Nonlinear multivariate statistical process monitoring of a water treatment plant

In this paper, a multivariate statistical process monitoring technique based on bottleneck auto-associative neural network is applied on a water treatment plant. First, the nonlinear principal component analysis (NLPCA) is carried out in order to identify and analyze the relationships among the correlated variables in the process by compressing multidimensional data set, extracting the original data from the principal components and then the squared prediction error is evaluated to find the erroneous data samples. So, the information obtained using this intelligent tool is used for diagnosis. The obtained results on realistic data demonstrate the effectiveness of the applied technique for monitoring water treatment plants.