Yesterday, in his post Rearming the Supply Chain, Matthew Brodsky shared a recent conversation he had with Jeff Scott Miller, vice president of Defense Supply Chain Solutions at Accenture Federal Services, which is helping the US Department of Defense with some predictive analytics. The Air Force, Brodskey writes, is using modeling for airplane maintenance. He quotes Miller's explanation for the usage: "They don't want planes falling out of the sky."
Well, thank goodness for that! I was glad to read that the Air Force is keen on keeping its pilots, crew, and other military personnel safe as they fly from point A to point B. But as a civilian, I must confess to being even happier to hear that commercial airlines want the same predictive capabilities for their fleets.
NASA is lending a helping hand toward these efforts, as I learned during a presentation last week at The Innovative Enterprise Ltd.'s Big Data Innovation Summit in Boston. According to Ashok Srivastave, the agency's principal scientist leader, NASA is analyzing data coming off of planes to study safety implications -- an effort that will ultimately help commercial airlines improve maintenance procedures and head off equipment failure.
"The work that we're doing in big-data has implications for anybody who flies on an airplane," he said.
And big-data it is. According to Srivastave, while in flight, an airplane records data at a rate of about 1,000 parameters per second. Some of the numeric data is continuous, while some of the data is discrete, telling how the pilot is working the aircraft. Flight and ground crews also write narrative reports, so NASA must examine text data, too.
Consider the roughly 10 million domestic flights annually, toss in radar and weather data -- and, well, you can see that "big" might not really even be the appropriate adjective to describe the massive size of the datasets NASA is mining.
The good news, Srivastave said (and I agree), is that airlines have "an extremely safe system." On a worldwide basis, he noted, "we don't hear or see too many issues on aviation safety, which is really a remarkable accomplishment."
The bad news is that one safety failure on an aircraft can have catastrophic consequences, as in the case of the Air France flight that crashed in the Atlantic Ocean three years ago. Devastating results like this -- 228 people lost their lives on that fateful flight -- live long in the public memory. Wouldn't it be wonderful to diminish such possibilities to a negligible state?
The key is measuring and monitoring these aspects of aviation through big-data analytics, which NASA does through its open-source Multiple Kernel Anomaly Detection (MKAD) algorithm, Srivastave said. Using MKAD, NASA can determine if two continuous data streams or two networks are similar, and then analyze them using a single, unified framework. "If we can extract patterns," Srivastave told the audience, "that could pose a tremendous advantage and help everybody proactively manage risk."
Investigating yesterday's crash data, while important, isn't enough. "That's fighting yesterday's challenge," Srivastave said. "We want to move in the right direction... and figure out what's going to happen before it happens." He added that numeric and text data in the MKAD algorithm significantly improves the rankings of the monitored anomalies by as much as 7,000 points.
But what does this mean for you, me, and the rest of the flying public? By 2015, it will mean a lot.
NASA has partnered with Honeywell Aerospace to find methods for automatically discovering precursors to adverse events while an airplane is in flight. With big-data innovations, carriers would be able to carry out real-time detection of problems, diagnostics, prognosis (how long before the event turns into a real problem), and mediation, all while in flight. Honeywell, Srivastave added, can already predict about 30 flights ahead of an engine failure -- meaning a carrier would be able to mitigate the problem 30 flights ahead of time. "With even more big-data initiatives, that will go to 50 flights," he said.
"This is real data, and it's posing a very positive future for an awful lot of us that do a lot of flying," said Srivastave, noting that this capability is planned for insertion on commercial aircraft like the Boeing 777 and 787 in 2015. NASA's work, he added, filters down through the Federal Aviation Administration to carriers (except for Southwest Airlines, which has a direct relationship with NASA).
If you're interested in learning more about what NASA and others are doing with big-data analytics to improve safety, you might find this hour-long TV program of interest:
Are you comfortable flying today? Do you think you'll be more comfortable after data mining goes airborne in 2015? Share your thoughts below.
@tinym. Really a freak incident. I forget the details, but the family didn't realize the couple was missing as nobody had been expecting to hear from them or show up anywhere. So it was a shock to all.
