Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Engineering
Machine Learning In Aerodynamic Shape Optimization, Jichao Li, Xiaosong Du, Joaquim R.R.A. Martins
Machine Learning In Aerodynamic Shape Optimization, Jichao Li, Xiaosong Du, Joaquim R.R.A. Martins
Mechanical and Aerospace Engineering Faculty Research & Creative Works
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, …
Inherent And Model-Form Uncertainty Analysis For Cfd Simulation Of Synthetic Jet Actuators, Daoru Frank Han, Serhat Hosder
Inherent And Model-Form Uncertainty Analysis For Cfd Simulation Of Synthetic Jet Actuators, Daoru Frank Han, Serhat Hosder
Mechanical and Aerospace Engineering Faculty Research & Creative Works
A mixed (aleatory and epistemic) uncertainty quantification (UQ) method was applied to computational uid dynamics (CFD) modeling of a synthetic jet actuator. A test case, (ow over a hump model with synthetic jet actuator control) from the CFDVAL2004 work-shop was selected to apply the Second-Order Probability framework implemented with a stochastic response surface obtained from Quadrature-Based Non-Intrusive Polynomial Chaos (NIPC). Three uncertainty sources were considered: (1) epistemic (model-form) uncertainty in turbulence model, (2) aleatory (inherent) uncertainty in free stream veloc-ity and (3) aleatory uncertainty in actuation frequency. Uncertainties in both long-time averaged and phase averaged quantities were quantified using a …
Uncertainty Quantification Integrated To The Cfd Modeling Of Synthetic Jet Actuators, Srikanth Adya, Daoru Frank Han, Serhat Hosder
Uncertainty Quantification Integrated To The Cfd Modeling Of Synthetic Jet Actuators, Srikanth Adya, Daoru Frank Han, Serhat Hosder
Mechanical and Aerospace Engineering Faculty Research & Creative Works
The Point Collocation Non-Intrusive Polynomial Chaos (NIPC) method has been applied to two stochastic synthetic jet actuator problems used as test cases in the CFDVAL2004 workshop to demonstrate the integration of computationally efficient uncertainty quantification to the high-fidelity CFD modeling of synthetic jet actuators. In Case1 where the synthetic jet is issued into quiescent air, the NIPC method is used to quantify the uncertainty in the long-time averaged u and v-velocities at several locations in the flow field, due to the uniformly distributed uncertainty introduced in the amplitude and frequency of the oscillation of the piezo-electric membrane. Fifth order NIPC …