Error compensation of A/D converters using neural networks

The paper describes a new technique for the error compensation of analog-to-digital converters (ADCs). It can he considered the improvement of the phase plane compensation technique: the idea is to exploit the generalization capabilities of artificial neural networks (ANNs) to reduce the huge amount of experiments required. The ANN building and setting-up are carried out in an ANN simulation environment using an ADC behavioral model, whose errors can be fixed to known values. In this way, a set of ADCs with very different performances could be simulated in order to investigate about the usefulness of the proposed approach in very different working conditions. Interesting considerations are drawn in the analysis of the first results carried out by comparing the behaviors of uncompensated and compensated ADC outputs