Chung Yuan Christian University, R&D Center of Smart Manufacturing
Summary Web interface of CPS platform:
Although many factories have introduced MES and scheduling systems, they have not been integrated with the CPS architecture. The transmission of information is not transparent and automated, and it is difficult to ensure the relevance and continuity of the information, which affects the control of the entire production process and the on-site real-time information. Our integrated CPS structure enables the project to obtain the best dispatch of the machine and the shortest delivery time. We also use DDS to receives real-time on-site information and presents it as a platform, which enables control the real-time on-site situation. We constructed an advanced plastic mold & molding service platform, combining CPS and cloud architecture, based on the production life cycle, integrating heterogeneous equipment and systems, and it achieves the goals of real-time monitoring of the manufacturing process, rapid iteration and dynamic optimization.

Process matching model based on cGAN:
The process identification smart agent handles the forecast request from the manufacturing scheduling expert system, allowing engineers to use the expert system while the smart system is also operating behind. In the integration of process identification, the system automatically captures images according to the angle required to recognize the model by the secondary development tool of CAD software. The system captures different views and models to display the structures, and convert the files into a general communication format, and then send them to the process identification recognition smart agent. After the graphic recognition, the identification result is fed back to the manufacturing scheduling expert system, and the process of the part is arranged. This integration technology will form a knowledge loop for the retraining of the smart model, and independently improves the identification performance of the model over time, which strengthen the applicability of smart system.

Static scheduling optimization for mold manufacturing:
With the development of smart manufacturing, the smart scheduling system can break through the development restrictions. The domestic mold industry has formed supply chain clusters in various regions due to odd jobs. Our smart scheduling-related technology can help companies analyze production bottlenecks and accumulate scheduling knowledge. We integrate virtual systems and actual fields to improve the efficiency of decision-making in the manufacturing. We combined EDD, GA, and ACO algorithms to perform multi-objective optimization based on completion time and delay indicators. In addition to obtaining the best scheduling results, the hybrid algorithm also improves computing performance. The smart scheduling system can calculate 40,000 transactions in about 2 minutes.
Technical Film
Keyword Web interface of CPS platform Process matching model based on cGAN Static scheduling optimization for mold manufacturing
Research Project
Research Team
More like this
Provide the latest information of AI research centers and applied industries