Neural Network Based Real-time Correction of Transducer Dynamic Errors

Roj, J.

doi:10.2478/msr-2013-0042

Abstract

In order to carry out real-time dynamic error correction of transducers described by a linear differential equation, a novel recurrent neural network was developed. The network structure is based on solving this equation with respect to the input quantity when using the state variables. It is shown that such a real-time correction can be carried out using simple linear perceptrons. Due to the use of a neural technique, knowledge of the dynamic parameters of the transducer is not necessary. Theoretical considerations are illustrated by the results of simulation studies performed for the modeled second order transducer. The most important properties of the neural dynamic error correction, when emphasizing the fundamental advantages and disadvantages, are discussed.

References

[1] Mukhopadhyay, S.C., Gupta, G.S. (2008). Smart Sensors and Sensing Technology. Lecture Notes in Electrical Engineering, Volume 20. Springer.10.1007/978-3-540-79590-2
Search in Google Scholar
[2] Frank, R. (2000). Understanding Smart Sensors. Second edition. Artech House Inc.10.1088/0957-0233/11/12/711
Search in Google Scholar
[3] Morawski, R.Z. (1994). Unified approach to measurand reconstruction. IEEE Transactions on Instrumentation & Measurement, 43 (2), 226-231.10.1109/19.293425
Search in Google Scholar
[4] Roj, J. (2013). Metrological properties of RBF and MLP neural networks used for static errors correction in a sampling transducer. Przegląd Elektrotechniczny, 89 (1a), 84-87. (in Polish)
Search in Google Scholar
[5] Jakubiec, J., Makowski, P., Roj, J. (2009). Error model application in neural reconstruction of nonlinear sensor input signal. IEEE Transactions on Instrumentation and Measurement, 58 (3), 649-656.10.1109/TIM.2008.2005076
Search in Google Scholar
[6] Roj, J. (2013). Neural Reconstruction of Measurement Signals. Gliwice, Wydawnictwo Politechniki Śląskiej. (in Polish)
Search in Google Scholar
[7] Haykin, S. (2008). Neural Networks: A Comprehensive Foundation. Third edition. Prentice Hall.
Search in Google Scholar
[8] Gupta, M., Homma, N., Jin, L. (2003) Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory. John Wiley & Sons.10.1002/0471427950
Search in Google Scholar
[9] Bishop, Ch.M. (1996). Neural Networks for Pattern Recognition. Oxford University Press.
Search in Google Scholar
[10] Jackowska-Strumiłło, L. (2001). Dynamic temperature error correction by the use of artificial naural networks. In TEMPMEKO 2001 : 8th International Symposium on Temperature and Thermal Measurements in Industry and Science, 19-21 June2001. Berlin: VDE-Verlag, 1097-1102.
Search in Google Scholar
[11] Wu, D., Huang, S., Zhao, W., Xin, J. (2009). Infrared thermometer sensor dynamic error compensation using Hammerstein neural network. Sensors and Actuators A: Physical, 149 (1), 152-158.10.1016/j.sna.2008.11.005
Search in Google Scholar
[12] Hornik, K., Stinchcombe, M., White, H. (1989).Multilayer feedforward networks are universal approximators. Neural Networks, 2, 359-366.10.1016/0893-6080(89)90020-8
Search in Google Scholar
[13] Feldkamp, L.A., Puskorius, G.V. (1998). A signal processing framework based on dynamic neural networks with application to problems in adaptation, filtering, and classification. Proceedings of the IEEE, 86 (11), 2259-2277.10.1109/5.726790
Search in Google Scholar
[14] Park, J., Sandberg, I.W. (1991). Universal approximation using radial-basis-function networks.Neural Computation, 3 (2), 246-257.10.1162/neco.1991.3.2.246
Search in Google Scholar
[15] Singh, A.P., Kamal, T.S., Kumar, S. (2006).Development of a virtual linearizer for correcting transducer static nonlinearity. ISA Transactions, 45 (3), 319-328.10.1016/S0019-0578(07)60215-8
Search in Google Scholar
[16] Patra, J.C., Chakraborty, G., Meher, P.K. (2008).Neural-network-based robust linearization and compensation technique for sensors under nonlinear environmental influences. IEEE Transactions on Circuits and Systems I: Regular Papers, 55 (5), 1316-1327.10.1109/TCSI.2008.916617
Search in Google Scholar
[17] Wang, Y.-X, Li, Z.-H., Zhang, T.-H. (2010). Research of ultrasonic flow measurement and temperature compensation system based on neural network. In International Conference on Artificial Intelligence and Computational Intelligence (AICI 2010), 23-24October 2010. IEEE, Vol. 1, 268-271.
