EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning-Based Fault Detection in VLSI Circuits

Sayali S. Somwanshi, Prof. Vaibhav A. Vyavhare, Dr. Divekar Sudhir Narsing, Dr. Date Archana Rajesh

International Journal of Scientific Research in Science, Engineering and Technology · 23.05.2026 · 13 (3) · 235-243

DOI: 10.32628/ijsrset2613327 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Scientific Research in Science, Engineering and Technology, online erschienen am 23.05.2026. Verfasst von Sayali S. Somwanshi und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The continuous advancement of Very Large Scale Integration (VLSI) technology has resulted in highly complex integrated circuits containing millions of transistors, increasing the likelihood of faults caused by manufacturing defects, process variations, aging effects, and environmental disturbances. Traditional fault detection techniques such as Automatic Test Pattern Generation (ATPG) and fault simulation often suffer from high computational complexity, increased testing time, and limited scalability for modern nanometer-scale circuits. This paper presents a machine learning-based fault detection framework for efficient identification and localization of faults in VLSI circuits. The proposed approach utilizes circuit response data generated from test patterns, followed by feature extraction and preprocessing to create meaningful input for machine learning models. Various algorithms, including Support Vector Machines (SVM), Random Forests, Artificial Neural Networks (ANN), and Graph Neural Networks (GNN), are employed to classify and detect different fault types. The performance of the models is evaluated using metrics such as accuracy, precision, recall, F1-score, and fault coverage. Experimental analysis demonstrates that machine learning techniques significantly improve fault detection accuracy while reducing testing effort and diagnosis time compared to conventional methods. Furthermore, graph-based and deep learning approaches show enhanced capability in handling complex circuit topologies and large-scale datasets.

Zitieren

APA

Somwanshi, S. S., Vyavhare, P. V. A., Narsing, D. D. S., & Rajesh, D. D. A. (2026). Machine Learning-Based Fault Detection in VLSI Circuits. International Journal of Scientific Research in Science, Engineering and Technology, 13(3), 235-243. https://doi.org/10.32628/ijsrset2613327

Vancouver

Somwanshi SS, Vyavhare PVA, Narsing DDS, Rajesh DDA. Machine Learning-Based Fault Detection in VLSI Circuits. International Journal of Scientific Research in Science, Engineering and Technology. 2026;13(3):235-243. doi:10.32628/ijsrset2613327

BibTeX
@article{Somwanshi2026,
  author = {Somwanshi, Sayali S. and Vyavhare, Prof. Vaibhav A. and Narsing, Dr. Divekar Sudhir and Rajesh, Dr. Date Archana},
  title = {Machine Learning-Based Fault Detection in VLSI Circuits},
  journal = {International Journal of Scientific Research in Science, Engineering and Technology},
  year = {2026},
  volume = {13},
  number = {3},
  pages = {235--243},
  doi = {10.32628/ijsrset2613327}
}
Kostenlos starten →