Open AccessMulti-objective optimization on supercritical CO2 recompression brayton cycle using Kriging surrogate model
Author(s) -
Lei Sun,
Chongyu Wang,
Di Zhang
Publication year - 2017
Publication title -
thermal science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.339
H-Index - 43
eISSN - 2334-7163
pISSN - 0354-9836
DOI - 10.2298/tsci17s1309s
Subject(s) - brayton cycle , supercritical fluid , kriging , process (computing) , computer science , genetic algorithm , selection (genetic algorithm) , process engineering , sample (material) , surrogate model , mathematical optimization , environmental science , mathematics , thermodynamics , mechanical engineering , heat exchanger , engineering , physics , operating system , machine learning , artificial intelligence
Supercritical CO2 cycle has become one of the most popular research fields of thermal science. The selection of operation parameters on thermodynamic cycle process is an important task. The computational model of supercritical CO2 recompression cycle is built to solve the multi-objective problem in this paper. Then, the optimization of parameters is performed based on genetic algorithm. Several Kriging models are also used to reduce the quantity of samples. According to the calculation, the influence of sample quantity on the result and the time cost is obtained. The results show that it is required to improve the heat transfer when improvement of the cycle efficiency is desired.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom