Neural networks-based parametric testing of analog IC

A new parametric approach for detecting defects in analog integrated circuits using the feed forward neural network trained by back-propagation method is presented. The neural network is used for classification of tested circuits by sensing differences observed in dynamic supply current of fault free and faulty circuits. The identification is performed in time and frequency domain, followed by a comparison of results achieved in both domains. It was shown that neural networks might be very efficient and versatile approach for identification of defective analog circuits as it offers also monitoring of other circuit´s parameters. Moreover, optimized architecture of the proper neural network was proposed using VHDL for FPGA realization and a possible off-chip hardware implementation of this approach is discussed as well.