Efficient LDMOS Design via Transferable Surrogate Models and Multi-Objective Optimization
- 7 July 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Electron Device Letters
- Vol. 46 (9) , 1593-1596
Abstract
Optimizing LDMOS performance requires balancing breakdown voltage (BV) and specific on-resistance ( $\text {R}_{\text {on},\text {sp}}$ ) under silicon-limit constraints. Conventional technology computer-aided design (TCAD)-based device design is time-consuming and inefficient for large parameter spaces. This work presents a machine learning (ML)-assisted framework that combines initial and fine-tuned deep neural network (DNN) surrogate models with multi-objective particle swarm optimization (MOPSO). The fine-tuned DNN adapts to a non-overlapping extended design space using only a small dataset, while the two surrogates are selectively applied during MOPSO to evaluate candidate designs, enabling significantly faster design evaluation compared to TCAD. SHAP analysis reveals consistent feature importance that aligns with the underlying device physics. The framework constructs diverse Pareto-optimal fronts, offering a scalable solution for automated LDMOS optimization under complex performance trade-offs.Keywords
Funding Information
- Zhejiang Province Key Research and Development programs (2024C01002)
- National Natural Science Foundation of China (62204217)
This publication has 26 references indexed in Scilit:
- Machine Learning-enhanced Multi-dimensional Co-Optimization of Sub-10nm Technology Node Options2019
- 0.18um BCD technology with best-in-class LDMOS from 6 V to 45 V2014
- 0.35μm, 30V fully isolated and low-Ron nLDMOS for DC-DC applications2013
- BCD8sP: An advanced 0.16 μm technology platform with state of the art power devices2013
- Automotive 130 nm smart-power-technology including embedded flash functionality2011
- On the static performance of the RESURF LDMOSFETS for power ICs2009 21st International Symposium on Power Semiconductor Devices & IC's, 2009
- Ultra-low on-resistance LDMOS implementation in 0.13µm CD and BiCD process technologies for analog power IC's2009 21st International Symposium on Power Semiconductor Devices & IC's, 2009
- aBCD18 - An advanced 0.18um BCD technology for PMIC application2009 21st International Symposium on Power Semiconductor Devices & IC's, 2009
- Dielectric resurf: breakdown voltage control by STI layout in standard CMOS2006
- Latin hypercube sampling and the propagation of uncertainty in analyses of complex systemsReliability Engineering & System Safety, 2003