Open AccessConstruction of Vehicle Operating Mode Based on K-Means Algorithm
Author(s) -
Liping Yuan,
Yang Li
Publication year - 2020
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 - 10.1088/1742-6596/1646/1/012129
Subject(s) - principal component analysis , kinematics , process (computing) , artificial neural network , computer science , driving cycle , cluster analysis , mode (computer interface) , construct (python library) , automotive engineering , automotive industry , calibration , algorithm , simulation , engineering , artificial intelligence , mathematics , power (physics) , statistics , physics , electric vehicle , classical mechanics , quantum mechanics , programming language , aerospace engineering , operating system
The vehicle driving condition(Driving Cycle), also called the vehicle test cycle, is to describe the speed-time curve of the vehicle driving process, which can reflect many kinematic characteristics of the vehicle’s exercise process on the road. At present, the operating conditions of automobile used in China can not meet the requirements of certification and calibration of automobile products, so it is urgent to develop the test conditions that can reflect the characteristics of automobile exercise in China. Using the method of neural network training to amplify the data, we can accurately fill the missing data in the course of driving find out the principal component of the kinematics segment of the vehicle by using principal component analysis, select some of the most expressive kinematics fragments by using the K-means clustering (K-Means Cluster) analysis method, and construct the model of the Vehicle working condition with little error from the real operating condition, thus effectively reduce the error caused by various environment, traffic, road surface and other external factors.