“…Early gradient-based inverse design algorithms were based on MLPs [2], [131], [132], which has proven to be a poor approach. The problems are as follows: a) these works, to some extent, are less accurate; and b) these works still require the parametrization of the geometric shapes of wings.…”
This paper reviews studies on neural networks in aerodynamic data modeling. In this paper, we analyze the shortcomings of computational fluid dynamics (CFD) and traditional reduced-order models (ROMs). Subsequently, the history and fundamental methodologies of neural networks are introduced. Furthermore, we classify the neural networks based studies in aerodynamic data modeling and illustrate comparisons among them. These studies demonstrate that neural networks are effective approaches to aerodynamic data modeling. Finally, we identify three important trends for future studies in aerodynamic data modeling: a) the transformation method and physics informed models will be combined to solve high-dimensional partial differential equations; b) in the research area of steady aerodynamic response predictions, model-oriented studies and data-integration-oriented studies will become the future research directions, while in unsteady aerodynamic response predictions, radial basis function neural networks (RBFNNs) are the best tools for capturing the nonlinear characteristics of flow data, and convolutional neural networks (CNNs) are expected to replace long short-term memories (LSTMs) to capture the temporal characteristics of flow data; and c) in the field of steady or unsteady flow field reconstructions, the CNN-based conditional generative adversarial networks (cGANs) will be the best frameworks in which to discover the spatiotemporal distribution of flow field data. INDEX TERMS Aerodynamics, convolutional neural networks, neural networks, generative adversarial networks, recurrent neural networks.
“…Early gradient-based inverse design algorithms were based on MLPs [2], [131], [132], which has proven to be a poor approach. The problems are as follows: a) these works, to some extent, are less accurate; and b) these works still require the parametrization of the geometric shapes of wings.…”
This paper reviews studies on neural networks in aerodynamic data modeling. In this paper, we analyze the shortcomings of computational fluid dynamics (CFD) and traditional reduced-order models (ROMs). Subsequently, the history and fundamental methodologies of neural networks are introduced. Furthermore, we classify the neural networks based studies in aerodynamic data modeling and illustrate comparisons among them. These studies demonstrate that neural networks are effective approaches to aerodynamic data modeling. Finally, we identify three important trends for future studies in aerodynamic data modeling: a) the transformation method and physics informed models will be combined to solve high-dimensional partial differential equations; b) in the research area of steady aerodynamic response predictions, model-oriented studies and data-integration-oriented studies will become the future research directions, while in unsteady aerodynamic response predictions, radial basis function neural networks (RBFNNs) are the best tools for capturing the nonlinear characteristics of flow data, and convolutional neural networks (CNNs) are expected to replace long short-term memories (LSTMs) to capture the temporal characteristics of flow data; and c) in the field of steady or unsteady flow field reconstructions, the CNN-based conditional generative adversarial networks (cGANs) will be the best frameworks in which to discover the spatiotemporal distribution of flow field data. INDEX TERMS Aerodynamics, convolutional neural networks, neural networks, generative adversarial networks, recurrent neural networks.
“…The authors of this paper have both been dedicated to an applicable airfoil/wing inverse design method with the help of ANN and database (Figure 3) in a design for a transonic swept wing of a passenger jet. 16 It can directly generate profiles fitting the requested aerodynamic performance with trained neural network, avoiding the repetitive cut-and-try. 35 Figure 3.An airfoil database for inverse design.…”
Section: Surrogate Model In Aerodynamic Design With Annmentioning
confidence: 99%
“…12 Parametric section (PARSEC) is compared with other kinds of parametrization method and is evaluated as appropriate for airfoil description due to its accuracy and intuitiveness. 16…”
Section: Surrogate Model In Aerodynamic Design With Annmentioning
confidence: 99%
“…Traditionally, airfoil design is important for aircraft wings, helicopter rotor blades, etc. 16 Given the boundary conditions of coming flow, the airfoil shape determines its aerodynamic performance including the pressure distribution over the surface. Navier-Stokes equations are applied for obtaining the pressure distribution of specified airfoil shape.…”
Artificial neural network surrogate modeling with its economic computational consumption and accurate generalization capabilities offers a feasible approach to aerodynamic design in the field of rapid investigation of design space and optimal solution searching. This paper reviews the basic principle of artificial neural network surrogate modeling in terms of data treatment and configuration setup. A discussion of artificial neural network surrogate modeling is held on different objectives in aerodynamic design applications, various patterns of realization via cutting-edge data technique in numerous optimizations, selection of network topology and types, and other measures for improving modeling. Then, new frontiers of modern artificial neural network surrogate modeling are reviewed with regard to exploiting the hidden information for bringing new perspectives to optimization by exploring new data form and patterns, e.g. quick provision of candidates of better aerodynamic performance via accumulated database instead of random seeding, and envisions of more physical understanding being injected to the data manipulation.
“…NNs have been a very popular approach to solving many different types of problems in aerospace engineering. NNs have been used for trajectory prediction [30], failure detection and identification [31], design of brake systems [32], aerodynamic coefficient prediction [33], motion control [34], and aircraft structure design [35]. Most relevant to this thesis is the application of NNs in identification and accommodation of abnormal conditions [36].…”
A detection and identification scheme for abnormal conditions was developed for an unmanned aerial vehicle (UAV) based on the artificial immune system (AIS) paradigm. This technique involves establishing a body of data to represent normal conditions referred to as "self" and differentiating these conditions from abnormal conditions, referred to as "non-self". Data collected from simulation of the UAV attempting to autonomously fly a pre-decided trajectory were used to develop and test a scheme that was able to detect and identify aircraft sensor and actuator faults. These faults included aerodynamic control surface locks and damages and angular rate sensor biases. The method used to create the AIS is known as the partition of the universe approach. This approach differs from standard clustering approaches because the universe is divided into uniform partition clusters rather than clustering data using some clustering algorithm. It is simpler and requires less computational resources. This will be the first time that this approach has been applied for use in aerospace engineering. Data collected from nominal flights were used to define self partitions, and the non-self partitions were defined implicitly. The creation scheme is also discussed, involving all software used for simulation, as well as the process of creating the self and the logic behind the detection and identification schemes. The detection scheme was evaluated based on detection rate, detection time, and false alarms for flights under both normal and abnormal conditions. The failure identification scheme was assessed in terms of identification rate and time. Investigation of the proposed technique showed promising results for the cases explored with comparable performance with respect to clustering-based approaches and motivates further research and extension of the proposed methodology toward a more complete health management system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
