JapanChemicals and materials2018 – ongoingSumitomo Bakelite
AI autonomous control and abnormality-sign detection on functional-chemicals lines
Sumitomo Bakelite ran functional-chemicals lines under AI control at four plants, some with about half the staff
Problem
Skilled workers were scarce and the workforce was aging. The company also wanted faster start-up of production lines in competitive development fields.
Approach
A project team started in 2018 with NEC on batch-continuous production lines. It collected equipment data, tested IoT devices and used NEC's EdgeCross platform to show temperature, speed and pressure in real time. AI analyzed sensor and quality data, flagged unusual equipment behavior as an early warning, and controlled the main process on its own. Veteran technicians' control know-how was turned into rules. The company planned to extend the system overseas.
Results
Takeaway
Capturing veterans' know-how as rules let the company move staff off some lines. The article gave no yield or quality figures.
Categories
- Industry
- Chemicals and materials
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and MLOptimization
- Adoption
- Partner co-development
- Evidence
- Company's own claim
Sources
Source summaries
Nikkan Kogyo reports on the AI work with NEC. Autonomous control runs at four domestic plants, and executives said some lines can run with about half the staff they needed before. No other quantified results are given.
Full details are in the original sources.