BETA
This is a BETA experience. You may opt-out by clicking here
Edit Story

A Real Need For Big Data: Preventing Airline Equipment Failures

SAP

By Christopher Koch, Editorial Director, SAP Services Marketing

For the past few months, I’ve been looking for stories about how big data can bring changes that would actually transform something meaningful—a function, a business model, an industry. I’ll be reporting more about this over time, but I think I’ve found the first one: airlines.

Waiting for the wrench

Turns out that airlines are essentially flying blind when it comes to keeping their expensive planes in the air. As passengers, we all have an arsenal of war stories of being trapped on the tarmac due to a “maintenance issue.” It’s little wonder that airlines are tied with newspapers for the lowest customer satisfaction score among 47 industries tracked by the American Customer Satisfaction Index.

Inefficient operations are more than a customer service nightmare. Air carriers lose a whopping $10,000 for every hour spent on the ground performing maintenance, repair, and overhaul (MRO). That inevitably shows up as checked baggage fees or pay-for-your-peanuts policies that further aggravate the flying public.

Even more importantly, inefficient maintenance operations create safety hazards. The U.S. Office of Special Counsel recently chastised the Federal Aviation Administration for years of inattention to “lax airline maintenance.” Then there’s the wasted fuel and pollution caused by poor maintenance information.

Data in real time would help

Equipment problems don’t have a schedule—they can happen at any time. But most airlines aren’t prepared to deal with the unexpected. That’s because they use overnight batch processing to track MRO. That’s tolerable for routine maintenance, but does little to address issues such as an unforeseen engine fault, or a tire that wears out prematurely.

Ironically, the planes have become smarter than the backend computer systems that support them. The latest generation of aircraft produce loads of data—several terabytes on a single transatlantic flight—that could streamline maintenance operations, decrease fuel consumption, improve safety, and increase customer satisfaction.

How to paint a more complete picture

Trouble is, that’s just the beginning of the data. Besides the plane itself, the other sources include the airline, aircraft manufacturers, external maintenance providers, regulators, and spare parts suppliers. Some of the data are structured (e.g., held within a database) but a significant subset—a pilot’s handwritten logbook entries, a technician’s notes—is unstructured.

What’s needed is a way to gather all the data coming from the ground and the air together and keep it fresh—not just for individual aircraft but for the entire fleet. If airlines had access to all that data at once, maintenance planning could happen in real-time.

For example, a maintenance planner could download a defect notification from a plane as it occurs and have the maintenance crew and replacement parts ready by the time the plane pulls up to the gate. Even better, airlines could eventually use the data to predict and take action before the problem occurs.

So the next time you feel the plane grind to halt before it’s even taxied to the runway and you hear the captain come on the intercom, know that there really is something they could have done about this.

Follow me on Twitter @ckochster