Multi-layered gradient-structured TPU/CNTs aerogel with ultra-wide pressure detection capabilities for machine learning–assisted fruit recognition

In recent years, as wearable electronics continue to advance toward flexible, lightweight, and versatile designs, flexible pressure sensors with wide response ranges and high sensitivity have shown tremendous research value and application potential. In this study, we fabricated TPU-based flexible pressure sensors with a multistage gradient porous structure using layer-by-layer freezing and solvent templating techniques. Due to the layered differences in Young’s modulus from varying porosities, these sensors exhibit high pressure sensitivity (S, S_MAX = 34.08 MPa⁻¹) and can accurately distinguish stresses across a wide range (0–1.2 MPa). Additionally, they demonstrate rapid response and recovery times (140 ms), durability over 3000 compression cycles, and the ability to detect both subtle movements (facial expressions and swallowing) and larger actions (joint bends, walking, and running). Furthermore, we developed a smart glove using these gradient-structured pressure sensors combined with a K-nearest neighbor (KNN) algorithm, enabling accurate identification of various fruit types. Notably, the TPU sensors also exhibit excellent thermal insulation and Joule heating properties, making them effective for human thermal management even in extreme temperatures.