Skip to main content
SpringerLink
Log in

Fault detection and measurements correction for multiple sensors using a modified autoassociative neural network

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Periodic manual calibrations ensure that an instrument will operate correctly for a given period of time, but they do not assure that a faulty instrument will remain calibrated for other periods. In addition, sometimes such calibrations are even unnecessary. In industrial plants, the analysis of signals provided by process monitoring sensors is a difficult task due to the high dimensionality of the data. A strategy for online monitoring and correction of multiple sensors measurements is therefore required. Thus, 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 monitor and are used in the control of an internal combustion engine installed in a mining truck. Results show that the proposed model is able to map and correct faulty sensor signals and achieve low error rates.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. Antory D, Irwin G, Kruger U, McCullough G (2005) Improved process monitoring using nonlinear principal component models. Int J Intell Syst 23:520–544

    Article  Google Scholar 

  2. Afonso P, Ferreira J, Castro J (1998) Sensor fault detection and identification in a pilot plant under process control. Chem Eng Res Design 76:490–498

    Article  Google Scholar 

  3. Böhme Th, Fletcher I, Cox C (1999) Reliable neuro self-tuning control using auto-associative neural networks for the water treatment. e&i Elektrotechnik und Informationstechnik 116:6

    Google Scholar 

  4. Bueno E, Ting D, Gonçalves I (2007) Development of an artificial neural network for monitoring and diagnosis of sensor fault and detection in the IEA-R1 research reactor at IPEN. In: INAC 2007—international nuclear atlantic conference, INAC 2007 DVD

  5. De Miguel L, Blázquez L (2005) Fuzzy logic-based decision-making for fault diagnosis in a DC motor. Eng Appl Artif Intell 18:423–450

    Article  Google Scholar 

  6. Eyng E, Silva F, Palú F, Fileti A (2008) Neural network based control of an absorption column in the process of bioethanol production. Braz Arch Biol Technol 52:961–972

    Article  Google Scholar 

  7. Fantoni PF, Hoffmann MI, Shankar R, Davis EL (2003) On-line monitoring of instrument channel performance in nuclear power plant using PEANO. Prog Nucl Energy 43:83–89

    Article  Google Scholar 

  8. Galotto L, Bose B, Leite C, Pereira J, Borges da Silva L, Lambert-Torres G (2007) Auto-associative neural networks based sensor drift compensation in indirect vector controlled drive system. In: 33rd annual conference of the IEE industrial electronics society, Taiwan

  9. Garcia-Alvarez D, Fuente MJ, Vega P, Sainz G (2009) Fault detection and diagnosis using multivariate statistical techniques in a wastewater treatment plant. In: Proceedings of the 7th IFAC international symposium on advanced control of chemical processes, Turkey

  10. Haykin S (1998) Neural networks: a comprehensive foundation. Macmillan College Publishing Company, New York

    Google Scholar 

  11. Hines J, Garvey D (2007) Process and equipment monitoring methodologies applied to sensor calibration monitoring. Qual Reliab Eng Int 23:123–135

    Article  Google Scholar 

  12. Hines J, Grinok A, Attieh I, Urigh R (2000) Improved methods for on-line sensor calibration verification. In: 8th International conference on nuclear engineering, Baltimore, USA

  13. Koscielny J, Syfert M (2006) 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

    MathSciNet  Google Scholar 

  14. Kramer MA (1991) Nonlinear principal component analysis using autoassociative neural networks. AIChE J 37(2):233–243

    Article  Google Scholar 

  15. Kramer MA (1992) Autoassociative neural networks. Comput Chem Eng 16(4):313–328

    Article  Google Scholar 

  16. Marseguerra M, Zoia A (2005) The autoassociative neural networks in signal analysis I: the data dimensionality reduction and its geometric interpretation. Ann Nucl Energy 32:1191–1206

