基于BP神经网络优化的卡尔曼滤波算法在轨道垂向不平顺估计中的应用
彭浪，梁树林*，池茂儒
（西南交通大学 牵引动力国家重点实验室，四川 成都 610031）
摘要：轨道不平顺是引起车辆和轨道振动的主要原因，也是影响列车平稳性和舒适性的关键因素。本文根据卡尔曼滤波（KF）最优估计原理，建立了车辆系统模型，通过观测车辆系统中车体、前后构架的多个惯性量，采用BP神经网络优化卡尔曼滤波（BP-KF），实现了轨道垂向不平顺的估计。结果表明，优化后的轨道垂向不平顺估计值，无论是在趋势上还是幅值上与原始值都具有较高的一致性，为轨道不平顺的间接估计提供了新的技术手段。
关键词：铁道车辆；轨道不平顺；卡尔曼滤波器；BP神经网络
中图分类号：U279.2 文献标志码：A doi：10.3969/j.issn.1006-0316.2023.05.010
文章编号：1006-0316 (2023) 05-0058-07
Application of Kalman Filter Algorithm Based on BP Neural Network Optimization in the Prediction of Vertical Track Irregularity
PENG Lang，LIANG Shulin，CHI Maoru
( State Key Laboratory of Traction Power, Southwest Jiaotong University, Chengdu 610031, China )
Abstract：Track irregularity is an important excitation source of vehicle and track vibration, and also a key factor affecting train ride and comfort. Based on the principle of Kalman filter (KF), a vehicle system model is established in this paper. By observing several inertial quantities of the vehicle system, the optimal estimation principle of Kalman filter is used to estimate the vertical irregularity of the track. Finally, BP neural network is used to optimize the Kalman filter. The results show that the optimized vertical irregularity estimates have a high consistency with the original values both in trend and amplitude, which provides a new technical method for the indirect estimation of track irregularity.
Key words：railway vehicle；track irregularity；Kalman filter；BP neural network
———————————————
收稿日期：2022-05-31
作者简介：彭浪（1998－），男，四川内江人，硕士研究生，主要研究方向为车辆智能运维，E-mail：1121241457@qq.com。*通讯作者：梁树林（1967－），男，山西盂县人，博士，教授级高工，主要研究方向车辆工程结构可靠性及动力学，E-mail：liangshulin@swjtu.edu.cn。
- 上一篇：3万吨列车编组方案车钩力研究
- 下一篇：两种新型材料地铁轨枕的频响特性和减振特性分析
设为首页 | 加入收藏 | 免责条款
《机械》杂志版权所有 Copyright©2008-2012 Jixiezazhi.com All Rights Reserved
电话：028-85925070 传真：028-85925073 E-mail：jixie@vip.163.com
地址：四川省成都锦江工业开发区墨香路48号 邮编：610063
Powered by PageAdmin CMS