基于FOA-LSSVM的汽轮机热耗率预测模型研究

发布时间：2018-05-09 15:56

本文选题：果蝇优化算法 + 最小二乘支持向量机　；参考：《热力发电》2017年05期

【摘要】：为了准确描述可控参数与热耗率之间的关系,采用偏相关分析法,结合汽轮机热耗率方程确定了影响汽轮机热耗率的5个主要变量,并将其作为模型的输入参数;通过比较分析,选用RBF_kernel为模型的核函数;利用果蝇优化算法(FOA)对最小二乘支持向量机(LSSVM)的惩罚因子和核径向范围2个参数进行优化,建立了FOA-LSSVM黑箱模型;以FOA-LSSVM为基础,建立了预测汽轮机热耗率的数学模型,并将其与采用LSSVM、RBF神经网络建立的热耗率预测模型进行对比,同时分析了该模型的鲁棒性。结果表明,基于FOA-LSSVM的汽轮机热耗率预测模型具有精度高、泛化能力强、鲁棒性强的优点。该模型为机组热经济性诊断、参数寻优提供了理论依据,具有一定的工程应用价值。
[Abstract]:In order to accurately describe the relationship between the controllable parameters and the heat consumption rate, the partial correlation analysis method and the heat consumption rate equation of the steam turbine are used to determine the five main variables that affect the heat consumption rate of the steam turbine, which are taken as the input parameters of the model. Through comparative analysis, RBF_kernel is chosen as kernel function of the model, and the penalty factor and kernel radial range of LSSVM are optimized by using Drosophila Optimization algorithm. The FOA-LSSVM black box model is established based on FOA-LSSVM. A mathematical model for predicting heat consumption rate of steam turbine is established and compared with the prediction model based on LSSVMU RBF neural network. The robustness of the model is analyzed at the same time. The results show that the prediction model of steam turbine heat consumption based on FOA-LSSVM has the advantages of high accuracy, strong generalization ability and strong robustness. The model provides a theoretical basis for the thermal economic diagnosis and parameter optimization of the unit, and has a certain engineering application value.
【作者单位】：华北电力大学能源动力与机械工程学院;
【基金】：北京市自然科学基金项目(3132028) 中央高校基本科研业务费专项资金资助项目(12NQ40)~~
【分类号】：TK261;TP18

【相似文献】