Loading...

Seismic Damage Prediction for Non-Structural Building Systems: a Framework Based on Building Information Modeling and Machine Learning

Mousavi, Milad | 2021

529 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 53856 (09)
  4. University: Sharif University of Technology
  5. Department: Civil Engineering
  6. Advisor(s): Alvanchi, Amin
  7. Abstract:
  8. Despite the vulnerability of non-structural systems in buildings to disasters, their resilient design has received minimal attention from the practitioners of the construction industry. However, interruption in the performance of these systems jeopardizes the functionality of the buildings and threatens the resilience of the whole community. To address this issue, the present study proposes a novel framework for predicting possible damage states of non-structural building systems under disasters. The proposed framework benefits from an automated combination of Building Information Modeling (BIM) as a visualized 3D database of the building's components and the Machine Learning (ML) classification techniques as the prediction engine. This framework's applicability is studied first by selecting the exterior infill walls in earthquakes as the target non-structural system. A literature review is conducted to identify the stability features of the exterior non-structural infill walls under earthquakes. Following that, an ML algorithm is developed from samples of exterior infill walls observed in Kermanshah's 2017 earthquake. The results show that the Extremely Randomized Trees (ERT) classifier with up to %87 accuracy can produce the best results for predicting new cases. A system for predicting the damage states of a design scenario's exterior walls under an earthquake similar to the Kermanshah event is developed and implemented. This framework adopts the engineering informatics systems to be at the service of buildings' designers and disaster managers as an additional tool in the design or operation phases to ensure non-structural systems' stability and enhance their resilience to disasters
  9. Keywords:
  10. Building Information Modeling ; Non-Structural Damage ; Machine Learning-based Methods ; Resilient Design ; Damage State Prediction ; Exterior Infill Walls ; Machine Learning-based Classification

 Digital Object List

 Bookmark

No TOC