A Reinforcement-Learning Based Approach for Designing High-Voltage SiC MOSFET Guard Rings
For high-power silicon carbide (SiC) devices, breakdown voltage analysis is an important parameter, especially for guard ring design. This work explores the implementation of machine learning on SiC guard ring parameters such as ion implanted dose and energy. In this work, the reinforcement learning...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Power Electronics |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10752388/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533439786876928 |
|---|---|
| author | Tejender Singh Rawat Chia-Lung Hung Yi-Kai Hsiao Wei-Chen Yu Surya Elangovan Wei-Ting Lin Yi-Rong Lin Kai-Lin Yang Nien-Yi Jan Yung-Hui Li Hao-Chung Kuo |
| author_facet | Tejender Singh Rawat Chia-Lung Hung Yi-Kai Hsiao Wei-Chen Yu Surya Elangovan Wei-Ting Lin Yi-Rong Lin Kai-Lin Yang Nien-Yi Jan Yung-Hui Li Hao-Chung Kuo |
| author_sort | Tejender Singh Rawat |
| collection | DOAJ |
| description | For high-power silicon carbide (SiC) devices, breakdown voltage analysis is an important parameter, especially for guard ring design. This work explores the implementation of machine learning on SiC guard ring parameters such as ion implanted dose and energy. In this work, the reinforcement learning method has been successfully implemented on the 1.7 kV SiC guard ring device TCAD simulated data for the prediction of parameters. Our work has predicted the parameters successfully for the 2.5 kV guard ring design. For training, proximal policy optimization (PPO) and advantage actor-critic (A2C) RL agents were deployed. The network architecture was kept at “auto” with 3 hidden layers of 128 neurons in each layer. Our method is practically feasible and easily implemented as compared to other works, and has been shown in this paper. By using the limited design parameters of the 1.7 kV guard ring device, the trained agent has successfully predicted the design parameters for the 2.5 kV guard ring device, which has been confirmed using TCAD simulations. This work is more accurate, practical, and result-oriented, and we believe that this can significantly minimize the computational cost as compared to the standalone TCAD simulations. Also, this implementation of ML on TCAD data can substantially accelerate the design exploration for the power devices and ultimately lower product-to-market time. |
| format | Article |
| id | doaj-art-c984072a957645a6ae41fee698ca4e6d |
| institution | Kabale University |
| issn | 2644-1314 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Power Electronics |
| spelling | doaj-art-c984072a957645a6ae41fee698ca4e6d2025-01-16T00:02:27ZengIEEEIEEE Open Journal of Power Electronics2644-13142024-01-0151853186110.1109/OJPEL.2024.349686510752388A Reinforcement-Learning Based Approach for Designing High-Voltage SiC MOSFET Guard RingsTejender Singh Rawat0https://orcid.org/0000-0001-7894-0463Chia-Lung Hung1https://orcid.org/0000-0002-6200-2517Yi-Kai Hsiao2https://orcid.org/0009-0005-7985-9188Wei-Chen Yu3https://orcid.org/0009-0009-1128-0195Surya Elangovan4Wei-Ting Lin5Yi-Rong Lin6Kai-Lin Yang7Nien-Yi Jan8https://orcid.org/0009-0003-6029-1882Yung-Hui Li9https://orcid.org/0000-0002-0475-3689Hao-Chung Kuo10Semiconductor Research Center, Hon Hai Research Institute (HHRI), Foxconn, TaiwanSemiconductor Research Center, Hon Hai Research Institute (HHRI), Foxconn, TaiwanSemiconductor Research Center, Hon Hai Research Institute (HHRI), Foxconn, TaiwanSemiconductor Research Center, Hon Hai Research Institute (HHRI), Foxconn, TaiwanSemiconductor Research Center, Hon Hai Research Institute (HHRI), Foxconn, TaiwanSemiconductor Research Center, Hon Hai Research Institute (HHRI), Foxconn, TaiwanAI Research Center, Hon Hai Research Institute (HHRI), Foxconn, TaiwanAI Research Center, Hon Hai Research Institute (HHRI), Foxconn, TaiwanAI Research Center, Hon Hai Research Institute (HHRI), Foxconn, TaiwanAI Research Center, Hon Hai Research Institute (HHRI), Foxconn, TaiwanSemiconductor Research Center, Hon Hai Research Institute (HHRI), Foxconn, TaiwanFor high-power silicon carbide (SiC) devices, breakdown voltage analysis is an important parameter, especially for guard ring design. This work explores the implementation of machine learning on SiC guard ring parameters such as ion implanted dose and energy. In this work, the reinforcement learning method has been successfully implemented on the 1.7 kV SiC guard ring device TCAD simulated data for the prediction of parameters. Our work has predicted the parameters successfully for the 2.5 kV guard ring design. For training, proximal policy optimization (PPO) and advantage actor-critic (A2C) RL agents were deployed. The network architecture was kept at “auto” with 3 hidden layers of 128 neurons in each layer. Our method is practically feasible and easily implemented as compared to other works, and has been shown in this paper. By using the limited design parameters of the 1.7 kV guard ring device, the trained agent has successfully predicted the design parameters for the 2.5 kV guard ring device, which has been confirmed using TCAD simulations. This work is more accurate, practical, and result-oriented, and we believe that this can significantly minimize the computational cost as compared to the standalone TCAD simulations. Also, this implementation of ML on TCAD data can substantially accelerate the design exploration for the power devices and ultimately lower product-to-market time.https://ieeexplore.ieee.org/document/10752388/Breakdown voltagemachine learningpower devicereinforcement learningSiC guard ring design |
| spellingShingle | Tejender Singh Rawat Chia-Lung Hung Yi-Kai Hsiao Wei-Chen Yu Surya Elangovan Wei-Ting Lin Yi-Rong Lin Kai-Lin Yang Nien-Yi Jan Yung-Hui Li Hao-Chung Kuo A Reinforcement-Learning Based Approach for Designing High-Voltage SiC MOSFET Guard Rings IEEE Open Journal of Power Electronics Breakdown voltage machine learning power device reinforcement learning SiC guard ring design |
| title | A Reinforcement-Learning Based Approach for Designing High-Voltage SiC MOSFET Guard Rings |
| title_full | A Reinforcement-Learning Based Approach for Designing High-Voltage SiC MOSFET Guard Rings |
| title_fullStr | A Reinforcement-Learning Based Approach for Designing High-Voltage SiC MOSFET Guard Rings |
| title_full_unstemmed | A Reinforcement-Learning Based Approach for Designing High-Voltage SiC MOSFET Guard Rings |
| title_short | A Reinforcement-Learning Based Approach for Designing High-Voltage SiC MOSFET Guard Rings |
| title_sort | reinforcement learning based approach for designing high voltage sic mosfet guard rings |
| topic | Breakdown voltage machine learning power device reinforcement learning SiC guard ring design |
| url | https://ieeexplore.ieee.org/document/10752388/ |
| work_keys_str_mv | AT tejendersinghrawat areinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT chialunghung areinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT yikaihsiao areinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT weichenyu areinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT suryaelangovan areinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT weitinglin areinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT yironglin areinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT kailinyang areinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT nienyijan areinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT yunghuili areinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT haochungkuo areinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT tejendersinghrawat reinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT chialunghung reinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT yikaihsiao reinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT weichenyu reinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT suryaelangovan reinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT weitinglin reinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT yironglin reinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT kailinyang reinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT nienyijan reinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT yunghuili reinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings AT haochungkuo reinforcementlearningbasedapproachfordesigninghighvoltagesicmosfetguardrings |