Aircraft Maintenance using IoT based Predictive

maintenance

Soumalya Kar(ECE) Tanmoy Dey(ECE) Rishi Mukherjee (EE)

Abstract

Aircrafts are indeed a majestic and complex set of machines. They have satisfied the
human dream to touch the skies. Owning an aircraft is however, no joke. They fall under the
category of machines that have some of the most rigorous and expensive maintenance
schedules. Aircrafts,in general, do suffer a lot of stress during long flights, and they rely upon
a preset standard schedule of maintenance for inspections and repairs of various
components, several standard safety checks and replacement of worn out parts from time to
time. Adhering to a strict maintenance schedule helps prevent potential accidents and
mishaps and is a commitment towards safety. It also helps operating companies and airports
from incurring huge financial losses due to delays and also keeps the trust of the commuters
or businesses in them. However , sometimes , issues may occur even before the scheduled
maintenance periods. Fortunately with the advancement of technology , it is now possible to
predict accurately where and when replacement/repair is required. This is where predictive
maintenance comes in. It is a relatively recent IoT-based technology that in this specific use
case, employs the usage of sensors, flight data recorder and various other algorithms,and
can actively predict where irregularities may occur and schedule maintenance ahead of time
or before unexpected breakdown. This can help prevent accidents as well as significantly
reduce the annual maintenance bill for the operators.

Research methodologies

1. Observations

Interestingly, the origin of predictive maintenance can be traced to aircraft maintenance.

Back in 1943, a British scientist named C.H. Waddington commented that “inspections tend
to increase breakdowns” after he observed the maintenance activities of the Royal Air Force
Coastal Command 502 Squadron. Instead, he recommended a process that was more
“in-tune with the actual condition of the equipment.”One of the most prevalent challenges in
the airline industry is the need to reduce costs and delays, while maintaining and improving
aircraft operational reliability. Currently, airlines and MROs are trying to leverage data and
technological progress to better predict and manage aircraft maintenance efforts through
Predictive maintenance (PdM). There are also other two well-known types of maintenance ;
Reactive and Preventive. Reactive maintenance refers to a timeline in which a particular part
of an aircraft is used to its limits and repairs are only performed after a failure.This method is
usually costly and dangerous for operational safety. Therefore, many aircraft operators use
Preventive aircraft maintenance (PM), also known as planned maintenance, which refers to
a determined timeline of checks on certain airplane components.The United States Federal
Aviation Administration (FAA) defines preventive maintenance as “simple or minor
preservation operations and the replacement of small standard parts not involving complex
assembly operations.”The biggest challenge in preventive aircraft maintenance is that it’s not
always easy to pinpoint a suitable time to carry out checks.According to a predictive
maintenance report from Market Research Future, the global predictive maintenance market
is expected to grow to 23B by 2025. As of 2017, about 53% of companies adopted big data
analytics, which includes predictive maintenance and IIoT technologies. The overall use of
predictive maintenance rose from 47% in 2017 to 51% in 2018. The highest number of
implementations are happening in the manufacturing sector, but all businesses that have a
lot of capital tied up in their equipment are very much interested in predictive
maintenance.The term predictive maintenance (PdM) is contrary to the reactive or
preventive approach that are still widely in use. PdM requires knowledge of the correct
information at the suitable moment to perform the necessary aircraft maintenance. PdM uses
Iot for collecting data from sensors and sending it to the cloud; after that it uses data analysis
and techniques to detect possible defects in the aircraft, which helps airlines carry out better
maintenance planning.While studying the survey of the US Department of Energy we have
estimated that a predictive maintenance program in an Aviation industry could realize an 6%
to 10% savings over a preventative only program. Depending on the facility, a predictive
program could achieve 25% to 35% savings.Based on the estimation, the following results
could come from a functional predictive maintenance program: 20% to 25% reduction in
maintenance cost, 60% to 65% reduction in breakdowns, 20% increase in
production.The survey projected an ROI of 8 times the investment. American MRO
company, Collins Aerospace, has also established its own predictive maintenance tool called
Collins Ascentia. The Collins Ascentia, according to the company, shows a 30% decrease in
potential delays and cancellations related to components and systems monitored on the
Boeing 787 fleet. Additionally, it also shows a 20% decrease in unscheduled removals for
various components on the Boeing 777 fleet.According to findings from an Oliver Wyman
annual MRO survey in 2016, the global fleet could generate upwards of 98 million
terabytes of data annually by 2026, creating new opportunities for better predictive
maintenance implementation. Worldwide spending on IoT technology is estimated to reach
$1.2 trillion in 2022 with a CAGR of 13.6%. 79% of businesses see predictive maintenance
as the main application of industrial data analytics.The introduction of new technologies and
the digitization of services means big benefits for airlines and the MRO industry. The growth
and demand of civil aviation in regions like Asia-Pacific means a rapid expansion of global
air passengers. In fact, Airbus has predicted that the expansive growth in global air
passengers will result in “33,000 new aircraft globally by 2035.”The IoT has already
implemented innovative solutions to tackle such problems. Augmented reality (AR) has
become a solution that has emerged to fill the gap within the MRO industry. XMReality is one
company that has revolutionized knowledge sharing through the IoT.Their usage of AR as a
remote guidance solution means onsite operators can be connected to licensed technical
experts from anywhere in the world. This real-time, cost-effective solution, provides expertise
from any remote location, bridging the shortage of available technicians allowing for
multinational line maintenance teams.
2. Implementations

