Open Access Open Access  Restricted Access Subscription or Fee Access

Prediction of Landing Gear Loads from Flight Test Data Using Gaussian Process Regression

E. J. CROSS, P. SARTOR, K. WORDEN, P. SOUTHERN

Abstract


The paper explores the use of Gaussian Process (GP) Regression for predicting landing gear loads from recorded in-flight parameters. Gaussian process regression is a powerful Bayesian machine learning tool whereby predictions and their distributions can be obtained without having to specify a particular model/functional form. Advantages of employing Gaussian Process regression in this case include its training speed in comparison to more traditional machine learning tools such as neural networks, and the ready availability of confidence intervals on predictions. The paper demonstrates the prediction capability of GP regressors applied to flight test data.

Full Text:

PDF