No Access

A GENERALIZED ABFT TECHNIQUE USING A FAULT TOLERANT NEURAL NETWORK

AMIR MOOSAVIE NIA

Faculty of Electrical Engineering, Khajeh Nasiroddin Toosi University, Sayed Khandan, Tehran, Iran

Search for more papers by this author

and

KARIM MOHAMMADI

Faculty of Electrical Engineering, Iran University of Science and Technology, Narmak, Tehran, 16844, Iran

Search for more papers by this author

https://doi.org/10.1142/S0218126607003708Cited by:6 (Source: Crossref)

Abstract

In this paper, a measure of sensitivity is defined to evaluate fault tolerance of neural networks and we show that the sensitivity of a link is closely related to the amount of information passed through it. Based on this assumption, we prove that the distribution of output error caused by s-a-0 (stuck at 0) faults in an MLP network has a Gaussian distribution function. UDBP (Uniformly Distributed Back Propagation) algorithm is then introduced to minimize mean and variance of the output error. Then an MLP neural network trained with UDBP, contributes in an Algorithm-Based Fault Tolerant (ABFT) scheme to protect a nonlinear data process block. A systematic real convolution code guarantees that faults representing errors in the processed data will result in notable nonzero values in syndrome sequence. A majority logic decoder can now easily detect and correct single faults by observing the syndrome sequence. Simulation results demonstrating the error detection and correction behavior against random s-a-0 faults are presented too.

Keywords:

