Design and Multiplierless Realization of Digital Synthesis Filters for Hybrid-Filter-Bank A/D Converters

Abstract

This paper studies the optimal least squares and minimax design and realization of digital synthesis filters for hybrid-filter-bank analog-to-digital converters (HFB ADCs) to meet a given spurious-free dynamic range (SFDR). The problem for designing finite-impulse-response synthesis filters is formulated as a second-order cone-programming problem, which is convex and allows linear and quadratic constraints such as peak aliasing error to be incorporated. The fixed coefficients of the designed synthesis filters are efficiently implemented using sum-of-power-of-two (SOPOT) coefficients, while the internal word length used for each intermediate data is minimized using geometric programming. The main sources of error are analyzed, and a new formula of SFDR in terms of these errors is derived. The effects of component variations of analog analysis filters on the HFB ADC are also addressed by means of two new robust HFB ADC design algorithms based on stochastic uncertainty and worst case uncertainty models. Design results show that the proposed approach offers more flexibility and better performance than conventional methods in achieving a given SFDR and that the robust design algorithms are more robust to parameter uncertainties than the nominal design in which the uncertainties are not taken into account.