International Journal of BIM and Engineering Science

Buildings account for nearly 40% of global final energy consumption, with heating, ventilation, and air conditioning systems responsible for the largest single share of that load. Conventional schedule-based HVAC controllers operate on fixed occupancy assumptions and are consequently unable to exploit the predictable but irregular occupancy patterns that characterise modern working environments. This paper proposes OccuTwin, an integrated framework that couples multi-step occupancy forecasting with a BIM-based digital twin to enable genuinely predictive HVAC optimisation. Four sequence models—Long Short-Term Memory, Gated Recurrent Unit, XGBoost with lag features, and a Temporal Fusion Transformer—are trained on the publicly available Mind Your Building occupancy dataset and the multi-building Building Data Genome Project benchmark to predict room-level occupancy at five-minute resolution. The best-performing Transformer model achieves 94.8% accuracy and an improved weighted F1- score on the 30% hold-out set, outperforming the LSTM baseline by 1.4 percentage points. An IFC-coupled co-simulation environment links real-time occupancy predictions to a virtual HVAC thermal model implemented in EnergyPlus, enabling zone-level set-point optimisation driven by predicted rather than sensed occupancy. Annual co-simulation across nine building zones documents 21.2% energy savings over a schedule-based rule controller while simultaneously improving the fraction of time within ASHRAE thermal comfort bounds from 92.4% to 97.2%. Ablation experiments identify temporal lag features and SMOTE-based class rebalancing as the two most critical preprocessing choices, and noise-injection tests confirm that the Transformer retains 95.1% accuracy under 15% sensor noise—a critical property for edge-deployed IoT environments.

Security validation in architectural design is commonly conducted through manual interpretation of drawings, expert walkthroughs, and late-stage design reviews. Such practice is valuable but difficult to reproduce, especially when crime-prevention criteria depend on visibility, access definition, territorial cues, and lighting quality. This paper presents an automated BIM-based framework for evaluating Crime Prevention through Environmental Design (CPTED) principles using semantic modelling, geometric reasoning, and rule-based inference. The proposed method transforms security-relevant BIM entities into a machine-readable CPTED knowledge layer, evaluates each space through formal rules, and produces interpretable scores that can guide design revision. The framework considers natural surveillance, access control, territoriality, and lighting as computationally linked design dimensions rather than independent checklist items. Results show that automated rule checking can reproduce expert assessment patterns while providing faster and more consistent space-level diagnosis. The paper contributes a transparent computational model for early-stage security validation and demonstrates how BIM can support evidence-based CPTED assessment before construction decisions become costly to revise.

Indoor fire evacuation requires decisions that change as smoke, heat, and occupant movement evolve. Conventional evacuation drawings are usually prepared before an incident and cannot represent real-time loss of visibility, blocked corridors, congested stairs, or the changing reliability of alternative exits. This paper proposes a dynamic evacuationrouting framework that connects IoT fire-sensor streams with a semantic graph derived from a BIM model. The building is represented as a weighted network of rooms, corridors, doors, stairs, and exits, while sensor readings are transformed into a time-dependent hazard index that continuously modifies edge costs. The proposed model integrates fire-safety asset recognition, semantic BIM enrichment, hazard propagation, congestion-aware edge weighting, and dynamic shortest-path recalculation. A controlled simulation demonstrates how the route recommendation changes during fire development and how dynamic routing reduces hazard exposure compared with a static egress plan. The study contributes a transparent computational structure for transforming BIM from a static documentation model into an adaptive emergency decision-support interface.

This paper provides a comprehensive systematic review of Building Information Modeling (BIM) integration across ten engineering disciplines, synthesising publications from January 2020 to January 2026. It identifies convergent trends, persistent knowledge gaps, and translational barriers that separate research prototypes from scalable industry practice. A PRISMA-guided systematic review was conducted across Scopus, Web of Science, ASCE Library, and ScienceDirect. An initial corpus of 4,712 records was screened and quality-assessed, yielding 63 papers for quantitative synthesis and a broader qualitative corpus of 293 studies spanning ten sub-domains: BIM–digital twin integration, BIM and artificial intelligence/machine learning, interoperability and IFC, structural engineering, MEP and building services, facility management and operations, BIM–GIS for smart cities, off-site and modular construction, adoption barriers, and energy and sustainability analysis. Annual BIM publications grew by approximately 256% between 2019 and 2024. BIM–AI/ML and BIM–digital twin integration are the two fastest-growing sub-domains, yet both remain constrained by data standardisation deficiencies and a shortage of domain-specific training datasets. IFC-based interoperability has matured significantly, but real-time bidirectional exchange across disciplines remains nascent. Structural engineering applications exhibit the highest technology readiness, while BIM–GIS integration for smart-city applications shows the widest gap between published prototypes and commercial deployment. The review delivers a thematic roadmap and a consolidated evidence base for prioritizing investment in digital workflows, standards development, and workforce training. An original four-layer integrated framework is proposed that connects engineering code provisions, AI/ML analytics, digital twin synchronisation, and automated quantity extraction within a single traceable workflow.

