ENAC Seminar Series by Dr S. Moghtadernejad
Event details
| Date | 03.02.2021 |
| Hour | 09:00 › 09:45 |
| Speaker | Dr Saviz Moghtadernejad |
| Location |
Zoom
Online
|
| Category | Conferences - Seminars |
09:00 – 09:45 – Dr Saviz Moghtadernejad
Postdoctoral fellow at ETH Zürich, Switzerland
Multi-criteria and data-driven decision-making frameworks for the development and management of sustainable and resilient infrastructure
Extreme climate events and conditions, such as floods and heavy storms, whose frequency of occurrence and severity is increasing due to climate change, are threatening the life-cycle performance of infrastructures. Moreover, as the construction industry is playing a significant role in the current climate change crisis, there is an urgent need for minimizing such negative environmental impacts and adopting new strategies to develop and manage resilient and high-performance infrastructure.
As the first step in the development of high-performance and resilient infrastructure, a systematic and multi-objective design paradigm has been introduced and applied to building enclosures to increase the overall building performance. In this design paradigm, Fuzzy multi-criteria decision-making methods and machine learning tools such as artificial neural networks are incorporated to model and assess the individual and collective importance of the objectives. In the second step, to manage and assess the condition states of infrastructure, an automated structural health-monitoring tool was developed and tested on the old Champlain Bridge in Montreal. Application of these methods in real-time monitoring of infrastructure results in significant savings in intervention costs caused by the lack of adequate and timely inspections.
Moreover, due to the fundamental role of infrastructure in the functioning of societies, the speed and costs of restoring them following extreme climate events are of utmost importance. Hence, a novel approach to identify optimal restoration programs was introduced that reduce the time between the occurrence of the extreme event and the moment the restoration work starts, using a double-staged optimization model. The effectiveness of the model was tested in a real-world case study after an extreme flood event in Chur, Switzerland.
Short bio:
Saviz Moghtadernejad is a postdoctoral fellow in the Institute for Construction and Infrastructure Management, in the Department of Civil, Environmental and Geomatic Engineering, at the Swiss Federal Institute of Technology in Zürich (ETHZ), Switzerland. At ETHZ, she works on the determination of optimal restoration programs, to improve asset management schemes for authorities and infrastructure managers and allow for more resilient multi-modal transport infrastructures. Moreover, she works on the application of data-driven methods to estimate deterioration curves of railway supporting structures and to provide solutions for tackling measurement errors and discrepancies in real-world time history inspection data using machine learning algorithms and Markov models. Dr. Moghtadernejad received her PhD in Civil Engineering from McGill University, Canada, where she developed an integrated and systematic paradigm to maximize the resilience and sustainability of buildings. The application of artificial intelligence and expert systems such as Fuzzy integrals and Neural Networks has been incorporated in her research to provide a reliable performance assessment and decision-making tool for choosing elite design alternatives.
Postdoctoral fellow at ETH Zürich, Switzerland
Multi-criteria and data-driven decision-making frameworks for the development and management of sustainable and resilient infrastructure
Extreme climate events and conditions, such as floods and heavy storms, whose frequency of occurrence and severity is increasing due to climate change, are threatening the life-cycle performance of infrastructures. Moreover, as the construction industry is playing a significant role in the current climate change crisis, there is an urgent need for minimizing such negative environmental impacts and adopting new strategies to develop and manage resilient and high-performance infrastructure.
As the first step in the development of high-performance and resilient infrastructure, a systematic and multi-objective design paradigm has been introduced and applied to building enclosures to increase the overall building performance. In this design paradigm, Fuzzy multi-criteria decision-making methods and machine learning tools such as artificial neural networks are incorporated to model and assess the individual and collective importance of the objectives. In the second step, to manage and assess the condition states of infrastructure, an automated structural health-monitoring tool was developed and tested on the old Champlain Bridge in Montreal. Application of these methods in real-time monitoring of infrastructure results in significant savings in intervention costs caused by the lack of adequate and timely inspections.
Moreover, due to the fundamental role of infrastructure in the functioning of societies, the speed and costs of restoring them following extreme climate events are of utmost importance. Hence, a novel approach to identify optimal restoration programs was introduced that reduce the time between the occurrence of the extreme event and the moment the restoration work starts, using a double-staged optimization model. The effectiveness of the model was tested in a real-world case study after an extreme flood event in Chur, Switzerland.
Short bio:
Saviz Moghtadernejad is a postdoctoral fellow in the Institute for Construction and Infrastructure Management, in the Department of Civil, Environmental and Geomatic Engineering, at the Swiss Federal Institute of Technology in Zürich (ETHZ), Switzerland. At ETHZ, she works on the determination of optimal restoration programs, to improve asset management schemes for authorities and infrastructure managers and allow for more resilient multi-modal transport infrastructures. Moreover, she works on the application of data-driven methods to estimate deterioration curves of railway supporting structures and to provide solutions for tackling measurement errors and discrepancies in real-world time history inspection data using machine learning algorithms and Markov models. Dr. Moghtadernejad received her PhD in Civil Engineering from McGill University, Canada, where she developed an integrated and systematic paradigm to maximize the resilience and sustainability of buildings. The application of artificial intelligence and expert systems such as Fuzzy integrals and Neural Networks has been incorporated in her research to provide a reliable performance assessment and decision-making tool for choosing elite design alternatives.
Practical information
- General public
- Invitation required
- This event is internal
Organizer
- ENAC
Contact
- Cristina Perez