JapanConsumer goods2020 – ongoingKao
AI early-warning monitoring at the Wakayama plant
Kao's Wakayama plant used AI warnings to investigate process deviations before problems developed
Problem
Less-experienced operators had to monitor complex batch processes with fewer staff. Existing alarms could arrive after an abnormal condition had already occurred.
Approach
Kao began testing Azbil's BiG EYES in February 2020 and started full operation in December. The system learned normal process behavior and detected small departures in time-series data. Operators developed monitoring models and discussed warning signals together.
Results
No published figures
Takeaway
Model development made experienced operators' monitoring knowledge more explicit. Azbil reported prevented problems without publishing a quantified reduction in incidents.
Categories
- Size
- Large enterprise
- Industry
- Consumer goods
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Vendor solution
- Goal
- Quality and risk
- Evidence
- Vendor case study
Sources
Source summaries
Azbil described Kao's deployment of AI monitoring for batch production at Wakayama. It reported earlier intervention and knowledge transfer during model development, without quantified incident or cost savings.
Full details are in the original sources.
