Transfer Learning Across Heterogeneous Structures for Large-Scale Structural Health Monitoring Purposes
January 31 @ 11:30 am - 12:30 pm
| Speaker: Hesam Soleimani, Ph.D. IDRE Postdoctoral Fellow Civil Engineering University of California Los Angeles
|
 |
Abstract: Urban infrastructure encompasses diverse systems, from residential buildings to critical facilities like power and transportation. Structural Health Monitoring (SHM) provides a framework to ensure the safety and continuity of these infrastructure systems by distinguishing between non-damaged and damaged states. The traditional methods for monitoring the health of such infrastructure face challenges in terms of scalability and generalizability. Emerging approaches, including Generative Adversarial Networks (GANs), Contrastive Learning, and Transfer Learning (TL), combined with SHM domain knowledge, address these limitations by enabling SHM models to function effectively without requiring observed damaged states. The presentation will cover these advancements, including research endeavors in the Taciroglu Research Group (TRG) at UCLA, that pave the way for scalable and reliable SHM in complex urban environments.
About the speaker: Dr. Soleimani is an IDRE fellow and a postdoctoral researcher in the Civil Engineering department at the Samueli School of Engineering. He holds a Ph.D. in Civil Engineering and an MSc in Computer Science, both obtained from Virginia Tech and his research has always been at the intersection of these two areas.