ADOPTION OF INTELLIGENT COMPUTATIONAL TECHNIQUES FOR STEAM BOILERS TUBE LEAK TRIP

Abstract

Frequent boiler tube trips in coal fired power plants can increase operating cost significantly. An early detection and diagnosis of boiler trips is essential for continuous safe operations in the plant. Several methodologies for the fault diagnosis in a plant have been developed. However these methodologies are difficult to be implemented. In this study, two artificial intelligent monitoring systems specialized in boiler trips have been proposed. The first intelligent monitoring system represents the use of pure artificial neural network system whereas the second intelligent monitoring system represents merging of genetic algorithms and artificial neural networks as a hybrid intelligent system. In the first system using pure artificial neural network, the trip was predicted 5 minutes before the actual trip occurrence. The hybrid intelligent system was able to optimize the selection of the most influencing variables successfully and predict the trip 2 minutes before the actual trip. The first intelligent system performed better than the second one based on the prediction time. The proposed artificial intelligent system could be adopted on-line as a reliable controller of the thermal power plant boiler.