Investigation of Artificial Neural Network Techniques for Thermistor Linearization

This paper presents the development of an artificial neural network (ANN)-based linearizer for thermistor connected in operational amplifier based inverting amplifier circuit. The op-amp based thermistor signal conditioning circuit exhibits a stable temperature-voltage relation over a temperature range of 0°C - 100°C with moderate linearity. The transformation technique is used for the analysis and design of the thermistor circuit. An ANN-based direct modeling technique is used for nonlinearity estimation of thermistor circuit to improve the linearity. In this paper, four neural network algorithms Levenberg-Marquardt, Broyden- Fletcher-Goldfarb-Shanno, scaled conjugate gradient and extreme learning machine algorithms are used for training and learning of ANN. The merits and de-merits of the algorithms are investigated for thermistor linearization. An embedded unit is used to implement the learning and training of the ANN techniques and the performance of the developed techniques is experimentally verified on a prototype unit. A notable feature of the developed technique is the non-linearity error remains very low over the entire dynamic range of the sensor. Copyright © 2015 IFSA Publishing, S. L.

[1]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[2]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[3]  Pasquale Daponte,et al.  ANN-based error reduction for experimentally modeled sensors , 2002, IEEE Trans. Instrum. Meas..

[4]  R. Sengupta.  A widely linear temperature to frequency converter using a thermistor in a pulse generator , 1988 .

[5]  Jafar Ghaisari,et al.  Intelligent Selection of Calibration Points Using a Modified Progressive Polynomial Method , 2012, IEEE Transactions on Instrumentation and Measurement.

[6]  Ganapati Panda,et al.  An intelligent pressure sensor using neural networks , 2000, IEEE Trans. Instrum. Meas..

[7]  J. Nocedal.  Updating Quasi-Newton Matrices With Limited Storage , 1980 .

[8]  A. Oliveira,et al.  An inherently linear transducer using thermistor practical approach , 2008, 2008 3rd International Conference on Sensing Technology.

[9]  Toshko G. Nenov,et al.  Linearization Circuit of the Thermistor Connection , 2009, IEEE Transactions on Instrumentation and Measurement.

[10]  L. F. Pau,et al.  Neural network signal understanding for instrumentation , 1990 .

[11]  F. Boudjema,et al.  Linearizing a thermistor characteristic in the range of zero to 100 degree C with two layer artificial neural networks , 1995, Proceedings of 1995 IEEE Instrumentation and Measurement Technology Conference - IMTC '95.

[12]  Daniele Marioli,et al.  Application of an optimal look-up table to sensor data processing , 1999, IEEE Trans. Instrum. Meas..

[13]  Octavian Postolache,et al.  A temperature-compensated system for magnetic field measurements based on artificial neural networks , 1998, IEEE Trans. Instrum. Meas..

[14]  Guang-Bin Huang,et al.  Trends in extreme learning machines: A review , 2015, Neural Networks.

[15]  B. Sundqvist.  Simple, wide-range, linear temperature-to-frequency converters using standard thermistors , 1983 .

[16]  L. M. Simmons,et al.  A Relationship between Resistance and Temperature of Thermistors , 1950 .

[17]  Ganapati Panda,et al.  Artificial neural network-based nonlinearity estimation of pressure sensors , 1994 .

[18]  J. Rivera,et al.  Improved progressive polynomial algorithm for self-calibration and optimal response in smart sensors , 2009 .

[19]  Guang-Bin Huang,et al.  An Insight into Extreme Learning Machines: Random Neurons, Random Features and Kernels , 2014, Cognitive Computation.

[20]  V. Jagadeesh Kumar,et al.  Linearizing Dual-Slope Digital Converter Suitable for a Thermistor , 2010, IEEE Transactions on Instrumentation and Measurement.

[21]  G. L. Pearson,et al.  Properties and Uses of Thermistors--- Thermally Sensitive Resistors , 1946, Transactions of the American Institute of Electrical Engineers.

[22]  P. Sankaran,et al.  A new compensation scheme for thermistors and its implementation for response linearization over a wide temperature range , 1993 .

[23]  Octavian Postolache,et al.  PDF-Based Progressive Polynomial Calibration Method for Smart Sensors Linearization , 2009, IEEE Transactions on Instrumentation and Measurement.

[24]  Anwar A. Khan.  An Improved Linear Temperature/Voltage Converter Using Thermistor in Logarithmic Network , 1985, IEEE Transactions on Instrumentation and Measurement.

[25]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[26]  O. Postolache,et al.  Fitting transducer characteristics to measured data , 2001 .

[27]  M. Sapoff,et al.  Theory and application of self-heated thermistors , 1963 .

[28]  Dario Petri,et al.  Dynamic Compensation of Nonlinear Sensors by a Learning-From-Examples Approach , 2008, IEEE Transactions on Instrumentation and Measurement.

[29]  D. Patranabis,et al.  A novel software-based transducer linearizer , 1989 .

[30]  M. J. Bowman,et al.  Linearizing the Self-Heated Thermistor Thermometer , 1972 .

[31]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[32]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[33]  J. Elazar,et al.  Thermistor Multivibrator as the Temperature-to-Frequency Converter and as a Bridge for Temperature Measurement , 1977, IEEE Transactions on Instrumentation and Measurement.

[34]  Jiann-Ming Wu,et al.  Multilayer Potts Perceptrons With Levenberg–Marquardt Learning , 2008, IEEE Transactions on Neural Networks.

[35]  S. Natarajan.  A modified linearized thermistor thermometer using an analog multiplier , 1990 .

[36]  S. Dyer,et al.  Cubic-spline interpolation. 1 , 2001 .

[37]  Nicolás J. Medrano-Marqués,et al.  Sensor linearization with neural networks , 2001 .