基于动力学模型优化PSO-RBF神经网络的水下机械臂控制  

Optimization of Underwater Manipulator Control of PSO-RBF Neural Network Based on Synamic Model

作　　者：田金鑫 原忠虎[1] 吴宝举 

机构地区：[1]沈阳大学,辽宁沈阳110044

出　　处：《工业控制计算机》2024年第10期56-58,61,共4页Industrial Control Computer

基　　金：辽宁省科技计划项目(2023JH2/101300205)。

摘　　要：随着我国海洋资源开发与利用的增加,对海洋资源开发能力的要求也日益提高。然而,我国在海洋探测方面的研究仍处于起步阶段,面临着复杂的海洋环境和海洋主权保护的挑战。研究聚焦于智能化水下机器人-机械臂系统UVMS的研究。基于Lagrange法和Morison方程,精确建立了六自由度水下机械臂的动力学模型。为了提高系统的稳定性和轨迹跟踪的准确性,采用了适应值优化的PSO粒子群算法结合RBF神经网络,并将其应用于水下机械臂的动力学模型中。仿真实验结果表明,改进的PSO-RBF神经网络自适应滑模控制算法较传统PID及RBF神经网络算法提前约0.3 s和0.1 s确定控制参数,提前达到稳定状态。China's research in ocean exploration is still in its infancy,and it is facing the challenges of complex marine environment and maritime sovereignty protection.This paper focuses on the research of intelligent underwater robot-robotic arm system UVMS.Based on the Lagrange method and Morrison equation,the dynamic model of the six-degree-of-freedom underwater manipulator was accurately established.In order to improve the stability of the system and the accuracy of trajectory tracking,the PSO particle swarm optimization algorithm combined with RBF neural network was adopted and applied to the dynamic model of the underwater manipulator.The simulation results show that compared with the traditional PID and RBF neural network algorithms,the improved PSO-RBF neural network adaptive sliding mode control algorithm can determine the control parameters about 0.3 seconds and 0.1 seconds earlier than the traditional PID and RBF neural network algorithms,and reach a stable state in advance.

关 键 词：UVMS RBF神经网络 动力学建模 PSO粒子群算法 水下机械臂 滑模控制 

分 类 号：TP241[自动化与计算机技术—检测技术与自动化装置] TP183[自动化与计算机技术—控制科学与工程]