摘要
提出了一种带模糊补偿的神经网络辨识器,并应用在某型涡扇发动机转速控制系统中。一个动态神经网络用于被控装置的在线辨识,然后根据被控装置的输出和参考模型的响应迭代出控制信号,具有4条简单规则的模糊逻辑块用于提高整个系统的闭环特性。试验结果显示,对比传统的机械-液压式控制器和模拟式电子控制器,提出的控制策略具有更好的瞬变特性及抗干扰特性,同时提高了系统的过渡过程品质,保证了航空发动机对高性能指标和高控制精度的要求。
A new neural network algorithm with fuzzy logic compensation was proposed and applied to an aero-engine rotating speed control system. A dynamic neural network was used to identify the plant on-line. The control signal was then calculated iteratively according to the responses of a reference model and the output of identified plant. A fuzzy logic block with four very Simple rules was added to the loop to improve the overall loop properties. Experimental results demonstrate that the proposed control strategy provides better disturbance reiection and transient properties than those achieved by conventional mechanical-hydraulic controller and Analogue Engine Electronic Controller （AEEC）. At the same time,it can improve transient quality in control system, and meet the requirements of high performance guideline and high control accuracy in turbofan engine.
出处
《航空动力学报》
EI
CAS
CSCD
北大核心
2006年第1期213-218,共6页
Journal of Aerospace Power
基金
国家自然科学基金资助项目(50276070)
关键词
航空、航天推进系统
航空发动机
神经网络辨识器
数字式电子控制器
超维学习
模糊逻辑补偿
aerospace propulsion system
aero-engine
neural network identifier
digital engine electronic controller
trans-dimensional learning
fuzzy logic compensation
作者简介
钱坤（1977-），男，湖南常德人，空军工程大学工程学院博士生，讲师，主要从事推进系统控制与状态监控的研究．
