When milliseconds matter: Building smarter, safer manufacturing

Optimizing processes and reducing downtime

Shah, Vice President of Applied AI and Products, oversees manufacturing analytics at Georgia-Pacific. He and his team of more than 70 employees scrutinize manufacturing data to spot inefficiencies. From plywood to corrugated boxes to paper napkins, Shah and his team run more than 30,000 machine learning models to calculate the optimal production settings. Even tiny adjustments can add up to millions in savings.

“SAS advanced analytics allows us to balance speed and quality to maximize profitability,” Shah says. “We’re constantly pushing the envelope of what’s possible with analytics.”

Shah and his team also use these tools to prevent downtime. They use real-time data from 85,000 vibration sensors to intervene early when models predict increased likelihood of process anomalies. By combining this information with historical asset performance, models provide automated reports and alerts that help machine operators and supervisors bundle repairs into planned maintenance events. Repairing machinery in a controlled environment helps technicians operate more safely and efficiently and reduce downtime.

Bakalar, Vice President of IT and Digital Transformation, underscores the impact, “We’ve seen great results in productivity, efficiency, yield and reduced downtime. There’s no way we could have achieved this without the robust capabilities provided by these tools.”

Additional AI innovations at Georgia-Pacific include:

• A process automation project that saves money by reusing and recycling expensive chemicals required for the manufacturing process.
• Supply chain innovations that improve product delivery to retailers.
• Autonomous guided vehicles and computer vision projects that improve quality and efficiency throughout the manufacturing process.
• Combining SAS Event Stream Processing with sophisticated computer vision algorithms in SAS Viya to improve employee safety.

Edge intelligence for scalable model deployment

The “build once, deploy anywhere, manage centrally” capability of SAS Event Stream Processing has become a strategic advantage. “With AI innovations, we can deploy thousands of models within minutes,” Shah says. “This quadruples our productivity. What previously took weeks or even months is now measured in hours or minutes. This solution enables us to implement sophisticated machine learning models right next to sensors, achieving real-time responses in less than 200 milliseconds.”

Rapid analysis quickly improved product quality by spotting manufacturing anomalies, safeguarding the company’s bottom line and reputation.

Open-source compatibility further amplifies these benefits. Georgia-Pacific’s data scientists can seamlessly integrate models built in Python or R into the SAS environment, speeding up innovation.

Empowering frontline employees and saving millions of dollars

Flexibility is a core reason Georgia-Pacific selected SAS Viya. Not only can data scientists code in multiple languages, but it also means that people who aren’t necessarily analytics experts can benefit from the powerful technology.

With infinite analytics projects and finite resources, Georgia-Pacific believes in empowering citizen data scientists – people who create analytical models, but whose primary job functions are outside the field of analytics. Georgia-Pacific has many employees with deep domain knowledge but little analytics experience. With the simple user interface and automated AI of Viya, anyone with a curious mind can be trained to make faster, better decisions.

“We also have a strategic partnership with AWS, and the combination of SAS with AWS provides us the necessary flexibility and scalability to put analytic capabilities in the hands of users across the organization,” Bakalar adds.

Coyne details the transformative nature of this integration: “ChatGP combines structured and unstructured data, creating a single, centralized hub for anomaly detection, predictive analytics and immediate corrective actions.”

The philosophy behind this success is simple, “No company succeeds with analytics unless they adopt a crawl, walk, run approach – meaning you fail fast, learn faster and innovate continuously,” Coyne says.

For Georgia-Pacific, SAS isn’t just software. It’s the intelligence enabling foresight, transformative operational efficiency and unparalleled safety. Underpinning all these technological advancements is the deep trust and collaborative spirit between Georgia-Pacific and SAS.

Shah sums it up, “SAS delivers more than technology – more than that, SAS brings a level of partnership we can trust. Quite often, their answer is ‘I don’t know, but we can work on it together and figure it out.’ To be honest, that’s a breath of fresh air.”

Together, Georgia-Pacific and SAS are crafting the future of manufacturing.