AI helps Army with Stryker maintenance

As part of a 2016 pilot project, the Army Materiel Command's Logistics Support Activity worked with IBM and its Watson artificial intelligence platform to help identify maintenance problems in Stryker combat vehicles before they occurred.

Sensors were installed on 350 Stryker vehicles, and Watson ingested and analyzed maintenance manuals and work orders to create a comprehensive maintenance picture. With that information, the system was able to flag anomalies and predict when components in the vehicles were likely to fail. That information helped the Army more easily spot and track problems in the field and limit the number of breakdowns that took vehicles out of operation.

With the massive volume of information Watson analyzed, the Army could set up maintenance for individual vehicles rather than sending them in groups for scheduled maintenance. It was a kind of "personalized medicine for each vehicle," Sam Gordy, general manager of IBM U.S. Federal, told GCN.

That approach could also help other agencies that maintain vehicle fleets, such as the U.S. Postal Service, he added.

Maintenance data gleaned from IoT-connected vehicles could save manufacturers and agencies time and money because they would know what parts to keep in inventory for likely repairs, said Chris O'Connor, general manager of IoT offerings at IBM, during a July 25 Connected Government event hosted by FCW.

The sensors used in the Army Stryker test were designed for that maintenance application, but many third-party IoT sensors and devices are making their way onto home, factory and city networks, which might open users to security vulnerabilities. That's why the National Institute of Standards and Technology is working with the Department of Homeland Security to develop an engineering framework to enhance the cybersecurity resilience of IoT devices.

But Brian Done, deputy CTO at DHS' Office of Cybersecurity and Communications, said more work must be done to secure current devices.

Although some companies are working to address concerns related to possible attacks on their IoT devices, Done said they do not come close to alleviating the concerns of DHS officials.

Jeffrey Voas, a computer scientist at NIST, said he is concerned about what could happen to IoT-connected medical devices. For instance, malicious actors could demand ransom payments to unlock "the data on your insulin pump versus the data on your computer," he added. "I hope that this all doesn't start to come together with the medical world."

The National Telecommunications and Information Administration recently released guidance to help IoT device manufacturers better communicate with consumers about the security features of their products and whether they can be patched or upgraded.