论文信息 - Automatic tire pressure fault monitor using wavelet-based probability density estimation

Automatic tire pressure fault monitor using wavelet-based probability density estimation

This paper is devoted to the problem of tire pressure monitoring and tire fault detection. Based on wavelet package transformation, the density of the tire's response vibration caused by the stochastic ground excitation is analyzed. Then using RBF neural networks to learn and classify the different types of vibration response, an automatic abnormal tire pressure detector is built. Theoretical analysis and simulation results show the I effectives of this new fault detector.

[1] C. Canudas-de-Wit. Comments on "A new model for control of systems with friction" , 1998, IEEE Trans. Autom. Control..

[2] Sung Yang Bang,et al. An Efficient Method to Construct a Radial Basis Function Neural Network Classifier , 1997, Neural Networks.

[3] N. C. Nigam. Introduction to Random Vibrations , 1983 .

[4] Ja-Yong Koo,et al. Wavelet deconvolution , 2002, IEEE Trans. Inf. Theory.

[5] Multiresolution analysis, wavelets, and probability density estimation , 1994, Proceedings of 1994 IEEE International Symposium on Information Theory.

[6] A. Tsybakov,et al. Wavelets, approximation, and statistical applications , 1998 .

[7] C. Canudas-de-Wit,et al. Observers for tire/road contact friction using only wheel angular velocity information , 1999, Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No.99CH36304).

[8] David Cebon,et al. Interaction Between Heavy Vehicles and Roads , 1993 .

[9] Asim Roy,et al. An algorithm to generate radial basis function (RBF)-like nets for classification problems , 1995, Neural Networks.