Optimization of an Artificial Neural Network System for the Prediction of Failure Analysis Success. (January 2019)

• Record Type: Journal Article
• Authors: Zhao, Lin; Goh, S.H.; Chan, Y.H.; Yeoh, B.L.; Hu, Hao; Thor, M.H.; Tan, Alan; Lam, Jeffrey
• Is Part Of: Microelectronics and reliability. Volume 92(2019)
• Page Start: 136
• Page End: 142
• Publication Date: 2019-01
• Subjects: Artificial Neural Network -- ATE testing -- Failure Analysis Success Rate -- Dynamic Photon Emission Microscopy; Electronic apparatus and appliances -- Reliability -- Periodicals; Miniature electronic equipment -- Periodicals; Appareils électroniques -- Fiabilité -- Périodiques; Équipement électronique miniaturisé -- Périodiques; Electronic apparatus and appliances -- Reliability; Miniature electronic equipment; Periodicals; 621.3815
• DOI: 10.1016/j.microrel.2018.11.014
• Languages: English
• ISSNs: 0026-2714

Abstract

Abstract: It is well known that fail dies that exhibit obvious static power supply leakage current have a higher success of finding a defect, hence, a higher likelihood to be selected for failure analysis. When presented with choices, fail dies that exhibit similar supply current to reference are omitted. Valuable defect learnings are lost as a result. The feasibility of applying an Artificial Neural Network to predict failure analysis success has been demonstrated in a previous report. Besides automating the fail dies selection process, more importantly, dies which could yield valuable findings but neglected otherwise by convention, can be identified. We extend the previous proof-of-concept to study the effects of learning iterations, learning rate and the number of nodes on prediction accuracy in this work. More experimental results which include an actual case study will also be presented to substantiate the value of machine learning in this application.