Search

Complex engineering systems require integration of simulation of sub-systems and calculation of metrics to drive design decisions. This paper introduces a methodology for designing computational or physical experiments for system-level uncertainty mitigation purposes. The methodology follows a previously determined problem ontology, where physical, functional and modeling architectures are decided upon. By carrying out sensitivity analysis techniques utilizing system-level tools, critical epistemic uncertainties can be identified. Afterwards, a framework is introduced to design specific computational and physical experimentation for generating new knowledge about parameters, and for uncertainty mitigation. The methodology is demonstrated through a case study on an early-stage design Blended-Wing-Body (BWB) aircraft concept, showcasing how aerostructures analyses can be leveraged for mitigating system-level uncertainty, by computer experiments or guiding physical experimentation. The proposed methodology is versatile enough to tackle uncertainty management across various design challenges, highlighting the potential for more risk-informed design processes.

In the early stages of aerospace design, reduced order models (ROMs) are crucial for minimizing computational costs associated with using physics-rich field information in many-query scenarios requiring multiple evaluations. The intricacy of aerospace design demands the use of high-dimensional design spaces to capture detailed features and design variability accurately. However, these spaces introduce significant challenges, including the curse of dimensionality, which stems from both high-dimensional inputs and outputs necessitating substantial training data and computational effort. To address these complexities, this study introduces a novel multi-fidelity, parametric, and non-intrusive ROM framework designed for high-dimensional contexts. It integrates machine learning techniques for manifold alignment and dimension reduction employing Proper Orthogonal Decomposition (POD) and Model-based Active Subspace with multi-fidelity regression for ROM construction. Our approach is validated through two test cases: the 2D RAE~2822 airfoil and the 3D NASA CRM wing, assessing combinations of various fidelity levels, training data ratios, and sample sizes. Compared to the single-fidelity PCAS method, our multi-fidelity solution offers improved cost-accuracy benefits and achieves better predictive accuracy with reduced computational demands. Moreover, our methodology outperforms the manifold-aligned ROM (MA-ROM) method by 50% in handling scenarios with large input dimensions, underscoring its efficacy in addressing the complex challenges of aerospace design.

Accurate modeling of aircraft environmental impact is pivotal to the design of operational procedures and policies to mitigate negative aviation environmental impact. Aircraft environmental impact segmentation is a process which clusters aircraft types that have similar environmental impact characteristics based on a set of aircraft features. This practice helps model a large population of aircraft types with insufficient aircraft noise and performance models and contributes to better understanding of aviation environmental impact. Through measuring the similarity between aircraft types, distance metric is the kernel of aircraft segmentation. Traditional ways of aircraft segmentation use plain distance metrics and assign equal weight to all features in an unsupervised clustering process. In this work, we utilize weakly-supervised metric learning and partial information on aircraft fuel burn, emissions, and noise to learn weighted distance metrics for aircraft environmental impact segmentation. We show in a comprehensive case study that the tailored distance metrics can indeed make aircraft segmentation better reflect the actual environmental impact of aircraft. The metric learning approach can help refine a number of similar data-driven analytical studies in aviation., Comment: 32 pages, 11 figures

In this work, a novel Stackelberg game theoretic framework is proposed for trading energy bidirectionally between the demand-response (DR) aggregator and the prosumers. This formulation allows for flexible energy arbitrage and additional monetary rewards while ensuring that the prosumers' desired daily energy demand is met. Then, a scalable (linear with the number of prosumers), decentralized, privacy-preserving algorithm is proposed to find approximate equilibria with online sampling and learning of the prosumers' cumulative best response, which finds applications beyond this energy game. Moreover, cost bounds are provided on the quality of the approximate equilibrium solution. Finally, real data from the California day-ahead market and the UC Davis campus building energy demands are utilized to demonstrate the efficacy of the proposed framework and algorithm., Comment: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

This work presents the application of a recently developed parametric, non-intrusive, and multi-fidelity reduced-order modeling method on high-dimensional displacement and stress fields arising from the structural analysis of geometries that differ in the size of discretization and structural topology.The proposed approach leverages manifold alignment to fuse inconsistent field outputs from high- and low-fidelity simulations by individually projecting their solution onto a common subspace. The effectiveness of the method is demonstrated on two multi-fidelity scenarios involving the structural analysis of a benchmark wing geometry. Results show that outputs from structural simulations using incompatible grids, or related yet different topologies, are easily combined into a single predictive model, thus eliminating the need for additional pre-processing of the data. The new multi-fidelity reduced-order model achieves a relatively higher predictive accuracy at a lower computational cost when compared to a single-fidelity model., Comment: The peer-reviewed and corrected version of this article has been accepted for publication in the Structural and Multidisciplinary Optimization Journal

In recent years, there has been a rapid growth in the application of machine learning techniques that leverage aviation data collected from commercial airline operations to improve safety. Anomaly detection and predictive maintenance have been the main targets for machine learning applications. However, this paper focuses on the identification of precursors, which is a relatively newer application. Precursors are events correlated with adverse events that happen prior to the adverse event itself. Therefore, precursor mining provides many benefits including understanding the reasons behind a safety incident and the ability to identify signatures, which can be tracked throughout a flight to alert the operators of the potential for an adverse event in the future. This work proposes using the multiple-instance learning (MIL) framework, a weakly supervised learning task, combined with carefully designed binary classifier leveraging a Multi-Head Convolutional Neural Network-Recurrent Neural Network (MHCNN-RNN) architecture. Multi-class classifiers are then created and compared, enabling the prediction of different adverse events for any given flight by combining binary classifiers, and by modifying the MHCNN-RNN to handle multiple outputs. Results obtained showed that the multiple binary classifiers perform better and are able to accurately forecast high speed and high path angle events during the approach phase. Multiple binary classifiers are also capable of determining the aircraft's parameters that are correlated to these events. The identified parameters can be considered precursors to the events and may be studied/tracked further to prevent these events in the future., Comment: 29 pages, 15 figures, 9 tables

