Fault Detection in the Activated Sludge Process using the Kohonen Self-Organising Map

This paper addresses the detection of faulty situations that develop in activated sludge wastewater treatment plants (ASWWTP). The Kohonen Self-Organising map (KSOM) has been utilised to detect and track changes in different parameters for real data collected from the Seafield wastewater treatment plant, Edinburgh, UK. The results demonstrate that this method is simple, computationally efficient and provides useful information for the process engineer who is faced with improving the performance of the WWTP.

[1]  Monique Polit,et al.  KSOM and MLP neural networks for on-line estimating the efficiency of an activated sludge process , 2006 .

[2]  Miklas Scholz,et al.  Applying Kohonen Self‐Organizing Map as a Software Sensor to Predict Biochemical Oxygen Demand , 2008, Water environment research : a research publication of the Water Environment Federation.

[3]  Esa Alhoniemi,et al.  SOM Toolbox for Matlab 5 , 2000 .

[4]  Rabee Rustum,et al.  Modelling activated sludge wastewater treatment plants using artificial intelligence techniques (fuzzy logic and neural networks) , 2009 .

[5]  Adebayo Adeloye,et al.  Replacing outliers and missing values from activated sludge data using kohonen self-organizing map , 2007 .

[6]  Thomas Maere,et al.  Dynamic modelling of solids in a full-scale activated sludge plant preceded by CEPT as a preliminary step for micropollutant removal modelling , 2016, Bioprocess and Biosystems Engineering.

[7]  Kang Song,et al.  Fault diagnosis and prognosis of wastewater processes with incomplete data by the auto-associative neural networks and ARMA model , 2017 .

[8]  T. L. Liu,et al.  Fault diagnosis based on PCA for sensors of laboratorial wastewater treatment process , 2013 .

[9]  Mika Liukkonen,et al.  Advanced monitoring platform for industrial wastewater treatment: Multivariable approach using the self-organizing map , 2013, Environ. Model. Softw..

[10]  Wei Sun,et al.  PCA and PLS monitoring approaches for fault detection of wastewater treatment process , 2016, 2016 IEEE 25th International Symposium on Industrial Electronics (ISIE).

[11]  Bengt Carlsson,et al.  Gaussian process regression for monitoring and fault detection of wastewater treatment processes. , 2017, Water science and technology : a journal of the International Association on Water Pollution Research.

[12]  K. Das,et al.  Process simulation and modeling: Anaerobic digestion of complex organic matter , 2016 .