Measurement Correction for Multiple Sensors Using Modified Autoassociative Neural Networks

  • Javier Reyes Sanchez
  • Marley Vellasco
  • Ricardo Tanscheit
Part of the Communications in Computer and Information Science book series (CCIS, volume 311)


In industrial plants, the analysis of signals provided by monitoring sensors is a difficult task due to the high dimensionality of the data. This work proposes the use of Autoassociative Neural Networks trained with a Modified Robust Method in an online monitoring system for fault detection and self-correction of measurements generated by a large number of sensors. Unlike the existing models, the proposed system aims at using only one neural network to reconstruct faulty sensor signals. The model is evaluated with the use of a database containing measurements collected by industrial sensors that control and monitor an internal combustion engine. Results show that the proposed model is able to map and correct faulty sensor signals and achieve low error rates.


sensors calibration fault detection autoassociative neural networks signal monitoring system 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Tian, G.Y., Zhao, Z.X., Baines, R.W.: A Fieldbus-based Intelligent Sensor. Mechatronics 10, 835–849 (1999)CrossRefGoogle Scholar
  2. 2.
    Afonso, P., Ferreira, J., Castro, J.: Sensor Fault Detection and Identification in a Pilot Plant under Process Control. Chemical Eng. Research and Design 76, 490–498 (1998)CrossRefGoogle Scholar
  3. 3.
    Monsef, W.A., Fayez, A.: Design of a Neural - PLC Controller for Industrial Plant. In: Int. Conf. on Mach. Learning - Models, Technologies & Applications, Las Vegas, USA (2007)Google Scholar
  4. 4.
    Garcia-Alvarez, D., Fuente, M.J., Vega, P., Sainz, G.: Fault Detection and Diagnosis using Multivariate Statistical Techniques in a Wastewater Treatment Plant. In: 7th IFAC International Symposium on Advanced Control of Chemical Processes, Turkey (2009)Google Scholar
  5. 5.
    Koscielny, J., Syfert, M.: Fuzzy Diagnostic Reasoning that takes into Account the Uncertainty of the Relation between Faults and Symptoms. Int. J. Appl. Math. Comput. Sci. 16, 27–35 (2006)MathSciNetGoogle Scholar
  6. 6.
    Theilliol, D., Noura, H., Ponsart, J.: Fault Diagnosis and Accommodation of a Three-Tank System based on Analytical Redundancy. The Instrumentation, Systems, and Automation Society 41(3), 365–382 (2002)Google Scholar
  7. 7.
    Najafi, M., Culp, C., Langari, R.: Enhanced Auto-Associative Neural Networks for Sensor Diagnosis (E_AANN). In: Int. J. Conf. on Neural Networks & IEEE Int. Conf. on Fuzzy Systems, Hungary (2004)Google Scholar
  8. 8.
    Kramer, M.A.: Nonlinear Principal Component Analysis using Autoassociative Neural Networks. A.I.Ch.E. Journal 37(2), 233–243 (1991)CrossRefGoogle Scholar
  9. 9.
    Coura, R., Seixas, J., Soares, W.: Classificação de Sinais de Sonar Passivo Utilizando Componentes Principais Não-lineares. Learning and Nonlinear Models 2, 60–72 (2004)Google Scholar
  10. 10.
    Cuenca, W., Seixas, J., Levy, A.: Análise de Componentes Principais para Identificar Descargas Parciais em Transformadores de Potência. In: Brazilain Symposium on Neural Nets, Rio de Janeiro, Brazil (2004)Google Scholar
  11. 11.
    Kramer, M.A.: Autoassociative Neural Networks. Computers in Chemical Engineering 16(4), 313–328 (1992)CrossRefGoogle Scholar
  12. 12.
    Wrest, D., Hines, W., Uhrig, R.: Instrument Surveillance and Calibration Verification through Plant Wide Monitoring Using Autoassociative Neural Networks. University of Tenn-Knoxville, USA (1996)Google Scholar
  13. 13.
    Hines, J., Garvey, D.: Process and Equipment Monitoring Methodologies applied to Sensor Calibration Monitoring. Wiley InterScience Quality and Reliability Engineering International 23, 123–135 (2007)CrossRefGoogle Scholar
  14. 14.
    Marseguerra, M., Zoia, A.: The Autoassociative Neural Networks in Signal Analysis II: Application to on-line monitoring of a simulated BWR component. Annals of Nuclear Energy 32, 1207–1223 (2005)CrossRefGoogle Scholar
  15. 15.
    Hines, J., Grinok, A., Attieh, I., Urigh, R.: Improved Methods for On-line Sensor Calibration Verification. In: 8th Int. Conf. on Nuclear Engineering, Baltimore, USA (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Javier Reyes Sanchez
    • 1
  • Marley Vellasco
    • 1
  • Ricardo Tanscheit
    • 1
  1. 1.Departmente of Electrical EngineeringPontifical Catholic University of Rio de JaneiroRio de JaneiroBrazil

Personalised recommendations