Knowledge Transfer in Board-Level Functional Fault Identification using Domain Adaptation

High integration densities and design complexity make board-level functional fault identification extremely difficult. Machine-learning techniques can identify functional faults with high accuracy, but they require a large volume of data to achieve high prediction accuracy. This drawback limits the effectiveness of traditional machine-learning algorithms for training a model in the early stage of manufacturing, when only a limited amount of fail data and repair records are available. We propose a board-level diagnosis workflow that utilizes domain adaptation to transfer the knowledge learned from a mature board to a new board in the ramp-up phase. First, a metric is designed to evaluate the similarity between products, and based on the calculated value of the similarity, either a homogeneous or a heterogeneous domain adaptation algorithm is selected. Second, these domain adaptation algorithms utilize information from both the mature and the new boards with carefully designed domain-alignment rules and train a functional fault identification classifier. Three complex boards in volume production and one new board in the ramp-up phase are used to validate the proposed domain-adaptation approach in terms of the diagnosis accuracy.