Next Article in Journal
Inaudible Attack on AI Speakers
Next Article in Special Issue
Field Programmable Analog Array Based Non-Integer Filter Designs
Previous Article in Journal
Heart Rate Variability during Virtual Reality Activity in Individuals after Hospitalization for COVID-19: A Cross-Sectional Control Study
Previous Article in Special Issue
CMOS Widely Tunable Second-Order Gm-C Bandpass Filter for Multi-Sine Bioimpedance Analysis
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Accelerating DC Circuit Simulation through Feature Selection and LSTM-Based Time-Step Control

1
Super Scientific Software Laboratory, China University of Petroleum-Beijing, Beijing 102249, China
2
School of Automation, Southeast University, Nanjing 211189, China
3
Huada Empyrean Software Co., Ltd., Beijing 100102, China
*
Author to whom correspondence should be addressed.
Electronics 2023, 12(8), 1927; https://doi.org/10.3390/electronics12081927
Submission received: 21 March 2023 / Revised: 14 April 2023 / Accepted: 17 April 2023 / Published: 19 April 2023

Abstract

Circuit simulation has become increasingly significant in circuit design with the development of very large scale integration, and direct current (DC) analysis, which serves as the basis of circuit behavior analysis, is the foundation for nonlinear electronic circuit simulation. Among the several continuation algorithms for DC analysis, pseudo-transient analysis (PTA) methods have gained great success. However, PTA tends to be computationally intensive without a proper time-step control method. In order to improve this problem, we propose a novel time-step control method enhanced by advanced deep learning in this paper. Specifically, a coarse and fine-grained hybrid sampling strategy is introduced to find the optimal time step, which resolves the problem that the optimal time step has no precise definition in PTA theory. After that, a long short-term memory (LSTM) network, with the ability to process temporal information, can be employed to learn the optimal time-step control method based on feature selection and a two-stage data preprocessing strategy, which accelerates DC analysis. Furthermore, random forest (RF) is also used to evaluate feature importance, which can achieve feature selection with reduced dimensions, thereby speeding up the network’s training speed and improving the accuracy of prediction. Experimental results demonstrate a significant speedup: up to 61.32 times.
Keywords: DC analysis; pseudo-transient analysis; time-step control; deep learning DC analysis; pseudo-transient analysis; time-step control; deep learning

Share and Cite

MDPI and ACS Style

Jin, Z.; Yang, Z.; Pei, H.; Zha, X.; Bai, Y.; Niu, D.; Zhou, Z.; Wu, X. Accelerating DC Circuit Simulation through Feature Selection and LSTM-Based Time-Step Control. Electronics 2023, 12, 1927. https://doi.org/10.3390/electronics12081927

AMA Style

Jin Z, Yang Z, Pei H, Zha X, Bai Y, Niu D, Zhou Z, Wu X. Accelerating DC Circuit Simulation through Feature Selection and LSTM-Based Time-Step Control. Electronics. 2023; 12(8):1927. https://doi.org/10.3390/electronics12081927

Chicago/Turabian Style

Jin, Zhou, Ziyi Yang, Haojie Pei, Xiaru Zha, Yinuo Bai, Dan Niu, Zhenya Zhou, and Xiao Wu. 2023. "Accelerating DC Circuit Simulation through Feature Selection and LSTM-Based Time-Step Control" Electronics 12, no. 8: 1927. https://doi.org/10.3390/electronics12081927

APA Style

Jin, Z., Yang, Z., Pei, H., Zha, X., Bai, Y., Niu, D., Zhou, Z., & Wu, X. (2023). Accelerating DC Circuit Simulation through Feature Selection and LSTM-Based Time-Step Control. Electronics, 12(8), 1927. https://doi.org/10.3390/electronics12081927

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop