Interaction-Effect Search Algorithm for the KSA Scheme

Chin Yi Lin, Yu Ming Hsieh, Fan-Tien Cheng, Yu Ru Yang, Muhammad Adnan

Research output: Contribution to journalArticle

Abstract

With the trend of even smaller workpieces and complicated processes in the semiconductor industry, yield enhancement becomes the crucial indicator of enterprise profits. However, the advancement of the manufacturing processes results in huge-and-complicated data, it becomes difficult to quickly search for the root causes that affect the yield from such big historical data. In light of this, the authors proposed the key-variable search algorithm (KSA) to resolve this problem. The KSA scheme provides users a quick-and-efficient way to identify the root causes of a yield loss. The inputs of this KSA scheme include production routes, process data, inline data, defects, and final inspection results. However, when an interaction effect exists between a key device/variable and the other device/variable, also, the impact of this effect is greater than those impacts of the original devices/variables, the original KSA scheme may not correctly find out the root causes. To remedy this insufficiency, this study develops the 'interaction-effect search algorithm (IESA).' The IESA scheme can not only identify the existence of an interaction effect but also determine the threshold of the key variable that causes this interaction effect.

Original languageEnglish
Pages (from-to)2778-2785
Number of pages8
JournalIEEE Robotics and Automation Letters
Volume3
Issue number4
DOIs
Publication statusPublished - 2018 Oct 1

Fingerprint

Interaction Effects
Search Algorithm
Roots
Industry
Profitability
Historical Data
Inspection
Semiconductor materials
Profit
Semiconductors
Resolve
Defects
Enhancement
Manufacturing

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Biomedical Engineering
  • Human-Computer Interaction
  • Mechanical Engineering
  • Computer Vision and Pattern Recognition
  • Computer Science Applications
  • Control and Optimization
  • Artificial Intelligence

Cite this

Lin, Chin Yi ; Hsieh, Yu Ming ; Cheng, Fan-Tien ; Yang, Yu Ru ; Adnan, Muhammad. / Interaction-Effect Search Algorithm for the KSA Scheme. In: IEEE Robotics and Automation Letters. 2018 ; Vol. 3, No. 4. pp. 2778-2785.
@article{efcdde48bf314abba2b6bdf041f6fc21,
title = "Interaction-Effect Search Algorithm for the KSA Scheme",
abstract = "With the trend of even smaller workpieces and complicated processes in the semiconductor industry, yield enhancement becomes the crucial indicator of enterprise profits. However, the advancement of the manufacturing processes results in huge-and-complicated data, it becomes difficult to quickly search for the root causes that affect the yield from such big historical data. In light of this, the authors proposed the key-variable search algorithm (KSA) to resolve this problem. The KSA scheme provides users a quick-and-efficient way to identify the root causes of a yield loss. The inputs of this KSA scheme include production routes, process data, inline data, defects, and final inspection results. However, when an interaction effect exists between a key device/variable and the other device/variable, also, the impact of this effect is greater than those impacts of the original devices/variables, the original KSA scheme may not correctly find out the root causes. To remedy this insufficiency, this study develops the 'interaction-effect search algorithm (IESA).' The IESA scheme can not only identify the existence of an interaction effect but also determine the threshold of the key variable that causes this interaction effect.",
author = "Lin, {Chin Yi} and Hsieh, {Yu Ming} and Fan-Tien Cheng and Yang, {Yu Ru} and Muhammad Adnan",
year = "2018",
month = "10",
day = "1",
doi = "10.1109/LRA.2018.2838323",
language = "English",
volume = "3",
pages = "2778--2785",
journal = "IEEE Robotics and Automation Letters",
issn = "2377-3766",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

Interaction-Effect Search Algorithm for the KSA Scheme. / Lin, Chin Yi; Hsieh, Yu Ming; Cheng, Fan-Tien; Yang, Yu Ru; Adnan, Muhammad.

In: IEEE Robotics and Automation Letters, Vol. 3, No. 4, 01.10.2018, p. 2778-2785.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Interaction-Effect Search Algorithm for the KSA Scheme

AU - Lin, Chin Yi

AU - Hsieh, Yu Ming

AU - Cheng, Fan-Tien

AU - Yang, Yu Ru

AU - Adnan, Muhammad

PY - 2018/10/1

Y1 - 2018/10/1

N2 - With the trend of even smaller workpieces and complicated processes in the semiconductor industry, yield enhancement becomes the crucial indicator of enterprise profits. However, the advancement of the manufacturing processes results in huge-and-complicated data, it becomes difficult to quickly search for the root causes that affect the yield from such big historical data. In light of this, the authors proposed the key-variable search algorithm (KSA) to resolve this problem. The KSA scheme provides users a quick-and-efficient way to identify the root causes of a yield loss. The inputs of this KSA scheme include production routes, process data, inline data, defects, and final inspection results. However, when an interaction effect exists between a key device/variable and the other device/variable, also, the impact of this effect is greater than those impacts of the original devices/variables, the original KSA scheme may not correctly find out the root causes. To remedy this insufficiency, this study develops the 'interaction-effect search algorithm (IESA).' The IESA scheme can not only identify the existence of an interaction effect but also determine the threshold of the key variable that causes this interaction effect.

AB - With the trend of even smaller workpieces and complicated processes in the semiconductor industry, yield enhancement becomes the crucial indicator of enterprise profits. However, the advancement of the manufacturing processes results in huge-and-complicated data, it becomes difficult to quickly search for the root causes that affect the yield from such big historical data. In light of this, the authors proposed the key-variable search algorithm (KSA) to resolve this problem. The KSA scheme provides users a quick-and-efficient way to identify the root causes of a yield loss. The inputs of this KSA scheme include production routes, process data, inline data, defects, and final inspection results. However, when an interaction effect exists between a key device/variable and the other device/variable, also, the impact of this effect is greater than those impacts of the original devices/variables, the original KSA scheme may not correctly find out the root causes. To remedy this insufficiency, this study develops the 'interaction-effect search algorithm (IESA).' The IESA scheme can not only identify the existence of an interaction effect but also determine the threshold of the key variable that causes this interaction effect.

UR - http://www.scopus.com/inward/record.url?scp=85063310055&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063310055&partnerID=8YFLogxK

U2 - 10.1109/LRA.2018.2838323

DO - 10.1109/LRA.2018.2838323

M3 - Article

AN - SCOPUS:85063310055

VL - 3

SP - 2778

EP - 2785

JO - IEEE Robotics and Automation Letters

JF - IEEE Robotics and Automation Letters

SN - 2377-3766

IS - 4

ER -