Getting more from the semiconductor test: Data mining with defect-cluster extraction

Melanie Po Leen Ooi; Eric Kwang Joo Joo; Ye Chow Kuang; Serge Demidenko; Lindsay Kleeman; Chris Wei Keong Chan

doi:10.1109/TIM.2011.2122430

Getting more from the semiconductor test: Data mining with defect-cluster extraction

Melanie Po Leen Ooi
, Eric Kwang Joo Joo
, Ye Chow Kuang
, Serge Demidenko
, Lindsay Kleeman
, Chris Wei Keong Chan

Monash University Malaysia
Royal Melbourne Institute of Technology University
Monash University
Freescale Semiconductor

Research output: Contribution to journal › Article › peer-review

33 Citations (Scopus)

Abstract

High-volume production data shows that dies, which failed probe test on a semiconductor wafer, have a tendency to form certain unique patterns, i.e., defect clusters. Identifying such clusters is one of the crucial steps toward improvement of the fabrication process and design for manufacturing. This paper proposes a new technique for defect-cluster identification that combines data mining with a defect-cluster extraction using a Segmentation, Detection, and Cluster-Extraction algorithm. It offers high defect-extraction accuracy, without any significant increase in test time and cost.

Original language	English
Article number	5740361
Pages (from-to)	3300-3317
Number of pages	18
Journal	IEEE Transactions on Instrumentation and Measurement
Volume	60
Issue number	10
DOIs	https://doi.org/10.1109/TIM.2011.2122430
Publication status	Published - Oct 2011
Externally published	Yes

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Keywords

Data mining
defect-cluster extraction
probe testing
segmentation
semiconductor manufacturing

Access to Document

10.1109/TIM.2011.2122430

Cite this

@article{2f2cefc9586849dcb9cb8c4849d9c583,

title = "Getting more from the semiconductor test: Data mining with defect-cluster extraction",

abstract = "High-volume production data shows that dies, which failed probe test on a semiconductor wafer, have a tendency to form certain unique patterns, i.e., defect clusters. Identifying such clusters is one of the crucial steps toward improvement of the fabrication process and design for manufacturing. This paper proposes a new technique for defect-cluster identification that combines data mining with a defect-cluster extraction using a Segmentation, Detection, and Cluster-Extraction algorithm. It offers high defect-extraction accuracy, without any significant increase in test time and cost.",

keywords = "Data mining, defect-cluster extraction, probe testing, segmentation, semiconductor manufacturing",

author = "Ooi, \{Melanie Po Leen\} and Joo, \{Eric Kwang Joo\} and Kuang, \{Ye Chow\} and Serge Demidenko and Lindsay Kleeman and Chan, \{Chris Wei Keong\}",

year = "2011",

month = oct,

doi = "10.1109/TIM.2011.2122430",

language = "English",

volume = "60",

pages = "3300--3317",

journal = "IEEE Transactions on Instrumentation and Measurement",

issn = "0018-9456",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "10",

}

TY - JOUR

T1 - Getting more from the semiconductor test

T2 - Data mining with defect-cluster extraction

AU - Ooi, Melanie Po Leen

AU - Joo, Eric Kwang Joo

AU - Kuang, Ye Chow

AU - Demidenko, Serge

AU - Kleeman, Lindsay

AU - Chan, Chris Wei Keong

PY - 2011/10

Y1 - 2011/10

N2 - High-volume production data shows that dies, which failed probe test on a semiconductor wafer, have a tendency to form certain unique patterns, i.e., defect clusters. Identifying such clusters is one of the crucial steps toward improvement of the fabrication process and design for manufacturing. This paper proposes a new technique for defect-cluster identification that combines data mining with a defect-cluster extraction using a Segmentation, Detection, and Cluster-Extraction algorithm. It offers high defect-extraction accuracy, without any significant increase in test time and cost.

AB - High-volume production data shows that dies, which failed probe test on a semiconductor wafer, have a tendency to form certain unique patterns, i.e., defect clusters. Identifying such clusters is one of the crucial steps toward improvement of the fabrication process and design for manufacturing. This paper proposes a new technique for defect-cluster identification that combines data mining with a defect-cluster extraction using a Segmentation, Detection, and Cluster-Extraction algorithm. It offers high defect-extraction accuracy, without any significant increase in test time and cost.

KW - Data mining

KW - defect-cluster extraction

KW - probe testing

KW - segmentation

KW - semiconductor manufacturing

UR - https://www.scopus.com/pages/publications/80052825489

U2 - 10.1109/TIM.2011.2122430

DO - 10.1109/TIM.2011.2122430

M3 - Article

AN - SCOPUS:80052825489

SN - 0018-9456

VL - 60

SP - 3300

EP - 3317

JO - IEEE Transactions on Instrumentation and Measurement

JF - IEEE Transactions on Instrumentation and Measurement

IS - 10

M1 - 5740361

ER -

Getting more from the semiconductor test: Data mining with defect-cluster extraction

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this