摘要
针对热力系统中的执行机构的结构特性,分析了热力系统执行机构的解析冗余,首次提出了在确定准静态子系统的基础上,利用RBF神经元网络构造控制器输出估计器,实现执行机构本身和其反馈传感器的故障诊断。本故障诊断方案已经应用在开原热电厂130 t/h煤粉炉的控制系统中,通过现场试验,证明本方法是有效的。
Considering the structure feature of operators in thermal system, the analytical redundancy of operators in thermal system is analyzed, and a new method to resolve the fault diagnosis of operators and their feedback sensors is proposed. A state observer is constructed by using RBF neural network to estimate the output of the controller after the quasi-static subsystem is selected. The technique has been applied in the boiler control system of Kaiyuan Power Plant.
出处
《电站系统工程》
北大核心
2003年第1期58-60,共3页
Power System Engineering
基金
国家经贸委最佳节能项目(case study 30)