    Article  Google Scholar 

  17. Marseguerra M, Zoia A (2005) The autoassociative neural networks in signal analysis II: application to on-line monitoring of a simulated BWR component. Ann Nucl Energy 32:1207–1223

    Article  Google Scholar 

  18. Marseguerra M, Zoia A (2006) The autoassociative neural networks in signal analysis III: enhancing the reliability of a NN with application to a BWR. Ann Nucl Energy 33:475–489

    Article  Google Scholar 

  19. Mendel JM (1995) Fuzzy logic systems for engineering: a tutorial. Proc IEEE 83(3):345–377

    Article  Google Scholar 

  20. Monsef WA, Fayez A (2007) Design of a neural: PLC Controller for Industrial Plant. In: International conference on machine learning; models, technologies & applications, MLMTA (June) 25–28, Las Vegas, Nevada, USA

  21. Najafi M, Culp Ch, Langari R (2004) Enhanced auto-associative neural networks for sensor diagnosis (E_AANN). In: Proceedings of international journal of conference on neural networks (IJCNN) and IEEE international conference on fuzzy systems, Hungary

  22. Qiao W, Venayagamoorthy G, Harley R (2009) Missing-sensor-fault-tolerant control for SSSC facts device with real-time implementation. IEEE Trans Power Deliv 24:2

    Article  Google Scholar 

  23. Reyes J, Vellasco M, Tanscheit R (2010) Sistemas de Inferência Fuzzy para Auto-Compensação e Auto-Validação em Sensores Inteligentes. In: XVIII Congresso Brasileiro de Automática, Bonito, Brazil (in Portuguese)

  24. Sanz J, Perera R, Huerta C (2007) Fault diagnosis of rotating machinery based on auto-associative neural networks and wavelet transforms. J Sound Vib 302:981–999

    Article  Google Scholar 

  25. Simani S, Fantuzzi C, Beghelli S (2000) Diagnosis techniques for sensor faults of industrial processes. IEEE Trans Control Syst Technol 8:848

    Article  Google Scholar 

  26. Singh H (2004) Development and implementation of an artificially intelligent search algorithm for sensor fault detection using neural networks. M.Sc. Thesis, Texas A&M University

  27. Soares-Filho W, Seixas J, Caloba L (2001) Principal component analysis for classifying passive sonar signals. IEEE Int Symp Circuits Syst Syd Aust 2:592–595

    Google Scholar 

  28. Theilliol D, Noura H, Ponsart J (2002) Fault diagnosis and accommodation of a three-tank system based on analytical redundancy. ISA 41(3):365–382

    Article  Google Scholar 

  29. Tian GY, Zhao ZX, Baines RW (1999) A Fieldbus-based intelligent sensor. Mechatronics 10:835–849

    Article  Google Scholar 

  30. Upadhyaya BR, Eryurek E (1992) Application of neural networks for sensor validation and plant monitoring. Nucl Technol 97:170–176

    Google Scholar 

  31. Wrest D, Hines W, Uhrig R (1996) Instrument surveillance and calibration verification through plant wide monitoring using autoassociative neural networks. University of Tenn-Knoxville, USA

    Google Scholar 

  32. Xiau X, Hines JW, Uhrig RE (1998) Online sensor calibration monitoring and fault detection for chemical processes. Maintenance and Reliability Center, University of Tennessee, USA

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical Engineering, Pontifical Catholic University of Rio de Janeiro, Rua Marquês de São Vicente, 225, Rio de Janeiro, RJ, 22.452-900, Brazil

    Javier Reyes, Marley Vellasco & Ricardo Tanscheit

Authors
  1. Javier Reyes
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Marley Vellasco
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ricardo Tanscheit
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Marley Vellasco.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Reyes, J., Vellasco, M. & Tanscheit, R. Fault detection and measurements correction for multiple sensors using a modified autoassociative neural network. Neural Comput & Applic 24, 1929–1941 (2014). https://doi.org/10.1007/s00521-013-1429-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-013-1429-4

Keywords

Search

Navigation