Model Identification of Gas-Steam Combined Cycle Unit Load System Based on ISCSO Algorithm
XU Xiaowen
KANG Yingwei
Abstract：Establishing an accurate mathematical model of the load object for a gas-steam combined cycle unit is a crucial prerequisite for improving the performance of its load control system.To address the limitations of traditional identification methods in terms of accuracy and convergence speed,this paper proposes a model identification approach based on an improved sand cat swarm optimization(ISCSO)algorithm.First,the initial population is enhanced using Logistic chaotic mapping.The sensitivity parameter is modified from linear to cosine-based variation.Additionally,a differential evolution mutation mechanism and Gaussian perturbation method are introduced to improve optimization efficiency and effectively avoid local optima.Then,the ISCSO algorithm is employed to optimize the model parameters and obtain their optimal values.Finally,model identification results from the ISCSO and SCSO algorithms are compared and validated using data obtained from an open-loop step experiment at the 312.06 MW load point of the gas-steam combined cycle unit.The effectiveness of the improvement strategies in the algorithm is validated through ablation experiments.The results demonstrate that the proposed algorithm establishes a more accurate load model compared to benchmark algorithms.The ISCSO-identified model achieves the lowest mean absolute percentage error(MAPE)and root mean square error(RMSE),exhibiting superior convergence performance.This work provides a new methodology for model identification.
Keywords：gas-steam combined cycle unitload objectmodel identificationimproved sand cat swarm optimization algorithm
Publication Date：2025-12-25
Online Publishing Date：2026-01-05(First online date of this platform, not the publication date of the document)
Pages：10( 49-58 )