UKF-CNN-LSTM Estimation of Sideslip Angle of Heavy-load AGV

张惠; 薛善良; 麻茹雪; 刘国辉

doi:10.13433/j.cnki.1003-8728.20230384

Chinese

您当前的位置：

首页 >

文章列表页 >

UKF-CNN-LSTM Estimation of Sideslip Angle of Heavy-load AGV

更新时间：2026-04-23

- UKF-CNN-LSTM Estimation of Sideslip Angle of Heavy-load AGV
- Mechanical Science and Technology for Aerospace Engineering Vol. 44, Issue 12, Pages: 2210-2217(2025)
- 作者机构：
  
  1. 南京航空航天大学计算机科学与技术学院,南京,211106
  2. 南京晨光集团有限责任公司,南京,210006
- 作者简介：
- 基金信息：
- DOI：10.13433/j.cnki.1003-8728.20230384
  CLC：
- Published：2025
- 稿件说明：
移动端阅览
张惠, 薛善良, 麻茹雪, et al. UKF-CNN-LSTM Estimation of Sideslip Angle of Heavy-load AGV[J]. Mechanical Science and Technology for Aerospace Engineering, 2025, 44(12): 2210-2217.
DOI：

张惠, 薛善良, 麻茹雪, et al. UKF-CNN-LSTM Estimation of Sideslip Angle of Heavy-load AGV[J]. Mechanical Science and Technology for Aerospace Engineering, 2025, 44(12): 2210-2217. DOI： 10.13433/j.cnki.1003-8728.20230384.

摘要

转运大型产品的重载自动导引车（AGV）运动稳定性控制至关重要，其关键是质心侧偏角的精确获取。为克服测量质心侧偏角成本高、动力学非线性和不确定性等问题，研究一种基于动力学模型与数据驱动的状态估计方法。将卷积神经网络（CNN）的特征提取能力和长短时记忆网络（LSTM）的数据记忆特性结合，生成时滞非线性状态估计的数据驱动模型，估计的“伪质心侧偏角”作为无迹卡尔曼滤波（UKF）的观测值，以修正基于动力学模型的估计值。对比实验表明，UKF-CNN-LSTM的质心侧偏角估计模型的估计较优。

Abstract

Motion stability control of heavy-load automated guided vehicle (AGV) transporting large products is very important

and the key is to obtain the accurate sideslip angle of mass center. In order to overcome the problems of high cost

dynamic nonlinearity and uncertainty

a state estimation method based on dynamic model and data driven was studied in this paper. The feature extraction ability of convolutional neural network (CNN) and the data memory characteristics of long short-term memory network (LSTM) were combined to generate a data-driven model for time-delay nonlinear state estimation. The estimated' fake sideslip angle' was used as the observation value of unscented Kalman filter (UKF) to correct the estimation value based on the dynamic model.The comparative experiments showed that the estimation model based on UKF-CNN-LSTM was better.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

CNN-DLSTM结合迁移学习的小样本轴承故障诊断方法

Fault Diagnosis of a Bearing using Feature Extraction Method based on CEEMD Algorithm and CNN

Related Author

仇芝

徐泽瑜

陈涛

石明江

韦明辉

Zhang Zhaolin

Fan Yugang

Related Institution

西南石油大学机电工程学院

Faculty of Information Engineering and Automation, Kunming University of Science and Technology

Engineering Research Center for Mineral Pipeline Transportation of Yunnan Province

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