Helios, SUN Automation Group’s new AI and machine learning platform tailored specifically to the corrugated converting industry, launched today.

The platform is OEM-agnostic and engineered to provide corrugated manufacturers access to insights into the performance of their machines – reportedly enabling minimized downtime, optimized maintenance schedules, and maximized profit.

“IIoT makes every bit of data actionable,” says Helios’ director of technology, Matthew C. Miller. “So many corrugated plants rely on human intuition and experience to drive their decisions.

“With Helios, anomalies that are imperceptible to even the most well-trained operators can be detected in real-time and acted upon. And the machine learning capabilities will mean that the platform only gets smarter the more data and user reactions that it is able to process.”

The new platform is designed to minimize downtime, maximize profitability, and decrease the opportunity costs associated with only taking machines offline for preventative maintenance (as opposed to for major malfunctions).

Other features include preventative/proactive parts ordering, knowledge about the exact time and cost of parts replacements, the ability for operators to pinpoint the source of slowdowns and other issues, and operator-efficiency training to help machine operators learn and adapt to best practices.

"We understand that data is only as powerful as the actionable insights it can provide,” says Chris Kyger, president of the SUN Automation Group. “That's why we are so excited to bring Helios to the corrugated industry. This incredible technology will help box plants increase productivity and efficiency while reducing costs and downtime.”

Helios provides core insights from an accessible, user-friendly dashboard enabling three key benefits: remote monitoring, predictive maintenance, and anomaly detection.

Remote monitoring provides deep insights into current and historical machine operation and performance that can be seen and accessed in real-time from any device. Meanwhile, predictive maintenance optimizes machine maintenance intervals using artificial intelligence that adapts based on the machine operation and usage.

Anomaly detection notifies users about abnormal machine states that allow operators to react to a potential issue before the failure occurs. The company says that more robust predictive analytics will be phased into the platform over time.