Ramco Blog - News, tips and insights on HCM, ERP, Logistics & Aviation enterprise software industry

Integrating Big Data In Aviation Industry

Written by Vishnu Prasad | February 11, 2014

Everyone is talking about Big Data. What actually is this Big Data?

Integrating Big Data in Aviation Industry

Big Data is a term used to describe the exponential growth and availability of data, both structured and unstructured. Gartner defines “Big data is high volume, high velocity, and/or high variety information assets that require new forms of processing to enable enhanced decision making, insight discovery and process optimization."3Vs" model is frequently used for describing big data.

Volume-Data growth have always been growing exponentially, from bytes of data it has grown into peta bytes of data generated every day with addition of different data sources like videos, music, text..Big data differs from other conventional methods by its virtue of storing large sets of data.

Velocity- Huge amount of data is generated and should be analyzed in real time by comparing the past data to predict the outcome based on the business functionality. Big data is capable of processing large varieties of data within seconds which make it differ from other technologies.

Variety- Data type generated is not uniform. It differs from the data source to another. Some data types may be structured some may not. Big data is capable of even handling huge varieties of data.

These properties define above describes what so called as Big Data. Aviation Industry is also in the verge of inducting Big Data Analytics due to its predictability nature with immense amount of data populating in and around an aircraft.

Aircraft Maintenance

Airlines spend a lion’s share of their profit for maintenance activities to make aircraft in airworthiness conditions, safe to fly. Currently majority of the aviation industry adopts On Condition/Preventive maintenance procedures due to its operational efficiency and it depends upon the failure mode calculations made after testing a part under circumstances. These conditions may vary depending on the external factors/Human errors which may result in the variation in the life time of components in turn reducing the operational efficiency of the aircrafts.

A study by FAA states that during a year jet engine generates data equivalent to 20TB. As of now large portion of this data is not used for any of the analytics purpose since this data is unstructured. Big Data analytics can be used to predict the failure of the component by comparing and analyzing data obtained from different sensors and history of the particular component attached to an aircraft, fleet or from the different aircraft fleet in which it is present.

Data Sources

  • Aircraft Data from ACARS
  • History Data from ERP\PIREP\AME Notes…
  • Weather Data
  • Engine Management System Data

Fig1: Schematic Representation of Data Flowing In/Out of Aircraft

Aircraft is made up of components working together simultaneously to make it in airworthiness condition. High stress, fatigue, corrosion….can make aircraft fail during its operations prior to the maintenance activities. Failure mode can be determined through Risk Analysis. Risk Analysis is a technique to identify the factors that are causing failure. With more data on board and comparing the past data, failure prediction can be done with Big Data in a precise manner. Risk Factor is calculated by simulating the conditions in which the part is being operated. The process is to simulate the experience for each part, and count how many fail.

These simulations will be run infinitely, comparing the part and the real model for any variations. The average number of failures is then obtained by dividing the total number of failures for all iterations by the number of iterations. Whenever the part reaches this risk factor, Planning Team\Maintenance departments will receive automatic alerts through the system integrated with Big Data. If the Planner is alerted in advance regarding the unplanned activity, he/she can schedule the maintenance activities, resources and procure part in advance. This will in turn reduce the TAT time which complements the operational efficiency of the airlines and hence profiting the organization.

Supply Chain Management (OEM perspective)

Airline’s\MRO’s stocks parts for its day to day operation from OEM, Original Engine Manufactures or suppliers with PMA approval. Currently OEM’s/Suppliers will require more than 8-10 week time to supply a part which is not in Stock. An article from ‘Aviation Today’ indicates that the manufacturing market leaders of aircraft parts requires more than 6 months time to supply the ordered part due to back logs caused by in efficient demand forecasting. This resulted in the reduction in profit margin of OEM’s since airlines preferred to go with alternate sources instead of waiting for the parts.

Data Sources

  • Market Data
  • Vendor Data
  • Competitor Data
  • Airline\MRO Part usage details from ERP

With the help of Big Data, OEM’s/Suppliers will be able to forecast the volume\quantity of parts that an airline will be ordering in the future from analyzing the above data sources and future trends in the aviation Industry. This helps OEM to re organize the production plan to meet the call and to supply the parts within short notice.

Procurement Management

Procurement plays an important role in aviation maintenance industry. Whenever an AOG situation occurs or material planner requires replenishment of stock, he need to check in internet to get the details of vendor’s who provides parts with quality, less price and less time. This is a tedious job as it requires handful of experience in making decision by comparing and analyzing from different vendors on different criteria’s.

Data Sources

  • Market Data
  • Vendor Data

With algorithms in build, Big Data will display the list of vendors having part in stock based on the parameters like supplier rating\location\quantity\lead time\agreements in rank basis. Automatic procurement process will be triggered based on the priority, thereby reducing the pre lead time of the procurement process.

Conclusion

According to the FAA estimate it states that airlines spend an average of $ 22mn per year for flight delays. Also passenger discomfort plays a vital role as it can cause decrease in the profit margin with the growing competitors in the league. Airlines are pouring in lot of money into unplanned maintenance activities to make it in airworthiness condition. In general, 8-10 percentage of total revenue is spend on total maintenance, material and repair cost expenditure. Out of which airlines spend more than 2 percentages for the unplanned activities. By inducting big data into aviation business, with features like predictability, social analytics etc., capable of processing real time data which can reduce the ‘extra cost’ incurred by airlines. This can reduce the unplanned maintenance cost incurred by the airlines.