Browse Prior Art Database

Real-time Aviation Operations Optimization (RAOO), Smart Analytics System to Enhance Airlines Operations and Maximize Efficiencies Disclosure Number: IPCOM000250628D
Publication Date: 2017-Aug-10
Document File: 4 page(s) / 146K

Publishing Venue

The Prior Art Database

This text was extracted from a Microsoft Word document.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 39% of the total text.

Real-time Aviation Operations Optimization (RAOO), Smart Analytics System to Enhance Airlines Operations and Maximize Efficiencies


Disclosed is a new cognitive analytics model that utilizes Real-time Aviation Operations Optimization (RAOO) to continually learn and automatically adjust individual airplane operations. By factoring in many variables, the RAOO enables self-optimization for each airplane, which promotes operational and cost efficiency as well as customer satisfaction.

Despite thorough planning, airplane pilots are still unable to obtain all relevant information that might affect a flight. As a result, pilots miss opportunities to reduce fuel usage, decrease flight time, and avoid turbulence. Airplanes are very complex machines that use a huge number of sensors to operate. As the technology evolves, airplanes have more complex computers and systems to improve the flight (e.g., security, efficiency, etc.). However, all the knowledge generated after each flight is lost when the pilot leaves the plane; the pilot is a variable that can alter the level of efficiency when all other variables are the same (e.g., type of airplane, weather conditions, flight path, etc.). A method is needed that can leverage all the data generated during the flight to determine the best actions/reactions to improve the efficiency.

Current data analysis methods are manual and have several disadvantages including:

  • Possible loss or corruption of data
  • Requiring dedicated, experienced resources to process and analyze the data
  • Needing a significant amount of time and resources for processing and analysis, which delays output of results
  • Limited processing capabilities (big data)
  • Lack of automation between main components of the system (i.e., inputs (sensors), processing (people), outputs (knowledge))
  • Inefficient distribution of knowledge

Currently the airlines rely on maintenance, operational procedures, and some best practices to reduce the fuel consumption. The issue is that each airplane, route path, weather conditions, passenger/cargo load etc. has varying degrees of variance. Therefore, the actual results may vary leading to variances that impact profitability, customer satisfaction, and reliability. Fuel consumption is one example. Moreover, these standard operations were created based on theoretical data and cyclical adjustments (such as winter weather increasing delays, so add 20 minutes to flight time.) Now, these models could be improved using real performance of the current fleet (which values may change over the time). New cognitive technology can integrate into analytics capabilities to leverage all the data while learning over time.

Consider, for airlines, cost reduction is a key objective. This even led companies to make huge investments in updating fleets to get airplanes more secure and with better fuel efficiency. Improvements in efficiency can reduce overall costs.

The novel contribution is a new cognitive analytics model that utilizes R...