Abstract

Operational transconductance amplifiers (OTA) are critical components in the design of analog circuits. Traditionally, designers have relied on methods such as square law, iterative simulation, and bias point simulation to determine the geometry of amplifiers. However, the miniaturization of transistors introduces effects like short channel and moderate weak inversion that compromise the effectiveness of these techniques. The gm/Id technique adeptly addresses these issues by employing a graphical strategy that analyses transistor characteristics, providing robust solutions to these miniaturization challenges. Building on this, the work used employed machine learning (ML) to further enhance design efficiency and accuracy. By integrating linear and polynomial regression, a significant improvement in the OTA design is demonstrated. The amplifier designed by the regression models yielded a gain of 42 dB for the polynomial regression and 36 dB for the linear regression, as compared to 32 dB in the gm/Id methodology. However, this performance gain incurs a slight power consumption increase of 20 μW. The ML approach demonstrated inherent adaptability and efficiency, particularly in its flexibility and speed when faced with changing input specifications. Polynomial regression model achieved an R2 Score of 0.935 with mean absolute percentage error of 7.5%, indicating high predictive accuracy. This integration of ML significantly reduces design automation time, addressing a major limitation of conventional methods and suggesting a transformative shift in analog circuit design strategies.

Keyword

Operational transconductance amplifiers, gm/Id method, Machine learning, Linear regression, Polynomial regression, Power consumption.

Cite this article

Sahoo DK, Bhuyan KC, Mishra C.Design of an operational transconductance amplifier configuration using machine learning. International Journal of Advanced Technology and Engineering Exploration. 2024;11(118):1286-1307. DOI:10.19101/IJATEE.2023.10102518

Refference

[1]Agbo SO, Fabricius ED. Integrated circuit design. In microelectronics 2018 (pp. 6-1). CRC Press.

[2]Girardi A, De-oliveira T, Ghissoni S, Aguirre PC, Compassi-severo L. A comprehensive review on automation-based sizing techniques for analog IC design. Journal of Integrated Circuits and Systems. 2022; 17(3):1-4.

[3]Eskiyerli M, Payne A. Square root domain filter design and performance. Analog Integrated Circuits and Signal Processing. 2000; 22:231-43.

[4]Gerlach A, Scheible J, Rosahl T, Eitrich FT. A generic topology selection method for analog circuits with embedded circuit sizing demonstrated on the OTA example. In design, automation & test in Europe conference & exhibition 2017 (pp. 898-901). IEEE.

[5]Javid F, Iskander R, Durbin F, Louërat MM. Analog circuits sizing using the fixed point iteration algorithm with transistor compact models. In proceedings of the 19th international conference mixed design of integrated circuits and systems-MIXDES 2012 (pp. 45-50). IEEE.

[6]Wu J, Wu C, Zhang W, Zhang C, Chen W. Manipulation of bilayer MoS2-based MESFET with flexoelectric polarization field. Nano Energy. 2024; 123:109415.

[7]Afacan E, Lourenço N, Martins R, Dündar G. Machine learning techniques in analog/RF integrated circuit design, synthesis, layout, and test. Integration. 2021; 77:113-30.

[8]Ghai D, Mohanty SP, Thakral G. Fast analog design optimization using regression-based modeling and genetic algorithm: a nano-CMOS VCO case study. In international symposium on quality electronic design 2013 (pp. 406-11). IEEE.

[9]Silveira F, Flandre D, Jespers PG. A g/sub m//i/sub d/based methodology for the design of CMOS analog circuits and its application to the synthesis of a silicon-on-insulator micropower OTA. IEEE Journal of Solid-State Circuits. 1996; 31(9):1314-9.

[10]Sabry MN, Omran H, Dessouky M. Systematic design and optimization of operational transconductance amplifier using gm/ID design methodology. Microelectronics Journal. 2018; 75:87-96.

[11]Panda M, Patnaik SK, Mal AK, Ghosh S. An evolutionary-based design methodology for performance enhancement of a folded-cascode OTA using symbiotic organisms search algorithm and gm/ID technique. Analog Integrated Circuits and Signal Processing. 2020; 105(2):215-27.

