JapanChemicals and materials2023 – ongoingKaneka
AI system optimizing the dryer in a resin plant
Kaneka's AI system for a resin plant dryer added about 100 tonnes of output a year
Problem
Operators set the conditions of a continuous dryer in a resin plant by hand, within limits on temperature and exhaust humidity.
Approach
Kaneka built an AI system on the Dataiku platform. It predicts the temperature of the intermediate product and the dryer output, then calculates the best operating settings and sends them to the control system. The platform is used at several domestic plants.
Results
Takeaway
The dryer was run by AI-calculated settings in production, and the gain was reported as extra output.
Categories
- Size
- Large enterprise
- Industry
- Chemicals and materials
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and MLOptimization
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
The article, based on a Kaneka talk at a Dataiku event, describes an in-house AI system that optimizes a resin plant's continuous dryer. It reports about 100 tonnes more output a year. It also covers Kaneka's data-skills training programme.
Full details are in the original sources.