Identification of Suspicious Semiconductor Devices Using Independent Component Analysis with Dimensionality Reduction

Abstract

In the semiconductor industry the reliability of devices is of paramount importance. Therefore, after removing the defective ones, one wants to detect irregularities in measurement data because corresponding devices have a higher risk of failure early in the product lifetime. Furthermore it would be desirable to consider multiple functional tests together due to existing dependencies. This paper presents a method to detect such suspicious devices where the screening is made on transformed measurement data. Additionally, a new dimensionality reduction is performed within the transformation so that the reduced and transformed data comprises only the informative content from the raw data. Therefore the complexity of the subsequent screening steps is simplified.