.png){kind=icon}
.png){kind=icon}
Return
Sustainable P3HB:ZnO Composite Piezoelectric Nanofibers for AI-Driven Gait Monitoring
.png){kind=icon}
OA
AI
M
K
D
X
Q
H
F
S
DOI：10.1002/smsc.70355.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Degrable, high-performance piezoelectric materials are critical for implantable and environmentally friendly devices capable of reliable sensing and energy harvesting while safely degrading after use. However, most degrable piezoelectric materials still suffer from limited electromechanical performance. Here, we report a high-performance poly(3-hydroxybutyrate):zinc oxide (P3HB:ZnO) composite piezoelectric nanofiber optimized using an integrated artificial neural network-genetic algorithm framework. The model identified an optimal ZnO content of 4.3 wt.%, resulting in significantly enhanced piezoelectric performance compared with pristine P3HB. The optimized nanofibers achieved a peak voltage sensitivity of 0.382 mV/kPa at 1 Hz and an effective piezoelectric voltage coefficient of 13.65 mV/m·N, with stable output over 1000 loading cycles and a response delay of 318 ms. Biodegradation studies showed approximately 38% mass loss after 6 weeks, while the nanofibers retained measurable piezoelectric functionality within this timeframe. Furthermore, integration with a multichannel sensing platform enabled a proof-of-concept AI-assisted gait-recognition demonstration. This work presents a scalable machine-learning-driven strategy for designing high-performance sustainable piezoelectric materials for self-powered transient bioelectronics.
Keywords:
artificial neural network
electrospinning
genetic algorithm
piezoelectricity
sustainable materials
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
S
IF:
8.3
Papers:
1.0K
Citations:
3.2K
Organization
Cited Papers