Open AccessImproved genetic algorithm applied to model identification of typical thermal process of gas-steam combined cycle unit
Author(s) -
Weichen Ni,
Haoran Li,
Xiaonan Cao,
Changzhi Zhang,
Yi Zhao,
Jian Wang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1629/1/012039
Subject(s) - genetic algorithm , process (computing) , thermal , identification (biology) , thermal power station , algorithm , combined cycle , unit (ring theory) , computer science , engineering , process engineering , mathematical optimization , mathematics , mechanical engineering , machine learning , waste management , physics , botany , mathematics education , turbine , meteorology , biology , operating system
The gas-steam combined cycle unit has high thermal efficiency, low pollution to the natural environment, and high cost performance. It has become the first choice in the sustainable development planning of the power industry, especially for the steel companies. It is of great practical value to establish the mathematical model of the combined cycle unit, especially the thermal process model. However, due to the influence of multi-parameters and non-linear correlation in a typical combined cycle unit, this paper uses an improved genetic algorithm to identify four typical thermal process models. The simulation results show that it is highly consistent with the measured results and is consistent with the traditional genetic algorithm. In contrast, there is also a significant improvement in fitting accuracy, which proves the feasibility and effectiveness of the improved algorithm in this paper in the identification of typical thermal process models of combined units.