Natural language processing (NLP) and association rules (AR)-based knowledge extraction for intelligent fault analysis: a case study in semiconductor industry

Zhiqiang Wang (), Kenneth Ezukwoke (), Anis Hoayek (), Mireille Batton-Hubert () and Xavier Boucher ()
Additional contact information
Zhiqiang Wang: Research Center
Kenneth Ezukwoke: Mines Saint-Étienne, Univ. Clermont Auvergne, CNRS UMR 6158 LIMOS
Anis Hoayek: Mines Saint-Étienne, Univ. Clermont Auvergne, CNRS UMR 6158 LIMOS
Mireille Batton-Hubert: Mines Saint-Étienne, Univ. Clermont Auvergne, CNRS UMR 6158 LIMOS
Xavier Boucher: Mines Saint-Étienne, Univ. Clermont Auvergne, CNRS UMR 6158 LIMOS

Journal of Intelligent Manufacturing, 2025, vol. 36, issue 1, No 19, 357-372

Abstract: Abstract Fault analysis (FA) is the process of collecting and analyzing data to determine the cause of a failure. It plays an important role in ensuring the quality in manufacturing process. Traditional FA techniques are time-consuming and labor-intensive, relying heavily on human expertise and the availability of failure inspection equipment. In semiconductor industry, a large amount of FA reports are generated by experts to record the fault descriptions, fault analysis path and fault root causes. With the development of Artificial Intelligence, it is possible to automate the industrial FA process while extracting expert knowledge from the vast FA report data. The goal of this research is to develop a complete expert knowledge extraction pipeline for FA in semiconductor industry based on advanced Natural Language Processing and Machine Learning. Our research aims at automatically predicting the fault root cause based on the fault descriptions. First, the text data from the FA reports are transformed into numerical data using Sentence Transformer embedding. The numerical data are converted into latent spaces using Generalized-Controllable Variational AutoEncoder. Then, the latent spaces are classified by Gaussian Mixture Model. Finally, Association Rules are applied to establish the relationship between the labels in the latent space of the fault descriptions and that of the fault root cause. The proposed algorithm has been evaluated with real data of semiconductor industry collected over three years. The average correctness of the predicted label achieves 97.8%. The method can effectively reduce the time of failure identification and the cost during the inspection stage.

Keywords: Fault analysis; Natural language processing; GCVAE; GMM; Association rules (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10845-023-02245-7 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:36:y:2025:i:1:d:10.1007_s10845-023-02245-7

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-023-02245-7

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().