Statistical neural network (SNN) for predicting signal-to-noise ratio (SNR) from static parameters and its validation in 16-bit, 125-MSPS analog-to-digital converters (ADCs)
- 1 August 2022
- journal article
- conference paper
- Published by AIP Publishing in Review of Scientific Instruments
- Vol. 93 (8) , 084701
Abstract
In the analog-to-digital converter (ADC) test process, the static and dynamic performance parameters are the most important, and the tests for these parameters account for the bulk of the ADC test cost. These two types of parameters follow certain relationships, which are incorporated into the ADC test to reduce the cost. In this paper, we focus on the signal-to-noise ratio (SNR), a key indicator of the dynamic performances of ADCs. A statistical neural network (SNN) with two hidden layers was constructed to predict the SNR from the feature variables, which were extracted from the static parameters. A 16-bit, 125-MSPS ADC was used to evaluate the proposed prediction model. Compared to the measured SNR obtained by traditional fast Fourier transform based test methods, the predicted value had a mean average error of only 0.75 dB. In addition, the Shapley additive explanations interpreter was adopted to analyze the feature dependences of the SNN model, and the results demonstrated that the deterioration of the integral nonlinearity-curve-related features could significantly decrease the SNR, which is consistent with previous research results. The reported results demonstrated that, at the cost of a slight loss of accuracy, the proposed SNN can significantly reduce the test complexity, avoid dynamic parameter measurements, and reduce the total test time by about 4%.Keywords
Funding Information
- National Natural Science Foundation of China (61671114)
- Sichuan Science and Technology Program (2019YJ0207)
- Fundamental Research Funds for Central Universities (ZYGX2020ZB001)
This publication has 17 references indexed in Scilit:
- Univariate and multivariate skewness and kurtosis for measuring nonnormality: Prevalence, influence and estimationBehavior Research Methods, 2016
- Explaining prediction models and individual predictions with feature contributionsKnowledge and Information Systems, 2013
- Testing ADC Spectral Performance Without Dedicated Data AcquisitionIEEE Transactions on Instrumentation and Measurement, 2012
- Measuring Dynamic Nonlinearity of Digitizers Affected by Time Base DistortionIEEE Transactions on Instrumentation and Measurement, 2010
- A Histogram-Based Testing Method for Estimating A/D Converter PerformanceIEEE Transactions on Instrumentation and Measurement, 2008
- Frequency Domain Analysis for Dynamic Nonlinearity Measurement in A/D ConvertersIEEE Transactions on Instrumentation and Measurement, 2007
- A First Step for an INL Spectral-Based BIST: The Memory OptimizationJournal of Electronic Testing, 2006
- Combined Spectral and Histogram Analysis for Fast ADC TestingIEEE Transactions on Instrumentation and Measurement, 2005
- Importance of input data normalization for the application of neural networks to complex industrial problemsIEEE Transactions on Nuclear Science, 1997
- Determining the effective number of bits of high resolution digitizersIEEE Transactions on Nuclear Science, 1997