart cities. However, technical limitations remain in manually converting and analyzing massive amounts of inspection data into Building Information Modeling (BIM) objects. This causes information delays and technical severance in data-driven smart-city infrastructure. To address these challenges, this study proposes an Agentic BIM framework that integrates Large Language Model (LLM), Model Context Protocol (MCP), and Retrieval Augmented Generation (RAG) technologies. The proposed methodology standardizes the control channel between the LLM and BIM software through a central MCP server, while securing the accuracy of engineering judgments by utilizing the RAG pipeline to reference national railway-track-maintenance guidelines. System validation results demonstrated that geometric inspection data, including gauge and alignment, were automatically generated as BIM objects without human intervention. Furthermore, the maintenance grades and deadlines for sections exceeding thresholds were immediately highlighted within the model as visual attributes. Consequently, this framework proves an autonomous decision-making system that organically links inspection data with maintenance regulations. By transforming static, manual-labor-centered maintenance workflows into intelligent automated models, it increases the efficiency of railway infrastructure management while providing a scalable technical foundation for overall asset management of future smart-city infrastructure.
Abstract
India's highway sector is experiencing a significant digital transformation driven by rapid infrastructure expansion, increasing freight movement and the need for sustainable asset management.¹ Traditional pavement management practices, based on periodic inspections and fragmented engineering records, are no longer adequate for managing complex highway networks efficiently.² The integration of Digital Twins with Building Information Modelling (BIM), intelligent design platforms, advanced pavement evaluation technologies and asset management systems offers a comprehensive framework for data-driven lifecycle management.³⁻⁵
This article examines the evolution of Digital Twin technology for smart pavement management in India. It discusses the integration of BIM, Bentley OpenRoads Designer, Geographic Information Systems (GIS), Falling Weight Deflectometer (FWD), Ground Penetrating Radar (GPR), LiDAR, Unmanned Aerial Vehicles (UAVs), Internet of Things (IoT) sensors and Artificial Intelligence (AI) to support predictive maintenance and optimise lifecycle performance.⁴⁻⁹ The paper also reviews implementation challenges, institutional collaboration, international best practices and future opportunities for adopting Digital Twin technology within Indian highway infrastructure. The proposed framework demonstrates how digital engineering can improve pavement performance, reduce lifecycle costs and contribute to resilient and sustainable transportation networks¹⁰.
Dil Khush Jha· International Journal For Mu...· 0 citations
Quality control data for construction materials is frequently exchanged as heterogeneous documents, limiting traceability and making element-level retrieval slow and error-prone. This study develops and assesses a digital methodology that integrates laboratory test results with BIM-referenced assets and delivers the integrated information via interactive 3D-enabled dashboards. The methodology comprises three stages, starting with the acquisition of data from laboratory deliverables and 3D models, followed by data standardisation and relational structuring in the software Power BI Desktop (version 2.157.879.0, Microsoft Corporation, Redmond, WA, USA), and finally the publishing of generated dashboards embedded in a web application environment. The methodology is assessed through a real case study of a railway infrastructure asset, showing how laboratory records can be accessed and interpreted within a 3D model context, while preserving stakeholder-specific visibility through access control. The proposed approach supports element-level navigation of quality control and provides a practical pathway for laboratories to centralise, filter, and communicate test results without embedding full datasets into the BIM environment.
F. Andrade, João Ventura, Cristina Ribeiro et al.· Infrastructures· 0 citations
Abstract. Artificial Intelligence (AI) integration has become an essential of modern AEC workflows, yet it has failed to gain a position in waste management. This gap is particularly prominent given the urgent environmental and legal imperatives for the sector to mitigate its demolition outputs. Existing approaches to waste classification and diversion cost estimation rely on manual interpretation of project documentation, a process that is both resource-intensive and structurally incompatible with the machine-readable data environments established by Building Information Modelling (BIM). This paper presents a framework that bridges Industry Foundation Class (IFC) compliant BIM data and Large Language Model (LLM) capabilities to automate Construction and Demolition Waste (C&DW) classification and probabilistic cost optimisation. The framework utilizes IfcOpenShell to extract element geometry and material data, channeling this information into a Retrieval-Augmented Generation (RAG) pipeline. To ensure rigorous compliance during classification, a FAISS-indexed knowledge base grounds a locally deployed Llama3 model against the specific mandates of Province of Ontario, Canada regulation 102/94. Diversion cost scenarios are computed through a Bayesian cost module coupled to a multi-objective genetic algorithm (MOGA) optimiser. Th proposed approach is evaluated against a labelled dataset of 104 IFC type-and-material combinations, the RAG classifier. Performance thresholds were established a piori based on multi-class classification benchmarks and Bayesian cost model uncertainty tolerances. The framework achieved a macro-average F1 of 0.84 and overall accuracy of 88%, satisfying the minimum criteria for automated C&DW characterization under Ontario Regulation 102/94.
