Abstract
Annotation – The article discusses the issues of increasing the efficiency of the combustion of liquid fuel in the furnaces of ship steam boilers using the proposed neural network system for automatic correction of the excess air coefficient. It is indicated that modern systems for automatic flame detection have a number of disadvantages, in particular, low sensitivity to extraneous illumination, etc. hot air or flue gases on the walls of the boiler furnace. Such pulsations reduce the reliability of the combustion monitoring and control system. Therefore, the task of developing and introducing on ships new, economically inexpensive and effective methods of effective control and management of the fuel combustion process in ship boilers using modern means of intelligent control is urgent. On the basis of the experiments carried out on a Mitsubishi MV 50 marine steam boiler and the collected experimental data, the values for training the neural network system of the air flow correction process, taking into account the color of the burner flame and the color of the flue gases, were obtained. The use of a trained neural network in the control system, taking into account the fuzzy expert system for monitoring the color of the flame and smoke, makes it possible to achieve the best excess air ratio depending on the steam load of the SEP units. Simulation modeling of the proposed neural system was carried out in a specialized program Matlab (Neural Networks Toolbox). The simulation results showed that the use of a neural network control system for the combustion of liquid fuel, using the example of a marine boiler, allows maintaining a given thermal regime over the entire range of steam load of the power plant units, and also allows timely correction of the excess air ratio, i.e. avoid excessive consumption of fuel.
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call