A Tensor-based Structural Health Monitoring Approach for\n Aeroservoelastic Systems

2018/12/10 by Prasad Cheema, Cheema, Prasad, Nguyen Lu Dang Khoa +5
Computer Science · Engineering · #Computational Physics and Python Applications #Elasticity and Material Modeling #FOS: Computer and information sciences #Fluid Dynamics and Vibration Analysis #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1812.04845

openalex publication_date 2018/12/10 · openalex created_date 2022/08/01 · openalex updated_date 2026/07/28

Abstract

Structural health monitoring is a condition-based field of study utilised to\nmonitor infrastructure, via sensing systems. It is therefore used in the field\nof aerospace engineering to assist in monitoring the health of aerospace\nstructures. A difficulty however is that in structural health monitoring the\ndata input is usually from sensor arrays, which results in data which are\nhighly redundant and correlated, an area in which traditional two-way matrix\napproaches have had difficulty in deconstructing and interpreting. Newer\nmethods involving tensor analysis allow us to analyse this multi-way structural\ndata in a coherent manner. In our approach, we demonstrate the usefulness of\ntensor-based learning coupled with for damage detection, on a novel N-DoF\nLagrangian aeroservoelastic model.\n

Related

• Incremental Bayesian tensor learning for structural monitoring data imputation and response forecasting
• Online Tensor-Based Learning for Multi-Way Data
• A Fast Parallel Tensor Decomposition with Optimal Stochastic Gradient Descent: an Application in Structural Damage Identification
• Multiple input tangential interpolation-driven damage detection of a jet trainer aircraft
• Semi-supervised and unsupervised learning for health indicator extraction from guided waves in aerospace composite structures