Search in Google Scholar
[18] Jackowska-Strumiłło, L., Urbański, M. (2001).Linearisation of thermistor characteristic by the use of artificial naural networks. In TEMPMEKO 2001 : 8th International Symposium on Temperature and Thermal Measurements in Industry and Science, 19-21June 2001. Berlin: VDE-Verlag, 1035-1040.
Search in Google Scholar
[19] Massicotte, D., Legendre, S., Barwicz, A. (1998).Neural-network-based method of calibration and measurand reconstruction for a high-pressure measuring system. IEEE Transactions on Instrumentation and Measurement, 47 (2), 362-370.10.1109/19.744175
Search in Google Scholar
[20] Morawski, R.Z., Miękina, A., Wiśniewski, M., Barwicz, A. (2002). Neural network based calibration of a mini-spectrophotometer. In Proceedings of the 19th IEEE Instrumentation and Measurement Technology Conference (IMTC 2002). IEEE, Vol. 2, 1083-1086.
Search in Google Scholar
[21] Rath, S.K., Patra, J.C., Kot, A.C. (2000). An intelligent pressure sensor with self-calibration capability using artificial neural networks. In IEEE International Conference on Systems, Man, and Cybernetics. IEEE, Vol. 4, 2563-2568.
Search in Google Scholar
[22] Nabielec, J. (1999). An outlook on the DSP dynamic error blind correction of the analog part of the measurement channel. In Proceedings of the 16th IEEE Instrumentation and Measurement Technology Conference (IMTC ’99). IEEE, Vol. 2, 709-712.
Search in Google Scholar
[23] Morawski, R.Z. (2007). On teaching measurement applications of digital signal processing. Measurement, 40 (2), 213-223.10.1016/j.measurement.2006.06.015
Search in Google Scholar
[24] Wu, J., Zhang, Z., Dong, G., Wang, W. (2011). Realtime correction for sensor's dynamic error based on DSP. In IEEE Instrumentation and Measurement Technology Conference (I2MTC), 10-12 May 2011.IEEE, 1-6.
Search in Google Scholar
[25] Wu, J., Zhang, Z., Wang, W. (2012). FPGA implementation of high speed parallel correction for sensor's dynamic error. Chinese Journal of Sensors and Actuators, 25 (1), 67-71.
Search in Google Scholar
[26] Jafaripanah, M., Al-Hashimi, B.M, White, N.M. (2005). Application of analog adaptive filters for dynamic sensor compensation. IEEE Transaction On Instrumentation and Measurement, 54 (1), 245-251.10.1109/TIM.2004.839763
Search in Google Scholar
[27] Jafaripanah, M., Al-Hashimi, B.M, White, N.M. (2003). Load cell response correction using analog adaptive techniques. In International Symposium on Circuits and Systems (ISCAS2003), 25-28 May 2003.IEEE, IV-752-IV-755.10.1109/ISCAS.2003.1206283
Search in Google Scholar
[28] Bahar, H.B., Safari, E., Ghazijahani, H.A. (2010).Artifcial neural networks based dynamicweight estimation with optical arrangement. Transactions D: Computer Science & Engineering and Electrical Engineering, 17 (2), 189-195.
Search in Google Scholar
[29] Bahar, H.B., Horrocks, D.H. (1998). Dynamic weight estimation using an artificial neural network. Artificial Intelligence in Engineering, 12 (1-2), 135-139.10.1016/S0954-1810(97)00017-4
Search in Google Scholar
[30] Fraden, J. (2010). Handbook of Modern Sensors.Springer.10.1007/978-1-4419-6466-3
Search in Google Scholar
[31] Burns, R.S.(2001). Advanced Control Engineering.Butterworth-Heinemann.
Search in Google Scholar
[32] Bojarska, M., Jakubiec, J. (2001). A method of modelling sampling converter dynamic errors.Metrology and Measurement Systems, 8 (4), 337-355.
Search in Google Scholar
[33] Palm, III, W.J. (2010). System Dynamics. Second edition. McGraw-Hill.
Search in Google Scholar
[34] Dorf, R.C., Bishop, R.H. (2008). Modern Control Systems. Eleventh edition. Prentice Hall.
Search in Google Scholar
[35] Jakubiec, J. (2010). Data Errors and Uncertainties in the Measurement and Control Systems. Gliwice, Wydawnictwo Politechniki Śląskiej. (in Polish)
Search in Google Scholar
[36] MathWorks Inc. Neural Network Toolbox: User’s Guide.
Search in Google Scholar
[37] Hagan, M.T., Menhaj, M. (1994). Training feedforward networks with the Marquardt algorithm.IEEE Transactions on Neural Networks, 5 (6), 989-993. 10.1109/72.32969718267874
Search in Google Scholar

Neural Network Based Real-time Correction of Transducer Dynamic Errors

Abstract

Paradigm

My account