Multiobjective optimization of three-shaft gas turbine based on intelligent algorithm and surrogate model

Three-shaft gas turbines are widely employed in power equipment drives and power generation. To address the development needs for high efficiency and low emissions in three-shaft gas turbines, a framework for multi-objective performance optimization of three-shaft gas turbines is proposed. First, a surrogate model of three-shaft gas turbine is built for optimization. Then, based on this model, a mathematical model of the multi-objective optimization problem is established, with the high- and low-pressure compressor guide vane angles as optimization variables. Finally, the multiobjective Grey Wolf Optimization (MOGWO) approach is used to address the issue. Experimental studies are conducted under full- and part-load conditions. Optimization results illustrate that the proposed approach can reduce fuel consumption by 1.01% and nitrogen oxide emissions by 2.03 ppm. Compared with optimization based on nonlinear models, the optimization efficiency is doubled. Compared with MOPSO, MOGWO shows superior global optimization ability and efficiency.