Abstract
Micro Electro Mechanical Systems will soon usher in a new technological renaissance. Learn about the state of the art, from inertial sensors to microfluidic devices [1]. Over the last few years, considerable effort has gone into the study of the failure mechanisms and reliability of MEMS. Although still very incomplete, our knowledge of the reliability issues relevant to MEMS is growing. One of the major problems in MEMS production is fault detection. After fault diagnosis, hardware or software methods can be used to overcome it. Most of MEMS have nonlinear and complex models. So it is difficult or impossible to detect the faults by traditional methods, which are model-based.In this paper, we use Robust Heteroscedastic Probabilistic Neural Network, which is a high capability neural network for fault detection. Least Mean Square algorithm is used to readjust some weights in order to increase fault detection capability.
This work has been partially supported by Iran Telecommunication Research Center.
An erratum to this chapter can be found at http://dx.doi.org/10.1007/11550907_163 .
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Murari, B.: Integrated Nanelectronic Components into Electronic Microsystems. IEEE Trans. on Reliability 52(1), 36–44 (2003)
Muller, R., Wagner, U., Bernhard, W.: Reliability of MEMS-a methodical approach. In: Proc.11th European symposium on reliability of electron devices, failure physics and analysis, pp. 1657–1662 (2001)
Rosing, R., Richardson, A.: Test Support Strategies for MEMS. In: IEEE International Mixed Signal Test Workshop, Whistler, Canada (June 1999)
Mir, S., Charlot, B.: On the Integration of Design and Test for chips embedding MEMS. IEEE design and Test of Computers (October-December 1999)
TIMA Lab research reports (2002-2004), http://Tima.imag.fr
Yang, S.H., Chen, B.H.: Neural Network Based Fault Diagnosis Using Unmeasurable Inputs. Journal of Artificial Intelligence-PERGAMON 13, 345–356 (2000)
El-Gamal, M.A.: Genetically Evolved Neural Networks for Fault Classification in Analog Circuits. Journal of Neural Computing & applications 11, 112–121 (2002)
Asgary, R., Mohammadi, K.: Pattern Recognition and Fault Detection in MEMS. In: Fourth International Conference on Computer Recognition System, Poland, May 2005, pp. 877–884 (2005)
Streit, R.L., Luginbuhl, T.E.: Maximum Likelihood Training of Probabilistic Neural Network. IEEE Trans. Neural Networks 5(5), 764–783 (1994)
Yang, Z.R., Zwolinski, M., Chalk, C.D., Williams, A.C.: Applying A Robust Heteroscedastic Probabilistic Neural Network to Analog Fault Detection and Classification. IEEE Trans. Computer-Aided Design of Integrated Circuits and Systems 19(1), 142–151 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Asgary, R., Mohammadi, K. (2005). A New Probabilistic Neural Network for Fault Detection in MEMS. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds) Artificial Neural Networks: Formal Models and Their Applications – ICANN 2005. ICANN 2005. Lecture Notes in Computer Science, vol 3697. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550907_140
Download citation
DOI: https://doi.org/10.1007/11550907_140
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28755-1
Online ISBN: 978-3-540-28756-8
eBook Packages: Computer ScienceComputer Science (R0)