3D Bristle-Structured, Knitted-Fabric-Based Triboelectric Sensors for Machine Learning-Based Motion Recognition

Area of Science:

• Materials Science
• Textile Engineering
• Sensor Technology

Background:

• Triboelectric-based sensors are gaining traction in healthcare and sports due to their self-powering capabilities and ease of manufacturing.
• 3D fabric-based triboelectric sensors offer advantages like breathability and enhanced surface area for improved sensitivity.

Purpose of the Study:

• To develop and investigate a novel 3D bristle-structured fabric for triboelectric sensor applications using digital knitting technology.
• To enhance the sensitivity and output performance of triboelectric sensors through increased specific surface area and microcapacitor effects.

Main Methods:

• Digital knitting technology was employed to create a 3D bristle-structured fabric.
• The performance of single jersey fabrics integrated with 3D bristle structures was systematically evaluated.
• Machine learning was integrated for motion recognition in a baseball pitching self-training system.

Main Results:

• The optimal 3D bristle-structured fabric sample demonstrated a 57% increase in output voltage compared to a standard 2D fabric.
• The 3D bristle structure effectively increased the specific surface area, leading to higher surface charge density.
• The developed fabric exhibited linear high sensitivity and distinct output performance as a sensor.

Conclusions:

• The 3D bristle-structured fabric presents a promising advancement for high-performance triboelectric sensors.
• This technology can be applied to create more sensitive and efficient wearable electronic devices.
• The integration with machine learning enables practical applications, such as intelligent sports training systems.