MODELING UNSTEADINESS IN STEADY SIMULATIONS WITH NEURAL NETWORK GENERATED LUMPED DETERMINISTIC SOURCE TERMS

The lumped deterministic source term – neural network (LDST-NN) approach has been developed to obtain quasi-time-average solutions of cavity flows that include unsteady cavity effects in steady-state computations without the cavity. The results obtained with the LDST-NN based steady calculations are compared to the time average of fully unsteady solutions via the shear force acting on the cavity walls. Two orders of magnitude less computational time is required to obtain a quasi-time average simulation relative to time accurate simulations; a substantial savings. The estimated error, based on the calculated drag force, in these simulations is between 4% and 15 % as compared to fully unsteady calculations, which is satisfactory for many design purposes. This should be compared to the 40% to 154% errors obtained by neglecting the cavity completely for these same cases. As such, the modified neural network-based LDST model is a viable tool for representing unsteady cavity effects. The LDST-NN quasi-time averaged solution was able to capture global unsteady effects correctly. The LDSTs were found to correlate directly with observed sound pressure level trends and provide an additional means of assessing unsteadiness. The LDSTs were found to reach a maximum near the cavity/main flow interface but also extended well into the field; indicating that boundary condition representations alone would be inadequate for capturing unsteady effects. Deterministic source terms were computed from unsteady simulations and modeled with a neural network for use in steady simulations sans cavity to capture the entire time average effect of the cavity. This was demonstrated for the entire range of Mach numbers, length-to-depth ratios and various translational velocities of the cavity wall. The results of the study showed that modeling flow over cavities is possible with steady simulations that include source terms provided by a neural network. This method permits a considerable reduction in CPU time and is attractive for large scale simulations since it includes the effects of the unsteady phenomena without computing the unsteady flow inside the cavity.

[1]  Sound generation by flow over a two-dimensional cavity , 1993 .

[2]  James C. Ross,et al.  Reducing Wind Tunnel Data Requirements Using Neural Networks , 1997 .

[3]  Oktay Baysal,et al.  Navier-Stokes Calculations of Transonic Flows Past Cavities , 1991 .

[4]  E. Capaldi,et al.  The organization of behavior. , 1992, Journal of applied behavior analysis.

[5]  G. Labonté,et al.  Neural network reconstruction of fluid flows from tracer-particle displacements , 2001 .

[6]  Supersonic open cavity flow physics ascertained from algebraic turbulence model simulations , 1996 .

[7]  Edward J. Hall,et al.  Parameterized study of high-speed compressor seal cavity flow , 1996 .

[8]  Philip J. Morris,et al.  Parallel computational aeroacoustic simulation of turbulent subsonic cavity flow , 2000 .

[9]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[10]  V. Sarohia.  Experimental investigation of oscillations in flows over shallow cavities , 1976 .

[11]  Deepak Shukla,et al.  DEVELOPMENT OF AN ADAPTIVE WEAPONS-BAY SUPPRESSION SYSTEM , 1999 .

[12]  K. K. Ahuja,et al.  Effects of cavity dimensions, boundary layer, and temperature on cavity noise with emphasis on benchmark data to validate computational aeroacoustic codes , 1995 .

[13]  E. R. V. Driest.  On Turbulent Flow Near a Wall , 1956 .

[14]  J. Rossiter.  Wind tunnel experiments on the flow over rectangular cavities at subsonic and transonic speeds , 1964 .

[15]  S. Chakravarthy,et al.  A Wall-Distance-Free k-ε Model With Enhanced Near-Wall Treatment , 1998 .

[16]  A. B. Turner,et al.  Simple Design Methods for the Prediction of Radial Static Pressure Distributions in a Rotor-Stator Cavity With Radial Inflow , 1995 .

[17]  P. Roe.  Approximate Riemann Solvers, Parameter Vectors, and Difference Schemes , 1997 .

[18]  Scott D. Hunter,et al.  Endwall Cavity Flow Effects on Gaspath Aerodynamics in an Axial Flow Turbine: Part II — Source Term Model Development , 2000 .

[19]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[20]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[21]  James E. Steck,et al.  Application of an artificial neural network as a flight test data estimator , 1995 .

[22]  Man Mohan Rai,et al.  Application of artificial neural networks to the design of turbomachinery airfoils , 1998 .

[23]  Sukumar Chakravarthy,et al.  A 'grid-transparent' methodology for CFD , 1997 .

[24]  Aldo Rona,et al.  Attenuation of cavity flow oscillation through leading edge flow control , 1999 .

[25]  William W. Durgin,et al.  Tone Generation by Flow Past Deep Wall Cavities , 1987 .

[26]  Paul D. Orkwis,et al.  Modeling Unsteadiness in Steady Cavity Simulations Part II: Neural Network Modeling , 2001 .

