基于粒子群优化神经网络的机械臂跟踪控制  

Manipulator Tracking Control Based on Particle Swarm Optimization Neural Network

作　　者：屈晓宇 王家隆 QU Xiaoyu;WANG Jialong(The Higher Educational Key Laboratory for Flexible Manufacturing Equipment Integration of Fujian Province,Xiamen Institute of Technology,Xiamen 361021,Fujian Province;Faculty of Mechanical,Electrical and Information Engineering,Xiamen Institute of Technology,Xiamen 361021,Fujian Province)

机构地区：[1]厦门工学院柔性制造装备集成福建省高校重点实验室,福建厦门361021 [2]厦门工学院机械电气与信息工程学院,福建厦门361021

出　　处：《沈阳工程学院学报(自然科学版)》2025年第1期48-54,共7页Journal of Shenyang Institute of Engineering:Natural Science

基　　金：国家自然科学基金区域联合重点项目(U21A20483);厦门工学院院级项目(XJYKT22004);厦门工学院院级教改项目(XJYJG23026)。

摘　　要：针对智能消防机械臂在无人情况下的系统操作精度问题,提出基于粒子群优化RBF神经网络自适应的控制方法。首先,采用RBF神经网络自适应控制算法跟踪机械臂各关节的轨迹;其次,采用粒子群优化算法对RBF神经网络的权值进行更新,并重新构建RBF神经网络;最后,通过MATLAB仿真验证所提出控制器的有效性和可行性。结果表明:与一般RBF神经网络自适应控制器相比,粒子群优化RBF神经网络自适应控制器在路径跟踪上具有更高的控制精度。Aiming at the problem of system operation accuracy of intelligent fire manipulator in unmanned condition,an adaptive control method based on particle swarm optimization RBF neural network is proposed.Firstly,the RBF neural network adaptive control algorithm is used to track the trajectory of each joint of the manipulator.Secondly,Particle Swarm Optimization(PSO)algorithm was used to update the weights of RBF neural network,and the RBF neural network was reconstructed.Finally,the effectiveness and feasibility of the proposed controller are verified by MATLAB simulation.The results show that compared with the general RBF neural network adaptive controller,the particle swarm optimization RBF neural network adaptive controller has higher control accuracy in path tracking.

关 键 词：智能消防机械臂 神经网络 自适应 粒子群优化算法 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]