Qin Lu
University of Connecticut
Degrees:
B.S. Beijing Jiaotong University – 2013
M.S. Tongji University – 2016
Ph.D. University of Connecticut – In Progress
Preferred Career after Graduation:
Civil Engineer
Broad research Area:
Damage modeling and evaluation using machine learning and Bayesian network
Specific Research Area:
Risk analysis of overhead power distribution systems
Other Interests & Activities: Reading and hiking
Student Bio: A fourth year Ph.D. student in Civil Engineering
Thesis title: Integrating Surrogate Modeling and Bayesian Updating for Damage Analysis
Thesis Summary: Besides service loads, loads induced by the ambient environment can also cause severe damages to infrastructures, such as hurricane-induced strong winds and fallen trees. Damage assessment is crucial to infrastructure management and mitigation strategy planning. Due to the uncertainties from loads, material properties, and empirical models used to describe the structural damages, the probabilistic damage assessment could be extremely time-consuming if feasible given that each damage simulation could be computationally expensive. Establishment of probabilistic and temporal load models can also be challenging because of data scarcity. In addition, material deterioration due to corrosive environments can make structural damage assessment a time-dependent process. To address these challenges, this dissertation proposes a list of efficient numerical schemes by integrating surrogate modeling and dynamic Bayesian network (DBN).
The probabilistic damage assessment of two structures with material degradation issues are discussed. For the coastal slender bridge, the temporal sequences of vehicle, wind and wave loads are simulated by Markov Chain Monte Carlo simulations based on the data collected by the in-field data-collecting systems. In a DBN framework, the evolution of the fatigue crack length in orthotropic steel deck (OSD) is evaluated with facilitation of surrogate model used to predict the fatigue crack length growth. For the overhead power distribution system (OPDS) composed of wooden poles, the risk model of fallen trees is developed using computer vision technique and the risk model of hurricane-induced wind is established through machine learning-based statistical model combined with historical hurricane track data. In the static analysis of OPDS subjected to wind loads, surrogate models are developed to predict the moments of poles using selected features as predictors. In the dynamic analysis of OPDS, physics-informed long short-term memory algorithm is utilized to predict the dynamic response of poles. The uncertainties of the material properties are reduced within the DBN framework to improve the damage assessment accuracy. The optimal hardening strategy for OPDS is selected through Bayesian decision network.
Presentation
Poster
