Evaluation and Improvement Performance of a Boiler in a Thermal Power Plant Using Artificial Neural Network

Abstract

This research aims to avoid damage in power plant boiler steam generation by using Artificial Neural Network techniques (ANN) to improve the boiler performance. The training and testing using ANN by Back Propagation (BP) algorithm. The inputs to the neural network such factors which include air fuel ratio, water level, flame, gas, pressure and temperature. Control of the optimum input variables represent the output of the neural network. Experimental data is obtained by using an industrial boiler operating at AL-Dura power plant.the method of control by ANN is off – line ,the information of boiler taken from real plant and applied in matlab program for training ANN to taken right decision for control of boiler. ANN results were used in the control of thermal parameters based on the software program Matlab\simulink and showed that the maximum deviation between experimental data is less than 0.01 from the predicted results of the neural network in comparison to the results with modeling of the match at High Rate with actual power plant. It is recommend that Artificial Neural Network techniques (ANN) can be used to predicate and optimization the performance of a power plant and many problem can be solve in engineering applications.

Keywords

• ann (artificial neural network
• boiler model
• power plant
• training
• prediction model