Development of thermistor signal conditioning circuit using artificial neural networks

Vaegae Naveen Kumar; Komanapalli Venkata Lakshmi Narayana

Development of thermistor signal conditioning circuit using artificial neural networks

View Fulltext

Author(s): Vaegae Naveen Kumar ¹ and Komanapalli Venkata Lakshmi Narayana ¹
- Affiliations: 1: School of Electrical Engineering, VIT University, Vellore, Tamilnadu 632014, India
Source: Volume 9, Issue 8, November 2015, p. 955 – 961
DOI: 10.1049/iet-smt.2015.0008 , Print ISSN 1751-8822, Online ISSN 1751-8830

Received 26/01/2015, Accepted 23/06/2015, Revised 16/06/2015, Published

Thermistor is most widely used sensor in the temperature measurement due to its high sensitivity and fast response. The non-linearity of the thermistor gives rise to several difficulties for on-chip interface, direct digital readout, wireless transmission and so on. Hence, an effective lineariser is needed to overcome the difficulties. In this study, an artificial neural network-based lineariser has been developed for the thermistor connected in operational amplifier circuit. Operational amplifier-based thermistor signal conditioning circuit exhibits a stable temperature–voltage relation over a range of 0–100°C with low linearity. A multilayer perceptron feed-forward neural network is used for non-linearity compensation of thermistor circuit to further improve the linearity. A linearity of ±0.3% is achieved over 0–100°C with high temperature stability. A notable feature of the proposed method is the non-linearity error remains low over the entire dynamic range of the thermistor. The efficacy of the method is established through simulation studies and its practicality demonstrated with experimental results obtained on a prototype unit built and tested.

