arXiv subjects

Xiaosong Du

Publications and source records attributed to Xiaosong Du.

8 recordsLinked to original sources

arXiv2026

Transformer-Guided Deep Reinforcement Learning for Optimal Takeoff Trajectory Design of an eVTOL Drone

The rapid advancement of electric vertical takeoff and landing (eVTOL) aircraft offers a promising opportunity to alleviate urban traffic congestion but is still limited by excessive power demands, especially during the takeoff phase. Thus, developing optimal takeoff trajectories for minimum energy consumption becomes essential for broader eVTOL aircraft applications. Conventional optimal control methods (such as dynamic programming and linear quadratic regulator) provide highly efficient and well-established solutions but are prohibited by problem dimensionality and complexity. Deep reinforcement learning (DRL) emerges as a special type of artificial intelligence tackling complex, nonlinear systems; however, the training difficulty is a key bottleneck that hinders DRL applications. To address these challenges, we propose the transformer-guided DRL to alleviate the training difficulty by exploring a realistic state space at each time step using a transformer. The proposed transformer-guided DRL was demonstrated on an optimal takeoff trajectory design of an eVTOL drone for minimal energy consumption while meeting takeoff conditions (i.e., minimum vertical displacement and minimum horizontal velocity) by varying control variables (i.e., power and wing angle to the vertical). Results presented that the transformer-guided DRL agent learned to take off with $4.57\times10^6$ time steps, representing $25\%$ of the $19.79\times10^6$ time steps needed by a vanilla DRL agent. In addition, the transformer-guided DRL achieved $97.2\%$ accuracy on the optimal energy consumption compared against the simulation-based optimal reference, while the vanilla DRL achieved $96.1\%$ accuracy. Therefore, the proposed transformer-guided DRL outperformed vanilla DRL in terms of both training efficiency and optimal design verification.

cs.LG↗

arXiv2025

Physics-Constrained Generative Artificial Intelligence for Rapid Takeoff Trajectory Design

To aid urban air mobility (UAM), electric vertical takeoff and landing (eVTOL) aircraft are being targeted. Conventional multidisciplinary analysis and optimization (MDAO) can be expensive, while surrogate-based optimization can struggle with challenging physical constraints. This work proposes physics-constrained generative adversarial networks (physicsGAN), to intelligently parameterize the takeoff control profiles of an eVTOL aircraft and to transform the original design space to a feasible space. Specifically, the transformed feasible space refers to a space where all designs directly satisfy all design constraints. The physicsGAN-enabled surrogate-based takeoff trajectory design framework was demonstrated on the Airbus A3 Vahana. The physicsGAN generated only feasible control profiles of power and wing angle in the feasible space with around 98.9% of designs satisfying all constraints. The proposed design framework obtained 99.6% accuracy compared with simulation-based optimal design and took only 2.2 seconds, which reduced the computational time by around 200 times. Meanwhile, data-driven GAN-enabled surrogate-based optimization took 21.9 seconds using a derivative-free optimizer, which was around an order of magnitude slower than the proposed framework. Moreover, the data-driven GAN-based optimization using gradient-based optimizers could not consistently find the optimal design during random trials and got stuck in an infeasible region, which is problematic in real practice. Therefore, the proposed physicsGAN-based design framework outperformed data-driven GAN-based design to the extent of efficiency (2.2 seconds), optimality (99.6% accurate), and feasibility (100% feasible). According to the literature review, this is the first physics-constrained generative artificial intelligence enabled by surrogate models.

cs.LG↗

arXiv2022

Machine Learning in Aerodynamic Shape Optimization

Machine learning (ML) has been increasingly used to aid aerodynamic shape optimization (ASO), thanks to the availability of aerodynamic data and continued developments in deep learning. We review the applications of ML in ASO to date and provide a perspective on the state-of-the-art and future directions. We first introduce conventional ASO and current challenges. Next, we introduce ML fundamentals and detail ML algorithms that have been successful in ASO. Then, we review ML applications to ASO addressing three aspects: compact geometric design space, fast aerodynamic analysis, and efficient optimization architecture. In addition to providing a comprehensive summary of the research, we comment on the practicality and effectiveness of the developed methods. We show how cutting-edge ML approaches can benefit ASO and address challenging demands, such as interactive design optimization. Practical large-scale design optimizations remain a challenge because of the high cost of ML training. Further research on coupling ML model construction with prior experience and knowledge, such as physics-informed ML, is recommended to solve large-scale ASO problems.

cs.LG↗

arXiv2022

Learning High-Dimensional Parametric Maps via Reduced Basis Adaptive Residual Networks

