Research on neural network PID adaptive control with industrial welding robot in multi-degree of freedom

摘要

Motion and control system with industrial robot in multi-degree of freedom (multi-DOF) is the typical mechatronics system, which combines mechanics, electronics, sensors, computer hardware and software, control, artificial intelligence and modeling technology, and many other advanced technologies. This paper establishes a six-DOF welding robot model, and proposes a complex control method based on improved neural network-PID which uses PSO algorithm's global optimization capability and strong convergence to improve BP network weights. The method is based on backward error propagation of the basic BP algorithm, adjusting the BP network weights and thresholds corresponding to the updating particle position. It takes full advantage of the global optimization of PSO algorithm and maintains the BP algorithm's back-propagation characteristics better. The simulation results show that the method can optimize the dynamic process and reduce the steady-state error of system. It has good value for the control technology.