Helicopter rotor smoothing based on GRNN neural network and genetic algorithm
-
摘要: 针对传统旋翼调整方法没有考虑调整参数与振动信号之间的非线性关系,提出一种结合广义回归神经网络GRNN(General Regression Neural Network)和遗传算法的旋翼调整方法,采用GRNN建立旋翼动平衡调整模型,以桨叶调整参数作为GRNN输入,以旋翼转轴3个方向的加速度测量值和机身3个方向加速度测量值作为网络输出,建立调整参数与直升机振动信号之间的模型.以直升机振动作为目标函数,采用改进的遗传算法对桨叶调整参数进行寻优,获得直升机振动最小时的桨叶的调整量.飞行实验表明,通过1到2次飞行调整,可使3个方向机身振动(旋翼的一阶振动)为最小,完成旋翼的动平衡调整.
-
关键词:
- 旋翼 /
- 动平衡 /
- 广义回归神经网络(GRNN) /
- 遗传算法 /
- 优化
Abstract: Considering traditional adjustment method without calculating possible nonlinear between rotor adjustments and fuselage vibration signals, a new rotor adjustment method based on general regression neural network (GRNN) and genetic algorithm was presented. GRNN network was employed to model the relationship between the rotor adjustments and the fuselage vibrations, whose inputs are rotor adjustment parameters and whose outputs are acceleration measurements along the three axes of rotor shaft and the fuselage. With helicopter vibration as objective function, genetic algorithm was used to make a global optimization to find the suitable rotor adjustments corresponding to the minimum vibrations. Flight test results indicate that proposed rotor adjustment method can minimize fuselage vibration at fundamental rotor frequency along the three axes, only in one or two adjustment flights, and that the neural networks may be updated to include new data thus allowing the system to evolve and mature in the course of its use.-
Key words:
- rotor /
- dynamic balance /
- general regression neural network (GRNN) /
- genetic algorithm /
- optimization
-
[1] Ventres Sam, Hayden Richard E. Rotor tuning using vibration data only American Helicopter Society 56th Forum. America: American Helicopter Society, 2000:623-629 [2] Wroblewski Dariusz, Grabill Paul. Neural network system for helicopter rotor smoothing Intelligent Automation Corporation. America: IEEE, 2000:271-276 [3] Wang Shengda, Danai Kourosh, Wilson Mark. Adaptive method of helicopter track and balance [J]. Journal of Dynamic Systems, Measurement, and Control, 2005, 127(6) :275-282 [4] 薛伟松,邢士喜,郑牧,等. 直升机旋翼锥体及动平衡设备校验系统的研究[J]. 测控技术, 2006,25(3): 4-7 Xue Weisong, Xing Shixi, Zheng Mu, et al. Research on checkout system for track-height and dynamic balance equipment of helicopter [J]. Testing and Control Technology, 2006, 25(3): 4-7(in Chinese) [5] 石喜光,郑立刚,周昊,等. 基于广义回归神经网络与遗传算法的煤灰熔点优化[J]. 浙江大学学报(工学版), 2005,39(8):1189-1192 Shi Xiguang, Zheng Ligang, Zhou Hao, et al. Combining general regression neural network and genetic algorithm to optimize ash fusion temperature [J]. Journal of Zhejiang University, 2005, 39(8):1189-1192(in Chinese) [6] 范辉,李为吉. MATLAB NN 和优化工具箱在设计优化中的应用[J]. 计算机工程与应用, 2006(16):187-189 Fan Hui, Li Weiji. Application of MATLAB neural network and optimization toolbox in design optimization [J]. Computer Engineering and Application, 2006(16):187-189(in Chinese) [7] 雷英杰,张善文,李续武,等. Matlab遗传算法工具箱及应用[M]. 西安:西安电子科技大学出版社,2005:45-61 Lei Yingjie, Zhang Shanwen, Li Xuwu, et al. Matlab genetic algorithm toolbox and application [M]. Xi’an: The Publishing Hause of Xi’an Electronic Science and Technology University, 2005:45-61(in Chinese) -
点击查看大图
计量
- 文章访问数: 2649
- HTML全文浏览量: 50
- PDF下载量: 938
- 被引次数: 0
下载:
