The world’s largest glass firm, AGC, makes glass for almost all the things, from “skyscrapers to microwave windows, automobiles, and everything in between,” mentioned Bradley Willson, electrical engineer for AGC Glass North America. The firm has amenities around the globe and has been optimizing operations at its float glass manufacturing operations in Spring Hill, Kan., Richmond, Ky., and Church Hill, Tenn., utilizing OSIsoft’s PI system for manufacturing information analyses. (Editor’s observe: At press time, Aveva had simply introduced its pending acquisition of OSIsoft. Read extra at http://awgo.to/bSDYc.)
AGC Glass North America has been utilizing OSIsoft’s PI System since 1996 to assist make sense of its manufacturing information. But whereas attending a current PI World occasion, AGC realized about PI’s transfer from information historians to a knowledge infrastructure, giving AGC new concepts for enhance its manufacturing operations.
AGC has been utilizing PI merchandise resembling ProcessBook, DataHyperlink, and Manual Logger to assist visualize information from PI historian servers and create reviews. These instruments are largely used for course of tuning of PID loops to verify they’re performing optimally. Now the corporate is “migrating towards OSIsoft’s new product, PI Vision, to build out our asset framework, create notifications, develop complex analyses, and integrate with our ERP system,” Willson mentioned.
PI Vision allows customers to investigate information in quite a lot of methods on any gadget. It can import graphic course of monitoring shows created by PI ProcessBook, for instance, and permit them to be seen in an online browser. It additionally helps cellular browsers and customised views for small-screen units to allow easy accessibility from anyplace.
Monitoring a number of processes
AGC makes use of PI instruments to observe its intense manufacturing course of. “This furnace is capable of melting roughly 600 tons of batch per day. And it’ll hold up to 1,700 tons of molten glass within the tank. It is a natural gas furnace that consumes roughly 120,000 cubic feet of natural gas per hour,” Willson mentioned. “The interior temperature of the furnace reaches roughly 3,000°F, and this furnace has been constantly melting batch 24 hours a day, seven days a week for 15-20 years.”
AGC screens about 1,500 information factors on every of its float strains. It additionally screens auxiliary processes all through its manufacturing amenities, resembling its sputter coating line, which produces high-efficiency glass by way of the appliance of a metallic movie added to glass surfaces. Likening the method to how ships cross by way of the Panama Canal—however decreasing air strain as an alternative of water degree—Willson defined how the glass will get transferred from chamber to chamber about each 20 seconds. “Once the glass reaches roughly 10-6 mbar, it gets transferred into the sputter coating compartments,” he mentioned. “Here, we inject argon and oxygen into each compartment and then ignite a large DC plasma field inside the compartment. The plasma grabs atoms of material from the precious materials, bounces around inside the compartment, and then deposits those precious materials onto the top surface of the glass.”
At AGC’s U.S. manufacturing amenities, information from varied automation units are despatched to the PI Vision Data Archive server through OPC and a relational database administration system, and from there into the PI Asset Framework server. Both of these servers are situated on premise at every website. At this level, a centralized, cloud-based PI Vision information server gathers information from every of the Asset Framework servers for additional evaluation.
The Richmond website stands aside from the opposite two amenities utilizing these PI applied sciences as a result of AGC is experimenting with machine studying there. “We’re using the PI OLEDB interface to push data up into the Amazon Web Services (AWS) cloud, where we’re doing some complex analyses and pushing data out through the clients via Tableau (business intelligence and dashboard software),” Willson mentioned.
Implementing new instruments
The shift to PI Vision has delivered new instruments for AGC’s analytics. Willson’s favourite, he mentioned, are the e-mail notifications. “You set these notifications up once and then PI does the rest of the work,” he mentioned. “It’s completely automated and, most of the time, these emails get sent out even before the operator notifies maintenance that there’s a problem. This helps reduce the amount of downtime and production outage.”
The Greenland facility in Church Hill has begun so as to add preemptive notifications as effectively, which might inform them when a course of is beginning to exit of tolerance and notify the workforce to take motion earlier than it turns into a difficulty.
PI Vision additionally allows manufacturing reporting, making it simple to match, for instance, what will get loaded in with what will get loaded out of a coater. “[We] can see how many square feet was loaded into the coater per hour, how many square feet of glass was loaded into the coater by shift, and how many square feet of glass was actually packed on the unload end,” Willson mentioned. “This could be expanded to a complete material balance as well.”
PI Vision can be getting used for troubleshooting. Willson defined how the software program was capable of uncover a seven-year development by which the temperature on a melter backwall was slowly rising. Without the long-term trending functionality, the adjustments would’ve been too small to note. “Due to this long-term trending [capability], we were able to identify that we had a problem, trace the events back to the start, and then install countermeasures to verify that the problem had been corrected—ultimately reducing downtime,” Willson mentioned. “In this example, we estimated that we would’ve had a two-week downtime if we had not noticed that the backwall was heating up. And that equates to roughly $2 million worth of downtime plus materials and labor.”
AGC plans to proceed exploring the extra instruments obtainable in PI Vision, with a plan to maneuver progressively towards preventive reasonably than reactive upkeep. “I’ve seen some really neat use cases for event frames, so I want to learn more about those. And we’re going to continue developing new analyses,” Willson mentioned. “We’ll continue to develop additional PI Vision screens. And then we’re going to begin rolling out these PI tools to our other facilities.”
The amenities additionally plan to proceed their efforts with machine studying, utilizing AWS and Tableau to make even higher use of the info.