Top Banner
Summary Advantages Inventors Flight Parameter Prediction Using Neural Networks UND Technology 14-25 Patent Number US 10,466,266 Date of Issuance: November 5, 2019 The University of North Dakota has patented a method for alerting aviators of potentially dangerous situations. The method includes training an artificial network with a flight information database. Training the neural network consists of comparing a predictive value from the neural network to a measured value of a flight parameter and modifying structural components of the neural network to bring the predictive value closer to the measured value. The trained neural network can then be used to detect and warn of anomalous conditions. Increases aviation safety by providing “early-warnings” to pilots, aircraft technicians, and aircraft maintenance staff Resources National General Aviation Flight Information Database (NGAFID) developed at the University of North Dakota Suitable for both piloted and unmanned aerial vehicle applications Works with existing aircraft sensors Dr. Jim Higgins Dr. Travis Desell Dr. Sophine Clachar
1

Flight Parameter Prediction Using Neural Networks

Oct 16, 2021

Download

Documents

dariahiddleston
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Flight Parameter Prediction Using Neural Networks

Summary

Advantages

Inventors

Flight Parameter Prediction Using Neural Networks

UND Technology 14-25 Patent Number US 10,466,266 Date of Issuance: November 5, 2019

The University of North Dakota has patented a method for alerting aviators of potentially dangerous situations. The method includes training an artificial network with a flight information database. Training the neural network consists of comparing a predictive value from the neural network to a measured value of a flight parameter and modifying structural components of the neural network to bring the predictive value closer to the measured value. The trained neural network can then be used to detect and warn of anomalous conditions.

• Increases aviation safety by providing “early-warnings” to pilots, aircrafttechnicians, and aircraft maintenance staff

• Resources National General Aviation Flight Information Database (NGAFID)developed at the University of North Dakota

• Suitable for both piloted and unmanned aerial vehicle applications• Works with existing aircraft sensors

• Dr. Jim Higgins• Dr. Travis Desell• Dr. Sophine Clachar