论文部分内容阅读
针对热耗率与其影响因素之间存在的复杂非线性关系,提出了基于自适应混沌反学习万有引力算法(ACOGSA)和最小二乘支持向量机(LSSVM)的汽轮机热耗率反向建模方法.利用某600 MW超临界汽轮机组运行数据,采用基于LSSVM的反向建模方法建立热耗率预测模型,采用ACOGSA算法解决LSSVM的模型参数优化问题,并与GSA-LSSVM模型和BP神经网络模型的预测结果进行比较.结果表明:所建立的模型比传统模型具有更好的泛化能力,更能准确地预测汽轮机的热耗率.
Aiming at the complex nonlinear relationship between heat rate and its influencing factors, a reverse modeling method of steam turbine heat rate based on ACOGSA and LSSVM is proposed. Based on the operation data of a 600 MW supercritical steam turbine unit, the LSSVM-based reverse modeling method was used to establish the heat rate prediction model. The ACOGSA algorithm was used to solve the model parameter optimization problem of LSSVM. The model was compared with the GSA-LSSVM model and the BP neural network model The results show that the established model has a better generalization ability than the traditional model and can predict the heat rate of steam turbine more accurately.