An efficient background calibration technique for analog-to-digital converters based on neural network |
| |
Affiliation: | 1. Tsinghua University, Beijing, China;2. Zhejiang University, Hangzhou, China;3. Shanghai Jiao Tong University, Shanghai, China;1. Universidad Autónoma de Tlaxcala, Electronics Engineering, Apizaquito, TLAX, Mexico;2. INAOE, Department of Electronics, 72840, Mexico;3. BUAP, Faculty of Electronic Sciences, 72570, Mexico;4. CINVESTAV, Computer Sciences Department, 07360, Mexico City, Mexico;5. Instituto de Microelectrónica de Sevilla, CSIC and Universidad de Sevilla, 41092, Sevilla, Spain |
| |
Abstract: | This paper introduces a background digital calibration algorithm based on neural network, which can adaptively calibrate multiple non-ideal factors in a single-channel ADC, such as gain error, mismatch, offset and harmonic distortion. It enables an efficient background calibration through a simple feed forward neural network and LM gradient descent algorithm. The simulation results show that in the case of a signal input close to the Nyquist frequency, for a 14-bit 500 MS/s prototype ADC, only about 40,000 data needed, the ENOB of the ADC can be increased from 7.81 to 13.06 and the SFDR from 49.7 dB to 106.8 dB assisted by a lower speed reference ADC. |
| |
Keywords: | Analog-to-digital converters Background calibration Neural network Multiple error calibration Reference channel |
本文献已被 ScienceDirect 等数据库收录! |
|