Helical gear vibration response and rigidity degradation prediction method

The invention discloses a helical gear vibration response and rigidity degradation prediction method, and belongs to the field of gear performance prediction. The method comprises the following steps: firstly, establishing a gear system lumped parameter dynamical model according to the meshing condition of a pair of gears, considering that the gear system lumped parameter dynamical model is a multi-degree-of-freedom system under the action of deterministic force and random force, establishing a system digital twin model under multiple time scales of characteristic time and operation time, and calculating a translation vibration coupling control equation; unscented Kalman filtering and machine learning are combined to establish a grey box model, combined state parameter estimation is carried out on collected data, a state prediction framework is constructed, and rigidity degradation is predicted at the operation time scale. According to the method, the response of a gear nonlinear multi-degree-of-freedom syste