摘要
针对火电机组灵活性运行下出现的电站辅机长期严重偏离设计工况运行的问题,提出对火力发电厂轴流风机的性能在线监测方法。该方法分析了轴流风机的设计工况静态性能曲线,采用径向基函数(Radial Basis Function,RBF)神经网络建立了风机静态性能模型,利用改进的粒子群算法(Improved Particle Swarm Optimization,IPSO)对RBF神经网络的隐含层基函数中心、宽度及隐含层与输出层之间的连接权值进行优化。仿真结果表明:该模型在训练集上的拟合优度为0.9994,均方根误差为0.0063,与BPSO-RBF算法、传统RBF算法和BP算法建立的模型相比,其拟合优度更接近1,均方误差更小,证明其有效性。基于上述风机静态性能模型,根据风机实测参数和风机相似定律,搭建了风机动态性能模型,并在此基础上建立风机喘振预警模型,开发了轴流风机性能可视化在线监测平台。实例证明,该方法实现了风机实际工况下流量等性能参数和工作点状态的实时监测。
To solve the problem of long-term serious deviation from design operating conditions of auxiliary equipment in power plants under the flexible operation of thermal power units,an online monitoring method for axial flow fan performance in thermal power plants was proposed.The static performance curves for axial flow fan under design conditions were analyzed,the static performance model of fan was established by a method of radial basis function(RBF)neural network,and an improved particle swarm optimization(IPSO)algorithm was used to optimize the center and width of the hidden layer basis function of the RBF neural network,as well as the connection weights between the hidden layer and the output layer.The simulation results show that the goodness of fit of the model on the training set is 0.9994,and the root mean square error(RMSE)is 0.0063.Compared with models established by BPSO-RBF algorithm,traditional RBF algorithm and BP algorithm,its goodness of fit is closer to 1,and the RMSE is smaller,proving its effectiveness.Combined with the above static performance model,measured parameters and similarity laws of fan,the dynamic performance model is built,then the surge warning model of the fan is formulated.The visual online monitoring platform of fan is developed.The experiment proves that the method can real-timely monitor the working point status and performance parameters such as flow of fan under actual working conditions.
作者
汤婧婧
牛玉广
陈玥
杜鸣
TANG Jingjing;NIU Yuguang;CHEN Yue;DU Ming(School of Control and Computer Engineering,North China University of Electric Power,Beijing,China,Post Code:102206)
出处
《热能动力工程》
CAS
CSCD
北大核心
2024年第8期174-182,共9页
Journal of Engineering for Thermal Energy and Power
基金
内蒙古自治区科技重大专项项目(2021ZD0026)。
