loading page

A Neural Network Based Background Calibration for Pipelined-SAR ADCs at Low Hardware Cost
  • +3
  • Yuguo Xiang,
  • Min Chen,
  • Danfeng Zhai,
  • Yutong Zhao,
  • Junyan Ren,
  • Fan Ye
Yuguo Xiang
Fudan University
Author Profile
Min Chen
Fudan University
Author Profile
Danfeng Zhai
Fudan University
Author Profile
Yutong Zhao
Fudan University
Author Profile
Junyan Ren
Fudan University
Author Profile
Fan Ye
Fudan University

Corresponding Author:fanye@fudan.edu.cn

Author Profile

Abstract

This paper proposes a background calibration scheme for the pipelined-SAR ADC based on the neural network. Due to the nonlinear function fitting capability of the neural network, the linearity of the ADC is improved effectively. However, the hardware complexity of the neural network limits its application and promotion in ADC calibration. Hence, this paper also presents the optimization schemes, including the neuron-based sharing neural network and the partially binarized with fixed neural network, in terms of calibration architecture and algorithm. A 60 MS/s 14-bit pipelined-SAR ADC prototyped in 28-nm technology is utilized to verify the feasibility of the proposed calibration method. The measurement results show that the proposed calibration enhances the SFDR and SNDR from 68.3 dB and 44.6 dB to 95.4 dB and 65.4 dB at low frequency, and from 56.8 dB and 35.6 dB to 90.6 dB and 63.6 dB at Nyquist frequency. Meanwhile, the original calibrator and improved calibrator are synthesized in Synopsys Design Compiler to compare their hardware complexity. Compared with the unoptimized version, the optimized schemes can decrease the logic area and the network weights up to 76% and 52%, with negligible loss in calibration performance.
13 Jun 2023Submitted to Electronics Letters
14 Jun 2023Submission Checks Completed
14 Jun 2023Assigned to Editor
27 Jun 2023Reviewer(s) Assigned
06 Jul 2023Review(s) Completed, Editorial Evaluation Pending
13 Jul 2023Editorial Decision: Revise Major
24 Jul 20231st Revision Received
25 Jul 2023Submission Checks Completed
25 Jul 2023Assigned to Editor
25 Jul 2023Review(s) Completed, Editorial Evaluation Pending
25 Jul 2023Reviewer(s) Assigned
30 Jul 2023Editorial Decision: Accept