TY - GEN
T1 - A Deep Learning-Based Screening Method for Improving the Quality and Reliability of Integrated Passive Devices
AU - Chuang, Chien Hui
AU - Hou, Kuan Wei
AU - Wu, Cheng Wen
AU - Lee, Mincent
AU - Tsai, Chia Heng
AU - Chen, Hao
AU - Wang, Min Jer
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/11/1
Y1 - 2020/11/1
N2 - Integrated passive devices (IPDs) have been widely used in advanced packaging of semiconductor chips, to improve their power integrity and impedance matching. There is a growing demand in guaranteeing signal and power integrity for the chips used in safety-critical products, such as those used in automotive, aviation, industrial, and defense systems, where IPDs help improve quality and reliability of the chips. Therefore, IPD testing and screening itself is essential. Note that the cost of replacing failed IPDs is much higher than the cost of manufacturing them, so screening bad IPDs before mounting is also crucial. In this work, we propose a machine learning (ML) based screening methodology to identifying the IPDs that have potential reliability issues. Based on the parametric data of 360,000 IPDs collected from the wafer probing test, the proposed Semiconductor Quality Net (SQnet) is trained to predict the IPDs which have low breakdown voltage, i.e., low reliability. Keeping the overkill rate below 10%, our method can screen out 6 to 15X more bad dies than the existing industrial methods, i.e., DPAT and GDBC.
AB - Integrated passive devices (IPDs) have been widely used in advanced packaging of semiconductor chips, to improve their power integrity and impedance matching. There is a growing demand in guaranteeing signal and power integrity for the chips used in safety-critical products, such as those used in automotive, aviation, industrial, and defense systems, where IPDs help improve quality and reliability of the chips. Therefore, IPD testing and screening itself is essential. Note that the cost of replacing failed IPDs is much higher than the cost of manufacturing them, so screening bad IPDs before mounting is also crucial. In this work, we propose a machine learning (ML) based screening methodology to identifying the IPDs that have potential reliability issues. Based on the parametric data of 360,000 IPDs collected from the wafer probing test, the proposed Semiconductor Quality Net (SQnet) is trained to predict the IPDs which have low breakdown voltage, i.e., low reliability. Keeping the overkill rate below 10%, our method can screen out 6 to 15X more bad dies than the existing industrial methods, i.e., DPAT and GDBC.
UR - http://www.scopus.com/inward/record.url?scp=85100220741&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85100220741&partnerID=8YFLogxK
U2 - 10.1109/ITC44778.2020.9325221
DO - 10.1109/ITC44778.2020.9325221
M3 - Conference contribution
AN - SCOPUS:85100220741
T3 - Proceedings - International Test Conference
BT - 2020 IEEE International Test Conference, ITC 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Test Conference, ITC 2020
Y2 - 1 November 2020 through 6 November 2020
ER -