Detection and Quantification of Multi-Analyte Mixtures Using a Single Sensor and Multi-Stage Data-Weighted RLSE

Abstract

This work reports the development and experimental verification of a sensor signal processing technique for online identification and quantification of aqueous mixtures of benzene, toluene, ethylbenzene, xylenes (BTEX) and 1, 2, 4-trimethylbenzene (TMB) at ppb concentrations using time-dependent frequency responses from a single polymer-coated shear-horizontal surface acoustic wave sensor. Signal processing based on multi-stage exponentially weighted recursive leastsquares estimation (EW-RLSE) is utilized for estimating the concentrations of the analytes in the mixture that are most likely to have produced a given sensor response. The initial stages of EW-RLSE are used to eliminate analyte(s) that are erroneously identified as present in the mixture; the final stage of EW-RLSE with the corresponding sensor response model representing the analyte(s) present in the mixture is used to obtain a more accurate quantification result of the analyte(s). The success of this method in identifying and quantifying analytes in real-time with high accuracy using the response of just a single sensor device demonstrates an effective, simpler, lower-cost alternative to a sensor array that includes the advantage of not requiring a complex training protocol.