OEM : Nonmetallic Mineral
Corning is one of the world’s leading innovators in materials science, with a 169-year track record of life-changing inventions. Corning applies its unparalleled expertise in glass science, ceramics science, and optical physics, along with its deep manufacturing and engineering capabilities, to develop category-defining products that transform industries and enhance people’s lives. Corning succeeds through sustained investment in RD&E, a unique combination of material and process innovation, and deep, trust-based relationships with customers who are global leaders in their industries. Corning’s capabilities are versatile and synergistic, which allows the company to evolve to meet changing market needs, while also helping our customers capture new opportunities in dynamic industries. Today, Corning’s markets include optical communications, mobile consumer electronics, display, automotive, and life sciences. Corning’s industry-leading products include damage-resistant cover glass for mobile devices; precision glass for advanced displays; optical fiber, wireless technologies, and connectivity solutions for state-of-the-art communications networks; trusted products to accelerate drug discovery and delivery; and clean-air technologies for cars and trucks.
How Corning Built End-to-end ML on Databricks Lakehouse Platform
Specifically for quality inspection, we take high-resolution images to look for irregularities in the cells, which can be predictive of leaks and defective parts. The challenge, however, is the prevalence of false positives due to the debris in the manufacturing environment showing up in pictures.
To address this, we manually brush and blow the filters before imaging. We discovered that by notifying operators of which specific parts to clean, we could significantly reduce the total time required for the process, and machine learning came in handy. We used ML to predict whether a filter is clean or dirty based on low-resolution images taken while the operator is setting up the filter inside the imaging device. Based on the prediction, the operator would get the signal to clean the part or not, thus reducing false positives on the final high-res images, helping us move faster through the production process and providing high-quality filters.