基于差分狼群算法优化SVM的主蒸汽流量测量  

Optimization of SVM for Main Steam Flow Measurement Based on Differential Wolf Pack Algorithm

作　　者：杜志祥 李杨 殷黄慧 毕小龙[1] 葛晓霞[1] Du Zhixiang;Li Yang;Yin Huanghui;Bi Xiaolong;Ge Xiaoxia(School of Energy and Power Engineering,Nanjing Institute of Technology,Nanjing 211167,Jiangsu,China)

机构地区：[1]南京工程学院能源与动力工程学院,江苏南京211167

出　　处：《电站辅机》2023年第2期5-9,共5页Power Station Auxiliary Equipment

基　　金：南京工程学院大学生科技创新基金项目(202203003)。

摘　　要：针对电厂中主蒸汽流量现有测量方法的不足,提出了基于差分进化狼群算法(DEWPA)进行主蒸汽流量测量的方法。首先,根据平均影响值的分配方法选取合适的主蒸汽流量影响因素,然后,采用差分进化狼群算法优化支持向量机模型参数,即在原始狼群算法的基础上,运用差分进化算法进行更新。仿真结果表面,差分进化狼群算法(DEWPA)预测模型的均方误差比粒子群算法(PSO)、遗传算法(GAO)更小,具有更高的预测精度。基于差分进化狼群算法优化SVM的算法为主蒸汽流量预测提供了一种新的方法。In response to the inadequacies of current methods for measuring primary steam flow in power plants,it proposed a method based on differential evolution wolf pack algorithm(DEWPA).Firstly,appropriate primary steam flow influencing factors are selected according to the allocation method of average influence value.Then,the parameters of the support vector machine model are optimized using DEWPA,which updates the original wolf pack algorithm with the differential evolution algorithm.Simulation results show that the DEWPA prediction model has a smaller mean square error than particle swarm optimization(PSO)and genetic algorithm optimization(GAO),indicating higher prediction accuracy.The DEWPA-optimized SVM algorithm provides a new method for predicting primary steam flow.

关 键 词：主蒸汽流量 支持向量机 差分进化狼群算法 预测模型 

分 类 号：TK313[动力工程及工程热物理—热能工程]