The value of predictive maintenance is already well recognized by the biggest players in the industry. For instance, Airbus’s Aircraft Maintenance Analysis (Airman), used by 106 customers, constantly monitors health and transmits faults or warning messages to ground control, providing rapid access to maintenance documents and troubleshooting steps prioritized by likelihood of success. Meanwhile, Boeing’s Airplane Health Management (AHM) is used on 2 000 aircraft for 53 customers. Experts estimate such approaches can increase aircraft availability by up to 35%. However, unlocking the secrets of big data in commercial aviation is still to be tackled.
Harnessing and leveraging big data has lately become one of the most heavily discussed topics within the industry. More and more operators and maintenance providers become interested in using it to boost efficiency and spot issues before they become problems. Recently, GE Aviation has announced its plans of increasing investment in big data analytics to flag potential engine performance trouble spots and has used some of this learning to revamp its engine support portal. The data push follows parent company GE’s investment in a group-wide facility employing 1 100 data scientists who specialize in identifying signatures in big data flows. Reports claim that adopting predictive maintenance through the use of data analysis can reduce maintenance budgets by 30-40%. Yet ways of thinking and business processes also must change.
“In commercial aviation there’s huge potential for using data to enable everything from predictive analytics to greater inventory optimization and better monitoring of health of equipment in real-time. But so far there has been little in the way of answers for its key uses, or more importantly, the means of identifying which data is useful, and which is not. By providing key data around asset failures, this can then be integrated into logistics systems to help inform and improve future designs, in order to optimize usage and lower the total life cycle cost,” comments Zilvinas Sadauskas, the CEO of Locatory.com.
Most carriers already collect and share data through a Flight Operations Quality Assurance (FOQA) or other flight data monitoring system. The real opportunity, however, is leveraging such programs as more than safety-improvement tools. For instance, having performance parameters could help their technical services team troubleshoot problems more quickly and accurately, which translates into safely keeping aircraft in service without resorting to costly manual inspections.
A recent incident with FlyBe’s Q400 provides a great example of such an approach. During one of the landings, the aircraft touched down hard enough to jar the passenger oxygen masks from the ceiling – an incident, which was written up as a possible hard landing. Normally, the aircraft would be pulled from service and given an examination by mechanics with input from the manufacturer. However, this aircraft was equipped to offload data automatically. So, after examining a number of parameters, such as the descent rate, the airline determined the incident was not a hard landing. As the manufacturer agreed, the aircraft was soon put back in service, thus sparing the carrier the cost of ferrying a replacement aircraft and mechanics to the scene.
“Lack of data is usually not a problem. Carriers already use this data for flight-monitoring, as required by regulations, and some could also be used for predictive maintenance. However, while OEMs, MROs and operators all have aspects of this data, not all the information has the same relevance. For instance, different information has been shown to have a different level of correlation to spare parts forecasting. Additionally, the data is not consistently shared across the value chain, which could greatly enhance its performance. Therefore, it is essential that strong trust is built up between the MRO and the flight operations, engineering and technical departments of an airline in order to really put it to good use,” concludes the CEO of Locatory.com.