Scholarlink

<p>The development of durable, intelligent wound-care systems is hindered by the mechanical fragility and signal instability of conventional flexible electronics. To address these limitations, this study presents a self-healing smart bandage integrating 2D material–based conductive networks, multimodal sensing, and AI-driven wound-state analytics. The objective is to design and simulate a fully flexible, self-repairing electronic platform capable of monitoring temperature, pH, moisture, and strain while maintaining long-term performance under repetitive deformation. Using COMSOL Multiphysics, the mechanical, electrical, and thermal behavior of a MXene/GO/MoS<sub>2</sub>–hydrogel composite was evaluated, demonstrating 94.7% mechanical healing efficiency, 93.9% electrical conductivity restoration, and temperature measurement accuracy within ± 0.35&#xa0;°C. Sensor-level simulations confirmed stable biochemical and mechanical responses after healing, while wireless modules achieved reliable BLE transmission up to 5&#xa0;m. MATLAB-based signal processing improved sensor signal-to-noise ratio by more than 70%, enabling clear feature separation across wound states. Machine-learning and deep-learning models, particularly LSTM networks, achieved 96% classification accuracy with an AUC of 0.97 and average prediction lag below 4&#xa0;min in early infection detection. These results establish a strong computational foundation for the experimental development of self-healing, AI-enabled smart bandages with significant potential for real-time, personalized wound management.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Self-healing 2D material composites for intelligent smart bandages: Multiphysics simulation and AI-enabled wound assessment

  • 期刊论文

  • 发表日期：

    2026年5月14日

查看全文
  • Gayatri Padole,
  • Pravin B. Pokle

摘要

The development of durable, intelligent wound-care systems is hindered by the mechanical fragility and signal instability of conventional flexible electronics. To address these limitations, this study presents a self-healing smart bandage integrating 2D material–based conductive networks, multimodal sensing, and AI-driven wound-state analytics. The objective is to design and simulate a fully flexible, self-repairing electronic platform capable of monitoring temperature, pH, moisture, and strain while maintaining long-term performance under repetitive deformation. Using COMSOL Multiphysics, the mechanical, electrical, and thermal behavior of a MXene/GO/MoS2–hydrogel composite was evaluated, demonstrating 94.7% mechanical healing efficiency, 93.9% electrical conductivity restoration, and temperature measurement accuracy within ± 0.35 °C. Sensor-level simulations confirmed stable biochemical and mechanical responses after healing, while wireless modules achieved reliable BLE transmission up to 5 m. MATLAB-based signal processing improved sensor signal-to-noise ratio by more than 70%, enabling clear feature separation across wound states. Machine-learning and deep-learning models, particularly LSTM networks, achieved 96% classification accuracy with an AUC of 0.97 and average prediction lag below 4 min in early infection detection. These results establish a strong computational foundation for the experimental development of self-healing, AI-enabled smart bandages with significant potential for real-time, personalized wound management.