Smart EMI monitoring of thin composite structures

International audienceThis paper presents a structural health monitoring (SHM) method for in-situ damage detection and localization in carbon fibre reinforced plates (CFRP). The detection isachieved using the electromechanical impedance (EMI) technique employing piezoelectric transducers as high-frequency modal sensors. Numerical simulations based on the finite element method are carried out so as to simulate more than a hundred damage scenarios. Damage metrics are then used to quantify and detect changes between the electromechanical impedance spectrum of a pristine and damaged structure. The localization process relies on artificial neural networks (ANN) whose inputs are derived from a principal component analysis of the damage metrics. It is shown that the resulting ANN can be used as a tool to predict the in-plane position of a single damage in a laminated composite plate