<img height="1" width="1" style="display:none" src="https://www.facebook.com/tr?id=1119659708214142&amp;ev=PageView&amp;noscript=1">
arrow2

Explained: Predictive maintenance & a transforming supply chain

Airlines and MROs alike are beginning to leverage large data sets and technological advancements to better predict and manage their maintenance efforts through a practice called predictive maintenance. But what exactly is predictive maintenance? And how can aircraft predictive maintenance benefit your supply chain and the aviation industry processes as a whole? We’ll take a closer look here.

Poor maintenance planning has real consequences for airlines— it keeps aircrafts grounded longer, passengers waiting, and can even lead to cancellations. Not to mention, an inaccurate overview of maintenance needs can lead to overstocking on parts you don’t even need – all in all leading to large sums of money lost.

While it’s a well-known fact that unexpected maintenance is costly and should be avoided, according to the multinational professional services network, PwC, 30 percent of total delay time in the aviation industry is still due to unexpected maintenance.

We present a panel of senior members in the aviation industry discussing the latest trends in predictive maintenance systems and data analytics for aviation and MRO, what they mean for the industry and how we can leverage them to achieve proactive, rather than reactive supply chains. Here’s the take aways. 

What is predictive maintenance for aircraft?

Predictive maintenance involves the use of information such as sensor data and maintenance logs to predict maintenance needs in advance, helping airlines carry out better maintenance planning. Making use of predictive maintenance can offer real and widespread advantages to companies who can best figure out how to leverage their data and reap the benefits. Over the last decade, a number of developments have laid the groundwork for predictive maintenance readiness: improved computational power, data storage capabilities as well as the overall amount of data and data parameters the industry can look to – thanks to the widely adopted use of sensors on aircraft and high-quality data routers. 

These advancements have allowed tools, such as machine learning – a form of artificial intelligence, in which computers learn to recognise advanced patterns through analysing large sets of data – to have applications in maintenance planning.

why-upskilling-02
READ MORE ABOUT:
Five emerging technologies that will change the MRO industry.

For Rhonda Walthall, a Technical Fellow in Prognostics & Health Management at UTC Aerospace Systems, this is what makes it such an exciting time for airlines suppliers and for aviation in general. 

»We’re moving away from just having data available from engines and engine components to now having a lot of data available for the aircraft components and systems besides propulsion,« she says, adding:

»For the first time, we’re really starting to get a lot of data on our components and how they’re performing and we’re starting to take that data and develop predictive analytics, so that we can understand when they’re about to fail and be able to predict the remaining useful life on that component.«

Why does predictive maintenance matter for aviation?

According to Micheál Armstrong, CEO of Armac Systems, demand for spare parts typically arises from one of four sources: planned demand, probabilistic demand, preventative and the newest form, predictive demand. 

The issue, he notes, is that around 80 percent of demand today is the probabilistic kind - reflected in RSPLs – but with the overwhelming number of parts that make up a plane, all with individually low demand, it would be nearly impossible to try to invest optimally. 

Aircraft called in for a service check by using best practices of predictive maintenance.

As a result, he explains, »We’re seeing removals of a little over 50 percent of what RSPLS were projecting.« 

This means only 50 percent of the parts anticipated to be used, were actually used. The problem gets even worse, though. On top of that, there are also removals of parts that weren’t anticipated at all.

This is why Armstrong is adamant that anything you can do to better plan demand will dramatically reduce your investment. As he explains it: »Predictive maintenance can turn unplanned into short-term plans.«

Rather than being caught completely off-guard by maintenance requirements, predictive maintenance can offer you around a 15-day heads-up. 

Predictive maintenance is transforming the supply chain

Predictive maintenance for aircraft can aid in determining the right moment to replace a part. This is critical because replacing too late can lead to unexpected failures, flight delays, cancellations, longer AOGs—not to mention, it can reduce asset availability. Replacing too soon, on the other hand, means forfeiting the benefits of the extended use. Further, more accurate maintenance planning can reduce your investments and inventory of the parts you don’t actually need. 

Just take it from Nicolas Kuhn, Head of Subcontracting at AFI KLM E&M. He’s been on the journey of implementing predictive maintenance at Air France, which began four years ago. Since then, he explains, they’ve been able to predict part failures up to 15 days in advance and the results have been stark: 

»The consequences on the supply chain are quite direct. We’re facing fewer AOGs on certain systems like the fuel system – we’re down to zero AOGs for unexpected removal for the last three years,« he says and continues:

»We reduced our inventory on-site because now we can anticipate the removal up to 50 percent and we have time to supply the airline.«

Use analytics to make the best use of predictive maintenance 

At the end of the day, the decision to implement predictive maintenance systems is the decision to fix a problem – the pain of cost. Ultimately, though, each aircraft type will have its own characteristics and problem components that tend to drive up costs and delays. The key is focusing your efforts on relevant signals that keep you ahead of failures.

But how do you focus your efforts?

According to Nicolas Kuhn, Head of Subcontracting at AFI KLM E&M, you need to focus your efforts on the components that have the greatest impact on your operations. For Air France’s A380 this was the fuel pump. 

