A physical model-neural network coupled modelling methodology of the hydraulic damper for railway vehicles

Abstract

The dynamic characteristics of the hydraulic damper are time-varying in the complex working environment. To reveal the internal influence mechanism of the boundary conditions on the dynamic performance of the hydraulic damper and take it into account in the multi-body dynamics calculation, the laboratory test of the hydraulic damper is carried out firstly, and it is confirmed that the hydraulic damper has significant frequency-dependent and amplitude-dependent and temperature-dependent characteristics. Then, combining the physical parameter model with the neural network model, an accurate hybrid neural network model of the hydraulic damper is proposed. The physical parameter model considers the damper structure, including orifice, damping valve, rubber joint and the relationship between temperature and viscosity of hydraulic oil. The neural network model describes the personality characteristics of the hydraulic damper, such as oil leakage, the internal friction force and the percentage of entrapped air in oil. Finally, the responses and the dynamic parameters of the hybrid neural network model are calculated and compared with the experimental results by considering various exciting amplitudes and frequencies. The results show that the proposed model can fully simulate the dynamic performance of the hydraulic damper under various operating conditions.

KEYWORDS:

• Railway vehicle
• multibody dynamics
• hydraulic damper
• hybrid neural network model
• dynamic performance

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data availability statement

All data included in this study are available upon request to the corresponding author.

Additional information

Funding

The present work has been supported by the National Key Research and Development Program of China [grant number 2018YFE0201401-01], National Science Foundation for Young Scientists of China [grant number 51805450], Sichuan Science and Technology Program [grant number 2020YJ0075], China Association of Science and Technology Young Talent Support Project [grant number 2019QNRC001].