TECH TALK
article in Ars Technica, NASA is working on developing algorithms related to anomaly detection and incident precursor identifi cation, and it began gathering commentary from industry on its approach. The expected end-game here is that the analytics being developed by NASA is that the AI can discern patterns of anomalies in-fl ight data that could identify systematic issues with commercial aircraft.
MRO
The aftermarket support area has seen much investment from software companies, airlines/operators and MRO providers in developing proactive means to identify problems, all to forestall issues leading to an unscheduled aircraft on the ground situation. There are many solutions off ered over the years, and they have evolved as more data is captured on aircraft, engines, and parts lifecycles and tracking. AI-based predictive analytics have emerged to help determine the maintenance needs of various parts of an aircraft, attempting to predict failure before it happens. The rewards for getting this right (or almost right) is massive, and this can reduce aircraft support costs and related expenditures (parts inventory, maintenance personnel costs, and outsourcing costs). In 2017, Airbus announced a new
aviation data platform, Skywise, in collaboration with Palantir Technologies, which is one of the earlier pioneers in big-data integration and advanced analytics. Skywise is designed to bring together data from disparate sources across the industry, such as work orders, component data, spares inventories, aircraft and fl eet confi gurations, aircraft onboard sensor data and
fl ight schedules, and present all of this in a user interface to a cloud- based platform. The software will be confi gured to use data which may not have been so easily reached in the past and get around the usual ‘islands of data’ problem which all industries and companies face. Skywise aims to bring together all of this information and assist airlines with “improved fl eet operational reliability through predictive & preventative maintenance; improved operational effi ciency for legacy fl eets; rapid root-cause analyses of in-service issues; optimizing each aircraft’s performance through fl ight operations data analytics; tracking maintenance eff ectiveness over time, and one-click reporting workfl ows, including complex reporting to regulatory bodies.” Delta is the fi rst major U.S. carrier to sign a multi-year agreement with Airbus to use the Skywise open- data platform and related predictive maintenance services. Delta will use Skywise for tracking and analyzing operations and performance data for its Airbus A320 / A330 aircraft to assess the failure probabilities of aircraft parts to anticipate maintenance tasks before an issue occurs. A startup named SparkCognition has been working with Boeing and the USAF on predictive maintenance and troubleshooting activities. SparkCognition’s AI solutions aim to warn of aircraft-related failures before they occur, and they work across multiple industries, so have an interesting perspective on identifying events. They use natural language processing to reduce troubleshooting time by automatically classifying fault codes and recommending best corrective actions, as well as capturing the previous experience of mechanics.
FINALLY There are hundreds of examples of how Artifi cial Intelligence and machine learning are changing the business of aviation, and we tried to capture a few of them here. Suffi ce it to say that the industry is moving forward much quicker than many could have ever thought in regard to automating decisions and operational tasks. The next twenty years could prove to be among the most interesting ever for not only the industry but the world. We have new types of aircraft and propulsion either entering the market or not too far away. We have more customer-facing changes in how we manage our travel needs, and in how airlines/operators will maintain and support their fl eets. And under the hood, everything which was once a core part of airlines, OEMs and MROs will be nearly completely changed.
John Pawlicki is CEO and principal of OPM Research. He also works with Information Tool Designers (ITD), where he consults to
the DOT’s Volpe Center, handling various technology and cyber security projects for the FAA and DHS. He managed and deployed various products over the years, including the launch of CertiPath (with world’s fi rst commercial PKI bridge). John has also been onic FAA 8130-3 forms, as well as in defi ning digital identities with PKI. His recent publication, ‘Aerospace Marketplaces Report,’ which analyzed third-party sites that support the trading of aircraft parts, is available on
OPMResearch.com as a PDF download, or a printed book version is available on
Amazon.com.
26
DOMmagazine.com | apr 2019
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68
