Single stuck-at-faults detection using test generation vector and deep stacked-sparse-autoencoder

This paper proposed a new method for testing digital circuits without hardware implementation. This data-based method detects hundreds of single stuck-at faults in the ALU circuits, utilizing deep stacked-sparse-autoencoder (SSAE). ATALANTA software is one of the free automatic test pattern generati...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:SN applied sciences Ročník 2; číslo 10; s. 1715
Hlavní autori: Malihi, Leila, Malihi, Razieh
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Cham Springer International Publishing 01.10.2020
Springer Nature B.V
Predmet:
Algorithms
Applied and Technical Physics
Artificial neural networks
Chemistry/Food Science
Circuits
Classification
Data augmentation
Decision theory
Deep learning
Digital electronics
Earth Sciences
Engineering
Engineering: Application of Machine Learning in Engineering
Environment
Fault detection
Faults
Feature extraction
Logic
Materials Science
Mathematical functions
Multilayer perceptrons
Neural networks
Pattern generation
Research Article
Software
Teaching methods
Test pattern generators
Softmax classifier
MLP
Stacked-sparse-autoencoder
Test vectors
ISSN:2523-3963, 2523-3971
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This paper proposed a new method for testing digital circuits without hardware implementation. This data-based method detects hundreds of single stuck-at faults in the ALU circuits, utilizing deep stacked-sparse-autoencoder (SSAE). ATALANTA software is one of the free automatic test pattern generation tools which cover faults in high accuracy. Test vectors which are extracted from bench circuits via ATALANTA software are the key point of the paper. Fault detection is introduced as a two-class problem. SSAE network is trained using the test vectors. Dimension reduction is done automatically in SSAE. Network performance is tested by changing sparse coefficients, number of stacked autoencoder and data augmentation. The results of this step are compared with the traditional multilayer perceptron classification. In this method, unlike SSAE, a manual method of reducing the dimension and extracting the feature is used. Fault coverage of ATALANTA software is over than 94%. Finally, the results obtained from the deep neural network show its significant performance in the circuit faults detection automatically.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2523-3963
2523-3971
DOI:10.1007/s42452-020-03460-0