Open AccessModelling and Optimization of Boiler Steam Temperature System Based on Neural Network and Genetic Algorithms
Author(s) -
Kailiang Zhang,
Fengping Li,
Yi Chen,
Liang Huang
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/772/1/012042
Subject(s) - superheater , boiler (water heating) , superheated steam , artificial neural network , baffle , flue gas , heat recovery steam generator , genetic algorithm , steam electric power station , engineering , process engineering , control theory (sociology) , algorithm , thermal power station , computer science , mechanical engineering , mathematical optimization , mathematics , waste management , combined cycle , artificial intelligence , control (management) , turbine
The combination of neural network and genetic algorithm not only can improve the operating efficiency and economy of the boiler, but also give the recommended values of the operating parameters for the boiler operation. Based on the field data from power plant, the errors of the 3 and 4-layer neural network were compared according to the data experiments. The 4-layer neural network was used to model the steam temperature system. Taking the standard heat consumption as the target value, the adjustable and non-adjustable quantities of the input parameters of the steam temperature system are determined, and the genetic algorithm is used for optimization. The results show that the standard heat consumptions of all the 100 groups of working conditions are reduced. The maximum reduction of heat consumption is 186.88 kJ/(kW·h), and the average reduction is 153.93 kJ/(kW·h). This indicates that the combination of neural network and genetic algorithm can optimize the boiler steam temperature system by optimizing parameters such as superheater de-superheating water flow, superheater flue gas baffle opening and reheater flue gas baffle opening, which provides guidance for actual production.