Anomaly detection and prediction of sensors faults in a refinery using data mining techniques and fuzzy logic

Scientific Research and Essays Vol. 6(27), pp. 5685-5695, 16 November, 2011
Anomaly detection and prediction of sensors faults in a refinery using data mining techniques and fuzzy logic
Mahmoud Reza Saybani*, Teh Ying Wah, Amineh Amini and Saeed Reza Aghabozorgi Sahaf Yazdi
saybani@gmail.com
saybani@siswa.um.edu.my
Department of Information Science, Faculty of Computer Science and Information Technology, University of Malaya (UM), 50603 Kuala Lumpur, Malaysia
Abstract
Refineries use many sensors to monitor and control the process of refining.  It is critical, therefore, to detect any sensor faults or anomalies as early as possible, and to be able to replace or repair a sensor well in advance of any fault.  Authors present a method for detecting anomalies in a sensor’s data, as well as to predict the next occurance of a sensor failure.
Data mining techniques to detect anomalies in sensor data and predict the occurrence of next faulty event were introduced. Researchers used MATLAB’s fuzzy logic toolbox tools to find clusters.  The MATLAB toolbox uses subtractive fuzzy clustering algorithm and generates a model, a Sugeno-type fuzzy inference system. The same toolbox was used to evaluate the model with promising results.
Free Full Text Source: http://www.academicjournals.org/SRE/PDF/pdf2011/16Nov/Saybani%20et%20al.pdf