Research on the virtual reality of vibration characteristics in vehicle cabin based on neural networks

A finite element model of commercial vehicles was firstly built in the paper to study the virtual reality of vibration characteristics, and the top 6-order modal was then computed and compared with the experimental results to verify the reliability of the computational model. Then, a neural network model of the cabin was built. Through road tests, the excitation signal at the cabin suspension point and the response signal of interior vibration noise were measured under the idle condition and constant speed condition. The measured excitation signal was applied to the prediction model for frequency response analysis, in order to compute the interior noise within the range 20–200 Hz. The obtained simulation result of the vibration noise was compared with the experimental result and analyzed. As indicated from the analysis, the influence of excitation spectrum and the model can be reflected by the simulation response spectrum, which is consistent with the experimental result. The higher precision can be also obtained when the model is applied to predict the interior noise.