Abstract
This work presents a PVT robust machine learning-based Voltage-controlled Oscillator (VCO) with an enhanced linearity range. The machine learning algorithm with PVT robustness is implemented digitally. Different from conventional methods, the proposed scheme does not require the VCO to be in working mode every time one needs the prediction of frequency. The proposed scheme uses the frequency to digital converter (FDC) output data as an input learning vector and uses a prediction block to predict the future frequencies. An 11-stage voltage-controlled oscillator with a machine learning algorithm is implemented in SCL 180 nm CMOS technology. The measurement results show that the proposed architecture is robust against PVT variations with an enhanced linearity range. Without a machine learning algorithm, the VCO’s control voltage linearity range is 0.28 V to 0.40 V that increases to the range from 0.1 to 1.8 V after applying the proposed machine learning algorithm. The maximum gain variation of 3.71% is observed at FF with respect to the TT corner after applying the proposed machine learning algorithm.
Similar content being viewed by others
Data Availability
Data sharing does not apply to this article as no datasets were generated or analyzed during the current study.
References
E. Afacan, N. Lourenço, R. Martins, G. Dündar, Review: Machine learning techniques in analog/RF integrated circuit design, synthesis, layout, and test. Integration 77, 113–130 (2021). https://doi.org/10.1016/j.vlsi.2020.11.006
J. Borgmans, E. Sacco, P. Rombouts, G. Gielen, Methodology for readout and ring oscillator optimization toward energy-efficient VCO-based ADCs. IEEE Trans. Circuits Syst. I Regul. Pap. (2021). https://doi.org/10.1109/tcsi.2021.31299199
Y. Cao, X. Chen, G. Wang, Dynamic behavioral modeling of nonlinear microwave devices using real-time recurrent neural network. IEEE Trans. Electron Devices 56(5), 1020–1026 (2009). https://doi.org/10.1109/ted.2009.2016029
F. Cardes, E. Gutierrez, A. Quintero, C. Buffa, A. Wiesbauer, L. Hernandez, 0.04-mm2 1.03-dB-A dynamic range second-order VCO-based audio sigma-delta ADC in 0.130 um CMOS. IEEE J. Solid-State Circuits 53(6), 1731–1742 (2018). https://doi.org/10.1109/jssc.2018.2799938
P.R. Castañeda-Aviña, E. Tlelo-Cuautle, L.G. de la Fraga, Single-objective optimization of a CMOS VCO considering PVT and Monte Carlo Simulations. Math. Comput. Appl. 25(4), 76 (2020). https://doi.org/10.3390/mca25040076
S. Choi, S. Yoo, Y. Lim, J. Choi, A PVT-robust and low-jitter ring-VCO-based injection-locked clock multiplier with a continuous frequency-tracking loop using a replica-delay cell and a dual-edge phase detector. IEEE J. Solid-State Circuits 51(8), 1878–1889 (2016). https://doi.org/10.1109/jssc.2016.2574804
E.T. Cuautle, M.A. Valencia-Ponce, L.G. de la Fraga, Sizing CMOS amplifiers by PSO and mol to improve DC operating point conditions. Electronics 9(6), 1027 (2020). https://doi.org/10.3390/electronics9061027
B. Drost, M. Talegaonkar, P.K. Hanumolu, Analog filter design using ring oscillator integrators. IEEE J. Solid-State Circuits 47(12), 3120–3129 (2012). https://doi.org/10.1109/jssc.2012.2225738
J.F. Epperson, An Introduction to Numerical Methods and Analysis (Wiley, New York, 2021)
X. Gui, R. Tang, Y. Zhang, D. Li, L. Geng, A voltage-controlled ring oscillator with VCO-gain variation compensation. IEEE Microw. Wirel. Compon. Lett. 30(3), 288–291 (2020). https://doi.org/10.1109/lmwc.2020.2967391
R. Guo, K. Qian, J. Wei, T. Chen, Y. Liu, D. Kong, J. Wang, Y. Wu, S.G. Hu, Q. Yu, Y. Liu, Design of a neural network-based VCO with high linearity and wide tuning range. IEEE Access 7, 60120–60125 (2019). https://doi.org/10.1109/access.2019.2915335
W. Guoying, K. Sun, S. Guo, T. Zhang, T. Xi, R. Wang, P. Gui, A Low-voltage and temperature compensated ring VCO design. 978-1-4799-5924-2/14/$31.00 ©2014 IEEE
