Paper
19 October 2023 Effect of discretization on the structure function method of artificial neural networks
Zhixin Fan, Yikang Wu, Zhaoyang Wei, Jianing Wang
Author Affiliations +
Proceedings Volume 12709, Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023); 127091A (2023) https://doi.org/10.1117/12.2685640
Event: Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023), 2023, Nanjing, China
Abstract
With the rapid development of power devices, the problem of thermal reliability of devices becomes more and more prominent, so how to accurately obtain the thermal resistance of devices is particularly critical. The traditional structure function method is the most effective method to analyze the thermal characteristics of power semiconductor devices at present, but the existing deconvolution algorithm has some problems, such as noise, uncertain number of iterations and long time. This paper presents a new structure function method based on ANN. Build model through ANN, and the sample set measured by Thermal resistance tester is used to train the ANN. Finally, the experimental results of discretization prove that discretization can be used as the output variable of the structural function method of artificial neural networks.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhixin Fan, Yikang Wu, Zhaoyang Wei, and Jianing Wang "Effect of discretization on the structure function method of artificial neural networks", Proc. SPIE 12709, Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023), 127091A (19 October 2023); https://doi.org/10.1117/12.2685640
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Artificial neural networks

Resistance

Education and training

Deconvolution

Thermal modeling

Data modeling

Neurons

Back to Top