Nolan Porther, Amirhossein Nourbakhshrezaei, M. Jadidi· The International Archives o...· 0 citations
Railway maintenance relies on effective assessment of asset health to ensure safety and reliability. It requires appropriate technologies, methodologies, and tools for monitoring the condition of railway assets. These technologies and tools often utilize advanced sensor technology for data acquisition, distributed computing for data processing, enhanced analytics for knowledge extraction, and visualization technologies for data representation. While significant progress has been made in data acquisition, processing, and analytics, data visualization has not received sufficient attention. In parallel, the emerging Industry 5.0 concept emphasizes human-centricity, resilience, and sustainability in industrial systems, highlighting the need for enhanced human-system interaction (HSI) in maintenance processes. HSI can be enhanced by using perception-enhancing technology such as Augmented Reality (AR). However, the effective integration of AR into railway maintenance requires structured frameworks that address the challenges of task workflow, interaction, and information presentation. Hence, the purpose of this paper is to propose a framework for enabling AR-based assistance in railway maintenance. Following a Design Science Research (DSR) methodology, the framework defines functional elements and information flows to support the execution of inspection tasks and is realized through an AR-based system that integrates procedural guidance, flexible workflow navigation, multimodal interaction, contextual information access, and automated inspection log generation. A controlled user study compares the AR-assisted inspection approach with a traditional inspection method using standardized usability measures. The results indicate that both approaches scored within the marginal usability range. These findings indicate the feasibility of AR-based assistance as a human-centric complement to existing railway maintenance practices, while motivating further refinement and evaluation in operational settings.
Parul Khanna, P. Tretten, Ramin Karim· IEEE Access· 0 citations
This paper presents the design phase of an Extended Reality (XR)-based platform aimed at optimising operation and maintenance for dynamic building envelopes. The proposed solution addresses the growing need for advanced facility management tools that support energy performance and operational efficiency throughout the building lifecycle. The platform integrates heterogeneous data sources, including Building Information Modelling (BIM), Internet of Things (IoT) sensors, and Digital Product Passports (DPPs), to enable real-time fault detection, remote technical assistance, and enhanced communication between key actors. Built on user story methodologies, the platform uses cloud architecture and consumer smart devices to deliver scalable, cost-effective maintenance workflows with XR technology. In addition, Artificial Intelligence (AI) capabilities are integrated to support historical data analysis and automated reporting generation. Preliminary platform validations in real-world environments have demonstrated encouraging results in terms of increased building intelligence, maintenance operation efficiency, and user satisfaction.
A. Pracucci, Matteo Giovanardi, Alessandro Zara· Journal of Facade Design and...· 0 citations
Dams are critical national infrastructure assets that the Indonesian government has developed extensively over the past decade to improve water security and mitigate the impacts of drought and extreme weather events. This large-scale development has created increasing demands for effective and sustainable dam maintenance. At present, dam maintenance activities have not been systematically implemented using a Work Breakdown Structure (WBS)-based approach. Ideally, maintenance performance should be optimized by first identifying the complete scope of maintenance components and then developing maintenance guidelines and Standard Operating Procedures (SOPs) for each identified component. These WBS-based maintenance procedures and guidelines can subsequently be integrated into a maintenance management model using Building Information Modeling (BIM). To support real-time monitoring and inspection, laser scanning (LS) technology can be integrated with BIM and information systems (IS). This study forms part of the development of an electronic dam maintenance (e-maintenance) system by examining the relationships among the key components of the proposed framework, namely WBS, Standard Operating Procedures (SOPs), BIM, laser scanning (LS), and information systems (IS), and their influence on improving dam maintenance performance. Multiple regression analysis, followed by expert validation, was employed to evaluate the significance of these variables in the proposed dam maintenance system. The results indicate strong relationships among the variables, with correlation coefficients ranging from 0.714 to 0.822. Among the variables, WBS exhibited the strongest influence on dam maintenance performance, with the highest standardized regression coefficient (b = 0.237), whereas the remaining variables produced coefficients ranging from 0.048 to 0.173.
Toha Saleh, Yusuf Latief, D. Sutjiningsih· Interdisciplinary Social Stu...· 0 citations