We propose a scalable framework for the learning of high-dimensional parametric maps via adaptively constructed residual network (ResNet) maps between reduced bases of the inputs and outputs. When just few training data are available, it is beneficial to have a compact parametrization in order to ameliorate the ill-posedness of the neural network training problem. By linearly restricting high-dimensional maps to informed reduced bases of the inputs, one can compress high-dimensional maps in a constructive way that can be used to detect appropriate basis ranks, equipped with rigorous error estimates. A scalable neural network learning framework is thus to learn the nonlinear compressed reduced basis mapping. Unlike the reduced basis construction, however, neural network constructions are not guaranteed to reduce errors by adding representation power, making it difficult to achieve good practical performance. Inspired by recent approximation theory that connects ResNets to sequential minimizing flows, we present an adaptive ResNet construction algorithm. This algorithm allows for depth-wise enrichment of the neural network approximation, in a manner that can achieve good practical performance by first training a shallow network and then adapting. We prove universal approximation of the associated neural network class for $L^2_ν$ functions on compact sets. Our overall framework allows for constructive means to detect appropriate breadth and depth, and related compact parametrizations of neural networks, significantly reducing the need for architectural hyperparameter tuning. Numerical experiments for parametric PDE problems and a 3D CFD wing design optimization parametric map demonstrate that the proposed methodology can achieve remarkably high accuracy for limited training data, and outperformed other neural network strategies we compared against.

cs.LG↗

arXiv2018

Effect of a surface tension gradient on the slip flow along a superhydrophobic air-water interface

Superhydrophobic surfaces have been shown to produce significant drag reduction in both laminar and turbulent flows by introducing an apparent slip velocity along an air-water interface trapped within the surface roughness. In the experiments presented within this study, we demonstrate the existence of a surface tension gradient associated with the resultant Marangoni flow along an air-water interface that causes the slip velocity and slip length to be significantly reduced. In this study, the slip velocity along a millimeter-sized air-water interface was investigated experimentally. This large-scale air-water interface facilitated a detailed investigation of the interfacial velocity profiles as the flow rate, interfacial curvature and interface geometry were varied. For the air-water interfaces supported above continuous grooves (concentric rings within a torsional shear flow) where no surface tension gradient exists, a slip velocity as high as 30% of the bulk velocity was observed. However, for the air-water interfaces supported above discontinuous grooves (rectangular channels in a Poiseuille flow), the presence of a surface tension gradient reduced the slip velocity and in some cases resulted in an interfacial velocity that was opposite to the main flow direction. The curvature of the air-water interface in the spanwise direction was found to dictate the details of the interfacial flow profile with reverse flow in the center of the interface for concave surfaces and along the outside of the interface for convex surfaces. The deflection of the air-water interface was also found to greatly affect the magnitude of the slip. Numerical simulations imposed with a relatively small surface tension gradient along the air-water interface were able to predict both the reduced slip velocity and back flow along the air-water interface.

physics.flu-dyn↗

arXiv2014

Fabrication and Characterization of an Amperometric Glucose Sensor on a Flexible Polyimide Substrate

This study details the use of printing and other additive processes to fabricate a novel amperometric glucose sensor. The sensor was fabricated using a Au coated 12.7 micron polyimide film as a starting material, where micro-contact printing, electrochemical plating and chloridization, electrohydrodynamic jet (e-jet) printing, and spin coating were used to pattern, deposit, print, and coat functional materials, respectively. We have found that e-jet printing was effective for the deposition and patterning of glucose oxidase inks between ~5 to 1000 micron in width, and we have demonstrated that the enzyme was still active after printing. The thickness of the permselective layer was optimized to obtain a linear response to glucose concentration up to 32 mM. For these sensors no response to acetaminophen, a common interfering compound, was observed.

cond-mat.mtrl-sci↗

arXiv2014

Role of Self-Assembled Monolayers on Improved Electrical Stability of Amorphous In-Ga-Zn-O Thin-Film Transistors

Self-assembled monolayers (SAMs) have been used to improve both the positive and negative bias-stress stability of amorphous indium gallium zinc oxide (IGZO) bottom gate thin film transistors (TFTs). N-hexylphosphonic acid (HPA) and fluorinated hexylphosphonic acid (FPA) SAMs adsorbed on IGZO back channel surfaces were shown to significantly reduce bias stress turn-on voltage shifts compared to IGZO back channel surfaces with no SAMs. FPA was found to have a lower surface energy and lower packing density than HPA, as well as lower bias stress turn-on voltage shifts. The improved stability of IGZO TFTs with SAMs can be primarily attributed to a reduction in molecular adsorption of contaminants on the IGZO back channel surface and minimal trapping states present with phosphonic acid binding to the IGZO surface.

physics.chem-ph↗

arXiv2006

Electronic and magnetic properties of V-doped anatase TiO$_{2}$ from first principles

We report a first-principles study on the geometric, electronic and magnetic properties of V-doped anatase TiO$_{2}$. The DFT+U (Hubbard coefficient) approach predicts semiconductor band structures for Ti$_{1-x}$V$_{x}$O$_{2}$ (x=6.25 and 12.5%), in good agreement with the poor conductivity of samples, while the standard calculation within generalized gradient approximation fails. Theoretical results show that V atoms tend to stay close and result in strong ferromagnetism through superexchange interactions. Oxygen vacancy induced magnetic polaron could produce long-range ferromagnetic interaction between largely separated magnetic impurities. The experimentally observed ferromagnetism in V-doped anatase TiO$_{2}$ at room temperature may originate from a combination of short-range superexchange coupling and long-range bound magnetic polaron percolation.

cond-mat.mtrl-sci↗