A Temperature Prediction Model for Flexible Electronic Devices Based on GA-BP Neural Network and Experimental...

Area of Science:

• Materials Science
• Electrical Engineering
• Computational Science

Background:

• Real-time thermal safety evaluation of flexible electronics is challenging.
• Existing methods for thermal analysis are often costly and time-consuming.
• Accurate temperature prediction is crucial for the reliability and longevity of flexible devices.

Purpose of the Study:

• To develop a computationally efficient and accurate model for predicting the thermal behavior of flexible electronic devices.
• To address the limitations of traditional thermal simulation and experimental methods.
• To establish a robust system for real-time thermal safety assessment.

Main Methods:

• A genetic algorithm-optimized backpropagation neural network (GA-BPNN) was developed.
• Finite element analysis software was used to simulate temperature data under various operating conditions.
• The GA-BPNN model was trained using simulated data and validated with experimental results.

Main Results:

• The GA-BPNN model demonstrated a prediction variance not exceeding 0.57 °C with good robustness.
• Thermal validation experiments showed prediction errors less than 0.9 °C compared to actual measurements.
• The model achieved high computational efficiency, significantly outperforming traditional methods.

Conclusions:

• The GA-BPNN model provides a rapid and accurate solution for real-time temperature prediction in flexible electronics.
• The developed model offers significant advantages in computational efficiency and integrated hardware-software application.
• This approach enhances the thermal safety evaluation and reliability of flexible electronic systems.