In the rapidly advancing era of intelligent technology, flexible strain sensors are emerging as a key component in wearable electronics. Laser-induced graphene (LIG) stands out as a promising fabrication method due to its rapid processing, environmental sustainability, low cost, and superior physicochemical properties. However, the stretchability and conformability of LIG are often limited by the substrate material, hindering its application in scenarios requiring high deformation. To address this issue, we propose a high-performance flexible and stretchable strain sensor fabricated by generating graphene on a polyimide (PI) substrate using laser induction and subsequently transferred onto a polydimethylsiloxane (PDMS). The resultant sensor demonstrates an ultra-low detection limit (0.1%), a rapid response time (150 ms), a wide strain range (40%), and retains stable performance after 1000 stretching cycles. Notably, this sensor has been successfully applied to the real-time monitoring of civil aviation test pilots during flight for the first time, enabling the accurate detection of physiological signals such as pulse, hand movements, and blink frequency. This study introduces a unique and innovative solution for the real-time health monitoring of civil aviation test pilots, with significant implications for enhancing flight safety.

Flexible wearable strain sensors demonstrate promising application prospects in health monitoring, human-machine interaction, motion tracking, and the detection of human physiological signals. Although laser-induced graphene (LIG) materials have been extensively utilized in these scenarios, traditional types of LIG sensors are constrained by intrinsic limitations, including discontinuous conductive networks and electromechanical responsive hysteresis. These limitations hinder their applications in micro-strain detection scenarios. Consequently, enhancing the performance of LIG-based sensors has become a crucial priority. To address this challenge, we developed a novel MXene/LIG composite featuring optimized conductive networks and interfacial coupling effects through the systematic enhancement of LIG. The flexible strain sensor fabricated using this composite exhibits exceptional performance, including an ultra-low sheet resistance of 14.1 Ω, a high sensitivity of 20.7, a micro-strain detection limit of 0.05%, and a rapid response time of approximately 65 ms. These improvements significantly enhance electromechanical responsiveness and strain detection sensitivity. Furthermore, the sensor exhibits remarkable stability under varying tensile strains, particularly showing outstanding repeatability across 2500 cyclic tests. Notably, when applied to the pilot health monitoring scenarios, the MXene/LIG-based sensor demonstrates robust capability in detecting body movement signals such as micro-expressions and joint movements. This establishes a novel and highly effective technological solution for the real-time monitoring of pilots’ motion states during operational scenarios.

To address the issue of low accuracy and stability in traditional Convolutional Neural Networks (CNN)-based defect depth prediction for civil aircraft composites, we propose an improved Feature Enhancement Network (FEN)-CNN-Bidirectional Long Short-Term Memory (BiLSTM) impact damage depth prediction method. By integrating terahertz (THz) time-domain, frequency-domain, and absorbance spectroscopy with Confocal Laser Scanning Microscopy (CLSM) depth measurements, the correlation between THz spectral features and impact damage defect depth is systematically elucidated, thereby constructing a “THz features-depth” dataset. Furthermore, by leveraging the FEN model’s feature enhancement and denoising capabilities, along with the BiLSTM model’s bidirectional sequence modeling capability, the underlying relationship between terahertz spectral features and defect depth is deeply learned. This approach improves the stability and accuracy of spectral feature extraction by the CNN model under complex conditions. Ablation experiments revealed the improved model, compared to traditional CNN, reduced Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) by 43.08%, 44.4%, 57.18%, and 34.56%, respectively. Additionally, it decreased the Relative Standard Deviation (RSD) by 32.14%, and increased the Coefficient of Determination (R²) by 6.8%. Comparative experiments demonstrated the proposed model achieved an MSE of 0.0075 and an R² of 0.9539, outperforming other models. This study provides a novel method for precise low-velocity impact damage assessment in carbon fiber reinforced composites, enhancing safety evaluation for civil aircraft composite structures and contributing to aviation safety.