摘要
在双抽汽轮机热电负荷协调控制问题的研究中,输出电负荷、抽汽高压热负荷和低压热负荷之间存在着严重的耦合关系,每个负荷的变化都会对其他负荷产生不同程度的影响,引起热、电负荷的频繁波动,从而影响到整个系统的控制性能.为了解决上述问题,提出了一种将简单的前馈补偿解耦和模糊神经网络相结合的改进多变量解耦控制方案.前馈补偿实现动静态解耦,神经网络实时调整模糊控制规则,从而提高了系统的控制效果和自适应能力.MATLAB仿真结果表明,改进的解耦控制方案解决了热电负荷的强耦合问题,提高了系统的鲁棒性和自适应能力,具有较强的实用价值.
In the research of control of double extraction steam turbine thermal-electric load coordinated,serious coupling relationship exists among the output of power load, pumping the high pressure heat load and low heat load,change of any load will have different degrees of impact on other loads,due to the frequent fluctuation of heat and electricity load,thus af-fecting the control performance of the whole system. In order to solve the above problems, this paper proposed a multi variable decoupling control scheme which combines the feed-for-ward decoupling and simple fuzzy neural network. The system dynamic and static decoupling is achieved through feed-forward compensation. The fuzzy control rules is adjusted in real time by neural network. Consequently, the control effect and adaptive ability of the system are improved. Matlab simulation results show that the improved control method solvest he strong coupling problem of the power load, improves the robustness and adaptability of the system and has great practical value.
作者
李艳
张晓婕
李可可
LI Yan ZHANG Xiaojie LI ke-ke(College of Electrical and Information Engineering, Shaanxi University of Science Technology, Xi’an 710021, China Shaanxi Resarch Institute of Agricultural Products Processing Technology, Xi’an 710021, China)
出处
《陕西科技大学学报（自然科学版）》
2017年第1期158-165,共8页
Journal of Shaanxi University of Science & Technology
基金
陕西省科技厅科学技术研究发展计划项目(2013K07-28)
陕西省教育厅专项科研计划项目(14JK1094)
关键词
汽轮机
热电负荷耦合
数学模型
前馈补偿
模糊神经网络
turbine
thermoelectric coupling load
mathematical model
feed-forward com-pensation
fuzzy neural network
