A New Automated Design Method Based on Machine Learning for CMOS Analog Circuits

ABSTRACT A new simulation based automated CMOS analog circuit design method which applies a multi-objective non-Darwinian-type evolutionary algorithm based on Learnable Evolution Model (LEM) is proposed in this article. The multi-objective property of this automated design of CMOS analog circuits is governed by a modified Strength Pareto Evolutionary Algorithm (SPEA) incorporated in the LEM algorithm presented here. LEM includes a machine learning method such as the decision trees that makes a distinction between high- and low-fitness areas in the design space. The learning process can detect the right directions of the evolution and lead to high steps in the evolution of the individuals. The learning phase shortens the evolution process and makes remarkable reduction in the number of individual evaluations. The expert designer’s knowledge on circuit is applied in the design process in order to reduce the design space as well as the design time. The circuit evaluation is made by HSPICE simulator. In order to improve the design accuracy, bsim3v3 CMOS transistor model is adopted in this proposed design method. This proposed design method is tested on three different operational amplifier circuits. The performance of this proposed design method is verified by comparing it with the evolutionary strategy algorithm and other similar methods.

[1]  Pradip Mandal,et al.  Modeling and design of CMOS analog circuits through hierarchical abstraction , 2013, Integr..

[2]  Pradip Mandal,et al.  CMOS op-amp sizing using a geometric programming formulation , 2001, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[3]  Rob A. Rutenbar,et al.  Anaconda: simulation-based synthesis of analog circuits viastochastic pattern search , 2000, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[4]  Günhan Dündar,et al.  An evolutionary approach to automatic synthesis of high-performance analog integrated circuits , 2003, IEEE Trans. Evol. Comput..

[5]  Brian A. A. Antao,et al.  ARCHGEN: Automated synthesis of analog systems , 1995, IEEE Trans. Very Large Scale Integr. Syst..

[6]  Tomoyuki Hiroyasu,et al.  SPEA2+: Improving the Performance of the Strength Pareto Evolutionary Algorithm 2 , 2004, PPSN.

[7]  Esteban Tlelo-Cuautle,et al.  Sizing Analog Integrated Circuits by Current- Branches-Bias Assignments with Heuristics , 2013 .

[8]  Rob A. Rutenbar,et al.  OASYS: a framework for analog circuit synthesis , 1989, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[9]  Chih-Kong Ken Yang,et al.  Convex Piecewise-Linear Modeling Method for Circuit Optimization via Geometric Programming , 2010, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[10]  Stephen P. Boyd,et al.  Optimal design of a CMOS op-amp via geometric programming , 2001, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[11]  Emil Hjalmarson.  Studies on Design Automation of Analog Circuits - the Design Flow , 2003 .

[12]  LiuBo,et al.  Analog circuit optimization system based on hybrid evolutionary algorithms , 2009 .

[13]  Ryszard S. Michalski,et al.  Learning and Evolution: An Introduction to Non-darwinian Evolutionary Computation , 2000, ISMIS.

[14]  Zheng Wang,et al.  Analog circuit optimization system based on hybrid evolutionary algorithms , 2009, Integr..

[15]  Nuno Horta,et al.  Analog circuits optimization based on evolutionary computation techniques , 2010, Integr..

[16]  David B. Fogel,et al.  Evolution-ary Computation 1: Basic Algorithms and Operators , 2000 .

[17]  Ryszard S. Michalski,et al.  The LEM3 implementation of learnable evolution model and its testing on complex function optimization problems , 2006, GECCO.

[18]  Zbigniew Michalewicz,et al.  Evolutionary Computation 1 , 2018 .

[19]  Fathey M. El-Turky,et al.  BLADES: an artificial intelligence approach to analog circuit design , 1989, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[20]  Lihong Zhang,et al.  A novel analog layout synthesis tool , 2004, 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No.04CH37512).

[21]  Denis Flandre,et al.  Improved synthesis of gain-boosted regulated-cascode CMOS stages using symbolic analysis and gm/ID methodology , 1997 .

[22]  Nuno Horta,et al.  Analog Circuit Design Based on Robust POFs Using an Enhanced MOEA with SVM Models , 2013 .

[23]  Chi-Chou Kao,et al.  ALGA: Automated layout generator for analog CMOS circuits , 2007 .

[24]  Roohollah Nakhaei,et al.  Performance Optimization of Folded Cascode OTA Using an Evolutionary Algorithm , 2013 .

[25]  Eric A. Vittoz,et al.  IDAC: an interactive design tool for analog CMOS circuits , 1987 .

[26]  C.-J. Richard Shi,et al.  IPRAIL - intellectual property reuse-based analog IC layout automation , 2003, Integr..

[27]  Keivan Navi,et al.  A new systematic design approach for low-power analog integrated circuits , 2012 .

[28]  Ryszard S. Michalski,et al.  LEARNABLE EVOLUTION MODEL: Evolutionary Processes Guided by Machine Learning , 2004, Machine Learning.

[29]  Stephen P. Boyd,et al.  Regular Analog/RF Integrated Circuits Design Using Optimization With Recourse Including Ellipsoidal Uncertainty , 2009, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.