Mechanical and Civil Engineering Faculty Publications

Document Type

Article

Publication Title

Integrated Construction Uncertainty Quantification Framework ICUQF

Abstract

This study develops ICUQF, an integrated uncertainty framework for digitally instrumented construction megaprojects that unite probabilistic simulation, fuzzy reasoning, Bayesian networks, AI-driven anomaly detection, BIM-linked digital twins, and organizational learning into a single operational architecture. The framework classifies uncertainty into aleatory variability, epistemic gaps, data-centric and model-centric risks, and cognitive or cultural sources, mapping each class to computational treatments such as Monte Carlo engines for stochastic variability, fuzzy intervals and p-boxes for imprecise expert judgments, and hierarchical Bayesian models for coherent evidence aggregation and online updating. ICUQF specifies data pipelines that connect IoT sensing, edge processing, cloud storage, and Common Data Environments so that BIM objects carry uncertainty annotations and twins maintain continuously updated state estimates. Methodological elements include surrogate and reduced-order models to relieve computational load, event aware covariance transport for discontinuous dynamics, and sensitivity analyses addressing likelihood and prior choices in Bayesian inversion. The operational design prescribes role-based dashboards exposing probabilistic ranges, fuzzy-derived criticalities, and anomaly alerts within adaptive learning loops that capture incidents, synthesize lessons, and recalibrate models. Implementation guidance covers phased pilots, multidisciplinary analytics teams, BIM execution planning, and cultural practices that support psychological safety for open reporting. Limitations concerning data quality, interoperability, computational scalability, and governance are acknowledged, and research directions propose standardized interoperable platforms, physics-informed and explainable AI, advanced surrogate methods, longitudinal pilots, and regulatory work on liability and certification for probabilistic and fuzzy-informed decisions. The contribution is a cohesive blueprint for converting multi-source uncertainty from a management liability into a managed asset for resilient, foresightful infrastructure delivery.

First Page

Aigboduwa, J. (2025). Intelligent risk management and decision-making in complex offshore engineering projects. International Journal of Petroleum and Gas Engineering Research, 8(2). https://doi.org/10.37745/ijpger.17/vol8n24481 Andrés Arcones, D., Weiser, M., Koutsourelakis, P.-S., & Unger, J. F. (2026). Embedded model form uncertainty quantification with measurement noise for bayesian model calibration. Data-Centric Engineering, 7. https://doi.org/10.1017/dce.2025.10035 Andrukhov, V., Potіekha, A., & Bassist, V. (2024). FEASIBILITY ASSESSMENT OF USING BIM TECHNOLOGIES FOR a CONSTRUCTION PROJECT. Modern Technology, Materials and Design in Construction, 36(1). https://doi.org/10.31649/2311-1429-2024-1-161-165 Bai, Y., & Lam, H. (2024). Uncertainty quantification and confidence intervals for naive rare event estimators. Journal of Applied Probability, 62(1). https://doi.org/10.1017/jpr.2024.43 Brehm, M., & Deraemaeker, A. (2015). Uncertainty quantification of dynamic responses in the frequency domain in the context of virtual testing. Journal of Sound and Vibration, 342. https://doi.org/10.1016/j.jsv.2014.12.020 Carbonell, J. G., & Siekmann, J. Lecture notes in artificial intelligence 4434 (Vol. 4434). Derbe, G., Li, Y., Wu, D., & Zhao, Q. (2020). SCIENTOMETRIC REVIEW OF CONSTRUCTION PROJECT SCHEDULE STUDIES: TRENDS, GAPS AND POTENTIAL RESEARCH AREAS. JOURNAL OF CIVIL ENGINEERING AND MANAGEMENT, 26(4). https://doi.org/10.3846/jcem.2020.12317 Dubois, D., & Guyonnet, D. (2011). Risk-informed decision-making in the presence of epistemic uncertainty. International Journal of General Systems, 40(2). https://doi.org/10.1080/03081079.2010.506179 Fan, Q., & Gühmann, C. (2025). Enhancing 3D point accuracy of laser scanner through multi-stage convolutional neural network for applications in construction. Tm - Technisches Messen, 92(s1). https://doi.org/10.1515/teme-2025-0045 Fan, Y., D’Elia, M., Yu, Y., Najm, H. N., & Silling, S. (2022). Bayesian nonlocal operator regression (BNOR): A data-driven learning framework of nonlocal models with uncertainty quantification. In arXiv preprint arXiv:2211.01330v1. https://arxiv.org/abs/2211.01330v1 Guvenc, M. A. (2025). Predictive maintenance and digital transformation: AI, machine learning, IoT, and digital TwinBased models. https://doi.org/10.58830/ozgur.pub746 Ibadov, N. (2017). Selection of construction project taking into account technological and organizational risk. Acta Physica Polonica A, 132(3-II). https://doi.org/10.12693/aphyspola.132.974 Kaveh, H., & Alhajj, R. (2025). Advancing civil infrastructure with digital twins: A review of applications and challenges. Journal of Civil Engineering and Management, 31(8). https://doi.org/10.3846/jcem.2025.24921

Last Page

Sajuyigbe, A. S., Ogundare, O. S., Sanusi, B. M., Akinbobola, A. O., Tella, A. R., & Obi, N. J. (2026). Assessing the mediating role of project management training on the nexus between job satisfaction and project performance in the nigerian construction industry. Journal of Construction Business and Management, 8(2). Schöbi, R., & Sudret, B. (2017). Structural reliability analysis for p-boxes using multi-level meta-models. Probabilistic Engineering Mechanics, 48. https://doi.org/10.1016/j.probengmech.2017.04.001 Shayakhmetova, A., Tasbolatuly, N., Akhmetova, A., Shurenov, M., & Nagibayeva, A. (2025). Development of a digital twin for system failure prediction using bayesian methods. International Journal of Innovative Research and Scientific Studies, 8(6). https://doi.org/10.53894/ijirss.v8i6.9560 Suhara, A., Setiawan, D., Dewadi, F., Putra, F., Musyaffa, G., & Nabawiyah, S. (2026). Autonomous smart manufacturing systems in the era of industry 5.0: A systematic review of AI-driven decision intelligence and industrial optimization. JADI (Jurnal Teknik Industri), 2(1). https://doi.org/10.66865/xv9yr868 Yang, H., Fujii, Y., Wang, K. W., & Gorodetsky, A. A. (2022). Control variate polynomial chaos: Optimal fusion of sampling and surrogates for multifidelity uncertainty quantifiation. In arXiv:2201.10745v1. https://arxiv.org/abs/2201.10745

Publication Date

Summer 7-28-2026

Download

Share

COinS