To address the issue of insufficient position control accuracy in the servo-hydraulic system of injection molding machines under nonlinear characteristics and external disturbances, this paper proposes a novel adaptive PID control strategy enhanced by the Deep Deterministic Policy Gradient (DDPG) algorithm. An auxiliary servo valve is introduced to improve flow capacity and enhance the system’s dynamic response performance. Meanwhile, the DDPG algorithm is utilized to adjust the PID parameters in real time based on tracking errors and system state feedback, thereby improving the controller’s adaptability to time-varying operating conditions. Compared with traditional control methods, the proposed strategy demonstrates superior tracking accuracy, faster convergence, and stronger robustness. In particular, this work innovatively integrates the DDPG algorithm with an auxiliary servo valve structure for PID parameter optimization and dynamic performance enhancement, offering new ideas and technical pathways for adaptive control of complex hydraulic systems.

In response to the issues of premature convergence and insufficient parameter control in Particle Swarm Optimization (PSO) for high-dimensional complex optimization problems, this paper proposes a Multi-Strategy Topological Particle Swarm Optimization algorithm (MSTPSO). The method builds upon a reinforcement learning-driven topological switching framework, where Q-learning dynamically selects among fully informed topology, small-world topology, and exemplar-set topology to achieve an adaptive balance between global exploration and local exploitation. Furthermore, the algorithm integrates differential evolution perturbations and a global optimal restart strategy based on stagnation detection, together with a dual-layer experience replay mechanism to enhance population diversity at multiple levels and strengthen the ability to escape local optima. Experimental results on 29 CEC2017 benchmark functions, compared against various PSO variants and other advanced evolutionary algorithms, show that MSTPSO achieves superior fitness performance and exhibits stronger stability on high-dimensional and complex functions. Ablation studies further validate the critical contribution of the Q-learning-based multi-topology control and stagnation detection mechanisms to performance improvement. Overall, MSTPSO demonstrates significant advantages in convergence accuracy and global search capability.