| Author: | Yao, Linyi |
| Title: | An intelligent pavement management framework for heterogeneous and interdependent road networks with enhanced sustainability |
| Advisors: | Leng, Zhen (CEE) Wei, Hsi Hsien (BRE) Xu, Yang (LSGI) |
| Degree: | Ph.D. |
| Year: | 2024 |
| Subject: | Pavements -- Management Roads -- Management Pavements -- Maintenance and repair -- Management Roads -- Maintenance and repair -- Management Hong Kong Polytechnic University -- Dissertations |
| Department: | Department of Civil and Environmental Engineering |
| Pages: | xv, 164 pages : color illustrations |
| Language: | English |
| Abstract: | Pavement systems are an important component of transportation infrastructure, characterized by heterogeneity and interdependence. Pavement segments in a road network are heterogeneous with different structures, traffic loads, and climatic conditions, etc. They are also interdependent, which can be either economic, functional, or stochastic, causing the maintenance and rehabilitation (M&R) strategies of different segments to be interdependent. While these issues can significantly affect maintenance decisions, they also add to the complexity of the problem and are often overlooked. On the other hand, technological advances and sustainable development have also created new requirements and goals for pavement management, requiring the pavement infrastructure to be more intelligent, sustainable, and resilient. To address these problems, this study aims to develop a comprehensive management framework for heterogeneous and interdependent pavement systems. A comprehensive pavement performance modelling and pavement sustainability assessment framework was constructed. Two maintenance optimization models based on the two-stage bottom-up (TSBU) and simultaneous network optimization (SNO) frameworks were then developed. Both models capture the segment heterogeneity and are built upon reinforcement learning (RL), with the difference that TSBU is more computationally efficient while SNO considers the functional dependence among road segments under traffic equilibrium. Comparing the two models allow to estimate the potential impact of ignoring segment interdependencies in maintenance planning. The long-term impact of climate change on asphalt pavements and the benefits of maintenance optimization in mitigating such impacts were also explored. The outcomes of this research indicate that the developed framework was effective in improving pavement management. The performance model can accurately predict pavement conditions, estimate uncertainties, and explore factors affecting pavement degradation. The sustainability assessment framework is able to evaluate pavement sustainability from multiple dimensions and identify critical factors and potential risks. Compared to the current practice, the TSBU model can save about 26.59% of the total cost, and the SNO model can save a further 3% of the total cost, while significantly improving the pavement performance by up to 17.5%. Thus, for access-controlled highway networks, ignoring functional dependencies will not cause large economic losses but may jeopardize pavement performance. Climate change will have different impacts on various pavement performance indicators, and the optimization-based SNO model can effectively mitigate these impacts. The framework developed in this study is expected to significantly improve current pavement management research and practice by providing effective tools and methods, thereby effectively enhancing the intelligence, sustainability, and resilience of road pavement infrastructure. |
| Rights: | All rights reserved |
| Access: | open access |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/12815