[12]Omran H, Amer MH, Mansour AM. Systematic design of bandgap voltage reference using precomputed lookup tables. IEEE Access. 2019; 7:100131-42.

[13]Hassanzadeh A, Hadidi S. Systematic approach for IG-FinFET amplifier design using gm/Id method. Analog Integrated Circuits and Signal Processing. 2021; 109(2):379-85.

[14]Devi S, Tilwankar G, Zele R. Automated design of analog circuits using machine learning techniques. In 25th international symposium on VLSI design and test 2021(pp. 1-6). IEEE.

[15]Koziel S, Szczepanski S. Design of highly linear tunable CMOS OTA for continuous-time filters. IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing. 2002; 49(2):110-22.

[16]Javid F, Iskander R, Louërat MM, Durbin F. A structured DC analysis methodology for accurate verification of analog circuits. In international symposium on circuits and systems 2013 (pp. 2662-5). IEEE.

[17]Wang Y, Xin J, Fang J, Chen X, Liu H, Qin Q, et al. Topology generic DC-model for accelerating analog circuit optimization. In international symposium of electronics design automation 2023 (pp. 65-70). IEEE.

[18]Kuang J, Zhao Y, Chen M. A 480 mVpp linear input range, low noise transconductance cell for multi-input sensor interface. IEEE Transactions on Circuits and Systems II: Express Briefs. 2023; 71(4):1774-8.

[19]Bandyopadhyay S, Mukherjee D, Chatterjee R. Design of two stage CMOS operational amplifier in 180nm technology with low power and high CMRR. International Journal of Latest Trends in Engineering and Technology. 2014; 11:239-47.

[20]Sharma K, Kumar R. Design of a two stage CMOS operational amplifier using 180 nm and 90 nm technology. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering. 2016; 5(5):3624-34.

[21]Sahoo DK, Bhuyan KC, Dastidar A. Design of switched capacitor-based charge amplifier in 180 nm technology. In innovation in electrical power engineering, communication, and computing technology: proceedings of second IEPCCT 2021 (pp. 139-50). Singapore: Springer Singapore.

[22]Flandre D, Viviani A, Eggermont JP, Gentinne B, Jespers PG. Improved synthesis of gain-boosted regulated-cascode CMOS stages using symbolic analysis and gm/ID methodology. IEEE Journal of Solid-State Circuits. 1997; 32(7):1006-12.

[23]Jespers P. The gm/ID methodology, a sizing tool for low-voltage analog CMOS circuits: the semi-empirical and compact model approaches. Springer Science & Business Media; 2009.

[24]Sahoo DK, Bhuyan KC, Mishra C, Dastidar A. Design of operational transconductance amplifier using g m/I d method in 180nm technology. In 2nd international symposium on sustainable energy, signal processing and cyber security 2022 (pp. 1-6). IEEE.

[25]Zhang Y, Ma D, Carrara S, Georgiou P. Design of low-power highly accurate CMOS potentiostat using the g m/I D methodology. In international symposium on medical measurements and applications 2021 (pp. 1-5). IEEE.

[26]Giustolisi G, Palumbo G. A gm/id-based design strategy for IoT and ultra-low-power OTAs with fast-settling and large capacitive loads. Journal of Low Power Electronics and Applications. 2021; 11(2):1-17.

[27]Zhang G, Xiao X, Xu J, Nie K, Gao Z. Particle swarm optimization design of low-power multistage amplifier using gm/ID methodology. Journal of Circuits, Systems and Computers. 2016; 25(9):1650104.

[28]Akbari M, Hashemipour O. Design and analysis of folded cascode OTAs using gm/id methodology based on flicker noise reduction. Analog Integrated Circuits and Signal Processing. 2015; 83:343-52.

[29]Wolfe G, Vemuri R. Extraction and use of neural network models in automated synthesis of operational amplifiers. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 2003; 22(2):198-212.

