Electroassisted Core-Spun Triboelectric Nanogenerator Fabrics for IntelliSense and Artificial Intelligence Perception

Area of Science:

• Materials Science
• Nanotechnology
• Electronics Engineering

Background:

• IntelliSense fabrics are crucial for flexible and wearable electronics, but current technologies primarily detect quasi-static forces.
• There is a need for fabrics capable of sensing dynamic mechanical interactions for advanced applications.

Purpose of the Study:

• To develop a novel triboelectric nanogenerator yarn for sensing transient mechanical stimuli.
• To enhance the accuracy of material identification using machine learning algorithms.
• To demonstrate the integration of this technology into an IntelliSense system for real-time control and interaction.

Main Methods:

• Fabrication of a sheath-core triboelectric nanogenerator (SC-TENG) yarn using an electroassisted core spinning technique.
• Utilizing a machine learning model (classification coding and recurrent neural network) to analyze output voltage peaks for material identification.
• Integration of SC-TENG yarn with Internet of Things (IoT) techniques for system control.

Main Results:

• The SC-TENG yarn successfully sensed and distinguished instantaneous mechanical stimuli from different materials.
• The machine learning model achieved high accuracy in predicting contact material types based on voltage profiles.
• Demonstrated real-time material identification and control of electronic systems.

Conclusions:

• The developed SC-TENG yarn offers a promising solution for advanced IntelliSense fabrics capable of dynamic mechanical sensing.
• The combination of SC-TENG technology and machine learning significantly improves sensing accuracy and material recognition.
• This technology holds potential for wearable energy harvesting, intelligent fabrics, and enhanced human-machine interfaces.