Big Data in Aviation - Reduce Costs trough Predictive Maintenance

The aviation industry is grasping for opportunities to reduce costs. Big data has been making headlines in several industries, promising to revolutionize the way in which businesses are able to make decisions. One of the sectors slated to benefit from the use of big data, and associated analytics, is the aviation industry. As new aircraft generate more in-flight data compared to older ones, innovative analysis methods summarised by Big Data Analytics enable the processing of large amounts of data in short amount of time. Last studies show a reduction of maintenance budgets by 30 to 40% if a proper implementation is undertaken. As a result, predictive analytics of flight recorded data is an exciting and promising field of aviation that airliners are starting to develop. However, data sensitivity and security are some added complications that must be overcome through strong bonds between the MRO, flight operations and engineering departments to ensure all the data is employed. Unlocking the valuable information within this data is referred to as Data Mining. Although used in several other industries, the use of these tools in the analysis of aircraft data is relatively new and upcoming in recent years (Canaday, 2013).

The increase in data

It is a fact that nowadays aircraft generate more data than ever. Currently, around 2 million of terabytes of data are generated every year by the global fleet, through the Flight Data Recorder and Aircraft Health Monitoring. By 2026 this may have grown to 98 million of terabytes per year as shown in below figure. In the last decade several factors have caused a huge increase in data. First, the digitization of information keeps on progressing, but also costs of sensors, data storage and data communication has significantly dropped over the years. Finally, the velocity of the incoming data has increased enormously, caused by the advancing information technologies which make it easier to generate data (van Kempen & van Eijk, 2014; Chen, Mao & Liu, 2014). At the same time, these huge amounts of data need to be explored to discover meaningful and useful information. This makes manual analysis impractical (Mosaddar & Shojaie, 2013). Datamining presents an opportunity to increase the rate at which the volume of data can be turned into useful information (Bastos, Lopes, & Pires, 2014).

Figure 1: Data Generated by global Fleet - Fleet & MRO Forecast by Oliver Wyman

Reduce costs through Predictive Maintenance

A subject within Big Data Analytics and Data Mining is predictive maintenance. Predictive maintenance is recognized by 66% of the airlines as one of the most prominent new technologies to have entered the market by 2020. Also, Big Data Analytics is being used by 54% of the airlines to enhance Maintenance Repair and Overhaul (MRO) systems, and almost 92% plan to use their fleet data to improve health monitoring and predictive MRO (Canaday, 2015). Until now, it has mainly been done by Original Equipment Manufacturers (OEM) and OEM shops, as operators and MRO’s want to see more proven track records in the technology and processes.

The aim of predictive maintenance in aviation

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 reduce unscheduled removals and avoid Aircraft-on-Ground (AOG).

Benefits of applying predictive maintenance in aviation

Improve operations:

forecast inventory
manage resources

Reduce costs:

minimizing the time, the equipment is being maintained
minimizing the production hours lost to maintenance, and
minimizing the cost of spare parts and supplies.

The difference between preventive and predictive maintenance

Preventive Maintenance:

Is useful when a strong correlation between equipment age and failure rate exists. For example, when abrasive, erosive, corrosive wear takes place or when the material properties change due to fatigue. In this case, the individual components and equipment probability of failure can be determined statistically, and the replacement of components is scheduled at a certain number of cycles.

Predictive Maintenance:

Can be described as “the intelligent way to maximize machine availability”. With the right information in the right time it is possible to determine the condition of in-service equipment in order to predict when maintenance should be performed. As a result, it is possible to conveniently schedule corrective maintenance actions, preventing equipment failure. Compared with preventive and reactive maintenance tasks are performed when warranted, right on time.

The adoption of Predictive Maintenance is growing. Nowadays AHM is necessary, especially regarding Engine Condition Monitoring, followed by airframe maintenance and component maintenance. However, competitive efforts by OEMs to claim ownership of data generated by aircraft systems Carriers must preserve full rights to their data, including the ability to share it with maintenance providers

Based on years of in-depth research EXSYN has identified three main phases, where the last defines the status of being able to become a predictive airline:

*Figure 3: Success levels towards predictive maintenance for an airline*

Let’s have a closer look at the three types of airline:

The reporting airline

The reporting airline is characterized by producing monthly reliability reports, drawing from manual work of retrieving the various information such as aircraft utilization, Pilot reports, Maintenance findings and component removals and then consolidate this data into Excel.

This typically is a very manual labour-intensive process and puts the reporting airline in a situation that they are able to produce the reports on monthly bases but not action on these reports.

The monitoring airline

The monitoring airline stands one level higher on the adoption success scale of becoming predictive. This type of airline typically already moved away from excel reports and uses an analytical tool and mostly also dashboards. This allows the airline to act more quickly on rising issues and monitor the fleet than rather reporting the status of their fleet.

However, it still draws on the same set of data, the SPEC2000 chapter 11 reliability data. Which ultimately prevents the airline of adopting any predictive maintenance models as data sets are to limit to become reliable enough for operational usage.

The data driven airline

The data driven airline, has the highest level of adoption success for predictive maintenance models. It used all character traits of the monitoring airline but has recognized the need of having access to larger sets of data beyond its own airline data, such as industry reliability data, Flight Data Recorder information, weather data as well as ADS-B transponder data. Ultimately the data driven airline implements a data driven platform in its organization that provides information to its operational units such as maintenance operations control to make informed decisions in day-of-operation itself.

The main question you have to ask yourself: 'Where are you currently standing: is your airline ready for predictive maintenance?'

In order to answers this question, you have to go through below list of questions and answer these either with yes or no:

Has your airline an integrated MRO software?
Is the MRO software less than 8 years old?
Is the MRO software updated at least once a year?
Does your airline have interfaces built between various sources of information within your IT setup? (i.e. Records, Maintenance, Engineering, Inventory, Finance & Resource, Flight Operations data)
Does your airline conduct data audits to secure that data is up to date?
Does your airline have a high data integrity/quality?
Do you cross-reference and update data against sources and revisions?
Does your airline use a software solution (not EXCEL) to perform reliability analysis?
Does your airline need to manipulate or correct data every time before the airline reliability report is published?
Does your airline have access to weather data?
Does your fleet use onboard data systems such as AHM or ACARS?
Is your airline's flight department willing to share Flight Data Recorder information with other departments?
Is your airline willing to share technical and operational data with other airlines that operate the same aircraft type(s)?

So, where are you currently standing, is your airline ready for predictive maintenance?

How EXSYN can help

EXSYN's team of aircraft data and aviation experts utilize a proven framework and methodology for adoption of predictive analytics in aviation. It has been applied to numerous fleets and aircraft and includes:

EXSYN’s pre-build AVILYTICS environment of analysis modules, widgets, formulas and algorithms on a wide range of ATA chapters and components
Workshops to identify the specific maintenance complaints to be monitored for each fleet operated by your airline
Implementation of identified complaints per aircraft type and registration into the AVILYTICS environment. Including data mining, validation and user interface design.
Native integration of the AVILYTICS modules in your own platform or hosting in the myEXSYN.com digital environment in case your airline does not have a data warehouse yet
Training of identified user groups
Adoption workshops to support successful day-to-day usage of the predictive analytical techniques and business models
Machine Learning to identify future potential maintenance complaints to be monitored
Ongoing software maintenance support for modules implemented