[30]Hyun JW, Nam JW. Regression model-based VCO design optimization technique. In international conference on electronics, information, and communication 2023(pp. 1-3). IEEE.

[31]Lberni A, Marktani MA, Ahaitouf A, Ahaitouf A. Analog circuit sizing based on evolutionary algorithms and deep learning. Expert Systems with Applications. 2024; 237:121480.

[32]Chowdhury SR, Bhardwaj S, Kitchen J. Design automation of CMOS Op-amps using statistical geometric programming. In international symposium on circuits and systems 2022 (pp. 1575-9). IEEE.

[33]Guerra-Gómez I, McConaghy T, Tlelo-Cuautle E. Study of regression methodologies on analog circuit design. In 16th Latin-American test symposium 2015 (pp. 1-6). IEEE.

[34]Hyun JW, Nam JW. AMS circuit design optimization technique based on ANN regression model with VAE structure. IEEE Access. 2023; 11:58850-62.

[35]Dam S, Mandal P. Modeling and design of CMOS analog circuits through hierarchical abstraction. Integration. 2013; 46(4):449-62.

[36]Bilski P. Analysis of the ensemble of regression algorithms for the analog circuit parametric identification. Measurement. 2020; 160:107829.

[37]Arce-zavala J, Vazquez AM, Padilla-cantoya I, Plascencia F. A gm-c notch filter implemented with gm over id technique for biosignal acquisition systems. In 17th international conference on electrical engineering, computing science and automatic control 2020 (pp. 1-6). IEEE.

[38]Allen PE, Holberg DR. CMOS analog circuit design. Elsevier; 2011.

[39]Behzad R. Design of analog CMOS integrated circuits. McGraw Hill; 2003.

[40]Razavi B, Behzad R. RF microelectronics. New York: Prentice hall; 2012.

[41]Sedra A, Smith KC, Carusone TC, Gaudet V. Microelectronic circuits 8th edition. Chapter. 2020; 14:1235-6.

[42]Pinjare SL, Nithya G, Nagaraja VS, Sthuthi A. A gm/id based methodology for designing common source amplifier. In 2nd international conference on micro-electronics and telecommunication engineering 2018 (pp. 304-7). IEEE.

[43]Singh NP, Gautam AK, Sharan T. An insight into the hardware and software aspects of a BCI system with focus on ultra-low power bulk driven OTA and gm-c based filter design, and a detailed review of the recent AI/ML techniques. Artificial Intelligence-Based Brain-Computer Interface. 2022: 283-315.

[44]Singh AK, Ragab K, Lok M, Caramanis C, Orshansky M. Predictable equation-based analog optimization based on explicit capture of modeling error statistics. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 2012; 31(10):1485-98.

[45]Balado L, Lupon E, Figueras J, Roca M, Isern E, Picos R. Verifying functional specifications by regression techniques on Lissajous test signatures. IEEE Transactions on Circuits and Systems I: Regular Papers. 2008; 56(4):754-62.

[46]Maricau E, Gielen G. Efficient variability-aware NBTI and hot carrier circuit reliability analysis. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 2010; 29(12):1884-93.

[47]Pradhan A, Vemuri R. Efficient synthesis of a uniformly spread layout aware pareto surface for analog circuits. In 22nd international conference on VLSI design 2009 (pp. 131-6). IEEE.

[48]De SB, Gielen GG. WATSON: design space boundary exploration and model generation for analog and RFIC design. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 2003; 22(2):213-24.

[49]Su L, Buntine W, Newton AR, Peters BS. Learning as applied to stochastic optimization for standard-cell placement. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 2001; 20(4):516-27.

[50]Joseph VR, Kang L. Regression-based inverse distance weighting with applications to computer experiments. Technometrics. 2011; 53(3):254-65.

[51]Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: machine learning in Python. The Journal of Machine Learning Research. 2011; 12:2825-30.

[52]Settaluri K, Liu Z, Khurana R, Mirhaj A, Jain R, Nikolic B. Automated design of analog circuits using reinforcement learning. IEEE transactions on computer-aided design of integrated circuits and systems. 2021; 41(9):2794-807.