桥式起重机神经网络自适应滑模定位防摆控制
Neural Network Adaptive Sliding Mode Positioning and Anti-swing Control of Overhead Crane
郭建明 1周惠兴 1徐佳琦 1吴昊1
作者信息
- 1. 北京建筑大学机电与车辆工程学院,北京 100044
- 折叠
摘要
针对桥式起重机非线性、存在外界干扰的特点,提出了 一种神经网络自适应滑模控制器.首先采用拉格朗日法建立桥式起重机动力学模型;然后在分层滑模控制器的基础上,设计了径向基函数神经网络权值自适应更新率,利用径向基函数神经网络补偿系统的非线性与外界干扰引起的不确定上界,并利用粒子群算法对控制器参数寻优,通过构造Lyapunov函数证明了系统的稳定性;最后设计了 1组仿真实验和1组在搭建的实验平台上的验证实验,仿真结果表明:在非线性及外界干扰作用下,神经网络自适应滑模控制器可以快速实现小车定位和负载消摆,控制器可以消除不确定上界对系统的影响.实验结果也表明,所设计的控制器可以使桥式起重机达到控制目标,具有一定的抗干扰能力.
Abstract
A neural network adaptive sliding mode controller was proposed for overhead crane with nonlinear and externally disturb-ance.Firstly,the dynamic model of overhead crane was established by Lagrange method.Then,based on the hierarchical sliding mode controller,the adaptive update rate of the radial basis function neural network weights was designed.The radial basis function neural network was used to compensate the uncertain upper bound caused by the nonlinear and external disturbance in the system,and the particle swarm optimization algorithm was used to optimize the parameters of controller.The stability of the system was proved by con-structing a Lyapunov function.Finally,one set of simulation experiments and one set of validation experiments on a established experi-mental platform were designed.The simulation results show that under the influence of nonlinear and externally disturbance,the neural network adaptive sliding mode controller can quickly achieve the positioning of the trolley and the swing suppression of the load,the controller can eliminate the influence of uncertain upper bound on the system.The experimental results also show that the designed con-troller can make the overhead crane reach the control target,and has a certain ability to resist disturbance.
关键词
桥式起重机/神经网络/自适应/滑模控制Key words
overhead crane/neural network/adaptive/sliding mode control引用本文复制引用
基金项目
北京建筑大学硕士研究生创新资助项目(PG2023140)
住房和城乡建设部研究开发项目(2020-K-150)
出版年
2024
NETL
NSTL
万方数据