Georgia-Pacific Reduces Unplanned Downtime by 30% While Improving Quality and Safety with SAS Viya and AWS

Georgia-Pacific, headquartered in Atlanta, Georgia, is a leading pulp and paper company that operates 140 production facilities. During the height of the COVID-19 pandemic, sales of its essential products such as paper towels, disposable napkins, and toilet paper surged significantly. As the global supply chain grappled with unprecedented demand, the company recognized the urgency to optimize manufacturing productivity and get more of its key products into stores as quickly as possible.

In collaboration with AWS Partner SAS, Georgia-Pacific deployed a solution using SAS real-time advanced analytics and artificial intelligence (AI), which are powered by SAS Viya on AWS. This implementation has enabled Georgia-Pacific to streamline its operations and cut unplanned downtime by 30 percent.

The beginning of the pandemic quickly led to two unique situations for Georgia-Pacific. On one hand, store shelves became empty, with manufacturers worldwide struggling to replenish stock. At the same time, restaurants, hotels, and corporate offices were closing—either temporarily or permanently—and demand in those sectors sank.

As stock replenishment continued to be problematic, on-time and in-full (OTIF) delivery also posed challenges, with many prominent retailers imposing harsh fines for delayed or partial shipments. "At that point, getting more products into stores faster and optimizing shipping logistics became our top priority," remarked Steven Bakalar, VP of IT digital transformation at Georgia-Pacific. "We knew that having better insight into our data would be key to improving productivity, so we focused our efforts on finding a solution that could make that happen for us."

To improve productivity and distribution, Georgia-Pacific implemented SAS Viya solutions running on Amazon Web Services. The SAS Viya AI and analytics platform powered by AWS Partner SAS provides end-to-end process automation for accessing and integrating data from disparate sources. Leveraging AI and machine learning, it builds predictive models that provide actional insights to fuel better decision-making.

Georgia-Pacific chose SAS Viya because of its versatile and user-friendly interface, which accommodates users across the spectrum, from novices to seasoned data scientists. “We also have a strategic partnership with AWS,” Bakalar said. “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.”

To get products into stores rapidly, Georgia-Pacific used SAS Viya’s advanced analytics, running more than 15,000 machine learning models to determine ideal production settings. “The advanced analytics enabled by SAS allow us to find the optimal balance of speed and quality to maximize profitability,” says Roshan Shah, vice president of collaboration and support center operations at Georgia-Pacific. “We’re constantly pushing the envelope of what’s possible with analytics.”

With the SAS Viya solution in place, Georgia-Pacific was able to reduce unplanned downtime by 30 percent across its production facilities. Utilizing real-time data from 85,000 vibration sensors, the company's manufacturing teams could proactively tackle potential issues, such as part failures or electrical problems. By referencing historical asset performance data, machinery operators fine-tuned processes, enhancing asset performance. Furthermore, the teams gained 10 percent increase in overall equipment efficiency (OEE).

The SAS automation capabilities alerts potential equipment failures, allowing Georgia-Pacific to incorporate repairs and replacements into its scheduled maintenance. This helps prevent safety incidents, inefficient machinery operation, and unanticipated production interruptions. “SAS gives us the structure we need to be successful with deployment and keeping this running in production,” said Sam Coyne, director of AI at Georgia-Pacific. “And with that structure comes resiliency, sound architecture, and confidence in a stable platform—which is critically important for us as manufacturers.”

Georgia-Pacific benefits from the Amazon Elastic Compute Cloud (Amazon EC2) which provides secure, adjustable computing power in a cloud environment, ensuring access to a reliable and scalable infrastructure as needed. The SAS Viya solution employs Amazon Simple Storage Service (Amazon S3) to provide Georgia-Pacific with a robust storage solution that offers industry-leading scalability, availability, security, and performance. Furthermore, it utilizes Amazon Elastic Kubernetes Service (Amazon EKS), a managed service that simplifies running Kubernetes on AWS and on premises.

Georgia-Pacific also employs the computer vision capabilities of SAS solutions to address paramount issues of quality and safety in manufacturing. The system provides automatic notifications when parts exhibit signs of wear, enabling proactive maintenance. This not only ensures the safety of technicians, but also promotes efficient operations.

Moreover, Georgia-Pacific utilizes computer vision models to oversee product quality on conveyor belts, notifying operators and automatically discarding defective materials. This integration of computer vision, deep learning models, and diverse neural networks also enables the company to efficiently detect unauthorized presence in restricted zones.