论文部分内容阅读
传统的直升机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,针对这一缺点,提出将广义回归神经网络(GRNN,General Regression Neural Network)和粒子群算法相结合的旋翼调整方法,采用GRNN网络建立旋翼动平衡调整模型,以桨叶的调整参数作为神经网络的输入,以旋翼转轴和机身的三向的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间的模型.以直升机振动作为目标函数,采用粒子群优化算法对桨叶的调整参数进行寻优,获得当直升机振动最小时的桨叶的调整量.飞行实验结果表明,此方法可通过飞行测试获得的新数据对神经网络进行更新,使系统在使用过程中不断完善,并可在较少的飞行调整下完成旋翼的动平衡调整.
The traditional helicopter rotor adjustment method does not consider the nonlinear relationship between the adjustment parameters and the vibration signal. In view of this shortcomings, this paper proposes a rotor adjustment method combining GRNN and particle swarm optimization, The model of rotor balance adjustment is established by using GRNN network. The parameters of blade are used as the input of neural network. The three-axis acceleration measurement of rotor shaft and fuselage is taken as the network output. The model is established between the adjustment parameters and the helicopter vibration signal. Taking helicopter vibration as objective function, particle swarm optimization (PSO) algorithm is used to optimize the parameters of the blade to obtain the blade adjustment when the helicopter vibration is the minimum.The experimental results show that this method can be used to obtain new data from flight test The neural network is updated so that the system can be continuously improved in use and the rotor balance can be adjusted with fewer flight adjustments.