Data Driven Multivariate Technique for Fault Detection of Waste Water Treatment Plant
Subhransu Padhee1, Nitesh Gupta2, Gagandeep Kaur3
1Subhransu Padhee, Department of Electrical and Instrumentation Engineering, Thapar University, Patiala, India.
2Nitesh Gupta, Department of Electrical and Instrumentation Engineering, Thapar University, Patiala, India.
3Gagandeep Kaur, Department of Electrical and Instrumentation Engineering, Thapar University, Patiala, India.
Manuscript received on March 01, 2012. | Revised Manuscript received on March 25, 2012. | Manuscript published on April 30, 2012. | PP: 45-50 | Volume-1 Issue-4, April 2012 | Retrieval Number: D0246031412/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Collection of raw data from different sensors, processing the data and extracting information from it is a very challenging task. Because of the enhanced memory capacity of the present day computers, data logging has reached to a new level. The analyst has to classify the data according to their traits from the offline logged data. The whole task of collection of raw data, classification of data according to their traits involves different statistical as well as soft computational techniques. This research paper takes a case study of waste water treatment plant and using different data driven multivariate statistical techniques and soft computational techniques determine the faults in the system. This paper uses principal component analysis and backpropagation algorithm to classify the data and detect the faults in a waste water treatment plant.
Keywords: Backpropagation, multivariate statistical technique, principal component analysis.