Physics-Based Artificial Neural Network Assisting in Extracting Transient Properties of Extrinsically Triggering Photoconductive Semiconductor Switches

• Published in: Micromachines (Basel) Vol. 15; no. 8; p. 1003
• Main Authors: Zheng, Zhong, Hu, Huiyong, Wang, Yutian, Zhao, Tianlong, Sun, Qian, Guo, Hui
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.08.2024; MDPI
• Subjects: Artificial neural networks; CAD; Computer aided design; Electric fields; Electrodes; extrinsically triggering photoconductive semiconductor switch (ET-PCSS); Laws, regulations and rules; Mixed mode simulation; Neural networks; Nitrogen; Photoelectric effect; Photoelectric emission; Photoelectricity; Physics; physics-based neural network (NN); Polynomials; regression fitting; Simulation; Spectrum analysis; Switches; Transient current; physics-based neural network (NN); extrinsically triggering photoconductive semiconductor switch (ET-PCSS); mixed-mode simulation; regression fitting
• ISSN: 2072-666X; 2072-666X
• DOI: 10.3390/mi15081003

In this paper, a physics-based ANN assisting method for extracting transient properties of extrinsically triggering photoconductive semiconductor switches (ET-PCSSs) is proposed. It exploits the nonlinear mapping of ANN between transient current (input) and doping concentration (output). According to the basic laws of photoelectric device operating, two types of ANN models are constructed by gaussian and polynomial fitting. The mean absolute error (MAE) of forecasting transient photocurrent can be less than 10 A under low triggering optical powers, which verifies the feasibility of ANN assisting TCAD applied to PCSSs. The results are comparable to computation by Mixed-Mode simulation, yet even thousands of seconds of CPU runtime cost are saved in every period. To improve the robustness of the Poly-ANN predictor, Bayesian optimization (BO) is implemented for minimizing the curl deviation of photocurrent-time curves.