Fault detection of an air quality monitoring network

Concerns for the environment, health and safety are of major importance and have been attracting considerable attention around the globe due to the new environmental challenges that are threatening our planet. In this paper, we propose to enhance the fault detection of an air quality monitoring network (AQMN) by using wavelet principal component analysis (WPCA)-based on generalized likelihood ratio test (GLRT). The presence of measurement noise in the data and model uncertainties degrade the quality of fault detection (FD) techniques by increasing the rate of false alarms. Therefore, the objective of this paper is to enhance the FD of an AQMN by using wavelet representation of data, which is a powerful feature extraction tool to remove the noises from the data. Wavelet data representation has been used to enhance the FD abilities of principal component analysis. Therefore, in the current work, we propose to use WPCA-based on GLRT technique for FD. The fault detection performances of the WPCA-based GLRT technique are shown using air quality monitoring network (AQMN). The results showed the detection efficiency of developed WPCA-based GLRT technique, when compared to classical PCA and WPCA techniques.