欢迎访问机床与液压官方网站!

咨询热线:020-32385312 32385313 RSS EMAIL-ALERT
基于DDPG的振动台控制参数整定方法
DOI:
作者:
作者单位:

北京工业大学

作者简介:

通讯作者:

中图分类号:

基金项目:

国家自然科学(51978015)


Parameter Tuning of Shaking Table Based on DDPG
Author:
Affiliation:

1.Beijing University of Technology;2.Beijing Key Lab of Earthquake Engineering and Structural Retrofit,Beijing University of Technology

Fund Project:

  • 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:

    三参量控制是地震模拟振动台的底层控制算法,三参量控制参数多,传统的参数整定方法存在效率低、过程繁琐等问题。为了提高整定效率和准确性,提出一种基于DDPG算法的振动台三参量控制参数整定算法。该方法通过将振动台三参量控制系统作为强化学习环境,利用DDPG算法对系统的状态-动作-奖励数据进行学习和训练;训练好的智能体则可以输出最优的控制参数,然后将整定完成的控制参数放在实际振动台系统中进行测试,结果表明,DDPG算法可以有效地优化振动台控制性能,提高试验结果的准确性和可靠性,具有实际应用价值。

    Abstract:

    Three variable control has commonly used as the underlying control algorithm in shaking table. However, the process of parameter tuning in three-variable control involves numerous parameters, and traditional parameter tuning methods suffer from problems such as low efficiency and complicated processes. In order to improve tuning efficiency and accuracy, a novel parameter tuning method for three variable control of shaking table based on the DDPG algorithm was proposed. The method builds a discrete model of shaking table and treats it as a reinforcement learning environment. By using the DDPG algorithm to learn and train the state-action-reward of the system, the optimal control parameters were obtained. The tuning parameters were then tested in shaking table and compared with traditional tuning methods. The results showed that the DDPG algorithm could effectively optimize the control performance of the shaking table, improve the accuracy and reliability of experimental results, and has practical application value.

    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:2023-06-26
  • 最后修改日期:2023-09-09
  • 录用日期:2023-09-26
  • 在线发布日期:
  • 出版日期: