A Mechanism and Data-Driven Hybrid Mechanical Model of Rotary Arm Positioning Rubber Joint

Rotary arm positioning rubber joint (hereinafter referred to as rubber joint) is an important component of railway vehicle which affects the stability and safety of the vehicle. So it’s of great significance to construct a high-precision mechanical model for rubber joint. This paper proposes a mechanism and data-driven hybrid mechanical model for rubber joint, mechanism part which is based on a superposition of elastic, friction and viscous forces calculates the trend of damping force. Then, data-driven part which is based on BP neural network optimizes the calculation precision of calculated damping force. Combined with the rail vehicle dynamic model, The simulation results show that the proposed model can characterize the non-linear damping force precisely of rubber joint in larger amplitude and wider frequency domain. Moreover, compared with normal temperature, the dynamic performance of rubber joints in low ambient temperature will worsen the curve passing performance and curve safety of the vehicle, which needs to be paid attention to in vehicle operation.