How should predictive maintenance inform our processes? 

Once we develop predictive maintenance capabilities for aircraft, the question that often arises is – how should it influence we processes? Should we, for example, remove a part as soon as we know it’s about to fail, or should we wait until it actually fails, but have the part stocked for quick replacement? 

According to Kuhn, as soon as a forecast is made and the anticipated failure is confirmed, the parts should be booked in the system, and made available to line maintenance as soon as a maintenance slot is available.

why-upskilling-02
RELATED ARTICLE:
Predicting the unknown: The rise of PHM-solutions.

Can predictive maintenance be carried out on older aircraft?

When we talk about predictive maintenance for aircraft, we often speak of intelligent components that can give us better data. This lends itself to the idea that such systems might only be relevant to newer planes that smart components can be built into. This is not the case, though. 

Experts resoundingly agree that the savings that better data and predictive maintenance can offer vastly overwhelm the potential costs of the retrofitting that may be required to get adequate data out of older planes. 

However, as older planes slowly move out of service to make way for new-generation aircraft, it will be easier to attract data from the planes in the future, so the future is looking bright for predictive maintenance. 

Image of the e-book Five Must Know Insights for 2020 with a download button

How can predictive data affect end-customers? 

The impacts of predictive maintenance aren’t restricted to suppliers and airlines alone. The effects are rippling. Cost savings on maintenance will work their way up to the customers in a number of ways. For one, savings for airlines very often mean customers can be offered less expensive tickets. 

Beyond savings, predictive maintenance can actually help airlines offer greater value to customers. For one, it can offer greater reliability. When airlines have an overview of maintenance requirements, delays and cancellations are less likely to plague customers. Further, predictive maintenance can secure greater safety for passengers. When components can be removed before failure, you dramatically reduce the risk of safety incidents. 

why-upskilling-02
EXECUTIVE PERSPECTIVES:
Fostering Technological Innovation in Organisations.

The future of predictive maintenance: The democratization of data 

The full realisation of predictive maintenance depends on readily available big data shared throughout the industry. A major roadblock, however, is that presently, data is viewed as a commodity and is, for the most part, tightly protected by the OEMs manufacturers, airlines, leasing companies, etc., that have a sense of ownership. 

And it’s not hard to understand why – this data helps them remain competitive in the marketplace. Many experts believe, though, that greater benefits could be had by all if the industry was more collaborative about sharing the data. 

As Micheál Armstrong, CEO of Armac Systems, puts it: 

»We need to have almost a taxonomy around this data so that we can all agree and share and benefit from this data. That’s almost a bigger challenge than the algorithms,« he says and continues: 

»Data needs to be democratised – we should be competing over the analytics, not the data. We’ve seen how monopolies are created when one person gets the data. You get Google, Facebook, Instagram – and everybody else gets squeezed out. We need to use blockchain technology to democratise the data and protect people’s confidentiality, but let the ledger information into the public domain, so that we’re not competing on the data. If we see the data as proprietary, then big data is gone.«

The data itself doesn’t give any one player a leg-up. All the data in the world is useless if it can’t be effectively analysed and acted upon. All aircraft and engine manufacturers today offer data tools as service products, and while the technology still has a way to go to fully realise its potential, the competitive direction is clear – the focus should be shifted on developing tools to best analyse data, not hoard it. 

 Aviation engineer performs a predictive maintenance check on an aircraft.

A call for data sharing and collaboration 

According to Rhonda Walthall, Technical Fellow in Prognostics & Health Management at UTC Aerospace, there is already a shift in the industry underway from data ownership and control to collaboration. 

»Stakeholders are coming together looking for opportunities to partner together and to share data yet still protect their intellectual property,« she says.

Players like Airbus, with their Skywise open platform, are already starting to sow the seeds of this shift toward collaboration. The platform, launched in June of 2017, is aimed at combining data from Airbus in-service aircraft with airline and OEM data, in order to conduct in-depth analysis aimed at anticipating and optimising processes such as maintenance. To bolster the data available for their analysis, Airbus offers free anonymised data to airlines that submit their own. 

According to Airbus, the company tripled the fleet covered by Skywise in just a little over one year – from 28 airlines with a total of 3500 aircraft to 100 airlines with a total of 10.000 aircraft under contract by the end of 2019. More aircraft subscriptions will means more data, which in turn result in more accurate predictions and more customer benefits. 

The popularization of digital services and the move toward data sharing is likely to have a trickle-down effect on the rest of the supply chain, including logistics providers and distributors such as Satair. It’s not hard to imagine the effect these services could have on the aftermarket business, as it will provide distributors and logistics providers with valuable insight into what parts the customers need and when they need them. 

Moving forward, these instances of collaboration and sharing, in conjunction with more intelligent products that can help us get better data from components, according to Walthall, will help the industry build what she calls the »digital thread for a component throughout its lifecycle.«

Join our newsletter

Inspiration and lots of aviation knowledge, great industry insights and market trends right in your inbox

About this blog

This blog is driven by Satair Marketing & Communication with input from both internal and external contributors.