Abstract: In intelligent manufacturing, the cloud control of low-level devices and visual sorting system are extremely critical and potential in the industry. We propose a deep learning-based material recognition and location system with cloud Programmable Logic Controller (PLC), which is demonstrated in 5G Time Sensitive Networking (TSN) network. First, traditional PLC is virtualized to realize flexible deployment of PLC function in the terminal and the cloud. Second, we establish an artificial intelligent platform in the cloud and design YOLOv5-based object detection algorithm to locate the position and recognize the types of the materials, and pixel coordinates are obtained. Third, the camera calibration method is utilized to transform pixel coordinates and world coordinates, and the material information consists of the world coordinates, types, and timestamps is sent to cloud PLC. Finally, the commands are transmitted by 5G TSN environment from cloud PLC that controls multi-crane cooperative running in real-time. We establish an experimental system to demonstrate the significance and effectiveness of the proposed scheme, which controls multi-crane operation synergistically. The mAP of material location is up to 99.65%, sorting accuracy reaches 96.67%, and the average consuming time of each object is 2.5s, which meets the requirements of low-latency and high-precision in industrial applications.