Teimouri, H. (2015) A New Statistical Approach to Strain-Based Structural Health Monitoring of Composites under Uncertainty. PhD Dissertation in Mechanical Engineering, University of British Columbia, BC, Canada.

has been cited by the following article:

• TITLE: On the Impact of Manufacturing Uncertainty in Structural Health Monitoring of Composite Structures: A Signal to Noise Weighted Neural Network Process

  AUTHORS: Hessamodin Teimouri, Abbas S. Milani, Rudolf Seethaler, Amir Heidarzadeh

  KEYWORDS: Composite Structures, Manufacturing Uncertainties, Structural Health Monitoring, Artificial Neural Networks, Signal-to-Noise Weighting

  JOURNAL NAME: Open Journal of Composite Materials, Vol.6 No.1, January 22, 2016

  ABSTRACT: This article investigates the potential impact of manufacturing uncertainty in composite structures here in the form of thickness variation in laminate plies, on the robustness of commonly used Artificial Neural Networks (ANN) in Structural Health Monitoring (SHM). Namely, the robustness of an ANN SHM system is assessed through an airfoil case study based on the sensitivity of delamination location and size predictions, when the ANN is imposed to noisy input. In light of the observed poor performance of the original network, even when its architecture was carefully optimized, it had been proposed to weigh the input layer of the ANN by a set of signal-to-noise (SN) ratios and then trained the network. Both damage location and size predictions of the latter SHM approach were increased to above 90%. Practical aspects of the proposed robust SN-ANN SHM have also been discussed.