Vertical GaN diode BV maximization through rapid TCAD simulation and ML-enabled surrogate model

Lu, Albert; Marshall, Jordan M.; Wang, Yifan; Xiao, Ming; Zhang, Yuhao; Wong, Hiu Yung

doi:10.1016/j.sse.2022.108468

Cited by 8 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, principal component analysis (PCA) 17 and analysis of variance (ANOVA) 18 are commonly used to perform sensitivity analysis for input features. ML algorithms, such as Random Forest (RF), Neural Networks (NN) and Support Vector Regression (SVR) have been used in defect detection, 19 electrical performance prediction [20][21][22][23] and the screening and optimization of materials and devices. 18 A multi-objective optimization with ML approach has been applied in device-level design based on novel 2D channel materials 24 and advanced stacked nanosheet transistors.…”

mentioning

confidence: 99%

Physics-Integrated Machine Learning for Efficient Design and Optimization of a Nanoscale Carbon Nanotube Field-Effect Transistor

Fan,

Low

2023

ECS J. Solid State Sci. Technol.

View full text Add to dashboard Cite

We propose a framework for optimizing the design of a carbon nanotube field-effect transistor (CNTFET) through the integration of device physics, machine learning (ML), and multi-objective optimization (MOO). First, we leverage the calibrated TCAD model based on experimental data to dissect the physical mechanisms of the CNTFET, gaining insights into its operational principles and unique physical properties. This model also serves as a foundation, enabling multi-scale performance evaluations essential for dataset construction. In the ML phase, a novel chain structure of support vector regression guided by a comprehensive statistical analysis of the design metrics yields a notable 97.35% accuracy without overfitting, even with limited data. The established ML model exhibits its competence in rapidly producing a global response surface for multi-scale CNTFET. Remarkably, an unusual trend within the CNTFET's behavior has been identified through this process, for which a physics explanation has been provided. We further compare shallow and deep learning-based TCAD digital twins for model selection guidance. Using the non-dominated sorted genetic algorithm-II (NSGA-II) in MOO, we harmonize metrics at both device and circuit levels, significantly reducing the design space. The closed-loop framework expedites the early-stage development of advanced transistors, overcoming the challenges posed by limited data.

show abstract

mentioning

confidence: 99%

Physics-Integrated Machine Learning for Efficient Design and Optimization of a Nanoscale Carbon Nanotube Field-Effect Transistor

Fan,

Low

2023

ECS J. Solid State Sci. Technol.

View full text Add to dashboard Cite

show abstract

AI‐assisted Field Plate Design of GaN HEMT Device

Xiang,

Palash,

Yagyu

et al. 2024

Advcd Theory and Sims

View full text Add to dashboard Cite

GaN High Electron Mobility Transistors (HEMTs) plays a vital role in high‐power and high‐frequency electronics. Meeting the demanding performance requirements of these devices without compromising reliability is a challenging endeavor. Field Plates are employed to redistribute the electric field, minimizing the risk of device failure, especially in high‐voltage operations. While machine learning is applied to GaN device design, its application to field plate structures, known for their geometric complexity, is limited. This study introduces a novel approach to streamlining the field plate design process. It transforms complex 2D field plate structures into a concise feature space, reducing data requirements. A machine learning‐assisted design framework is proposed to optimize field plate structures and perform inverse design. This approach is not exclusive to the design of GaN HEMTs and can be extended to various semiconductor devices with field plate structures. The framework combines technology computer‐aided design (TCAD), machine learning, and optimization, streamlining the design process.

show abstract

General neural network-based static performance prediction model construction techniques for gate-all-around and planar field effect transistor

Chen,

Wu,

et al. 2024

Microelectronics Journal

View full text Add to dashboard Cite

Vertical GaN diode BV maximization through rapid TCAD simulation and ML-enabled surrogate model

Cited by 8 publications

References 7 publications

Physics-Integrated Machine Learning for Efficient Design and Optimization of a Nanoscale Carbon Nanotube Field-Effect Transistor

Physics-Integrated Machine Learning for Efficient Design and Optimization of a Nanoscale Carbon Nanotube Field-Effect Transistor

AI‐assisted Field Plate Design of GaN HEMT Device

General neural network-based static performance prediction model construction techniques for gate-all-around and planar field effect transistor

Contact Info

Product

Resources

About