Monitoring of Wastewater Treatment Process Based on Slow Feature Analysis Variational Autoencoder

The wastewater treatment process (WWTP) is a complex nonlinear, uncertain and dynamic physical and biochemical reaction process. The non-linearity, uncertainty and dynamicity of the WWTP increase the difficulty of extracting data features, and also make it difficult to monitor the faults in this process. Aiming at the problems of non-linearity, uncertainty and dynamicity, a slow feature variational autoencoder (SFAVAE) process monitoring model is proposed. With the dynamicity of WWTP data taken into account, the slow feature analysis algorithm (SFA) is used to extract the slowly changing dynamic features of wastewater data. The variational autoencoder can impose Gaussian distribution restrictions on its hidden layer features, so that it can simultaneously learn nonlinear and certain features that obey the Gaussian distribution to deal with the nonlinearity and uncertainty of data. Finally, the hidden layer space of the variational autoencoder model is used to construct hidden layer feature statistics Z2 to realize process monitoring. Compared with the principal component analysis (PCA), independent component analysis (ICA), kernel principal analysis (KPCA) and variational auto-encoder (VAE) models, the experimental results of the benchmark simulation model 1 (BSM1) model show that the SFAVAE model has higher effectiveness in process monitoring.