基于RBF神经网络的水轮机振源参数识别方法

在对水轮机进行力学建模和分析时,其振动荷载特性往往是未知的,但却是十分重要的.基于径向基函数(RBF)神经网络,提出了水轮机振动荷载参数识别方法.根据在丰满水电站现场观测的水轮机振动响应数据,识别出了水轮机在不同运行状态下的振动荷载参数,其中包括振动力的频率、相位差和幅值.利用人工神经网络具有解决参数识别反问题不适定性的能力,建立了水轮机系统响应与模型参数之间近似的非线性函数关系.现场实际应用结果表明,经过充分训练的神经网络具有较快的收敛能力和较高的预测精度.

Identification procedure of vibrating load parameters of hydraulic generator with RBF neural network

Vibrating dynamic characteristics have been unknown but important in the modeling and mechanical analyses of large hydraulic generators.An identification algorithm for vibrating dynamic characterization by using RBF(radial basis function) artificial neural network is developed for multi-degree of freedom systems.By means of measured dynamic responses of the hydraulic generator at Fengman Hydropower Plant,the indentification algorithm identifies the loading parameters which include the main frequencies,phase differences and amplitudes of vibrating forces.The artificial neural network is used to tackle an ill-posed problem of the parameter identification and to approximate nonlinear function relationship between the vibration responses of the hydraulic generator and model parameters. It is demonstrated that a well-trained artificial neural network reveals an extremely fast convergence and a high degree of accuracy in the parameter identification of hydraulic generator vibration.