摘要
通过对电力工业中广泛应用的通风机性能曲线的曲面、超曲面特性的分析 ,提出应用神经网络进行通风机性能曲线的曲面拟合。并以实验室4- 73№ 8D通风机为研究对象 ,建立了神经网络与机理的组合模型 ,并提出与DCS结合的通风机性能监测及通风系统管网故障诊断模型。
The curved surface and hypersurface characteristic of fans used widely in the power industry is analyzed.On the basis of it,a method using neural network to accomplish the curved surface fit is put forward.After that,the integrated model of neural net and mechanism has been constructed.In the end combining with DCS,the monitoring model of fan performance and the diagnosis model of fan system is put forward. Key word:Centrifugal fan Neural network simulation Diagnosis
出处
《风机技术》
北大核心
2002年第3期29-32,共4页
Chinese Journal of Turbomachinery