Within aviation maintenance and engineering the aim of predictive maintenance is first to
predict when a component failure might occur, and secondly, to prevent the occurrence of
the failure by performing maintenance. Monitoring for future failure allows maintenance to be
planned before the failure occurs, thus reducing unscheduled removals and avoiding
Aircraft-on-Ground (AOG).
There are three main components that allow PdM to track asset condition and warn
technicians about upcoming equipment failures:
*Installed condition-monitoring sensors send real-time performance data and machine health
data.
*IoT technology enables the communication between machines, software solutions, and
cloud technology; essentially helping to collect and analyze huge amounts of data.
*Predictive data models are fed with all of that processed data so they can spit out failure
predictions.

1) CM technology and predictive maintenance techniques

There are a variety of condition-monitoring sensors and equipment that can be
installed/retrofitted. You can measure electrical currents, vibrations, temperature, pressure,
oil, noise, corrosion levels, and more.
The Sensors to go with depends on what type of assets that will be on our PdM and what we
want to track.
For Example, In an Aircraft, Oil/Lubricants analysis is used to test the quality of
oil/lubricant for free movement of hydraulics attached to touch-down wheels, brakes, jet-fuel.
Vibration analysis is used to identify defects due to misalignments, imbalances or design
flaws. Usually in Wings, Engines, Body-frame, touch-down Wheels.
Motor circuit analysis is used to detect any short circuit or overload in AC compressors,
fuel pumps, generators, etc.
Thermography is used to detect sudden increase or decrease in temperature, Usually in
Cooling Systems, Engines and also in Wheels where temp. rises due to friction and braking.
These are some of the listed CM techniques performed with different types of sensors like
OQS2, vibration sensor, MCSA sensor , infrared thermography sensor, respectively.

2) The role of IoT technology

It is one thing to gather data, but quite another to be able to analyze and use the data for its
intended purpose. By using Internet of Things (IoT) technology, sensors mentioned earlier
can collect and share data. PdM relies heavily on these sensors to connect the assets to a
central system that stores the information coming in. These central hubs run using WLAN or
LAN-based connectivity or cloud technology.From there, the assets can communicate, work
together, analyze data, recommend remedial action, or take action directly, based on how
the system is set up.

