摘要
为了防止火电厂锅炉消防设计中冷凝器因结垢而引起锅炉的火灾和爆炸事故,需要对冷凝器污垢系数的发展规律进行预测。设计了一种结合K-均值算法和Chebyshev神经网络的污垢系数预测模型,针对Chebyshev神经网络的弊端,应用K-均值算法对其进行改进,将污垢系数随时间发展的曲线分为启动阶段、粘附阶段和老化阶段3类。结果表明,改进Chebyshev神经网络模型有效地预测了冷凝器污垢系数发展规律,得到的输出结果比渐进预测和幂率预测模型的预测结果更准确,该模型具有算法简单、收敛速度快的特点。
In order to prevent the condenser scaling from causing fire and explosion accidents,it is necessary to predict the law of development of fouling factor in the condenser.A fouling factor predicting model combining K-mean algorithm and Chebyshev neural network was designed.Aiming at the disadvantages of Chebyshev neural network,the K-mean algorithm can be used to improve the curve of fouling factor development over time,which can be divided into three stages:starting stage,adhesion stage and aging stage.Results showed that,the modified Chebyshev neural networks can predict the law of development of condenser fouling factor effectively,and is more accuracy than progressive prediction and power-law prediction;the algorithm is simple and has fast convergence speed.
作者
周广宏
任万英
ZHOU Guang-hong;REN Wan-ying(Department of Control Technology,Wuxi Institute of Technology,Jiangsu Wuxi 214121,China;Department of Electrical Engineering,North China University of Water Resources and Electric Power,Henan Zhengzhou 450003,China)
出处
《消防科学与技术》
CAS
北大核心
2020年第10期1465-1468,共4页
Fire Science and Technology
基金
2018年度河北省高等教育教学改革项目“分布式光伏水力发电微电网供能系统的实践研究”(ZZJG-C6047)
关键词
火电厂
消防安全
冷凝器
神经网络
污垢系数
coal power station
fire safety
condenser
neural network
fouling factor