A.S. Hajimiri, S. Limotyrakis, T.H. Lee, Jitter and phase noise in ring oscillators. IEEE J. Solid-State Circuits 34(6), 790–804 (1999)
S. Huang, S. Liu, J. Hu, R. Wang, Z. Zhu, A 12-GHz wideband fractional-N PLL with robust VCO in 65-nm CMOS. IEEE Microw. Wirel. Compon. Lett. 29(6), 397–399 (2019). https://doi.org/10.1109/lmwc.2019.2909656
K. Järvinen, Linear prediction theory, a mathematical basis for adaptive systems. Signal Process. 21(3), 284–285 (1990). https://doi.org/10.1016/0165-1684(90)90096
X. Jianjun, M.C.E. Yagoub, R. Ding, Q.J. Zhang, Neural-based dynamic modeling of nonlinear microwave circuits, in 2002 IEEE MTT-S International Microwave Symposium Digest (Cat. No.02CH37278) (2002). https://doi.org/10.1109/mwsym.2002.1011838
C.W. Lim, H.Y. Noh, T.Y. Yun, Small VCO-gain variation adding a bias-shifted inversion-mode MOS varactor. IEEE Microwave Wirel. Compon. Lett. 27(4), 395–397 (2017). https://doi.org/10.1109/lmwc.2017.2678431
M. Loukrakpam, M. Choudhury, Hardware-efficient VLSI design for cascade support vector machine with on-chip training and classification capability. Circuits Syst. Signal Process. 39(10), 5272–5297 (2020). https://doi.org/10.1007/s00034-020-01415-99
H. Maghami, P. Payandehnia, H. Mirzaie, R. Zanbaghi, S. Dey, K. Mayaram, T.S. Fiez, T, A highly linear OTA-free VCO-based 1–1 MASH delta-sigma ADC. IEEE Trans. Circuits and Syst. I: Regul. Pap. 66(7), 2440–2453 (2019). https://doi.org/10.1109/tcsi.2019.2897785
R.S. Michalski, Y. Kodratoff, R. Bareiss, Machine Learning: An Artificial Intelligence Approach (M. Kaufmann, New York, 1990)
F. Mkadem, S. Boumaiza, Physically inspired neural network model for RF power amplifier behavioral modeling and digital predistortion. IEEE Trans. Microw. Theory Tech. 59(4), 913–923 (2011). https://doi.org/10.1109/tmtt.2010.2098041
B. Mutnury, M. Swaminathan, J. Libous, Macro-modeling of non-linear I/O drivers using spline functions and finite time difference approximation, in Electrical Performance of Electrical Packaging (IEEE Cat. No. 03TH8710) (2003). https://doi.org/10.1109/epep.2003.1250048
J.W. Nam, Y.K. Lee, Machine-learning based analog and mixed-signal circuit design and optimization, in 2021 International Conference on Information Networking (ICOIN). (2021). https://doi.org/10.1109/icoin50884.2021.9333856
Q. Pan, Y. Guo, J. Jin, J. Zhou, A linearization technique for ring VCO exploiting bulk-modulation, in 2021 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS) (2021). https://doi.org/10.1109/mwscas47672.2021.9531742
Y.S. Park, W.Y. Choi, Supply noise insensitive ring VCO with on-chip adaptive bias-current and voltage-swing control, in 2011 IEEE International Symposium of Circuits and Systems (ISCAS) (2011). https://doi.org/10.1109/iscas.2011.5937543
Y.S. Park, W.Y. Choi, On-chip compensation of ring VCO oscillation frequency changes due to supply noise and process variation. IEEE Trans. Circuits Syst. II Express Briefs 59(2), 73–77 (2012). https://doi.org/10.1109/tcsii.2011.2180092
N.H. Patel, Review on machine learning for analog circuit design. Int. J. Eng. Res. V9(05), 710 (2020). https://doi.org/10.17577/ijertv9is050710
A.D. Poularikas, The least mean-square algorithm, in Adaptive Filtering, pp. 203–237 (2017)
P. Prabha, S.J. Kim, K. Reddy, S. Rao, N. Grieser, A. Rao, G. Winter, P.K. Hanumolu, A highly digital VCO-based ADC architecture for current sensing applications. IEEE J. Solid-State Circuits 50(8), 1785–1795 (2015). https://doi.org/10.1109/jssc.2015.2414428
A. Rao, M. Mansour, G. Singh, C.H. Lim, R. Ahmed, D.R. Johnson, A 4–6.4 GHz LC PLL with adaptive bandwidth control for a forwarded clock link. IEEE J. Solid-State Circuits 43(9), 2099–2108 (2008). https://doi.org/10.1109/jssc.2008.2001870