@tinym -- especially tough to take since it took the recovery team something like a day or more to realize that a car was buried under the wreckage. So the story changed from "Whew, no loss of life," to "Oh, sorry, we made a mistake about that." You can imagine public reaction wasn't good.
tinym, unfortunately Union Pacific's use of predictive analytics, which the InformationWeek article you cite describes in this way, "UP would like to be able to predict when a wheel is going to fail weeks before it causes a 1.5-mile-long, 20,000-ton coal train running at 70 miles per hour to derail, risking lives, causing delays, and losing the company money. UP has been using technology to predict and prevent derailments for well over a decade," didn't work this summer in Chicago. A Union Pacific freight train derailed, a bridge collapsed, and the whole mess landed atop a car, and killed two people. As reported by Fox News (and many, many others):
"Burton and Zorine Lindner were driving under the railroad bridge about 1:45 p.m. Wednesday when the train derailed. Twenty-eight of the rail cars piled up on the bridge, causing it to collapse over a road between the suburbs of Glenview and Northbrook — twisted train cars and coal filling the gap where the bridge had been."
The Fox News report included a possible explanation:
"Temperatures soared above 100 degrees in the Chicago area Wednesday, and investigators believe the extreme heat may have caused a rail to expand and led to the derailment. The bridge collapsed under the weight of the toppled rail cars. Each one weighed 75 to 85 tons.
"That's what we're looking at the likely scenario," said Tom Lange, a Union Pacific spokesman.
And, Noreen, that what's learned through the analytics also gets incorporated into the automated systems navigating & flying planes today! It sounded to me as if a pilot would rarely encounter an inflight problem as those would be identified and fixed long before that state, thanks to the predictive analytics applied to big-data.
LEADERS FROM THE BUSINESS AND IT COMMUNITIES DUEL OVER CRITICAL TECHNOLOGY ISSUES
The Current Discussion
Visual Analytics: Who Carries the Onus? The Issue: Data visualization is an up-and-coming technology for businesses that want to deliver analytical results in a visual way, enabling analysts the ability to spot patterns more easily and business users to absorb the insight at a glance and better understand what questions to ask of the data. But does it make more sense to train everybody to handle the visualization mandate or bring on visualization expertise? Our experts are divided on the question. The Speakers: Hyoun Park, Principal Analyst, Nucleus Research; Jonathan Schwabish, US Economist & Data Visualizer
Dynamic data visualizations let analysts and business users interact with the data, changing variables or drilling down into data points, and see results in a flash. Advance your use of data visualization with tools that support features like auto-charting, explanatory pop-ups, and mobile sharing.
No doubt your enterprise is amassing loads of data for fact-based decision-making. Hand in hand with all that data comes big computational requirements. Can traditional IT infrastructure handle the increasing number and complexity of your analytical work? Probably not, which is why you need a backend rethink. Big data calls for a high-performance analytics infrastructure, as Fern Halper, a partner at the IT consulting and research firm, Hurwitz & Associates, discusses here.
Redbox's bright-red DVD kiosks are all but ubiquitous these days, located in more than 28,000 spots across the country. Jayson Tipp, Redbox VP of Analytics and CRM, provides an insider's look at how the company has accomplished its phenomenal nine-year growth.
InterContinental Hotels Group (IHG), a seven-brand global hotelier, has woven analytics into the fabric of its operations. David Schmitt, director of performance strategy and planning, shares IHG's analytics story and his lessons learned.
Elizabeth Barth-Thacker, a BI and informatics technology manager at Humana, tells us how her team is creating data transparency and building engagement with the business – with the help of an internal collaboration portal called Humanalytics.
Whether working in major league sports, financial services, or healthcare, analytics, and data, professionals are checking out how visual analytics and high-performance technologies can help them optimize their environments, shrink their cycle times, and improve decision making, as attendees at the recent SAS Executive Briefing in New York share with us.
Jim Davis, SVP and CMO at SAS, talks with us at a recent SAS Executive Briefing about how high-performance analytics and visual analytics take away the concerns over big-data and let companies get down to business with their data.