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，本文提出对火力发电厂轴流风机的性能在线监测方法，可及时预警风机喘振故障，从而提高电厂的经济性和安全性。首先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，为提高模型的精确度，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。基于风机静态性能模型，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。结果表明，该方法能实现了风机实际工况下流量等其他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 of axial flow fans in thermal power plants is proposed to warn the surge fault of fan timely and enhance the economy and safety of the power plant. Based on analysis of the characteristics about the static performance curves for axial flow fan under design conditions, the static performance model of fan is established with a method of radial basis function (RBF) neural network. To improve the accuracy of the model, 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. Combined with the static performance model, measured parameters, and similarity laws of fan, The dynamic performance model was built, then the surge warning model of the fan was formulated. Finally，the visual online monitoring platform of fan was developed. The results show that the method can real-timely monitor working point status and performance parameters such as flow of fan under different conditions online．

内蒙古自治区科技重大专项项目