Bilal Mufti

Bilal Mufti

Auto-generated profile, based on publicly available information

Bilal Mufti

Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology , Atlanta, Georgia 30332

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2024 in Physics of Fluids
Verified
Journal Article
Closed access
PDF file
BMBilal Mufti
Bilal Mufti
ABAnindya Bhaduri
Anindya Bhaduri
SGSayan Ghosh
Sayan Ghosh
LWLiping Wang
Liping Wang
Dimitri MavrisDimitri Mavris
Dimitri Mavris
Transonic flow fields are marked by shock waves of varying strength and location and are crucial for the aerodynamic design and optimization of high-speed transport aircraft. While deep learning methods offer the potential for predicting these fields, their deterministic outputs often lack predictive uncertainty. Moreover, their accuracy, especially near critical shock regions, needs better quantification. In this paper, we introduce a domain-informed probabilistic (DIP) deep learning framework tailored for predicting transonic flow fields with shock waves called DIP-ShockNet. This methodology utilizes Monte Carlo dropout to estimate predictive uncertainty and enhances flow-field predictions near the wall region by employing the inverse wall distance function-based input representation of the aerodynamic flow field. The obtained results are benchmarked against the signed distance function and the geometric mask input representations. The proposed framework further improves prediction accuracy in shock wave areas using a domain-informed loss function. To quantify the accuracy of our shock wave predictions, we developed metrics to assess errors in shock wave strength and location, achieving errors of 6.4% and 1%, respectively. Assessing the generalizability of our method, we tested it on different training sample sizes and compared it against the proper orthogonal decomposition (POD)-based reduced-order model (ROM). Our results indicate that DIP-ShockNet outperforms POD-ROM by 60% in predicting the complete transonic flow field.

1 March 2025 in Physics of Fluids
Verified
Journal Article
Closed access
BMBilal Mufti
Bilal Mufti
CPChristian Perron
Christian Perron
Dimitri MavrisDimitri Mavris
Dimitri Mavris
This paper presents a nonlinear reduced-order modeling (ROM) framework that leverages deep learning and manifold learning to predict compressible flow fields with complex nonlinear features, including shock waves. The proposed DeepManifold (DM)-ROM methodology is computationally efficient, avoids pixelation or interpolation of flow field data, and is adaptable to various grids and geometries. The framework consists of four main steps: First, a convolutional neural network-based parameterization network extracts nonlinear shape modes directly from aerodynamic geometries. Next, manifold learning is applied to reduce the dimensionality of the high-fidelity output flow fields. A multilayer perceptron-based regression network is then trained to map the nonlinear input and output modes. Finally, a back-mapping process reconstructs the full flow field from the predicted low-dimensional output modes. DM-ROM is rigorously tested on a transonic RAE2822 airfoil test case, which includes shock waves of varying strengths and locations. Metrics are introduced to quantify the model's accuracy in predicting shock wave strength and location. The results demonstrate that DM-ROM achieves a field prediction error of approximately 3.5% and significantly outperforms reference ROM techniques, such as proper orthogonal decomposition (POD)-ROM and isometric mapping (ISOMAP)-ROM, for various training sample sizes.

1 October 2024 in AIAA Journal
Verified
Journal Article
Closed access
BMBilal Mufti
Bilal Mufti
CPChristian Perron
Christian Perron
DMDimitri N. Mavris
Dimitri N. Mavris
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 multifidelity, parametric, and nonintrusive ROM framework designed for high-dimensional contexts. It integrates machine learning techniques for manifold alignment and dimension reduction—employing proper orthogonal decomposition and model-based active subspace—with multifidelity regression for ROM construction. Our approach is validated through two test cases: the 2D RAE 2822 airfoil and the 3D NASA CRM wing, assessing various fidelity levels, training data ratios, and sample sizes. Compared to the single-fidelity principal component–active subspace (PCAS) method, our multifidelity solution offers improved cost-accuracy benefits and achieves better predictive accuracy with reduced computational demands. Moreover, our methodology outperforms the manifold-aligned ROM method by 50% in handling scenarios with large input dimensions, underscoring its efficacy in addressing the complex challenges of aerospace design.

1 July 2019
Verified
Conference Paper
Closed access
BMBilal Mufti
Bilal Mufti
TKT.I. Khan
T.I. Khan
JMJ. Masud
J. Masud
ZTZakria Ghazanfar Toor
Zakria Ghazanfar Toor
The understanding of the flow field in the vicinity of fuselage/air inlet integration area and inside air intake is important for performance estimation of an air intake-propulsion system combination. In this paper flow field simulation of a Diverterless Supersonic Inlet (DSI) is carried out using Embedded LES (ELES) methodology. Zonal embedded mesh strategy is devised to resolve the integral length scale in LES zone. The analysis is carried out at a subsonic Mach number $\mathbf{M}_{\infty}=\mathbf{0 . 8}$ and a supersonic Mach number $\mathbf{M}_{\infty}=\mathbf{1 . 53}$. For each Mach number analysis is initially carried out at a design mass flow rate condition, flow field variations are subsequently analyzed for low and high mass flow rate conditions. Flow field is analyzed to ascertain the quality of flow exiting the air intake duct and entering engine. The existence of turbulent vortical structures formed inside duct due to wall shear effects is observed. The duct curvature adds an inherent swirl to the flow. Secondary flow structure at engine face plane remains relatively uniform at low and design mass flow rates for both subsonic and supersonic conditions. At high mass flow rate condition the secondary flow structure loses its uniformity with an increase in swirl magnitude. The shockwave structure on the bump compression surface is also effectively captured using the ELES methodology. The subsonic and supersonic total pressure recovery characteristic computed using ELES methodology showed agreement when compared with wind tunnel data.