Health indicators (HIs) are central to diagnosing and prognosing the condition of aerospace composite structures, enabling efficient maintenance and operational safety. However, extracting reliable HIs remains challenging due to variability in material properties, stochastic damage evolution, and diverse damage modes. Manufacturing defects (e.g. disbonds) and in-service incidents (e.g. bird strikes) further complicate this process. This study presents a comprehensive data-driven framework that learns HIs via two learning approaches integrated with multi-domain signal processing. Because ground-truth HIs are unavailable, a semi-supervised and an unsupervised approach are proposed: (i) a diversity deep semi-supervised anomaly detection (Diversity-DeepSAD) approach augmented with continuous auxiliary labels used as hypothetical damage proxies, which overcomes the limitation of prior binary labels and enables modelling of intermediate degradation, and (ii) a degradation-trend-constrained variational autoencoder (DTC-VAE), in which the monotonicity criterion is embedded via an explicit trend constraint. Guided waves with multiple excitation frequencies are used to monitor single-stiffener composite structures under fatigue loading. Time, frequency, and time–frequency representations are explored, and per-frequency HIs are fused via unsupervised ensemble learning to mitigate frequency dependence and reduce variance. Using fast Fourier transform features, the models achieved fitness scores of 81.6% (Diversity-DeepSAD) and 92.3% (DTC-VAE), indicating improved monotonicity and consistency over existing baselines. The proposed history-independent framework, supported by prognostic metrics–guided Bayesian optimisation and excitation frequency-agnostic HI fusion, enables the estimation of more robust HIs for aeronautical composite structures.

Touchscreens are used increasingly in moving environments, where they can in fact be very difficult to use. A key issue is biodynamic feedthrough (BDFT): perturbing finger movements induced by feedthrough of motion accelerations (e.g., turbulence) through users' outstretched arms. Modeling the BDFT dynamics allows such erroneous components of touchscreen inputs to be computationally removed. Estimating accurate BDFT models using system identification methods traditionally requires experiments with prolonged measurement times. However, for touchscreen BDFT measurements, where participants generally keep their arms outstretched for the full measurement duration, long measurements lead to muscle fatigue, which impacts data quality. By means of a dedicated human-in-the-loop simulator experiment, this paper shows that reducing the measurement duration to around 30 s does not significantly affect participants BDFT dynamics, or our ability to model them. As a result, these experimental findings enable future investigations to use shorter measurement times to increase participant comfort without compromising BDFT model quality.