Application of on-line wavelet decomposition technology in drift detection of gas sensor

In order to improve the sensitivity of drift detection for gas sensors, an on-line wavelet decomposition algorithm (OLMS) is applied. Unlike the traditional wavelet decomposition algorithm, OLMS is adaptively used on line. Applying this algorithm, the sensor signal can be decomposed into multi-scales, which makes the drift features separated sensitively from noises or other events. Moreover, a modified median filtering method is proposed to eliminate the outliers in the collected data successfully. Detailed description of the algorithm is given and its superior performances are illustrated by simulation.