Indirect Test Pattern Generation for Mixed-Signal Circuits Using Machine Learning

Editor’s notes: This article presents a machine-learning-based approach for generating indirect test patterns in analog and mixed-signal circuits. The method leverages a low-cost test generation tool to simulate circuit specifications and parametric measures, while accounting for variability through Monte Carlo simulations. —Ney Calazans, Federal University of Santa Catarina (UFSC), Brazil —Bruno Zatt, Federal University of Pelotas (UFPel), Brazil