'Techno' logical solutions

University research center targets factory downtime with 'predictive intelligence'

Breakdowns of industrial machinery cost companies millions of dollars each year, with most of the cost resulting from lost production time while performing unscheduled repairs or maintenance.

The problem has manufacturers working with researchers in Wisconsin and Michigan to develop cost-effective technology that predicts when machinery needs maintenance, long before a breakdown occurs.

The research also will produce electronic tools to help customers make decisions about how to handle potential problems, and allow them to monitor performance of equipment simply by walking by with a Palm Pilot or cell phone.

Such innovations are taking shape at the Center for Intelligent Maintenance Systems (IMS), a joint research center of the University of Wisconsin-Milwaukee (UWM) and the University of Michigan.

 The universities recently received a five-year grant from the National Science Foundation that supports the work of the IMS Center and its industrial member partners, and designates it as an NSF Industry/ University Cooperative Research Center. Located in Milwaukee’s Cozzens & Cudahy Research Center, the center is developing software and other computing solutions that aid in predictive maintenance. IMS also is researching remote monitoring and Web-enabled agents to achieve near-zero-breakdown conditions on the factory floor.

It’s a project that joins business and science in the name of reliability. Led by Jay Lee, a global authority on e-manufacturing and e-maintenance research, the center already has more than 40 companies as member partners.

The center’s first innovation — intelligent software called the Watchdog Agent — can be embedded in a product or machinery to allow continuous assessment. It essentially serves as a digital doctor, alerting operators of changes, or degradation, through a wireless device or over the Internet.

Along with prognostics, the center is developing Web-enabled agents to track status information and maintenance history of equipment and then store it in an e-service data warehouse. The center also is generating “data mining” models that, using stored data, will proactively predict customer service solutions. Also in the works is a Web-enabled platform that makes monitoring equipment possible from anywhere in the world.

Information related to degradation is accessible in real time online and, if a problem is apparent, the self-diagnosing system will directly contact a service provider.

The collaborative research is being integrated into a test bed at the Citation Custom Products plant in Milwaukee, a major supplier to Ford Motor Company.

Intelligent maintenance has a variety of applications and is already used in the transportation industry, says Lee.

Lee asserts that two significant business and industrial trends make research into such systems critical.

“The growth of e-commerce and use of the Internet has injected a velocity into industry and societal interactions that allows little room for downtime,” he said. “So much is being done at the last minute, and being done quickly, that any breakdown in the chain will have a major impact.”

He also cited the aging of many existing products and facilities (40-year-old aircraft, 50-year-old public facilities and infrastructures), along with the aging and retirement of the senior and most experienced members of the workforce, as driving new approaches to maintenance and upkeep.

This article appeared in the June/July 2002 issue of MRO Today magazine. Copyright, 2002.

back to top

back to Manufacturing excellence archives