References

1. 1)
  - 20. Attari, M., Boudjema, F., Heniche, M.: ‘Linearizing a thermistor characteristic in the range of zero to 100 degree C with two layers artificial neural networks’. Proc. of Int. Conf. on Instrumentation and Measurement Technology, 1995, pp. 119–122.
2. 2)
  - 10. Kaliyugavaradan, S., Sankaran, P., Murti, V.G.K.: ‘A new compensation scheme for thermistors and its implementation for response linearization over a wide temperature range’, IEEE Trans. Instrum. Meas., 1993, 42, (5), pp. 952–956 (doi: 10.1109/19.252535).
3. 3)
  - 13. Pereira, J.M.D., Postolache, O., Girao, P.M.B.: ‘PDF based progressive polynomial calibration method for smart sensor linearization’, IEEE Instrum. Meas., 2009, 58, (9), pp. 3245–3252 (doi: 10.1109/TIM.2009.2022360).
4. 4)
  - 5. Sengupta, R.N.: ‘A widely linear temperature to frequency converter using a thermistor in a pulse generator’, IEEE Trans. Instrum. Meas., 1988, 37, (1), pp. 62–65 (doi: 10.1109/19.2665).
5. 5)
  - 19. Marconato, A., Hu, M., Boni, A., Petri, D.: ‘Dynamic compensation of nonlinear sensors by a learning-from-examples approach’, IEEE Trans. Instrum. Meas., 2008, 57, (8), pp. 1689–1694 (doi: 10.1109/TIM.2008.922074).
6. 6)
  - 7. Rosa, V.C., Palma, L.S., Oliveira, A., Torres, T.R.: ‘An inherently linear transducer using thermistor practical approach’. Proc. of third Int. Conf. on Sensor Technologies, 2008, pp. 491–495.
7. 7)
  - 14. Rivera, J., Herrera, G., Chacón, M.: ‘Improved progressive polynomial algorithm for self-calibration and optimal response in smart sensors’, Measurement, 2009, 42, (9), pp. 1395–1401 (doi: 10.1016/j.measurement.2009.05.010).
8. 8)
  - 1. Ramon, P.A., Webster, J.G.: ‘Sensors and signal conditioning’ (John-Wiley, 2013).
9. 9)
  - 12. Pereira, J.M.D., Girao, P.M.B.S., Postolache, O.: ‘Fitting transducer characteristics to measured data’, IEEE Instrum. Meas. Mag., 2001, 4, (4), pp. 26–39 (doi: 10.1109/5289.975463).
10. 10)
  - 25. Haykin, S.: ‘Neural networks: a comprehensive foundation’ (Prentice-Hall, 2008).
11. 11)
  - 16. Patra, J.C., Pal, R.N.: ‘Inverse modeling of pressure sensors using artificial neural networks’. Proc. of AMSE Int. Conf. on Signals, Data, and Systems, Bangalore, India, 1993, pp. 225–236.
12. 12)
  - 26. Hagan, M.T., Menhaj, M.: ‘Training feedforward networks with the Marquardt algorithm’, IEEE Trans. Neural Netw., 1994, 5, (6), pp. 989–993 (doi: 10.1109/72.329697).
13. 13)
  - 17. Khan, S.K., Agarwala, A.K., Shahani, D.T.: ‘Artificial neural network (ANN) based nonlinearity estimation of thermistor temperature sensors’. Proc. of 24th National Systems Conf., Bangalore, India, 2000, pp. 296–302.
14. 14)
  - 24. Zhao, H., Peng, L., Takahashi, T., Shimizu, K., Yamamoto, T.: ‘ANN based data integration for multi-path ultrasonic flowmeter’, IEEE Sens. J., 2014, 14, (2), pp. 362–370 (doi: 10.1109/JSEN.2013.2282466).
15. 15)
  - 2. Bowan, M.J., Sagar, F.H.: ‘Linearizing the self heated thermistor thermometer’, IEEE Trans. Instrum. Meas., 1972, 21, (1), pp. 48–53 (doi: 10.1109/TIM.1972.4313955).
16. 16)
  - 4. Khan, A.A.: ‘An improved linear temperature/voltage converter using thermistor in logarithmic network’, IEEE Trans. Instrum. Meas., 1985, 34, (5), pp. 635–638 (doi: 10.1109/TIM.1985.4315424).
17. 17)
  - 6. Natarajan, S.: ‘A modified linearized thermistor thermometer using an analog multiplier’, IEEE Trans. Instrum. Meas., 1990, 39, (2), pp. 440–441 (doi: 10.1109/19.52533).
18. 18)
  - 23. Hagan, M.T., Demuth, H.B.: ‘Neural network design’ (China Machine Press, Suzhou, China, 2005).
19. 19)
  - 21. Medrano-Marques, N.J., Martin-del-Brio, B.: ‘Sensor linearization with neural networks’, IEEE Trans. Ind. Electron., 2001, 48, (6), pp. 1288–1290 (doi: 10.1109/41.969414).
20. 20)
  - 15. Rahili, S., Ghaisari, J., Gilfar, A.: ‘Intelligent selection of calibration points using a modified progressive polynomial method’, IEEE Trans. Instrum. Meas., 2012, 61, (9), pp. 2519–2523 (doi: 10.1109/TIM.2012.2188662).
21. 21)
  - 8. Nenova, Z.P., Nenov, T.G.: ‘Linearization circuit of the thermistor connection’, IEEE Trans. Instrum. Meas., 2009, 58, (2), pp. 441–449 (doi: 10.1109/TIM.2008.2003320).
22. 22)
  - 9. Mohan, N.M., Kumar, V.J., Sankaran, P.: ‘Linearizing dual slope digital converter suitable for a thermistor’, IEEE Trans. Instrum. Meas., 2011, 60, (5), pp. 1515–1521 (doi: 10.1109/TIM.2010.2092875).
23. 23)
  - 29. Rivera-Mejia, J., Carrillo-Romero, M., Herrera-Ruiz, G.: ‘Self-compensation to build reconfigurable measurement systems’, IEEE Instrum. Meas. Mag., 2013, 16, pp. 10–19 (doi: 10.1109/MIM.2013.6495675).
24. 24)
  - 27. Hagan, M.T., Demuth, H.B., Beale, M.: ‘Neural network design’ (PWS-Kent, Boston, MA, USA, 1996).
25. 25)
  - 18. Arpia, P., Daponte, P., Grimaldi, D., Michaeli, L.: ‘ANN-based error reduction for experimentally modeled sensors’, IEEE Trans. Instrum. Meas., 2002, 51, (1), pp. 23–30 (doi: 10.1109/19.989891).
26. 26)
  - 3. Stankovic, D.K., Elazar, J.: ‘Thermistor multivibrator as the temperature-to-frequency converter and as a bridge for temperature measurement’, IEEE Trans. Instrum. Meas., 1977, 26, (1), pp. 41–46 (doi: 10.1109/TIM.1977.4314482).
27. 27)
  - 28. Wu, J.M.: ‘Multilayer Potts perceptrons with Levenberg–Marquardt learning’, IEEE Trans. Neural Netw., 2008, 19, (12), pp. 2032–2043 (doi: 10.1109/TNN.2008.2003271).
28. 28)
  - 22. Volgin, L.I.: ‘Electrical transducers for measurement instruments and systems’ (Sovetskoe Radio, Moscow, Russia, 1971) (in Russian).
29. 29)
  - 11. Dyer, S.A., Dyer, J.S.: ‘Cubic-spline interpolation 1’, IEEE Instrum. Meas. Mag., 2001, 4, (1), pp. 44–46 (doi: 10.1109/5289.911175).
30. 30)
  - 20. Attari, M., Boudjema, F., Heniche, M.: ‘Linearizing a thermistor characteristic in the range of zeroto 100 degree Cwith two layers artificial neural networks’. Proc. of Int. Conf. on Instrumentation and Measurement Technology, 1995, pp. 119–122.

Login

Not registered yet?

Share

Tools

Login to add to favourites

Key

Development of thermistor signal conditioning circuit using artificial neural networks

References

Related content