S. Rao, K. Reddy, B. Young, P.K. Hanumolu, A deterministic digital background calibration technique for VCO-based ADCs. IEEE J. Solid-State Circuits 49(4), 950–960 (2014). https://doi.org/10.1109/jssc.2013.2293753
J.K. Sahani, A. Singh, A. Agarwal, Fast locking and low jitter hybrid ADPLL architecture with bang-bang PFD and PVT calibrated flash TDC. AEU-Int. J. Electron. C. 124, 153344 (2020). https://doi.org/10.1016/j.aeue.2020.153344
Z. Sakka, N. Gargouri, M. Samet, A low-power ring oscillator with temperature compensation for IR-UWB applications. J. Circuits Syst. Comput. 27(12), 1850186 (2018)
K. Settaluri, A. Haj-Ali, Q. Huang, K. Hakhamaneshi, B. Nikolic, Autockt: Deep reinforcement learning of analog circuit designs (2020). arXiv:2001.01808
J. Shin, H. Shin, A 1.9–3.8 GHz delta sigma fractional-N PLL frequency synthesizer with fast auto-calibration of loop bandwidth and VCO frequency. IEEE J. Solid-State Circuits 47(3), 665–675 (2012). https://doi.org/10.1109/jssc.2011.2179733
H. Sun, J. Muhlestein, S. Leuenberger, K. Sobue, K. Hamashita, U.K. Moon, A 50 MHz bandwidth 54.2 dB SNDR reference-free stochastic ADC using VCO-based quantizers, in 2016, IEEE Asian Solid-State Circuits Conference (A-SSCC) (2016). https://doi.org/10.1109/asscc.2016.7844201
H. Sun, K. Sobue, K. Hamashita & U. Moon (2018). An Oversampling Stochastic ADC Using VCO-Based Quantizers. IEEE Transactions on Circuits and Systems I: Regular Papers, 65(12), 4037–4050. http://doi:https://doi.org/10.1109/tcsi.2018.2836466
G. Taylor, I. Galton, A mostly-digital variable-rate continuous-time delta-sigma modulator ADC. IEEE J. Solid-State Circuits 45(12), 2634–2646 (2010). https://doi.org/10.1109/jssc.2010.2073193
G. Taylor, I. Galton, A reconfigurable mostly-digital delta-sigma ADC with a worst-case FOM of 160 dB. IEEE J. Solid-State Circuits 48(4), 983–995 (2013). https://doi.org/10.1109/jssc.2013.2239113
T.Y. Tsai, T.S. Wang, Y.J. Chiu, C.C. Wang, A PVT validation phase-lock loop with multi-band VCO applied in closed-loop FOGs, in 2019 International Conference on IC Design and Technology (ICICDT) (2019). https://doi.org/10.1109/icicdt.2019.8790948
L. Wang, H. Tian, H. Zhang, Soft fault diagnosis of analog circuits based on semi-supervised support vector machine. Analog Integr. Circ. Sig. Process. 108(2), 305–315 (2021). https://doi.org/10.1007/s10470-021-01851-w
B. Wittenmark, Adaptive filter theory. Automatica 29(2), 567–568 (1993). https://doi.org/10.1016/0005-1098(93)90162
T. Wu, P.K. Hanumolu, K. Mayaram, U.K. Moon, Method for a constant loop bandwidth in LC-VCO PLL frequency synthesizers. IEEE J. Solid-State Circuits 44(2), 427–435 (2009). https://doi.org/10.1109/jssc.2008.2010792
Z. Yang, W. Wang, Z. Chen, Q. Fan, X. Chen, LSTM-RNN based analog IC automated sizing model for operational amplifier and VCO, in 2020 IEEE 5th International Conference on Integrated Circuits and Microsystems (ICICM) (2020). https://doi.org/10.1109/icicm50929.2020.92922522
H. Yu, M. Swaminathan, C. Ji, D. White, A nonlinear behavioral modeling approach for voltage-controlled oscillators using augmented neural networks, in 2018 IEEE/MTT-S International Microwave Symposium-IMS (2018). https://doi.org/10.1109/mwsym.2018.8439324
Q.J. Zhang, K.C. Gupta, V.K. Devabhaktuni, Artificial neural networks for rf and microwave design-from theory to practice. IEEE Trans. Microw. Theory Tech. 51(4), 1339–1350 (2003). https://doi.org/10.1109/tmtt.2003.809179
Acknowledgements
The Ministry of Electronics and Information Technology (MeitY), GoI, through the SMDP-VLSI C2SD project, is gratefully acknowledged for providing research facilities and support.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kandpal, N., Singh, A. & Agarwal, A. A Machine Learning Driven PVT-Robust VCO with Enhanced Linearity Range. Circuits Syst Signal Process 41, 4275–4292 (2022). https://doi.org/10.1007/s00034-022-02001-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-022-02001-x