Home - Laboratory for Structural Efficiency (LASE)

Graph neural network-based stress field prediction in stiffened panels
Our GNN-based approach for stress prediction effectively captures entire stress field in stiffened panels under various loadings and with wide geometrical variations. For more, please see: Y. Cai, J. Jelovica (2024) Efficient graph representation in graph neural networks for stress predictions in stiffened panels. Thin-Walled Structures, Vol. 203, 112157. Read More
KATO: Neural-reparameterized topology optimization framework
Our novel neural-reparameterization for topology optimization generates stress-optimal structures by training a convolutional KAN network. The framework is completely data-free, outperforming MMA and CNN models. For more, see: S. Yan, J. Jelovica (2025) KATO: Neural-reparameterized topology optimization using convolutional Kolmogorov-Arnold network for stress minimization, International Journal for Numerical Methods in Engineering, Vol. 126:e70034, Read More
Structural vibrations in engine room of a ship
Our graduate students participated in vibration and noise measurements in engine room of a science vessel. Thank you Yuecheng, Jason and Mostafa for your help. Read More
Analytical assessment of nonlinear forced vibration of functionally graded porous beams
Our recent paper published in Composite Structures journal (https://doi.org/10.1016/j.compstruct.2022.115994). Read More
Stress-based topology optimization of sandwich panel’s joints
Our recent paper in OMAE 2022 conference presents topology optimization of joints for prismatic sandwich panels. Stress is minimized for a range of material volume fractions. In comparison to conventional joint, maximum von Mises stress is reduced 2-3 times for a few loading scenarios. Read More
Neural network-assisted constraint handling in evolutionary optimization algorithms
One of our research topics is on improving the performance of evolutionary (and swarm) optimization algorithms – here we propose a method to make them more efficient when dealing with complex structural problems. Read More

Welcome to the website of Structural Efficiency Laboratory. Our motto is: Get more out of a structure.

Our focus is modeling behavior of innovative structural components that offer advanced mechanical properties. In addition to mechanics, we focus on development of optimization and machine learning algorithms to create more advanced structures and systems. To allow production of these structures, we are investigating advanced welding techniques to ensure high quality and structural integrity.

Home Departments

We are supported by Departments of Mechanical Engineering and Civil Engineering at The University of British Columbia (UBC), Vancouver.

Funding support

Graph neural network-based stress field prediction in stiffened panels

KATO: Neural-reparameterized topology optimization framework

Structural vibrations in engine room of a ship

Analytical assessment of nonlinear forced vibration of functionally graded porous beams

Stress-based topology optimization of sandwich panel’s joints

Neural network-assisted constraint handling in evolutionary optimization algorithms

Welcome to the website of Structural Efficiency Laboratory. Our motto is: Get more out of a structure.