Zarembski is recognized worldwide for his expertise in railway engineering, including track system analysis, railway component failure analysis, track strength, and maintenance planning. He is a pioneer in the use of “big data”—gathering, analyzing, and efficiently converting large volumes of complex data into useful information—in railroad engineering. Under Zarembski’s leadership, UD is a partner, along with Virginia Tech, on a five-year Tier 1 University Transportation Center (UTC) program awarded in 2016 to the University of Nevada at Las Vegas for “Improving Rail Transportation Infrastructure Sustainability and Durability.”
This partnership has allowed Zarembski to expand UD’s Railroad Engineering and Safety Program and upgrade its research capabilities. Now Zarembski and his colleagues are using big data to forecast the longevity of railroad tracks, an important question since it would cost about $100 billion to replace all the tracks in the U.S., said Zarembski. Several railroad companies are providing data for UD engineers to analyze.
The rise of big data in rail engineering
For the past four years, Zarembski has organized the international Big Data in Railroad Maintenance Planning conference, held annually at UD. This conference brings together railroad experts from academia and industry to discuss maintenance planning and techniques for big data analysis. Some presentations are theoretical; some are practical.
“This conference has grown in the quality of papers, quality of speakers, and level of interest of attendees every year,” said Zarembski.
The most recent conference, held Dec. 14 and 15, was the largest yet, with 220 international registrants.
When the Big Data in Railroad Maintenance Planning conference started four years ago, speakers shared their plans to use big data. In 2017, they shared how they have used big data to improve efficiency and safety. Some participants now have titles such as “director of big data” or “chief data scientist.” The conference has also expanded beyond track engineering, including railroad experts in issues such as locomotive performance and maintenance.
The keynote speaker was Wick Moorman, [past] president and CEO of Amtrak, who described how the company has benefited from the use of data sciences. The Northeast Corridor’s railroad tracks contain more than 1,500 curves, which were traditionally surveyed manually by inspectors with printed charts. Now, rail cars outfitted with sensors collect data, which can be rapidly updated and used to calculate safe speeds. This is a case where big data could save lives.
“The two big derailments we’ve seen in recent years happened with unsafe speeds around curves,” said Zarembski.
Zarembski and co-organizer Nii Attoh-Okine, a professor of civil and environmental engineering who recently published Big Data and Differential Privacy: Analysis Strategies for Railway Track Engineering, a book on big data analysis in railway engineering, are already building the lineup for the 2018 event, which will be held in December.
In addition to teaching undergraduate and graduate courses in railroad engineering and safety, Zarembski also shares his expertise through UD’s Graduate Certificate in Railroad Engineering and short courses in collaboration with Professional Engineering Outreach. Next up: Operations & Operations Management for Passenger Rail on March 7 and 8. Registration is open until Feb. 28.
About Allan Zarembski
Prior to joining UD in 2012, Allan Zarembski was the president of ZETA-TECH Associates, Inc. He also served as Director of R&D for Pandrol Inc., Director of R&D for Speno Rail Services Co., and Manager, Track Research for the Association of American Railroads. He received his doctoral degree in civil engineering from Princeton University in 1975.
Editor’s Note This article originally appeared on the University of Delaware website’s UDaily section. Dr. Zarembski is a frequent contributor to Railway Age, Railway Track & Structures and International Railway Journal, and a speaker at many Simmons-Boardman Railway Division conferences.