New monitoring technique with an ICA algorithm in the wastewater treatment process

• Published in: Water science and technology 2003-01, Vol.47 (12), p.49-56
• Main Authors: LEE, J.-M, YOO, C.-K, LEE, I. B
• Format: Article
• Language: English
• Subjects: Algorithms; Applied sciences; Benchmarking; Computer simulation; Detection; Environmental Monitoring; Exact sciences and technology; Fault detection; Fault diagnosis; Gaussian distribution; General purification processes; Independent component analysis; Mathematical models; Models, Theoretical; Monitoring; Monitoring methods; Normal distribution; Pollution; Principal components analysis; Variance analysis; Vectors; Waste Disposal, Fluid; Wastewater; Wastewater treatment; Wastewater treatment plants; Wastewaters; Water Purification; Water treatment and pollution
• ISSN: 0273-1223; 1996-9732
• DOI: 10.2166/wst.2003.0627

A new monitoring method using independent component analysis (ICA) is suggested for the wastewater treatment process (WWTP). ICA is an extension of PCA (Principal Component Analysis). While PCA can only impose independence up to the second order (mean and variance) with constraint on the direction vectors to be orthogonal, ICA imposes statistical independence up to more than second order on the individual component and has no orthogonal condition. When the variables have the Gaussian distribution, PCA itself provides a satisfactory result in monitoring performance. However, the measured variables are not often normally distributed. In this case, ICA can provide better monitoring results than PCA since ICA is based on the assumption that the latent variables are not normally distributed. In this paper, the ICA monitoring algorithm with kernel density estimation was applied to fault detection and diagnosis of the wastewater simulation benchmark. ICA with kernel density estimation gives better results than PCA in disturbance detection in spite of severe periodic features of the wastewater plant.