Improving aircraft performance using machine learning: A review

Clainche, Soledad Le; Ferrer, Esteban; Gibson, Sam; Cross, Elizabeth J.; Parente, Alessandro; Vinuesa, Ricardo

doi:10.1016/j.ast.2023.108354

Cited by 46 publications

(11 citation statements)

References 319 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to known procedures [19][20][21], the methodology for determining the characteristics of flight range and duration in a typical flight of a passenger aircraft [25][26][27] is integrated with the procedure for design calculation of a propeller [28][29][30][31]. The improvement of these procedures was intended to take into account the effect of propeller operation on the aerodynamic performance of an aircraft that previously had a different type of engine.…”

Section: Discussion Of Results Of Studying the Parametric Appearance ...mentioning

confidence: 99%

Design of the parametric appearance of the power plant for modifications of the regional passenger aircraft An-158

Loginov,

Ukrainets,

Humennyi

et al. 2023

EEJET

View full text Add to dashboard Cite

The object of research is the process of remotorization of a regional passenger aircraft to increase its fuel efficiency. Based on the conceptual requirements for the remotorization of the An-158 aircraft with turbojet bypass engines, a parametric appearance of three modifications of this aircraft with turboprop engines for 80, 100, and 120 passenger seats was formed. The study was carried out on the basis of the well-known modular software systems «Integration 2.1» and «Air propeller 2.2» for typical flight profiles of the An-158 aircraft. Improved procedures of weight design and determination of the takeoff characteristics of aircraft with different types of power plant engines have made it possible to identify the most advantageous flight speeds of aircraft modifications with a turboprop engine corresponding to different flight masses. The results of the study of flight performance for optimal and «non-optimal» modifications of the aircraft are reported. The parametric appearance of the propeller was formed, the shape of the propeller blade for the cruising flight mode was determined for modifying the aircraft with a maximum number of passengers – 120 people. It is shown that the propeller for this modification of the aircraft cannot have less than 8 blades since with a smaller number of blades, the maximum chord of the propeller blade increases. The inductive power costs increase significantly due to the small elongation of the blades and, as a result, the flight efficiency of the propeller decreases. It is shown that the total fuel consumption for the entire typical flight of all modifications of the aircraft with turboprop engine at all studied flight speeds is less than the total fuel consumption of the An-158 base aircraft

show abstract

Section: Discussion Of Results Of Studying the Parametric Appearance ...mentioning

confidence: 99%

Design of the parametric appearance of the power plant for modifications of the regional passenger aircraft An-158

Loginov,

Ukrainets,

Humennyi

et al. 2023

EEJET

View full text Add to dashboard Cite

show abstract

“…Furthermore, heat transfer applications, concerning the addition of nanoparticles in simple fluids [97][98][99][100][101][102] or the investigation of flows in microfluidic channels [103][104][105][106][107][108] play a central role. Of equal significance, though with fewer instances, several recent reviews refer to aerodynamics [109][110][111][112][113], geosciences, geoengineering and environmental subjects [114][115][116][117][118][119][120][121][122][123][124][125][126], energy applications [127][128][129][130], biological processes [131][132][133][134], control processes [135][136][137], multiscale simulations [138][139][140][141], and general ML [2,…”

Section: A Brief Overview and Methods Classificationmentioning

confidence: 99%

Can Artificial Intelligence Accelerate Fluid Mechanics Research?

Drikakis

Sofos

2023

Fluids

View full text Add to dashboard Cite

The significant growth of artificial intelligence (AI) methods in machine learning (ML) and deep learning (DL) has opened opportunities for fluid dynamics and its applications in science, engineering and medicine. Developing AI methods for fluid dynamics encompass different challenges than applications with massive data, such as the Internet of Things. For many scientific, engineering and biomedical problems, the data are not massive, which poses limitations and algorithmic challenges. This paper reviews ML and DL research for fluid dynamics, presents algorithmic challenges and discusses potential future directions.

show abstract

“…In parallel with the recent innovations in flow control, the irruption of machine-learning (ML) techniques has brought tremendous potential to the aeronautics industry, both in terms of studying fundamental problems in fluid mechanics [7,8] and devising completely new strategies for active and passive flow control (AFC and PFC, respectively) [9]. Deep reinforcement learning (DRL) is one of the fastest-growing fields within ML [10] and one of the techniques attracting most interest.…”

Section: Introductionmentioning

confidence: 99%

Flow control of three-dimensional cylinders transitioning to turbulence via multi-agent reinforcement learning

Suárez,

Álcantara-Ávila,

Rabault

et al. 2024

Preprint

View full text Add to dashboard Cite

Designing active-flow-control (AFC) strategies for three-dimensional (3D) bluff bodies is a challenging task with critical industrial implications. In this study we explore the potential of discovering novel control strategies for drag reduction using deep reinforcement learning. We introduce a high-dimensional AFC setup on a 3D cylinder, considering Reynolds numbers (Re_D) from 100 to 400, which is a range including the transition to 3D wake instabilities. The setup involves multiple zero-net-mass-flux jets positioned on the top and bottom surfaces, aligned into two slots. The method relies on coupling the computational-fluid-dynamics solver with a multi-agent reinforcement-learning (MARL) framework based on the proximal-policy-optimization algorithm. MARL offers several advantages: it exploits local invariance, adaptable control across geometries, facilitates transfer learning and cross-application of agents, and results in a significant training speedup. For instance, our results demonstrate 21% drag reduction for Re_D=300, outperforming classical periodic control, which yields up to 6% reduction. To the authors' knowledge, the present MARL-based framework represents the first time where training is conducted in 3D cylinders. This breakthrough paves the way for conducting AFC on progressively more complex turbulent-flow configurations.

show abstract

Improving aircraft performance using machine learning: A review

Cited by 46 publications

References 319 publications

Design of the parametric appearance of the power plant for modifications of the regional passenger aircraft An-158

Design of the parametric appearance of the power plant for modifications of the regional passenger aircraft An-158

Can Artificial Intelligence Accelerate Fluid Mechanics Research?

Flow control of three-dimensional cylinders transitioning to turbulence via multi-agent reinforcement learning

Contact Info

Product

Resources

About