Evaluation of global resilience in large and complex networks of infrastructure (water and wastewater, transport and railway systems etc.) can be computationally a challenging task for resilience promotion in Smart Cities in the future. One of the main reasons is the substantial time required to perform each round of the system simulation and resilience evaluation. As a result, Smart Cities will require innovative strategies to cope with this computational challenge. This study will fill this gap by applying artificial neural network (ANN) to develop a surrogate model that will be used as an implicit global resilience evaluator to reduce the computational time while preserving the accuracy of evaluations.
The approach of this study will have the potential to be extensively used in efficient and effective management of large and complex networks in Smart Cities.
Some potential objectives of this project could be outlined as:
1. To investigate and identify the potential failure states (FSs) of the network (regardless of their origin, all- hazards approach) 2. To define and develop a global resilience measure for the network 3. To develop the ANN-based surrogate model (inputs, outputs, functions….) using FSs and global resilience measure 4. To test and evaluate the surrogate model’s efficiency using two benchmark case-studies (one in water system and one in transport system).
The project will involve computer scientists and engineers from different infrastructure systems. The project will be desktop-based and will require specialist software/tools above what is currently available within the Faculty of Science & Technology. There are potential organisations interested to join and collaborate.
If you wish to be considered for this project, we strongly advise you contact the proposed supervisory team. You will also need to formally apply for our Built Environment PhD. In the section of the application form entitled 'Outline research proposal', please quote the above title and include a research proposal.