An intelligent fault detection approach for digital integrated circuits through graph neural networks
To quickly and accurately realize the fault diagnosis of analog circuits, this paper introduces the graph neural network method and proposes a fault diagnosis method for digital integrated circuits. The method filters the signals present in the digital integrated circuit to remove noise signals and...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2023-03-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2023438?viewType=HTML |
| _version_ | 1827964792562778112 |
|---|---|
| author | Zulin Xu |
| author_facet | Zulin Xu |
| author_sort | Zulin Xu |
| collection | DOAJ |
| description | To quickly and accurately realize the fault diagnosis of analog circuits, this paper introduces the graph neural network method and proposes a fault diagnosis method for digital integrated circuits. The method filters the signals present in the digital integrated circuit to remove noise signals and redundant signals and analyzes the digital integrated circuit characteristics after the filtering process to obtain the digital integrated circuit leakage current variation. To the problem of the lack of a parametric model for Through-Silicon Via (TSV) defect modeling, the method of TSV defect modeling based on finite element analysis is proposed. The common TSV defects such as voids, open circuits, leakage, and unaligned micro-pads are modeled and analyzed by using industrial-grade FEA tools Q3D and HFSS, and the equivalent circuit model of resistance inductance conductance capacitance (RLGC) for each defect is obtained. Finally, the superior performance of this paper in fault diagnosis accuracy and fault diagnosis efficiency is verified by comparing and analyzing with the traditional graph neural network method and random graph neural network method for active filter circuits. |
| first_indexed | 2024-04-09T17:22:05Z |
| format | Article |
| id | doaj.art-dedf447596a2416dae7776a7db61408b |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-04-09T17:22:05Z |
| publishDate | 2023-03-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-dedf447596a2416dae7776a7db61408b2023-04-19T01:22:12ZengAIMS PressMathematical Biosciences and Engineering1551-00182023-03-0120699921000610.3934/mbe.2023438An intelligent fault detection approach for digital integrated circuits through graph neural networksZulin Xu 0SDU-ANU Joint Science College, Shandong University, Shandong 264209, ChinaTo quickly and accurately realize the fault diagnosis of analog circuits, this paper introduces the graph neural network method and proposes a fault diagnosis method for digital integrated circuits. The method filters the signals present in the digital integrated circuit to remove noise signals and redundant signals and analyzes the digital integrated circuit characteristics after the filtering process to obtain the digital integrated circuit leakage current variation. To the problem of the lack of a parametric model for Through-Silicon Via (TSV) defect modeling, the method of TSV defect modeling based on finite element analysis is proposed. The common TSV defects such as voids, open circuits, leakage, and unaligned micro-pads are modeled and analyzed by using industrial-grade FEA tools Q3D and HFSS, and the equivalent circuit model of resistance inductance conductance capacitance (RLGC) for each defect is obtained. Finally, the superior performance of this paper in fault diagnosis accuracy and fault diagnosis efficiency is verified by comparing and analyzing with the traditional graph neural network method and random graph neural network method for active filter circuits.https://www.aimspress.com/article/doi/10.3934/mbe.2023438?viewType=HTMLgraph neural networkintelligent fault detectiondigital integrated circuitsartificial intelligence |
| spellingShingle | Zulin Xu An intelligent fault detection approach for digital integrated circuits through graph neural networks Mathematical Biosciences and Engineering graph neural network intelligent fault detection digital integrated circuits artificial intelligence |
| title | An intelligent fault detection approach for digital integrated circuits through graph neural networks |
| title_full | An intelligent fault detection approach for digital integrated circuits through graph neural networks |
| title_fullStr | An intelligent fault detection approach for digital integrated circuits through graph neural networks |
| title_full_unstemmed | An intelligent fault detection approach for digital integrated circuits through graph neural networks |
| title_short | An intelligent fault detection approach for digital integrated circuits through graph neural networks |
| title_sort | intelligent fault detection approach for digital integrated circuits through graph neural networks |
| topic | graph neural network intelligent fault detection digital integrated circuits artificial intelligence |
| url | https://www.aimspress.com/article/doi/10.3934/mbe.2023438?viewType=HTML |
| work_keys_str_mv | AT zulinxu anintelligentfaultdetectionapproachfordigitalintegratedcircuitsthroughgraphneuralnetworks AT zulinxu intelligentfaultdetectionapproachfordigitalintegratedcircuitsthroughgraphneuralnetworks |