Abstract
Abstract A large part of the cost of producing Digital to Analog Converters (DACs) is related to testing, due to factors such as long time taken for analog fault diagnosis, increased testing time and expensive equipment being required for testing. Therefore, using Machine Learning (ML) based fault classification offers a promising alternative method for testing DACs compared to traditional testing, as it reduces complexity while also improving fault diagnostic accuracy. This study compares the performance of Back Propagation Neural Network (BPNN), Support Vector Machine (SVM), and Probabilistic Neural Network (PNN) to classify catastrophic faults in both 16-bit Charge Scaling and Binary Weighted DACs that have experienced process variation such as variable threshold voltage, oxide thickness and temperature. Additionally, this paper proposes a framework to eliminate the need for additional test hardware, as the simulated fault signatures are used to develop and validate classifiers for both Charge Scaling and Binary Weighted DACs. The experimental results indicate that the BPNN classified faults with an average classification accuracy of 100% for Charge Scaling DACs and 95.1% for Binary Weighted DACs. Meanwhile, the SVM classified faults with an average classification accuracy of 97.8% for Charge Scaling DACs and 94.09% for Binary Weighted DACs. The proposed PNN achieves significantly better performance with 100% classification accuracy, precision, recall and F1 score for Charge Scaling DAC; 95.5%, 95.1%, 95.5% and 95.3% for Binary Weighted DAC than both SVM and BPNN classifiers. Novelty of this work is the complete benchmarking of the performance of the three classification algorithms for methodically classifying faults in both 16-bit Charge Scaling and Binary Weighted DACs across a range of process variations and thus providing a highly reliable and inexpensive solution for automated DAC fault detection without the need for additional testing apparatus.