High-Precision Trajectory Tracking Technology for Dual-Axis Robotic Arms based on Higher-Order Sliding Mode Control
Against the backdrop of rapid progress in industrial automation and intelligent manufacturing, this paper presents a hierarchical fusion control strategy that combines High- Order Sliding Mode Control (SOSM), deep learning, and Model Predictive Control (MPC) to address the critical bottlenecks of traditional Proportional-Integral-Derivativ (PID) control in dual-axis robotic arms, including initial trajectory deviation, residual vibration, and model uncertainty. The robotic arm is physically modeled using SolidWorks, imported into Sysplorer for dynamic simulation, and the control module is developed via Syslab. A well-designed sliding mode surface and exponential convergence law are adopted to realize robust SOSM control, while a dual-layer Long Short-Term Memory (LSTM) network is introduced to compensate for model uncertainties such as friction and vibration. A hierarchical control architecture is constructed: the upper layer uses MPC for 50 ms global trajectory planning, and the lower layer applies SOSM for real-time tracking with a 0.01 s sampling period, balancing global optimization and real-time response. Experimental results confirm that the proposed strategy outperforms conventional PID control in trajectory tracking precision, dynamic response, and robustness, providing a high-precision and robust control scheme for industrial applications. This work contributes to the technological innovation and engineering application of control system theory, robotics, artificial intelligence, and automation technologies, enriches the technical reserve of cross-field integration, and provides a reference for academic exchanges, technical demonstrations, and industrial cooperation in related cutting-edge fields, so as to boost global knowledge sharing and collaborative innovation.