High-Order Sliding Mode Control for Three-Joint Rigid Manipulators Based on an Improved Particle Swarm Optimization Neural Network

This paper presents a control method for the problem of trajectory jitter and poor tracking performance end three-joint rigid manipulator. The is based on high-order particle swarm optimization algorithm with an improved sliding mode neural network. Although variable structure has certain degree robustness, because its own switching characteristics, chattering can occur in later stage manipulator end. Hence, basis control, homogeneous continuous law super-twisting adaptive were added to further improve robustness system. radial function network was used compensate errors modeling process, designed update weights middle layer Furthermore, established applied optimize parameters network, which Finally, MATLAB simulation results indicated validity superiority proposed compared other algorithms.