Nonlinear inverse dynamic models of gas sensing systems based on chemical sensor arrays for quantitative measurements

Gas sensing systems based on low-cost chemical sensor arrays are gaining interest for the analysis of multicomponent gas mixtures. These sensors show different problems, e.g., nonlinearities and slow time-response, which can be partially solved by digital signal processing. Our approach is based on building a nonlinear inverse dynamic system. Results for different identification techniques, including artificial neural networks and Wiener series, are compared in terms of measurement accuracy.

[1]  Wojtek J. Bock,et al.  Neural processing-type fiber-optic strain sensor , 1992 .

[2]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[3]  Ingemar Lundström,et al.  Artificial neural networks and gas sensor arrays: quantification of individual components in a gas mixture , 1991 .

[4]  Hanns-Erik Endres,et al.  Signal Evaluation of Gas Sensors with Artificial Neural Nets , 1997 .

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

[6]  Julian W. Gardner,et al.  Sensors and Sensory Systems for an Electronic Nose , 1992 .

[7]  Udo Weimar,et al.  Polymer-based sensor arrays and multicomponent analysis for the detection of hazardous oragnic vapours in the environment , 1995 .

[8]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[9]  R. Haber,et al.  Parametric identification of nonlinear dynamic systems based on nonlinear crosscorrelation functions , 1988 .

[10]  Philippe Breuil,et al.  Application of Multivariate Analysis to Gas Detection with Semiconductor Sensors , 1997 .

[11]  K. Cammann.  Continuous pollution control by chemical sensors , 1992 .

[12]  Wolfgang Göpel,et al.  SnO2 sensors: current status and future prospects☆ , 1995 .

[13]  Corrado Di Natale,et al.  Redundancy in sensor arrays , 1993 .

[14]  S. A. Billings,et al.  Introduction to Nonlinear Systems Analysis and Identification , 1985 .

[15]  Ingemar Lundström,et al.  Identification of paper quality using a hybrid electronic nose , 1995 .

[16]  R. D. Figueiredo.  The Volterra and Wiener theories of nonlinear systems , 1982 .

[17]  Fabrizio Davide,et al.  Dynamic calibration of QMB polymer-coated sensors by Wiener kernel estimation , 1995 .

[18]  S.M. Riad,et al.  The deconvolution problem: An overview , 1986, Proceedings of the IEEE.

[19]  Pierre Cardaliaguet,et al.  Approximation of a function and its derivative with a neural network , 1992, Neural Networks.

[20]  Y. W. Lee,et al.  Measurement of the Wiener Kernels of a Non-linear System by Cross-correlation† , 1965 .

[21]  R. Müller.  High electronic selectivity obtainable with nonselective chemosensors , 1991 .

[22]  Fabrizio Davide,et al.  Different strategies for the identification of gas sensing systems , 1996 .

[23]  K. Naka,et al.  Identification of multi-input biological systems. , 1974, IEEE transactions on bio-medical engineering.