3 papers
cs.LG2021
A Data-Driven Approach to Full-Field Damage and Failure Pattern Prediction in Microstructure-Dependent Composites using Deep Learning
Reza Sepasdar, Anuj Karpatne, Maryam Shakiba
An image-based deep learning framework is developed in this paper to predict damage and failure in microstructure-dependent composite materials. The work is motivated by the comple…
cs.LG2021
System-reliability based multi-ensemble of GAN and one-class joint Gaussian distributions for unsupervised real-time structural health monitoring
Mohammad Hesam Soleimani-Babakamali, Reza Sepasdar, Kourosh Nasrollahzadeh +1
Unsupervised health monitoring has gained much attention in the last decade as the most practical real-time structural health monitoring (SHM) approach. Among the proposed unsuperv…
physics.comp-ph2019
Overcoming the Convergence Difficulty of Cohesive Zone Models through a Newton-Raphson Modification Technique
Reza Sepasdar, Maryam Shakiba
This paper studies the convergence difficulty of cohesive zone models in static analysis. It is shown that an inappropriate starting point of iterations in the Newton-Raphson metho…