Leveraging Unsupervised Learning for Identifying Unknown Defects in New Semiconductor Products

Tarun Parmar

doi:10.5281/zenodo.14840180

Leveraging Unsupervised Learning for Identifying Unknown Defects in New Semiconductor Products

Author(s)	Tarun Parmar
Country	United States
Abstract	Semiconductor manufacturing faces significant challenges in terms of identifying and resolving unknown defects during the introduction of new products. Traditional root cause analysis methods struggle to detect and classify novel defect types, leading to delays, increased cost, and potential quality issues. Unsupervised learning has emerged as a promising approach for addressing these challenges by automatically discovering patterns, anomalies, and relationships within large, complex datasets without the need for predefined labels. This review explores the potential of unsupervised learning techniques, such as clustering algorithms, dimensionality reduction, and anomaly detection, to enhance the root cause analysis in semiconductor manufacturing. Case studies demonstrated the effectiveness of methods such as principal component analysis, k-means clustering, autoencoders, and generative adversarial networks in grouping similar defect patterns, identifying rare defects, visualizing high-dimensional data, and uncovering hidden correlations. However, challenges remain in handling high-dimensional data, addressing imbalanced datasets, interpreting results, and integrating the domain knowledge. Future research directions include combining unsupervised and supervised learning, incorporating temporal data, applying deep learning to defect image analysis, and developing real-time monitoring systems. Integrating unsupervised learning with domain expertise promises to significantly improve the quality control efficiency and effectiveness in semiconductor manufacturing, ultimately leading to faster time-to-market, reduced costs, and improved product quality for new semiconductor devices.
Keywords	semiconductor manufacturing, root cause analysis, unknown defects, unsupervised learning, clustering algorithms, anomaly detection
Field	Engineering
Published In	Volume 1, Issue 3, November 2020
Published On	2020-11-10
Cite This	Leveraging Unsupervised Learning for Identifying Unknown Defects in New Semiconductor Products - Tarun Parmar - IJLRP Volume 1, Issue 3, November 2020. DOI 10.5281/zenodo.14840180
DOI	https://doi.org/10.5281/zenodo.14840180
Short DOI	https://doi.org/g84hh6

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJLRP DOI prefix is
10.70528/IJLRP

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 5 Isu 12 Cover Page Vol 5 Isu 11 Cover Page Vol 5 Isu 10

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJLRP Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijlrp.com

International Journal of Leading Research Publication

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Leveraging Unsupervised Learning for Identifying Unknown Defects in New Semiconductor Products

Share this