Miso Information Technology 加入 138 億韓元 AI 模具維護項目

Miso Information Technology, a multimodal data platform and AI company, said on Oct. 20 it has been selected to participate in a government-backed research and development (R&D) project for autonomous manufacturing using tandem presses, led by the Ministry of Trade, Industry and Resources (MOTIR).

The project aims to automate die changes, anomaly detection and equipment control in tandem presses, which are key machines used in automotive parts manufacturing, while developing AI-based autonomous manufacturing technologies.

Led by automotive parts manufacturer Sewon Mulsan, the project has a total budget of 13.8 billion won. Its targets include completing a single die change in less than five minutes, achieving a 90% unmanned operation rate and reaching 98% accuracy in anomaly detection.

Miso Information Technology will develop a manufacturing AI data platform and predictive maintenance technologies that integrate equipment, sensor, production and quality data from manufacturing sites. The system will use AI to predict changes in die conditions and identify early signs of abnormalities.

Currently, die changes take approximately 40 minutes, reducing production efficiency, while die condition assessments and maintenance depend heavily on workers' experience. The project aims to replace these practices with AI-based autonomous manufacturing.

The company will also consolidate equipment and quality data scattered across separate systems into a data lake using data collection technology based on its IoT Prism platform.

Miso Information Technology expects the integration of data from different types of equipment, combined with AI models trained on historical failures and abnormal operating patterns, to enable earlier anomaly detection and faster identification of equipment failure causes.

The company plans to establish an end-to-end manufacturing AI system covering data collection and integration, anomaly detection, failure prediction and maintenance operations. The goal is to shift from reactive maintenance to data-driven predictive maintenance.

The project will also combine automation of major manufacturing processes, including press forming, welding and inspection, with AI-based analysis and decision-making technologies to improve production efficiency and quality.

It aims to create an intelligent manufacturing environment capable of process optimization and autonomous operation, ultimately enabling equipment and production processes to analyze data and make decisions independently.

"In the long term, we plan to integrate AI, digital twins, vision AI, IoT and robotic control technologies to make production, assembly, inspection and logistics more intelligent," Miso Information Technology said.

"The ultimate goal is to achieve Level 5 fully autonomous manufacturing and dark factories, where AI independently perceives, decides and executes operations."