基于非参数核密度估计法的车辆大数据服役载荷外推方法

Extrapolation Method of Vehicle Big-data Service-loads Based on Non-parametric KDE Method

提出了基于非参数核密度估计法的用户使用习惯特征统计方法和车辆全寿命周期服役载荷外推方法。以某型宽体轻客的全国大范围用户使用习惯数据调研和道路载荷谱大数据采集为基础,运用非参数一维核密度估计法,研究了90%分位下用户使用习惯典型特征的统计方法。运用非参数二维核密度估计法结合蒙特卡罗仿真,研究了基于用户道路实测载荷的车辆全寿命周期服役载荷外推方法。此外,研究了不同核密度估计法多次外推结果的变化特性,研究结果表明多次载荷外推保持了较好的载荷损伤与分布的一致性。

A customer-usage-behavior characteristic statistical method and vehicle life cycle service-load extrapolation method were presented based on non-parametric KDE method.After the national wide investigation of customer-usage-behavior data survey and big-data collection of road load spectra,a statistical analysis method for 90%quantile customer usage typical behavior characteristics was studied by applying non-parametric one-dimensional KDE method.Combining non-parametric two-dimensional KDE method with Monte Carlo simulation,a vehicle life cycle service-load extrapolation method was carried out based on the collected customer road loads.Furthermore,the variation characteristics of multiple extrapolations with different KDE methods were studied.Results show good consistency of load spectra damage and distribution of multiple load extrapolations.