Neural networks to classify atmospheric turbulence from flight test data: an optimization of input parameters for a generic model

Oliveira, M.M. de; Mayor, Gabriel S.; Macedo, João Paulo; Bidinotto, Jorge Henrique

doi:10.1007/s40430-022-03386-1

Cited by 5 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Turetta et al modeled the behavior of a pilot in some flight test maneuvers, presented in [14] and [15]. In the same way, Oliveira et al [16] evaluated the use of ANN to classify turbulence levels in a real aircraft using flight test data. This type of classification, as well as in PIO tests, is done subjectively, while Efremov [17] performs a tendency analysis and prediction criteria for the occurrence of the PIO phenomenon.…”

Section: 2pio Rating Scalementioning

confidence: 99%

Artificial Neural Networks for PIO Events Classification Comparing Different Data Collection Procedures

Bruschi,

Drewiacki,

Bidinotto

2024

Preprint

Self Cite

View full text Add to dashboard Cite

This work evaluates the accuracy and reliability of PIO test classification using the PIO Rating Scale and proposes using an automatic tool for this evaluation based on test data to eliminate the subjectivity inherent to the application of rating scales. Two test procedures (Discrete Synthetic Task and Pitch Capture) are executed in a flight simulator, using aircraft dynamic models with different PIO proneness and experienced flight test pilots. The results show a significant effect of subjectivity in pilot rating and various reliability for different test procedures. This data is used to build an Artificial Neural Network (ANN) proposed to classify the executions using the PIO Rating Scale. The ANN presented low computational cost and 97.1% accuracy when using data extracted from the Pitch Capture test procedure.

show abstract

Section: 2pio Rating Scalementioning

confidence: 99%

Artificial Neural Networks for PIO Events Classification Comparing Different Data Collection Procedures

Bruschi,

Drewiacki,

Bidinotto

2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In terms of aircraft turbulence prediction, some classic algorithms have been used by scholars to construct models, such as Random Forests (RFs) and Gradient-Boosted Regression Trees (GBRTs) explored by Domingo et al [23]; Support Vector Machine (SVM) algorithms explored by Abernethy et al [30] and Mizuno et al [28]; and Multilayer Perceptron (MLP) networks explored by Oliveira et al [31]. However, in the field of aviation meteorology, especially in the field of aircraft bumpiness, there are still many opportunities for classical methods to be fully tried and explored.…”

Section: Artificial Intelligence Algorithmsmentioning

confidence: 99%

Characteristic Analysis and Short-Impending Prediction of Aircraft Bumpiness over Airport Approach Areas and Flight Routes

Ding,

Zhang,

Wang

et al. 2023

Atmosphere

View full text Add to dashboard Cite

Based on the Quick Access Recorder (QAR) data covering over 9000 routes in China, the monthly and intra-day distribution characteristics of aircraft bumpiness at different levels were analyzed, and the relationships between the eddy dissipation rate (EDR) and other aircraft flight status elements during bumpiness occurrence were also analyzed. Afterward, aircraft bumpiness routes were constructed using 19 machine learning models. The analyses show that (1) aircraft bumpiness was mainly concentrated between 0:00 a.m. and 17:00 p.m. Severe aircraft bumpiness occurred more frequently in the early morning in January, especially between 5:00 a.m. and 6:00 a.m., and moderate bumpiness always occurred from 3:00 a.m. to 11:00 a.m. (2) The relationship between the left and right attack angles and aircraft bumpiness on the routes was more symmetrical, with a center at 0 degrees, unlike in the approach area where the hotspots were mainly concentrated in the range of −5 to 0 degrees. In the approach area, the larger the Mach number, the more severe the bumpiness. (3) The performances of the Automatic Relevance Determination Regression (ARD), Partial Least Squares Regression (PLS), Elastic-Net Regression (ENR), Classification and Regression Tree (CART), Passive Aggressive Regression (PAR), Random Forest (RF), Stochastic Gradient Descent Regression (SGD), and Tweedie Regression (TWD) based models were relatively good, while the performances of the Huber Regression (HUB), Least Angle Regression (LAR), Polynomial Regression (PLN), and Ridge Regressor (RR) based models were very poor. The aircraft bumpiness prediction models performed best over the approach area of ZBDT (airport in Datong), ZULS (airport in Lhasa), ZPPP (airport in Kunming), and ZLQY (airport in Qingyang). The model performed best in predicting the ZLLL-ZBDT air route (flight routes for Lanzhou to Datong) with different prediction times.

show abstract

Artificial neural networks for PIO events classification comparing different data collection procedures

Bruschi,

Drewiacki,

Bidinotto

2024

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

Neural networks to classify atmospheric turbulence from flight test data: an optimization of input parameters for a generic model

Cited by 5 publications

References 13 publications

Artificial Neural Networks for PIO Events Classification Comparing Different Data Collection Procedures

Artificial Neural Networks for PIO Events Classification Comparing Different Data Collection Procedures

Characteristic Analysis and Short-Impending Prediction of Aircraft Bumpiness over Airport Approach Areas and Flight Routes

Artificial neural networks for PIO events classification comparing different data collection procedures

Contact Info

Product

Resources

About