A Data Compression Strategy for the Efficient Uncertainty Quantification of Time-Domain Circuit Responses

This paper presents an innovative modeling strategy for the construction of efficient and compact surrogate models for the uncertainty quantification of time-domain responses of digital links. The proposed approach relies on a two-step methodology. First, the initial dataset of available training responses is compressed via principal component analysis (PCA). Then, the compressed dataset is used to train compact surrogate models for the reduced PCA variables using advanced techniques for uncertainty quantification and parametric macromodeling. Specifically, in this work sparse polynomial chaos expansion and least-square support-vector machine regression are used, although the proposed methodology is general and applicable to any surrogate modeling strategy. The preliminary compression allows limiting the number and complexity of the surrogate models, thus leading to a substantial improvement in the efficiency. The feasibility and performance of the proposed approach are investigated by means of two digital link designs with 54 and 115 uncertain parameters, respectively.

[1]  R. Shah,et al.  Least Squares Support Vector Machines , 2022 .

[2]  Madhavan Swaminathan,et al.  Machine Learning and Uncertainty Quantification for Surrogate Models of Integrated Devices With a Large Number of Parameters , 2019, IEEE Access.

[3]  Dongbin Xiu,et al.  The Wiener-Askey Polynomial Chaos for Stochastic Differential Equations , 2002, SIAM J. Sci. Comput..

[4]  Stefano Grivet-Talocia,et al.  Rational Polynomial Chaos Expansions for the Stochastic Macromodeling of Network Responses , 2020, IEEE Transactions on Circuits and Systems I: Regular Papers.

[5]  Ken Wu,et al.  High-Speed Channel Modeling With Machine Learning Methods for Signal Integrity Analysis , 2018, IEEE Transactions on Electromagnetic Compatibility.

[6]  B. Sudret,et al.  An adaptive algorithm to build up sparse polynomial chaos expansions for stochastic finite element analysis , 2010 .

[7]  Huan Yu,et al.  Behavioral Modeling of Tunable I/O Drivers With Preemphasis Including Power Supply Noise , 2020, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[8]  Vladimir Cherkassky,et al.  The Nature Of Statistical Learning Theory , 1997, IEEE Trans. Neural Networks.

[9]  S. Marelli,et al.  Sparse polynomial chaos expansions of frequency response functions using stochastic frequency transformation , 2016, 1606.01662.

[10]  Paolo Manfredi,et al.  Machine Learning for the Performance Assessment of High-Speed Links , 2018, IEEE Transactions on Electromagnetic Compatibility.

[11]  José Carlos Pedro,et al.  Behavioral Modeling of IC Memories From Measured Data , 2011, IEEE Transactions on Instrumentation and Measurement.

[12]  Tsui-Wei Weng,et al.  Big-Data Tensor Recovery for High-Dimensional Uncertainty Quantification of Process Variations , 2017, IEEE Transactions on Components, Packaging and Manufacturing Technology.

[13]  Sonja Kuhnt,et al.  Design and analysis of computer experiments , 2010 .

[14]  Xu Chen,et al.  Comparison of Machine Learning Techniques for Predictive Modeling of High-Speed Links , 2019, 2019 IEEE 28th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS).

[15]  Majid Ahadi,et al.  Sparse Linear Regression (SPLINER) Approach for Efficient Multidimensional Uncertainty Quantification of High-Speed Circuits , 2016, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[16]  Bruno Sudret,et al.  Adaptive sparse polynomial chaos expansion based on least angle regression , 2011, J. Comput. Phys..

[17]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[18]  Flavio Canavero,et al.  Black-Box Modeling of the Maximum Currents Induced in Harnesses During Automotive Radiated Immunity Tests , 2020, IEEE Transactions on Electromagnetic Compatibility.

[19]  Stefano Grivet-Talocia,et al.  Constructive Signal Approximations for Fast Transient Simulation of Coupled Channels , 2019, IEEE Transactions on Components, Packaging and Manufacturing Technology.

[20]  Tom Dhaene,et al.  Review of Polynomial Chaos-Based Methods for Uncertainty Quantification in Modern Integrated Circuits , 2018 .

[21]  Madhavan Swaminathan,et al.  A Spectral Convolutional Net for Co-Optimization of Integrated Voltage Regulators and Embedded Inductors , 2019, 2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).

[22]  Riccardo Trinchero,et al.  Combining LS-SVM and GP Regression for the Uncertainty Quantification of the EMI of Power Converters Affected by Several Uncertain Parameters , 2020, IEEE Transactions on Electromagnetic Compatibility.

[23]  Stefano Marelli,et al.  UQLab: a framework for uncertainty quantification in MATLAB , 2014 .

[24]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[25]  Philippe Besnier,et al.  Variability Impact of Many Design Parameters: The Case of a Realistic Electronic Link , 2018, IEEE Transactions on Electromagnetic Compatibility.

[26]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[27]  Dries Vande Ginste,et al.  Stochastic transmission line analysis via polynomial chaos methods: an overview , 2017, IEEE Electromagnetic Compatibility Magazine.

[28]  Andreas C. Cangellaris,et al.  Random-Space Dimensionality Reduction for Expedient Yield Estimation of Passive Microwave Structures , 2013, IEEE Transactions on Microwave Theory and Techniques.

[29]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[30]  R. Trinchero,et al.  Statistical Analysis of the Efficiency of an Integrated Voltage Regulator by means of a Machine Learning Model Coupled with Kriging Regression , 2019, 2019 IEEE 23rd Workshop on Signal and Power Integrity (SPI).

[31]  Ramachandra Achar,et al.  Generalized Hermite Polynomial Chaos for Variability Analysis of Macromodels Embeddedin Nonlinear Circuits , 2014, IEEE Transactions on Components, Packaging and Manufacturing Technology.