Accelerating DC Circuit Simulation through Feature Selection and LSTM-Based Time-Step Control
Open Access
- 19 April 2023
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 12 (8) , 1927
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
Funding Information
- National Key RD Program of China (2022YFB4400400, 62234010, 62204265)
- Key Program of the National Natural Science Foundation of China (2022YFB4400400, 62234010, 62204265)
This publication has 17 references indexed in Scilit:
- An Adaptive Time-Step Control Method in Damped Pseudo-Transient Analysis for Solving Nonlinear DC Circuit EquationsIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2017
- An Effective Embed Algorithm for Newton Fixed-Point Homotopy Method in MOS Transistor CircuitsInternational Journal of Information and Electronics Engineering, 2015
- Jumping NLP Curves: A Review of Natural Language Processing Research [Review Article]IEEE Computational Intelligence Magazine, 2014
- A PTA method using numerical integration algorithms with artificial damping for solving nonlinear DC circuitsNonlinear Theory and Its Applications, IEICE, 2014
- Effective Implementation and Embedding Algorithms of CEPTA Method for Finding DC Operating PointsIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2013
- A Practical Regularization Technique for Modified Nodal Analysis in Large-Scale Time-Domain Circuit SimulationIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2012
- An Effective SPICE3 Implementation of the Compound Element Pseudo-Transient AlgorithmIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2007
- A study of convergence on the Newton-homotopy continuation methodApplied Mathematics and Computation, 2005
- A fixed-point homotopy method for solving modified nodal equationsIEEE Transactions on Circuits and Systems I: Regular Papers, 1999
- Convergence Analysis of Pseudo-Transient ContinuationSIAM Journal on Numerical Analysis, 1998