A Flight Simulation Model Architecture for Reinforcement Learning

2022 ◽  
pp. 381-391
Author(s):  
KaiXuan Wang ◽  
YuTing Shen ◽  
FuQuan Zhang ◽  
Nan Zhao ◽  
Lijie Yang
Keyword(s):  
Reinforcement Learning ◽  
Simulation Model ◽  
Flight Simulation

Rotorcraft Lateral-Directional Oscillations: The Anatomy of a Nuisance Mode

2021 ◽  
Author(s):  
Dheeraj Agarwal ◽  
Linghai Lu ◽  
Gareth D. Padfield ◽  
Mark D. White ◽  
Neil Cameron
Keyword(s):  
Simulation Model ◽  
Simulation Models ◽  
Flight Test ◽  
Flight Simulation ◽  
Stability And Control ◽  
Systems Research ◽  
Control Derivatives ◽  
Research Aircraft ◽  
Level Of Understanding ◽  
And Control

High-fidelity rotorcraft flight simulation relies on the availability of a quality flight model that further demands a good level of understanding of the complexities arising from aerodynamic couplings and interference effects. One such example is the difficulty in the prediction of the characteristics of the rotorcraft lateral-directional oscillation (LDO) mode in simulation. Achieving an acceptable level of the damping of this mode is a design challenge requiring simulation models with sufficient fidelity that reveal sources of destabilizing effects. This paper is focused on using System Identification to highlight such fidelity issues using Liverpool's FLIGHTLAB Bell 412 simulation model and in-flight LDO measurements from the bare airframe National Research Council's (Canada) Advanced Systems Research Aircraft. The simulation model was renovated to improve the fidelity of the model. The results show a close match between the identified models and flight test for the LDO mode frequency and damping. Comparison of identified stability and control derivatives with those predicted by the simulation model highlight areas of good and poor fidelity.

Trimming of flight simulation ground models

1997 ◽  
Vol 211 (2) ◽  
pp. 91-102 ◽  
Author(s):  
B Mallock ◽  
C J Harris ◽  
C R Hogg ◽  
D Jones
Keyword(s):  
Simulation Model ◽  
Equilibrium Condition ◽  
Flight Simulation ◽  
Time Saving ◽  
Research Programmes ◽  
Method Of Solution ◽  
Full Simulation

A number of research programmes are being undertaken in the field of flight simulation. This paper accounts for a component of the research being performed under one of those programmes. The specific aim of the work presented in the paper was to establish a means whereby an aircraft and its associated undercarriage could be ‘trimmed’. The equilibrium condition is found without the need to run the full simulation model. This results in time saving without loss of accuracy. The trimming algorithm is detailed in terms of the method of solution and the range of shock strut and tyre models that can be employed. Sample results are presented in the paper.

A STUDY OF ROUTING METHODS IN URBAN WIRELESS MESH NETWORKS BASED ON REINFORCEMENT LEARNING

2021 ◽  
Author(s):  
В.Д. ФАМ ◽  
Р.В. КИРИЧЕК ◽  
А.С. БОРОДИН
Keyword(s):  
Artificial Intelligence ◽  
Reinforcement Learning ◽  
Simulation Model ◽  
Network Traffic ◽  
Mesh Networks ◽  
Mesh Network ◽  
Queueing Model ◽  
Traffic Routing ◽  
Wireless Mesh ◽  
Routing Methods

Приведены результаты исследования методов маршрутизации на основе обучения с подкреплением с помощью имитационной модели. Рассмотрена задача маршрутизации сетевого трафика для фрагмента ячеистой сети городского масштаба, управляемой на основе технологий искусственного интеллекта. Представлена модель системы массового обслуживания для изучения процесса маршрутизации, а также обучения выбора маршрута. Имитационная модель фрагмента ячеистой сети разработана в пакете Anylogic и обучается на основе платформы Microsoft Bonsai. The results of the study of network traffic routing methods based on reinforcement learning using a simulation model are presented. The problem of network traffic routing for a fragment of a city-scale mesh network, controlled on the basis of artificial intelligence technologies, is considered. The article presents a queueing model for studying the routing process, as well as learning how to choose a route. The mesh network fragment simulation model was developed in the Anylogic package and is trained on the basis of the Microsoft Bonsai platform.

scholarly journals Validation of the sonAIR aircraft noise simulation model

Noise Mapping ◽  
2021 ◽  
Vol 8 (1) ◽  
pp. 95-107
Author(s):  
David Jäger ◽  
Christoph Zellmann ◽  
Felix Schlatter ◽  
Jean Marc Wunderli
Keyword(s):  
Simulation Model ◽  
Input Data ◽  
Aircraft Noise ◽  
Flight Simulation ◽  
Operating Conditions ◽  
Simulation Accuracy ◽  
Noise Simulation ◽  
Land Cover Data ◽  
Noise Measurements ◽  
Emission Models

Abstract sonAIR is a recently developed aircraft noise simulation model designed for single flight simulation while still being applicable for calculation of entire airport scenarios. This paper presents a rigorous validation exercise, wherein roughly 20’000 single flights were simulated using the 22 currently available sonAIR emission models of turbofan aircraft and compared against noise measurements. The measurements were recorded with the noise monitoring terminals at Zurich and Geneva airport, Switzerland, and with additional microphones installed by the author’s institution. Data from 22 measurement positions were analyzed, covering all departure and approach routes at distances from 1.8 to 53 kilometers from the airports. sonAIR was found to be accurate for departures and approaches under different operating conditions and aircraft configuration. The mean overall differences between simulation and measurements were well below ±1 dB in terms of noise event levels, with standard deviations of ±1.7 dB respectively ±2.4 dB, depending on the model type. A few aircraft types that displayed larger deviations are discussed individually. A sensitivity analysis on the input data found the quality and level of detail of the land cover data to be critical for the simulation accuracy. Changes in other input data such as atmospheric profiles and buildings had non-significant impacts.

Sign in / Sign up

Export Citation Format

Share Document