Corpus ID: 18188441

NEURAL NETWORK – BASED DEFECT DETECTION IN ANALOG AND MIXED IC USING DIGITAL SIGNAL PREPROCESSING Viera Stopjaková — Pavol Malošek —

@inproceedings{Nagy2006NEURALN,
  title={NEURAL NETWORK – BASED DEFECT DETECTION IN ANALOG AND MIXED IC USING DIGITAL SIGNAL PREPROCESSING Viera Stopjakov{\'a} — Pavol Malo{\vs}ek —},
  author={V. Nagy},
  year={2006}
}
The major goal of our work was to develop an efficient defect-oriented parametric test method for analog & mixed-signal integrated circuits based on Artificial Neural Network (ANN) classification of a selected circuit’s parameter using different methods of signal preprocessing. Thus, ANN has been used for detecting catastrophic defects in an experimental mixedsignal CMOS circuits by sensing the abnormalities in the analyzed circuit’s response and by their consequent classification into a proper… Expand

References

SHOWING 1-10 OF 23 REFERENCES
Classification of Defective Analog Integrated Circuits Using Artificial Neural Networks
TLDR
This paper presents a new approach for detecting defects in analog integrated circuits using the feed-forward neural network trained by the resilient error back-propagation method and optimized hardware architecture of the selected neural network type was designed using VHDL for FPGA realization. Expand
Neural-network based analog-circuit fault diagnosis using wavelet transform as preprocessor
TLDR
An analog-circuit fault diagnostic system based on backpropagation neural networks using wavelet decomposition, principal component analysis, and data normalization as preprocessors that performs significantly better in fault diagnosis of analog circuits due to the proposed preprocessing techniques. Expand
A novel wavelet transform-based transient current analysis for fault detection and localization
  • S. Bhunia, K. Roy, J. Segura
  • Engineering, Computer Science
  • IEEE Transactions on Very Large Scale Integration (VLSI) Systems
  • 2005
TLDR
Wavelet-based detection method shows better sensitivity than spectral and time-domain methods and effectiveness of the localization method in presence of complex power supply network, measurement noise, and process variation is addressed. Expand
Analog fault diagnosis of actual circuits using neural networks
TLDR
The studies indicate that features extracted from actual circuits lie closer to each other and exhibit more overlap across fault classes compared to SPICE simulations, which implies that the neural network architecture which can most reliably perform fault diagnosis of actual circuits is one whose outputs estimate the probabilities that input features belong to different fault classes. Expand
Using artificial neural networks or Lagrange interpolation to characterize the faults in an analog circuit: an experimental study
A technique for diagnosing multiple faults in analog circuits from their impulse response function using a fault dictionary was developed. Dirac impulse input to the circuit was simulated and timeExpand
Transient power supply current testing of digital CMOS circuits
  • R. Makki, S. Su, H. T. Nagle
  • Engineering, Computer Science
  • Proceedings of 1995 IEEE International Test Conference (ITC)
  • 1995
TLDR
The physical experimental results show i/sub DDT/ to be effective in detecting disturb faults in SRAMs and drain/ source opens in general CMOS logic structures. Expand
Increased CMOS IC stuck-at fault coverage with reduced I/sub DDQ/ test sets
TLDR
The authors discuss the significant improvements that were achieved when a conventional ATPG (automatic test pattern generation) algorithm was modified to generate test sets suitable for I/sub DDQ/ testing, including increased SAF coverage, reduced vector set sizes, coverage of logically redundant SAFs and multiple SAFs, and reduced CPU cost for ATPG and fault simulation. Expand
A 12-bit intrinsic accuracy high-speed CMOS DAC
A 12-bit intrinsic accuracy digital-to-analog (D/A) converter integrated in a standard digital 0.5 /spl mu/m CMOS technology is presented. It is based on a current steering doubly segmented 6+2+4Expand
Current ratios: a self-scaling technique for production IDDQ testing
TLDR
This paper describes a method of using "current signatures" which uses only simple comparisons on the tester, and which automatically scales with process variations which give a wide range of background currents. Expand
Fundamentals of Artificial Neural Networks
  • M. Hassoun
  • Computer Science
  • Proceedings of the IEEE
  • 1996
TLDR
Fundamentals of Artificial Neural Networks provides the first systematic account of artificial neural network paradigms by identifying clearly the fundamental concepts and major methodologies underlying most of the current theory and practice employed by neural network researchers. Expand
...
1
2
3
...