References

Z. Vukic, D. Pavlekovic and H. Ozbolt, Rudder servo_system fault diagnosis using neural network fault modeling, Ocean'98 Conf. Proc.1 (1998) pp. 538–543. Google Scholar
A. Berneiri, M. D'Apuzzo and L. Sansone, A neural network approach for identification and fault diagnosis on dynamic systems, Instrumentation and Measurement Technology Conf. (1993) pp. 564–569. Google Scholar
C.-Y. Tyan , P. P. Wang and D. R. Bahler , Neural fault diagnosis and fuzzy fault control for a complex linear dynamic system , Int. Joint Conf. Fourth IEEE Int. Conf. Fuzzy Systems ( 1995 ) . Google Scholar
T. Tanprasert and C. Tanparasert, Probing technique for neural net fault detection, IEEE Int. Conf. Neural Networks2 (1996) pp. 1001–1005. Google Scholar
C. Khunasaraphan, K. Vanapipat and C. Lursinsap, IEEE Trans. Neural Networks 5, 651 (1994), DOI: 10.1109/72.298234. Crossref, Web of Science, Google Scholar
A. Moosavienia and K. Mohammadi, An ABFT for FIR systems using a time delay neural network, Proc. 4th Int. Wireless and Telecommunications Symp., IWTS2000 (2000) pp. 244–248. Google Scholar
B. W. Johnson , Design and Analysis of Fault Tolerant Digital Systems ( Addison-Wesley, Pub. , 1989 ) . Google Scholar
S. Yajnik and N. Jha, IEEE Trans. Parallel and Distributed Syst. 8, 757 (1997), DOI: 10.1109/71.598349. Crossref, Web of Science, Google Scholar
Y. Taniguchi and N. Kamiura, Activation function manipulation for fault tolerant feed forward neural networks, Proc. Eight Asian Test Symp. (1998) p. 203. Google Scholar
A. F. Murray and P. J. Edwards, IEEE Trans. Neural Networks 4, 722 (1993), DOI: 10.1109/72.238328. Crossref, Web of Science, Google Scholar
T. Ito and I. Takanami, On fault injection approaches for fault tolerance of feed forward neural networks, Proc. Sixth Asian Test Symp. (1997) pp. 88–93. Google Scholar
C. Neti, M. H. Schneider and E. D. Young, IEEE Trans. Neural Networks 3, 14 (1992), DOI: 10.1109/72.105414. Crossref, Web of Science, Google Scholar
T. Zhang , D. Hu and S. Yang , Fault tolerant analysis of feedback neural networks with threshold neurons , Proc. Eight Asian Test Symp. ( 1998 ) . Google Scholar
C. T. Chiuet al., Training techniques to obtain fault tolerant neural networks, Digest FTCS (1994) pp. 360–369. Google Scholar
O. J. Kwon and S. Y. Bang, Electron. Lett. 33, 1055 (1997), DOI: 10.1049/el:19970729. Crossref, Web of Science, Google Scholar
C. J. Anfinson, IEEE Trans. Comput. 37, 1599 (1988), DOI: 10.1109/12.9736. Crossref, Web of Science, Google Scholar
V. S. S. Nair and J. A. Abraham, IEEE Trans. Comput. 39, 426 (1990), DOI: 10.1109/12.54836. Crossref, Web of Science, Google Scholar
D. L. Tao and C. R. Hartmann, IEEE Trans. Parallel and Distributed Syst. 4, 198 (1993), DOI: 10.1109/71.207595. Crossref, Web of Science, Google Scholar
S.-J. Wang and N. K. Jha, IEEE Trans. Comput. 43, 849 (1994), DOI: 10.1109/12.293265. Crossref, Web of Science, Google Scholar
K. N. Balasubramanya, K. Bhuvaneswari and C. S. R. Murthy, IEEE Trans. Parallel and Distributed Syst. 9, 825 (1998). Web of Science, Google Scholar
A. R. Chowdhury and P. Banerjee, IEEE Trans. Comput. 45, 38 (1996). Google Scholar
G. R. Redinbo and B. Zagar, IEEE Trans. Infor. Theor. 39, 553 (1993), DOI: 10.1109/18.212285. Crossref, Web of Science, Google Scholar
J.-L. Sung and G. R. Redinbo, IEEE Trans. Comput. 45, 425 (1996), DOI: 10.1109/12.494100. Crossref, Web of Science, Google Scholar
D. M. Blough and A. Pelc, IEEE Trans. Parallel and Distributed Syst. 5, 532 (1994), DOI: 10.1109/71.282563. Crossref, Web of Science, Google Scholar
J. Baylis , Error-Correcting Codes: A Mathematical Introduction ( Chapman and Hall Ltd. , 1998 ) . Crossref, Google Scholar
B. Sklar, A tutorial on convolutional coding for M-ary signals, Trellis coded modulation, Military Communications Conf. (1988) pp. 637–645. Google Scholar
G. R. Redinbo and B. Zagar, IEEE Trans. Infor. Theor. 39, 553 (1993), DOI: 10.1109/18.212285. Crossref, Web of Science, Google Scholar
A. J. Viterbi and J. K. Omura , Principles of Digital Communication and Coding ( McGraw-Hill , 1985 ) . Google Scholar
L. Fausett , Fundamental of Neural Networks ( Prentice Hall , 1994 ) . Google Scholar
D. R. Hush and B. G. Horne, IEEE Signal Process. Mag. 10, 8 (1993), DOI: 10.1109/79.180705. Crossref, Web of Science, Google Scholar
R. Beale and T. Jackson , Neural Computing: An Introduction ( IOP Publishing Ltd. , 1990 ) . Crossref, Google Scholar
A. Adibi, A. Moosavienia and P. Moallem, Fast neural network learning using a variable learning parameter value, Proc. 3rd Iranian Conf. Electrical Engineering (ICEE95), Computer (1995) pp. 69–76. Google Scholar
T. Ito and I. Takanami, On fault injection approaches for fault tolerance of feed forward neural networks, Proc. Sixth Asian Test Symp. (1997) pp. 88–93. Google Scholar
R. G. Brown and P. Y. C. Hwang , Introduction to Random Signal and Applied Kalman Filtering, with MATLAB Exercise and Solutions ( John Wiley & Sons , 1997 ) . Google Scholar
E. P. Cunningham , Digital Filtering: An Introduction ( John Wiley & Sons , 1995 ) . Google Scholar