Free knot recursive B-spline for compensation of nonlinear smart sensors

Abstract Compensation of nonlinear smart sensors is an important topic that must always be considered to assure the accuracy of measurement systems. Nowadays, with the advent of microprocessor devices in smart sensors, advanced compensation algorithms can be implemented to improve the accuracy of measurement. In this paper, an inverse modeling methodology based on B-spline is proposed for the compensation of nonlinear smart sensors. To avoid complicated least squares solution of the B-spline, a training algorithm in a recursive form is proposed to reduce the training cost and make the on-chip training of B-spline available. Moreover, the choices of B-spline knots and training points are important designed parameters in this methodology. So the free knot insertion algorithm and training points’ selection method are used prior to the training process to improve the accuracy of the inverse models and avoid the under and over fitting. Simulations and results are presented to validate the theoretical expectations.

[1]  Carl de Boor,et al.  A Practical Guide to Splines , 1978, Applied Mathematical Sciences.

[2]  Hakim Baha,et al.  A Novel Neural Network-Based Technique for Smart Gas Sensors Operating in a Dynamic Environment , 2009, Sensors.

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

[4]  Sergey Y. Yurish.  Smart Sensors Systems Design: New curricula based on Marie Curie Chairs Excellence (EXC) project’s results , 2010 .

[5]  J.H. Huijsing,et al.  Low-Cost Calibration Techniques for Smart Temperature Sensors , 2010, IEEE Sensors Journal.

[6]  Patrizia Ciarlini,et al.  Free-knot cubic spline modelling in cryogenic thermometer calibration , 2006 .

[7]  D. Petri,et al.  A Resource-Constrained Sensor Dynamic Compensation Using a Learning-from-Examples Approach , 2007, 2007 IEEE Instrumentation & Measurement Technology Conference IMTC 2007.

[8]  Randy Frank.  Understanding Smart Sensors , 1995 .

[9]  Wang Jian.  New signal processing method for thermocouple based on RBF neural network , 2007 .

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

[11]  K. Draxler,et al.  Fusion of smart sensor standards and sensors with self-validating abilities , 2008, 2008 IEEE/AIAA 27th Digital Avionics Systems Conference.

[12]  Gábor Renner,et al.  Exact and approximate computation of B-spline curves on surfaces , 2004, Comput. Aided Des..

[13]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[14]  Jinwei Sun,et al.  Signal processing method with cold junction compensation for thermocouple , 2009, 2009 IEEE Instrumentation and Measurement Technology Conference.

[15]  O.A. Postolache,et al.  Smart Sensors Network for Air Quality Monitoring Applications , 2005, IEEE Transactions on Instrumentation and Measurement.

[16]  Octavian Postolache,et al.  Smart Sensor Network for Air Quality Monitoring Applications , 2009, 2005 IEEE Instrumentationand Measurement Technology Conference Proceedings.

[17]  Pietro Valdastri,et al.  Smart optical CMOS sensor for endoluminal applications , 2010 .

[18]  Shakeb A Khan,et al.  Sensor calibration and compensation using artificial neural network. , 2003, ISA transactions.

[19]  Jagdish Chandra Patra,et al.  A novel neural network-based linearization and auto-compensation technique for sensors , 2006, 2006 IEEE International Symposium on Circuits and Systems.