On-chip calibration of RF detectors by DC stimuli and artificial neural networks

In the nanometer regime, especially the RF and analog circuits exhibit wide parameter variability, and consequently every chip produced needs to be tested. On-chip design for testability (DfT) features, which are meant to reduce test time and cost also suffer from parameter variability. Therefore, RF calibration of all on-chip test structures is mandatory. In this paper, artificial neural networks (ANN) are employed as multivariate regression technique to architect a general RF calibration scheme using DC- instead of RF stimuli. This relaxes the routing requirements on a chip for GHz test signals along with the reduction in test time and cost. The RF detector, a key element of a radio front-end DfT circuitry, designed in 65 nm CMOS is used to demonstrate the calibration scheme.