Modification and Noise Reduction Design of Gear Transmission System of EMU Based on Generalized Regression Neural Network

Abstract

In view of traction gear vibration and noise affecting the performance of the transmission system and the comfort of passengers when the electric multiple units (EMU) is running at high speed, taking the traction gear transmission system of an EMU as the research object by using Romax software to construct the parametric modification model of the gear transmission system based on gear modification theory. Combined with multibody dynamics, the vibration response characteristics of the transmission system are simulated and analyzed. A radiated noise prediction model is established using the acoustic boundary element method, based on the generalized regression neural network (GRNN). To further explore the influence of gear modification methods and parameters on vibration and noise characteristics and minimize gear transmission’s radiation noise. A particle swarm optimization (PSO) algorithm is designed to solve the optimal modification parameters. The simulation results reveal that after the optimization and modification, the gear transmission error is significantly reduced, the contact status is considerably improved, and the root mean square value of the acoustic power level is reduced by 13.10 dB, which is a reduction of 14%. It shows that the design can effectively reduce the radiation noise of EMU gear trans-mission system.

Keywords

• gear transmission system
• GRNN
• PSO algorithm
• modification noise reduction
• optimal design