Statistical Monitoring of Wastewater Treatment Plants Using Variational Bayesian PCA

Abstract

Multivariate statistical projection methods such as principal component analysis (PCA) are the most common strategy for process monitoring in wastewater treatment plants (WWTPs). Such monitoring strategies can indeed recognize faults and achieve better control performance for fully observed data sets but can be more difficult in the case of having missing data. This study presents a variational Bayesian PCA (VBPCA) based methodology for fault detection in the WWTPs. This methodology not only is robust against missing data but also reconstructs missing data. Furthermore, a novel historical data preprocess method is proposed to deal with diurnal behaviors in the WWTPs with fast sample rate. These methodologies have been validated by process data collected from two WWTPs with different process characteristics and different sample rates. The results showed that the proposed methodology is capable of detecting sensor faults and process faults with good accuracy under different scenarios (highly and lowly instrumented WWTP).

Development of a Novel Adaptive Soft-Sensor Using Variational Bayesian PLS with Accounting for Online Identification of Key Variables

“…VB method is, in fact, a way to approximate a posterior distribution which has a highly complex form for which expectations are not analytically tractable. 28,29 In this paper, the computation of latent variables together with all other parameters are treated as posterior calculation and identified by VB. Also, due to employing VB for parameter identification, the risk of overfitting is capable of being reduced.…”

Multimode complex process monitoring using double‐level local information based local outlier factor method

“…During the last decades, industrial process monitoring approaches have developed rapidly to fit the increasingly urgent demands of ensuring processes safety and improving product quality . Due to the extensive applications of distributed control systems and sensor networks in modern industrial processes, a huge amount of process data are available and data‐driven process monitoring is attracting more and more research interests.…”

Multi‐block principal component analysis based on variable weight information and its application to multivariate process monitoring

“…To handle multiscale characteristics of industrial data, multiscale PCA was implemented by Lau et al by combining wavelet analysis. Other extended PCA methods can be seen in the related work …”

“…Other extended PCA methods can be seen in the related work. [13][14][15][16][17] All these aforementioned PCA methods develop one global statistical model, which means all measured variables are considered as a whole. However, many faults only affect a few variables but not all variables, especially in the large-scale process.…”