1Department of Electrical Engineering, San Jose State University, San Jose, CA 95112, USA
2Virginia Polytechnic Institute, State University, Blacksburg, VA 24060, USA
3Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA 90089, USA
4Development Department, Novel Crystal Technology Inc., Sayama 3501328, Japan
Abstract: This work, for the first time, experimentally demonstrates a TCAD-Machine Learning (TCADML) framework to assist the analysis of device-to-device variation and operating (ambient) temperature without the need of physical quantities extraction. The ML algorithm used in this work is the Principal Component Analysis (PCA) followed by third order polynomial regression. After calibrated to limited ‘expensive’ experimental data, ‘low cost’ TCAD simulation is used to generate a large amount of device data to train the ML model. The ML was then used to identify the root cause of device variation and operating temperature from any given experimental current-voltage (I-V) characteristics. We applied this framework to study the ultra-wide-bandgap gallium oxide (Ga2O3) Schottky barrier diode (SBD), an emerging device technology that holds great promise for temperature sensing, RF, and power applications in harsh environments. After calibration, over 150,000 electrothermal TCAD simulations are performed with random variation of physical parameters (anode effective work function, drift layer doping, and drift layer thickness) and operating temperature. An ML model is trained using these TCAD data and we found 1,000-10,000 TCAD data can train an accurate machine. We show that without physical quantities extraction, performing PCA is essential for the TCAD trained ML model to be applicable to analyze experimental characteristics. The physical parameters and temperatures predicted by the ML model show good agreement with experimental analysis. Our TCAD-ML framework shows great promise to accelerate the development of new device technologies with a significantly more efficient process of material and device experimentation.
FIG: Flow chart diagram of the proposed TCAD-Machine Learning framework. All components are demonstrated in this article except the MLDatabase which stores previously trained ML algorithms.
Acknowledgment: The authors thank Dr. Pooya Jannaty of Cruise and Dr. Philip Leong of the University of Sydney for the discussion of ML algorithms. The experimental work is in part supported by the Southeastern Center for Electrical Engineering Education program and the High Density Integration industry mini-consortium of the Center for Power Electronics Systems at Virginia Tech.
