Electromechanical Impedance-Based Hybrid Physical Features and Data-Driven Framework for Simulated Damage Identification and Prediction of Composites in Noisy Environments

Data-driven models are transforming structural health monitoring (SHM) for composites. However, excessive sensor costs and scarce, noise-contaminated data hinder model accuracy and generalizability. In this study, an electromechanical impedance (EMI)-based physical features and data-driven framework for high-precision damage assessment under conditions with noise and limited data is proposed. An experimental system that incorporates random noise to simulate operational environment noise was used to simulate seven progressive simulated damage states in CFRP laminates. Adaptive low-pass parabolic filtering via a fast Fourier transform smoothing filter (FFT-SF) denoised conductance signals in the frequency domain, increased efficiency over the Hinkley criterion, and significantly suppressed false alarms from sensor drift. Three input variables were selected: the resonant frequency F (reflecting structural stiffness), the resonant amplitude A (reflecting structural damping), and the root mean square deviation (RMSD) index (a statistical measure of spectral deviation). These three variables, two physics-based features and one statistical index, formed the inputs to a three-input artificial neural network (ANN). The fusion model achieved an RMSE of 0.0752 and an R2 of 0.9807 on 105 small samples, significantly outperforming a purely data-driven single-input RMSD-ANN (RMSE of 0.1066; R2 of 0.9612). Critically, Shapley Additive Explanation (SHAP) analysis revealed that the physical features significantly enhance model interpretability and predictive reliability, maintaining >98% simulated damage identification accuracy with extremely limited real data. This provides a cost-effective, high-precision, and scalable paradigm for aerospace composite SHM.