面向无人驾驶碾压机的容错控制方法研究
DOI:
作者:
作者单位:

天津大学

作者简介:

通讯作者:

中图分类号:

基金项目:

天津市人工智能科技重大专项


Research on fault tolerant control method for unmanned roller
Author:
Affiliation:

Tianjin University

Fund Project:

Science and Technology Major Project on Artificial Intelligence of Tianjin

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    无人驾驶碾压机高精度路径跟踪控制依赖于传感器对车体信息的准确测量,但在恶劣的高原大坝环境下,定位传感器极易出现信号突变、信号丢失现象,对系统的安全性与稳定性构成极大威胁。针对无人驾驶碾压机在恶劣工况下传感器的短时定位失效问题,提出了基于自学习模型的信号代偿容错控制方法。首先,根据无人驾驶碾压机运行过程中体现出的转向系统漂移特性,构造了带流量损耗参数的线性转向模型。进而,提出了模型参数在线学习算法,主要用于学习系统的流量损耗特性。最后以串联抗扰控制器作为车辆控制基础,实现定位短时失效场景下的容错控制。实车验证结果表明:车辆能够在传感器失效后的40s内继续进行高精度碾压作业,与无代偿和模型无自学习代偿两种情况对比,分别延长了近18.7倍和2.7倍的运行时间,极大地提高了系统的安全性与作业效率。

    Abstract:

    The high-precision path tracking control of unmanned roller relies on the accurate measurement of the vehicle’s location information by sensors. However, in the harsh plateau dam environment, the positioning sensors’ signals are prone to sudden changes and loss, which poses a great threat to the safety and stability of the system. For this reason, a fault-tolerant control method based on signal compensation by using self-learning model was proposed. First, according to the drift characteristic of the steering system reflected in the operation of unmanned roller, the complex hydraulic steering system was simplified, and a linear steering model with flow loss parameter was constructed. After that, an online learning algorithm was proposed to mainly learn the flow loss characteristic of the system. Finally, a cascaded disturbance rejection controller was used to realize the path tracking control. The results show that the vehicle can continue high-precision running within 40s after the sensor fails. Compared with the case of no fault-tolerant control and fault-tolerant control without model self-learning, the running time is extended by 18.7 times and 2.7 times respectively, which greatly improves the safety and efficiency of the system.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-02-19
  • 最后修改日期:2021-04-14
  • 录用日期:2021-04-15
  • 在线发布日期:
  • 出版日期: