Dynamic measurements with chemical sensor arrays based on inverse modelling

Author

Pardo, A. ; Marco ; Samitier, J.

Author_Institution

Barcelona Univ., Spain

Volume

1

fYear

1996

fDate

1996

Firstpage

570

Abstract

Low cost chemical sensor arrays are gaining interest for the measurement of multicomponent gas mixtures. While usually only static measurements are done, this paper faces the problem of carrying out dynamic measurements when the mixture undergoes changes with the same time-scale than the sensors time-constants. Our approach is to build inverse models which allow the reconstruction of the gases concentrations presented to the sensor array. Different model structures, including linear and non-linear, have been tested

Keywords

Gaussian processes; MIMO systems; arrays; autoregressive processes; feedforward neural nets; gas sensors; inverse problems; modelling; nonlinear dynamical systems; parameter estimation; stochastic processes; ANN; MIMO system; Wiener model; autoregressive with exogeneous inputs; chemical sensor arrays; dynamic measurements; finite impulse response model; identification; inverse modelling; linear model structures; low cost arrays; multicomponent gas mixture measurements; nonlinear model structures; parametric model; quartz microbalance gas sensors; white Gaussian concentrations; Chemical sensors; Costs; Gas detectors; Gases; Inverse problems; Nonlinear control systems; Nonlinear dynamical systems; Sensor arrays; Sensor systems; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation and Measurement Technology Conference, 1996. IMTC-96. Conference Proceedings. Quality Measurements: The Indispensable Bridge between Theory and Reality., IEEE

Conference_Location

Brussels

Print_ISBN

0-7803-3312-8

Type

conf

DOI

10.1109/IMTC.1996.507447

Filename

507447