3) Applying predictive algorithms

The most important part of predictive maintenance (and arguably the hardest one) is building
predictive (a.k.a prognostic) algorithms. In essence, we have to build a model that will
consider many different variables and how they interconnect and impact one another – with
the ultimate goal being able to predict machine failures.The more variables we will use, the
more accurate our models will be. This is why building predictive models is an iterative
process.The initial models will be based on asset history stored in a CMMS(Computerized
Maintenance Management System) or file cabinets, personal observations, FEMA analysis,
already available internal sensors like accelerometers and flow meters, and similar sources.
There might even be a need to first install condition-monitoring sensors and run them for a
while to gather baseline data and finish the initial predictive models. Over time, the installed
sensors will generate more and more data which can be used to improve the initial models
and make near-perfect failure predictions.
Here is how the algorithms work. They follow a set of predetermined rules that compare the
asset’s current behavior against its expected behavior. Deviations are an indication of
gradual deterioration that will lead to asset failure. Based on deviations, current operating
conditions, past failure data, and all the other variables built into the data model, the
algorithms try to predict failure points.
The end result is an automated system that:
*monitors operating conditions via installed sensors
*understands and predicts patterns created by data anomalies
*creates alerts when there is a deviation from established thresholds
Strengths and weaknesses

Strengths:
1.Minimizes the occurrences of unscheduled downtime and maximizes asset uptime.
2.Some predictive maintenance can be carried out on running assets, that ensures asset
availability.
3.Minimal disruption in productivity.
4.Optimizes the time required for maintenance work.
5.Requirement of skilled-maintenance technicians, improves workforce and decreases
service loss.
6.Lowers life risk of commuters by alerting any failure ahead of time to the aviation company.

Weakness:
1.CyberSecurity while implementing Iot.
2.High setup and installation cost including sensors.
3.Time consuming in setup and implementation.
4.Errors in hardware and software technology pose safety issues.
5.Time taking training causes shortage of qualified-maintenance technicians.
Conclusion

Aircrafts and Aviation industry is becoming increasingly central to people's everyday lives. It
however still suffers from many failures and mishaps. It is important to detect disaster
before it strikes.
IoT technology is changing the aviation industry in multiple ways indeed. IoT sensors
support continuous monitoring of aircraft systems in flight to create more effective predictive
maintenance, leading to fewer failures and more reliable (and more efficient) operations.
Today's aircrafts are abundant with internet of things (IoT) sensors. The latest generation of
aircraft has essentially become a flying network producing vast streams of real-time
performance data. In fact, the 787 aircraft transmits 28 times more data in flight than a 777.
Predictive maintenance, based on the increased use of IoT sensors, is a great example of
the ways in which IoT technology and big data are being used to boost aircraft safety in
newer machines. Air passengers and air cargo shippers can feel more confident that flight
operations are efficient and safe because of predictive maintenance based on IoT.
Lufthansa Technik, one of the biggest MRO solution providers, has also developed its own
predictive maintenance instrument called AVIATAR. Airlines, including Wizz Air or Sichuan
Airlines, are already utilizing this technology as a predictive maintenance tool to optimize
fleets and decrease manual and paper-based processes.
Predictive aircraft maintenance systems are mostly being applied to engine maintenance,
component maintenance and airframe maintenance, respectively.
According to the latest data, the market remains uncertain regarding predictive aircraft
maintenance with 44% indicating increasing or new investment, but nearly 25% indicating
a decreasing, or no planned, investment during the COVID-19 pandemic, as per Oliver
Wyman MRO Survey 2020 report.
Despite the obstacles in PdM implementation, this is in the long-standing interest from
industry leaders who are in search of more cost-efficient methods to improve aircraft
maintenance performance.
References

1. https://www.aerotime.aero/28331-predictive-aircraft-maintenance-MRO
2. https://limblecmms.com/predictive-maintenance/
3. https://www.fiixsoftware.com/maintenance-strategies/predictive-maintenance/
4. https://www.e-spincorp.com/advantages-and-disadvantages-of-predictive-maintenanc
e/
5. https://www.mromagazine.com/features/complete-list-of-condition-monitoring-techniq
ues/
6. https://blog.gutenberg-technology.com/en/predictive-maintenance-increasing-your-eq
uipments-roi
7. https://www.exsyn.com/blog/big-data-in-aviation-predictive-maintenance