Modern day engineering problems are ubiquitously characterized by sophisticated computer codes that map parameters or inputs to an underlying physical process. In other situations, experimental setups are used to model the physical process in a laboratory, ensuring high precision while being costly in materials and logistics. In both scenarios, only limited amount of data can be generated by querying the expensive information source at a finite number of inputs or designs. This problem is compounded further in the presence of a high-dimensional input space. State-of-the-art parameter space dimension reduction methods, such as active subspace, aim to identify a subspace of the original input space that is sufficient to explain the output response. These methods are restricted by their reliance on gradient evaluations or copious data, making them inadequate to expensive problems without direct access to gradients. The proposed methodology is gradient-free and fully Bayesian, as it quantifies uncertainty in both the low-dimensional subspace and the surrogate model parameters. This enables a full quantification of epistemic uncertainty and robustness to limited data availability. It is validated on multiple datasets from engineering and science and compared to two other state-of-the-art methods based on four aspects: a) recovery of the active subspace, b) deterministic prediction accuracy, c) probabilistic prediction accuracy, and d) training time. The comparison shows that the proposed method improves the active subspace recovery and predictive accuracy, in both the deterministic and probabilistic sense, when only few model observations are available for training, at the cost of increased training time.

We consider the fusion of two aerodynamic data sets originating from differing fidelity physical or computer experiments. We specifically address the fusion of: 1) noisy and in-complete fields from wind tunnel measurements and 2) deterministic but biased fields from numerical simulations. These two data sources are fused in order to estimate the \emph{true} field that best matches measured quantities that serves as the ground truth. For example, two sources of pressure fields about an aircraft are fused based on measured forces and moments from a wind-tunnel experiment. A fundamental challenge in this problem is that the true field is unknown and can not be estimated with 100\% certainty. We employ a Bayesian framework to infer the true fields conditioned on measured quantities of interest; essentially we perform a \emph{statistical correction} to the data. The fused data may then be used to construct more accurate surrogate models suitable for early stages of aerospace design. We also introduce an extension of the Proper Orthogonal Decomposition with constraints to solve the same problem. Both methods are demonstrated on fusing the pressure distributions for flow past the RAE2822 airfoil and the Common Research Model wing at transonic conditions. Comparison of both methods reveal that the Bayesian method is more robust when data is scarce while capable of also accounting for uncertainties in the data. Furthermore, given adequate data, the POD based and Bayesian approaches lead to \emph{similar} results., Comment: 33 pages, 19 figures

The adaptability of the convolutional neural network (CNN) technique for aerodynamic meta-modeling tasks is probed in this work. The primary objective is to develop suitable CNN architecture for variable flow conditions and object geometry, in addition to identifying a sufficient data preparation process. Multiple CNN structures were trained to learn the lift coefficients of the airfoils with a variety of shapes in multiple flow Mach numbers, Reynolds numbers, and diverse angles of attack. This is conducted to illustrate the concept of the technique. A multi-layered perceptron (MLP) is also used for the training sets. The MLP results are compared with that of the CNN results. The newly proposed meta-modeling concept has been found to be comparable with the MLP in learning capability; and more importantly, our CNN model exhibits a competitive prediction accuracy with minimal constraints in a geometric representation.

This paper presents a methodology that enables projection-based model reduction for black-box high-fidelity models such as commercial CFD codes. The methodology specifically addresses the situation where the high-fidelity model may be a black-box but there is complete knowledge of the governing equations. The main idea is that the linear operator matrix, resulting from the discretization of the linear differential terms is approximated directly using a suitable discretization method such as the Finite Volume Method and requires only the computational grid as input. In this regard, the governing equations are first cast in terms of a set of scalar observables of the state variables, leading to a linear set of equations. By applying the snapshots of the observables to the discrete linear operator, a right hand side vector is obtained, providing the necessary system matrices for the Galerkin projection step. This way an online database of ROMs are generated for various parameter snapshots which are then interpolated online to predict the state for new parameter instances. Finally, the reduced order model is posed as a non-linear constrained optimization problem that can be solved at a significantly cheaper cost compared to the full order model. The method is successfully demonstrated on on a canonical non-linear parametric PDE with exponential non-linearity, followed by the compressible inviscid ow past the NACA0012 airfoil. As a first step, this paper focuses only on establishing feasibility of the method., Comment: 36 pages. Submitted to the AIAA Journal

In a multi-agent system, agents coordinate to achieve global tasks through local communications. Coordination usually requires sufficient information flow, which is usually depicted by the connectivity of the communication network. In a networked system, removal of some agents may cause a disconnection. In order to maintain connectivity in agent removal, one can design a robust network topology that tolerates a finite number of agent losses, and/or develop a control strategy that recovers connectivity. This paper proposes a decentralized control scheme based on a sequence of replacements, each of which occurs between an agent and one of its immediate neighbors. The replacements always end with an agent, whose relocation does not cause a disconnection. We show that such an agent can be reached by a local rule utilizing only some local information available in agents' immediate neighborhoods. As such, the proposed message passing strategy guarantees the connectivity maintenance in arbitrary agent removal. Furthermore, we significantly improve the optimality of the proposed scheme by incorporating $\delta$-criticality (i.e. the criticality of an agent in its $\delta$-neighborhood)., Comment: 9 pages, 9 figures