Parameter Identification of Vibration Loads of Hydro Generator Using Neural Networks

Vibrating dynamic characteristics have been a major unknown in the modeling and mechanical analysis of large hydro generators. An identification algorithm for vibrating dynamic characterization by using artificial neural network is developed for multi-degree-offreedom systems. By making use of measured dynamic responses of the hydro generator at Fengman Hydropower Plant, the estimation algorithm identifies the loading parameters which include the main frequencies and amplitudes of vibrating forces. The artificial neural network is used to tackle an illposed problem of the parameter identification. Artificial neural network abilities to approximate nonlinear functions and capture complex relationships in the data are instrumental abilities which could support the loading parameter identification. 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 hydro generator vibration.