摘要
随着电力工业的发展,大型单元制火力发电机组在电网中所占的比例愈来愈大,单元机组控制对象为强耦合,时变,非线性,大滞后的复杂生产过程,当各种扰动作用时导致控制对象的参数不确定,模型难于准确建立,属于复杂难控的大型生产过程。在常规局部控制系统基础上发展起来的协调控制系统是解决这个问题的有效途径。本文先采用一种基于遗传算法和RBF网络相结合的算法建模,结合广义预测控制策略,经过在线滚动优化和反馈校正,实现预测控制。仿真结果表明在系统工况发生变化,参数发生变化,有滞后作用时,均具有很强的鲁棒性。
With the development of power industry,the proportion of Large-scale Generating Unit in power grid is getting bigger and bigger.The control object of the generating unit is a complicated manufacturing process which is strong-coupling,Time-variable,nonlinear and big-lag.It is difficult to establish accurate model when the parameters of control object is uncertainty because of all disturbances,and it is a Complex rambunctious large-scale production process.The efficient way to solve the problem is coordinated control system which is developed based on Conventional local control system.GA-RBF network is used to identify the coordinated control system for establishing a predictive model in Generalized predictive control strategy,achieves predictive control with online rolling optimization and real time feedback revision.The results of the emulation show that it has strong robustness when the load condition changes,the parameter changes or lag affects.
出处
《内蒙古工业大学学报（自然科学版）》
2011年第3期364-370,共7页
Journal of Inner Mongolia University of Technology：Natural Science Edition
基金
国家自然科学基金项目(69964001)
内蒙古自然科学基金重点项目(200408020802)
关键词
遗传算法
RBF神经网络
广义预测控制
单元机组
鲁棒性
Genetic algorithm
RBF neural network
Generalized predictive control
Generating unit
robustness
