Industrial Semiconductor GPT: A Question-and-Answer System that Provides Professional Advice and Problem-Solving Methods for Semiconductor and Factory Equipment and Process

Yi Cheng Yu*, Cheng Fu Liou, Shang Wen Chuang, Chen Yi Lee

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Research on PHM(Predictive Health Management) for detecting or predicting abnormalities in semiconductors and factory equipment and processes typically focuses on improving accuracy and reducing model size. However, in actual factory settings, on-site personnel not only need to accurately detect and predict abnormalities in processes and equipment but also require an understanding of how to handle the encountered abnormal problems when they occur. This study proposes Industrial Semiconductor GPT technology, which embeds relevant professional technical documents of process equipment into a vector database and generates possible professional questions and answers. When on-site personnel inquire, a natural language processing algorithm is used to compare the generated answers with actual answers. Furthermore, this study verifies the collected expert data through prompting engineering, resulting in an approximately 9.39 % increase in similarity, ensuring that factory personnel can obtain accurate and helpful answers when facing abnormal situations.

Original languageEnglish
Title of host publication2024 33rd International Symposium on Industrial Electronics, ISIE 2024 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350394085
DOIs
StatePublished - 2024
Event33rd International Symposium on Industrial Electronics, ISIE 2024 - Ulsan, Korea, Republic of
Duration: 18 Jun 202421 Jun 2024

Publication series

NameIEEE International Symposium on Industrial Electronics
ISSN (Print)2163-5137
ISSN (Electronic)2163-5145

Conference

Conference33rd International Symposium on Industrial Electronics, ISIE 2024
Country/TerritoryKorea, Republic of
CityUlsan
Period18/06/2421/06/24

Keywords

  • ChatGPT
  • Industrial
  • natural language processing
  • PHM
  • prompting engineering
  • Semiconductor
  • vector database

Fingerprint

Dive into the research topics of 'Industrial Semiconductor GPT: A Question-and-Answer System that Provides Professional Advice and Problem-Solving Methods for Semiconductor and Factory Equipment and Process'. Together they form a unique fingerprint.

Cite this