
What happened
MHI-MS commercialized a world-first add-on electrical control unit for its corrugated machines that uses AI to predict warp-free machine settings for each paper type, and is now selling it in Japan and abroad.
Why it matters
The device lets production run warp-free from the first lot without veteran operators' experience, supporting the shift to high-mix, low-volume corrugated box output amid operator retirements and labor shortages.
WHO IT HITSCorrugated box manufacturers running MHI-MS corrugated machines, especially plants facing retirements of veteran operators, gain a way to set machines automatically per paper type; the device is an add-on electrical control unit, so it applies to existing machines.
Summaries like this, every morning.
The device addresses a specific production problem: corrugated sheets are made by gluing two liner sheets and a wave-shaped medium sheet and drying them at high temperature, and differences in moisture between the front and back liners cause the sheet to warp. Because standard machine settings do not work across many paper types, skilled operators have adjusted machines by experience and intuition. MHI-MS says that know-how is getting harder to pass on as veteran operators retire and labor shortages bite, while domestic demand shifts toward high-mix, low-volume box production that conventional warp-control devices struggle to keep up with — including warping that changes over time.
The new unit pairs MHI-MS's warp-control technology with AI from Mitsubishi Heavy Industries' research institute. It continuously and automatically accumulates data on liner moisture, temperature and warp amount per paper type and learns the right machine settings, so the AI can predict settings that produce no warping. MHI-MS says this makes it possible to produce warp-free product from the first lot of a run.
The sales push rests on a long installed base: MHI-MS delivered its first corrugated machine in 1956 and has since supplied more than 300 units in Japan and overseas. The company says it will keep drawing on technology built across the Mitsubishi Heavy Industries group to meet market needs at home and abroad.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
Amphenol reported adjusted earnings of 80 cents per share, up 74% year over year, and revenues of $10.23 billi…

Lockheed Martin's AI Center (LAIC) applies RAGE — Responsible AI Governance and Evaluation — at multiple tollg…

Analog Devices, collaborating with Nvidia on AI data-center infrastructure, physical AI and edge robotics, ran…

Charles Schwab is expanding AI tools for registered investment advisors, integrating Claude for Financial Advi…

Octus says it routes more than 20 billion tokens a year through its data science models, using what it calls a…

T-Mobile beat forecasts and set out a mid-term plan covering an AI build-out and a pay-out
