ABSTRACT
ABSTRACT: The aim of this paper is to identify the dynamic driving conditions of heavy duty vehicle through building the Hierarchical Hidden Markov models into the rollover warning system of heavy duty vehicle. After choosing the typical driving conditions of the heavy duty vehicle, the corresponding data under those driving conditions are collected and put to test with the Student’s t Test method and Grubbs’s Test method. The outliers filtered by T-G test from the data are detected and eliminated. Applications of the K-Means algorithm which is used to set up the driving threshold value for the heavy duty vehicle, and the Baum-Welch algorithm which is used to optimize the proposed HHMM model are discussed in detail. Simulations under a variety of driving conditions are carried out to verify the optimized HHMM model. The simulation results show that the proposed model can accurately and effectively identify the driving status under a variety of driving conditions.
1 INTRODUCTION
