Open AccessApplication of MIV-NARX to Identify Road Roughness
Author(s) -
Yong He,
Guofang Zhang,
Jingfen Song
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1748/4/042014
Subject(s) - nonlinear autoregressive exogenous model , artificial neural network , smoothness , autoregressive model , noise (video) , computer science , mean squared error , surface roughness , surface finish , artificial intelligence , pattern recognition (psychology) , machine learning , statistics , engineering , mathematics , image (mathematics) , materials science , mechanical engineering , mathematical analysis , composite material
Aiming at the deficiencies in the existing research on road roughness recognition based on neural networks, the road roughness and 16 vehicle response data are simulated based on the filtered white noise model and the smoothness seven-degree-of-freedom model, NARX neural network is built to identify road roughness. The coefficient of determination and the root mean square error are introduced as the evaluation indicators of the model, the MIV method is used to evaluate and screen each input response. Research shows that MIV method improves the performance of NARX neural networks, MIV-NARX can effectively identify road roughness.