Laser-Induced Graphene-Based Strain Sensor Array Integrated into Smart Tires for a Load Perception.

Area of Science:

• Materials Science
• Sensor Technology
• Artificial Intelligence

Background:

• Tire deformation monitoring is crucial for vehicle safety and intelligent transport.
• Existing flexible strain sensors often lack directional sensitivity and real-world validation for smart tire applications.

Purpose of the Study:

• To fabricate a flexible piezoresistive strain sensor with directional force recognition for smart tires.
• To validate the sensor's performance and real-world applicability in dynamic driving conditions.

Main Methods:

• Fabrication of a porous laser-induced graphene (LIG) and Ecoflex elastomer composite sensor.
• Integration with a convolutional neural network (CNN) for multi-directional stress recognition.
• In-situ testing of the sensor inside passenger car tires under various loads and speeds.

Main Results:

• The LIG-Ecoflex sensor demonstrated a high gauge factor (9.7), fast response/recovery, and over 10,000 cycle stability.
• Combined with CNN, the sensor achieved >98% accuracy in multi-directional stress recognition.
• Reliable tire deformation monitoring correlated with load and velocity was confirmed in real-world driving tests.

Conclusions:

• The developed sensor offers a new approach for direction-aware, high-performance strain sensing in intelligent tires.
• This technology has potential applications in wearable electronics, vehicle health monitoring, and the Internet of Vehicles.