Artificial neural network approach for fault detection in LPG transfer system

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. Generally the LPG 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. This paper deals with the design and development of artificial neural network based model for the fault detection in LPG Transfer system. The model is used to predict the occurrence of various faults in the critical sections of the LPG bottling plant. The training and testing data required to develop the neural model were collected from the records maintained by the operator and through off line simulation. The performance of the trained network is found to be satisfactory for the real time fault diagnosis.