To address the challenge of implementing 5G wireless networks in industrial process control, this paper integrates deep learning and reinforcement learning in AI with anti-disturbance industrial control to propose an anti-latency optimized control method for 5G wireless networks. The proposed method includes: an anti-latency controller based on data-driven signal compensators with PID controllers and the controller parameters self-optimization algorithm combining digital twin and reinforcement learning. The proposed anti-latency control method is integrated with end-edge-cloud collaboration technologies of Industrial Internet to create an intelligent control system architecture that achieves anti-latency optimized control. A control experimental system based on commercial 5G and Industrial Ethernet was established, and anti-latency control experiments are conducted on an actual heat exchange system. The experimental results indicate that the proposed anti-latency intelligent control method significantly eliminates the impact of 5G random latency on the dynamic performance of the control system.