Open AccessRoad Friction Coefficient Estimation Based on Improved Keras Model
Author(s) -
。 对车辆进行动力学分析,
找出与路面附着系数相关的动力,
学参数作为神经网络模型的输入量 通过各种工况的仿真试验建立数据集 以 Keras,
模型为基础 结合限幅递推平均滤波算,
强化学习 提出改进,
Keras 模型的路面附着系数估计器,
K 折验证用于扩大样本空间,
Dropout,
正则化可以降低模型的过拟合现象 提高模型泛化能力,
Sarsa,
提出的方法相比原 Keras,
模型平均绝对误差降低了,
均方根误差降低了,
Fen Lin,
Zhengwei Wang,
Youqun Zhao,
Yizhang Cai,
棻等 基于改进 Keras
Publication year - 2021
Publication title -
journal of mechanical engineering
Language(s) - Uncategorized
Resource type - Journals
SCImago Journal Rank - 0.342
H-Index - 50
ISSN - 0577-6686
DOI - 10.3901/jme.2021.12.074
Subject(s) - friction coefficient , estimation , mathematics , computer science , materials science , engineering , composite material , systems engineering
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom