A BIM-based ontological seismic multi-objective evaluation and optimisation design for buildings

Gao, Shang 2025. A BIM-based ontological seismic multi-objective evaluation and optimisation design for buildings. PhD Thesis, Cardiff University. Item availability restricted.

Preview	PDF (Thesis) - Accepted Post-Print Version Download (20MB) | Preview
	PDF (Cardiff University Electronic Publication Form) Restricted to Repository staff only Download (118kB)

Abstract

The proposal of Performance-Based Seismic Design (PBSD) theory improves the efficiency of simultaneously designing and evaluating structures in earthquake engineering. Leveraging digital tools to enhance the quality and efficiency of engineering application is an important proposition for the information reform in the field of seismic design. Based on PBSD theory and with the help of Building Information Modeling (BIM), semantic web, Artificial Intelligence (AI) and other technologies, this thesis realises the automated evaluation and optimization design for individual buildings to analyse their seismic performance. Additionally, it predicts the seismic damage of groups of building in a specific location. The research will provide effective guidance for the overall and detail-oriented regional seismic precaution. In 2001, the Applied Technology Council (ATC) received the initial contract from the Federal Emergency Management Agency (FEMA) to create advanced PBSD for both newly constructed and pre-existing structures. The main outcome of this project is a collection of volumes, supporting documents, and digital resources known as the FEMA P-58 Seismic Performance Assessment of Building, Methodology and Implementation. This thesis utilises BIM technology to seamlessly integrate and convey detailed technical information at the component level, following the guidelines set by above documents in its first section. Then, Ontology is utilised to articulate the evaluation content and reasoning, while also organising, storing, associating and interacting with the many and disparate data sources for evaluation in a cohesive manner. This enables the automated evaluation of seismic performance for individual buildings. Therefore, the seismic optimisation design, guided by the “Return on Investment” (ROI) criterion, aims to achieve an equilibrium between the initial building expense and the anticipated earthquake damage. The multi-objective genetic algorithm, known as NSGA-II, is employed to carry out the optimisation iterations at the building’s component level. The second section focuses on multi-scale regional seismic precaution and establishes a seismic response prediction model using Artificial Neural Network (ANN). This model not only expedites the rapid acquisition of seismic performance distribution for building groups, but also provides a framework for more comprehensive seismic design and evaluation of individual buildings with significant damage. Ultimately, this thesis demonstrates the enhancement of seismic performance assessment quality for building and the optimisation degree of seismic design through the application of practical cases. Furthermore, the operational efficiency of both has been improved. Moreover, this thesis not only I II guarantees the precision of seismic response prediction, but also expands the model’s applicability by facilitating the adoption of PBSD from individual buildings to regional groups. Keywords: PBSD, Ontology, BIM, ANN

Item Type:	Thesis (PhD)
Date Type:	Completion
Status:	Unpublished
Schools:	Schools > Engineering
Date of First Compliant Deposit:	11 April 2025
Last Modified:	11 Apr 2025 14:27
URI:	https://orca.cardiff.ac.uk/id/eprint/177611

Actions (repository staff only)

Edit Item