Ghavidel, A (2025) AI-informed multi-threat decision-support methodology for long-term bridge asset management. PhD thesis, University of Texas at San Antonio, USA.
Abstract
This dissertation develops a methodology and tools for a risk-based multi-threat decision-support tool for long-term bridge asset management (BAM), with a particular focus on chronic aging-induced condition deterioration and more abrupt and extreme seismic hazard impact. In Volume 1, a stochastic bridge condition deterioration and seismic damage simulation module is developed. Seismic fragility modeling and risk assessment is carried out, considering site-specific seismic hazard and the effect of seismic retrofitting actions. A life cycle cost analysis module is introduced to holistically quantify and aggregate the direct and indirect costs incurred from bridge condition deterioration, seismic damage, and intervention actions over a prolonged planning horizon. A benefit-cost analysis for various seismic retrofitting actions is also performed. Then, by integrating the above bridge deterioration and seismic damage simulation module and the life-cycle cost analysis module with the advanced AI technique, deep reinforcement learning (DRL), a methodology for generating AI-based policies for sequential maintenance decision support for a portfolio of bridges is proposed. Departing from traditional reactive condition-based decision policies, these AI-based policies can offer much more proactive and adaptive decisions to minimize the expected long-term life-cycle costs. Practical action constraints are also introduced to align with real-world engineering practices. The proposed AI-based policies are evaluated based on individual bridges as well as on a portfolio of bridges and demonstrate superior performance in reducing the life-cycle costs compared with other condition-based policies. In addition, the AI-based policies also exhibit robustness to potential human override. Moreover, an investigation into the effect of seismic retrofitting, coupled with AI-based agents, is conducted for more comprehensive life-cycle benefit-cost evaluation of seismic retrofit actions.In Volume 2, the bridge-level AI-based maintenance decision policy previously developed in Volume 1 is further integrated into a network-level decision support framework by considering network-level budget and resource constraints. A Pareto Frontier-based ranking approach is proposed to rank the maintenance projects suggested by the bridge-level maintenance policies by holistically considering multiple decision factors. The top-ranked projects are then allocated with the funding and resources for actual implementation. A thorough comparative study is carried out by comparing the efficacy of AI or other condition-based policies at the bridge level under the proposed network-level decision framework and different budget scenarios. It is observed that the AI-based policy outperforms other traditional condition-based policies in almost all considered cases.In conclusion, the research tools developed from this dissertation can not only offer proactive and adaptive bridge maintenance decisions at the individual bridge level, but can also optimize the budget and resource allocation at the network level by better utilizing the limited resources, preserving the overall asset conditions, and reducing the socioeconomic impact due to deteriorating bridge assets.
| Item Type: | Thesis (Doctoral) |
|---|---|
| Thesis advisor: | Du, A |
| Uncontrolled Keywords: | asset management; bridge; cost analysis; decision framework; decision support; deterioration; funding; learning; life cycle; life cycle cost; policy; resource allocation; retrofit; risk assessment; simulation |
| Index terms: | dissertation, implementation, modelling, risk assessment, reinforcement, funding, comparative study, investigation, module, aggregate, life cycle cost analysis, life cycle, decision framework, resource allocation, indirect cost, agent, retrofitting, methodology, resource constraint, asset management, life cycle cost, cost analysis, deterioration, decision support |
| Subjects: | operations management, contractual arrangements, economic analysis, analytical methods, research dissemination and communication, materials science, practitioner, asset management, architectural elements, research methods, financial risk, building materials, material degradation and durability, resource management, financial and cost management, data collection methods, research design and methodology, value management, decision analysis, cost management, renovation and retrofit, economics |
| Topics: | Risk Management, Procurement, Engineering Principles, Project Management, Site Management, Design Practice, Roles and Professions, Cost Management, Business Strategy, Construction Materials, Research Practice |
| Descriptive scope: | 4 PCTA |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here