Citation

Rajakarunakaran S, Devaraj D, Venkat Ratnam GS, Surya Prakasa Rao K. Int. J. Indust. Eng. 2006; 13(3): 292-298.

Affiliation

A.K College of Engineering, Virudhungar Dist., Tamil Nadu, India

Copyright

(Copyright © 2006, University of Cincinnati)

DOI

unavailable

PMID

unavailable

Abstract

The activities related to bottling of Liquefied Petroleum Gas (LPG) pose lot of risk for the people working in the plant and in the surrounding area. Early detection of equipment failure and excursions of variables outside their acceptable bounds is of paramount importance for the safe operation of the plant. Generally, the plant operators are assigned the job of monitoring and diagnosis of the plant for the safe operation of the plant. The operator may require monitoring a number of variables for identification of normal and abnormal condition. Since a human operator cannot monitor all variables simultaneously, an automated approach is needed for the real time monitoring and diagnosis of the plant. This paper presents the development of fuzzy logic based model for the real time condition monitoring of certain critical sections of the LPG bottling plant. The developed model is tested for a total of thirty seven faults in the LPG transfer system. The performance of the developed model is compared with the traditional approaches for fault diagnosis. Significance: LPG bottling is one of the critical plants which require a number of safety related issues to be addressed. Generally the plants are designed to operate safely under normal conditions; however improper operation can lead to equipment failure and release of potentially hazardous materials. This necessitates continuous monitoring of various parameters of the plant on real time basis. Because of the ability of the fuzzy logic to incorporate uncertainty and heuristic knowledge of the operation it is more suitable for fault diagnosis in LPG transfer system.

Language: en