Construction safety management increasingly depends on the ability to connect static building information models with dynamic evidence from site operations. This paper proposes a BIM-integrated semantic risk intelligence model that translates accident narratives into work-zone risk indicators and uses them to infer safety severity. The model links textual incident evidence with BIM-relevant descriptors, including construction phase, spatial zone, temporary protection status, energy isolation, and proximity to safety constraints. A formal risk-scoring layer is combined with supervised severity learning to provide interpretable decision support for safety planning and 4D coordination. The study contributes a reproducible methodology for converting unstructured safety reports into BIM-actionable risk representations, supporting early hazard prioritisation, design-for-safety review, and site control planning. The findings indicate that semantic evidence becomes more useful when it is explicitly fused with BIM phase and spatial context, rather than being treated as disconnected textual data.

Building information modelling is increasingly applied to structure engineering information across the life cycle of built assets, but existing buildings are often underconnected to operational data for retrofit prioritisation. This research proposes a BIM-connected retrofit prioritisation model that converts building-performance information into an engineering information layer for initial screening. The method integrates BIM-aligned feature organisation, transparent machine learning, diagnostic validation, and scenario-driven screening to flag buildings for further assessment by engineers. The paper proposes a workflow for institutions and cities seeking to transition from disparate disclosure records to evidence-based retrofit prioritisation without relying on the immediate availability of digital twins. The results suggest that operational, geometric, and typological features can be used to generate interpretable screening markers that help guide engineering judgement, benchmarking, and incremental retrofit strategies. This research offers a replicable model that supplements, rather than substitutes for, in-depth audit and modelling.

Accurate object semantics are essential for building information modeling (BIM) workflows to enable interoperability, model checking, quantity take-off, performance analysis, and other downstream engineering applications. However, in practice, Industry Foundation Classes (IFC)-based model exchanges often feature limited or poorly identified semantic tags, particularly during interoperability with authoring and reviewing tools. This research proposes a re-producible, geometry-based learning algorithm for the automatic recognition of BIM element categories based on publicly available IFC-based property data. The empirical analysis is based on 780 object instances from ten BIM categories from a publicly available sample of IFC object records. A rule based parser translates semi-structured BIM text exports into engineering features as bounding box dimensions, coordinates, elevations and object-status. The study compares three supervised machine-learning baselines via stratified five-fold cross-validation: logistic regression, random forest and extra trees. Random forest performed best overall with an accuracy of 0.992, balanced accuracy of 0.971, a weighted F1-score of 0.992, and a macro F1-score of 0.970. The analysis of feature importance shows that bounding-box height, width, length, spatial coordinates and externality related descriptors are the most important features. The results demon-strate significant semantics can be extracted from minimal engineering descriptors without the need for deep learning of meshes. This work provides an interpretable and efficient baseline for BIM enrichment, assessment, and interoperability-focused preprocessing for engineering science use-cases.

Construction supply chains are inherently sensitive to spatial and logistical disruptions, yet conventional project planning approaches including standalone 4D BIM, rarely incorporate geospatial risk factors. This study proposes an integrated GIS-MCDM-4D BIM framework to quantify, simulate, and operationalize geospatial logistics risks within construction supply chains. The framework systematically translates GIS-derived spatial risk indicators such as supplier accessibility, transportation network variability, and route vulnerability into temporal constraints embedded in 4D BIM simulations. A real-world case study of a reinforced concrete project in Syria, involving multiple suppliers and a heterogeneous transportation network, is employed to validate the approach. Findings indicate that even minor spatial disruptions can cascade through interdependent construction activities, resulting in significant schedule delays. The integration of GIS and 4D BIM enables proactive, risk-informed planning, demonstrating that geospatial conditions exert a substantial influence on construction timelines. This framework advances beyond descriptive GIS applications by providing a quantitative, operational tool for enhancing schedule reliability, supplier selection, and decision-making in complex and unstable construction environments. The proposed methodology offers a transferable solution for managing geospatial logistics risks in diverse construction contexts.

Purpose: this study aims to develop a Building Information Modeling (BIM)-enabled methodology that integrates Saudi Building Code (SBC) seismic detailing provisions for reinforced concrete shear walls into a rule-based parametric modeling environment. The research seeks to enhance compliance traceability, automate code interpretation, and improve quantity accuracy for mixed-use high-rise buildings with significant vertical zoning effects. Approach, Selected SBC shear wall provisions were translated into computable IF–THEN engineering rules linked to BIM parameters. The methodology incorporated vertical zoning, axial load ratio evaluation, rule-based reinforcement detailing, and automated quantity extraction. The framework was validated using a large-scale Saudi healthcare mixed-use case study through comparison of BIM-derived quantities with independent SBC-consistent reference calculations on a zone-by-zone basis. Findings, Results indicate that axial load ratio governs boundary element activation and confinement reinforcement demand. BIM-generated reinforcement distributions aligned closely with SBC intent, showing average differences of 2–4% for concrete volume, 3–6% for longitudinal reinforcement, and 4–8% for confinement reinforcement. Boundary confinement was concentrated within the lower 30–40% of building height, while zone-based detailing reduced upper-zone reinforcement by approximately 15–25%. Practical Implications, the methodology improves automated compliance verification, reduces overdesign, enhances reproducibility, and supports efficient structural modeling for complex mixed-use buildings. Originality/Value, the study establishes a direct digital linkage between SBC provisions, parametric BIM modeling, and automated structural quantity outputs.