Adaptive consensus principal component analysis for on-line batch process monitoring

As the regulations of effluent quality are increasingly stringent, the on-line monitoring of wastewater treatment processes becomes very important. Multivariate statistical process control such as principal component analysis (PCA) has found wide applications in process fault detection and diagnosis using measurement data. In this work, we propose a consensus PCA algorithm for adaptive wastewater treatment process monitoring. The method overcomes the problem of changing operating conditions by updating the covariance structure recursively. The algorithm does not require any estimation compared to typical multiway PCA models. With this method process disturbances are detected in real time and the responsible measurements are directly identified. The presented methodology is successfully applied to a pilot-scale sequencing batch reactor for wastewater treatment.