[27]  A. Hamed,et al.  Unsteady supersonic cavity flow simulations using coupled k-epsilon and Navier-Stokes equations , 1994 .

[28]  R. Benning,et al.  Initial studies of predicting flow fields with an ANN hybrid , 2001 .

[29]  R. C. Bauer,et al.  Experimental and Predicted Acoustic Amplitudes in a Rectangular Cavity , 2000 .

[30]  H. E. Plumblee,et al.  A THEORETICAL AND EXPERIMENTAL INVESTIGATION OF THE ACOUSTIC RESPONSE OF CAVITIES IN AN AERODYNAMIC FLOW , 1962 .

[31]  Comparison of Baldwin-Lomax Turbulence Models for Two-Dimensional Open Cavity Computations , 1996 .

[32]  R. Greenman.  Two-dimensional high-lift aerodynamic optimization using neural networks , 1998 .

[33]  P. Orkwis,et al.  Observations on using experimental data as boundary conditions for computations , 1995 .

[34]  Paul D. Orkwis,et al.  Modeling Unsteadiness in Steady Cavity Simulations Part I: Parametric Solutions , 2001 .

[35]  M. Pindera.  Adaptive flow control using simple artificial neural networks , 2002 .

[36]  Ndaona Chokani,et al.  Navier-Stokes study of supersonic cavity flowfield with passive control , 1992 .

[37]  P. Disimile,et al.  Pressure Oscillations in a Subsonic Cavity at Yaw , 1998 .

[38]  Theodore H. Okiishi,et al.  Modeling Shrouded Stator Cavity Flows in Axial-Flow Compressors , 1999 .

[39]  J. Denton.  Loss Mechanisms in Turbomachines , 1993 .

[40]  Peter J. Disimile,et al.  Algebraic turbulence model simulations of supersonic open-cavity flow physics , 1996 .

[41]  K. Krishnamurty,et al.  Acoustic radiation from two-dimensional rectangular cutouts in aerodynamic surfaces , 1955 .

[42]  Richard E. Dix,et al.  Aeroacoustic Effects of Body Blockage in Cavity Flow , 1987 .

[43]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[44]  Charles Meneveau,et al.  A deterministic stress model for rotor-stator interactions in simulations of average-passage flow , 2002 .

[45]  Timothy J. Bencic,et al.  Tone Noise and Nearfield Pressure Produced by Jet-Cavity Interaction , 1999 .

[46]  P. C. Ivey,et al.  An Experimental Examination of Cantilevered and Shrouded Stators in a Multistage Axial Compressor , 1998 .

[47]  B. Lukovic,et al.  Modeling Unsteady Turbomachinery Purge Cavity Flows with Rotating Walls , 2002 .

[48]  Yongliang Zhu,et al.  Adaptive Output Feedback Control of Nonlinear Systems , 2004 .

[49]  J. Y. Kazakia,et al.  Air flow in cavities of labyrinth seals , 1995 .

[50]  O. Baysal,et al.  Navier-Stokes Computations of Cavity Aeroacoustics with Suppression Devices , 1994 .

[51]  L. F. East,et al.  Three-dimensional flow in cavities , 1963, Journal of Fluid Mechanics.

[52]  Morteza Gharib,et al.  The effect of flow oscillations on cavity drag , 1987, Journal of Fluid Mechanics.

[53]  Wei Shyy,et al.  Shape Optimization of Supersonic Turbines Using Response Surface and Neural Network Methods , 2001 .

[54]  Aldo Rona,et al.  AN OBSERVATION OF PRESSURE WAVES AROUND A SHALLOW CAVITY , 1998 .

[55]  Xin Zhang,et al.  Compressible cavity flow oscillation due to shear layer instabilities and pressure feedback , 1995 .

[56]  Roger L. Davis,et al.  DETERMINISTIC STRESS MODELING OF HOT GAS SEGREGATION IN A TURBINE , 2000 .

[57]  Roger L. Davis,et al.  Modeling turbomachinery unsteadiness with lumped deterministic stresses , 1996 .

[58]  William E. Faller,et al.  Real-time prediction of unsteady aerodynamics: Application for aircraft control and manoeuvrability enhancement , 1995, IEEE Trans. Neural Networks.

[59]  Li He,et al.  Some Modeling Issues on Trailing-Edge Vortex Shedding , 2001 .

[60]  James E. Steck,et al.  Some applications of artificial neural networks in modeling of nonlinear aerodynamics and flight dynamics , 1997 .

[61]  W. L. Hankey,et al.  Analyses of Pressure Oscillations in an Open Cavity , 1980 .

[62]  Martin T. Hagan,et al.  Neural network design , 1995 .

[63]  J. Owen,et al.  Flow and Heat Transfer in a Preswirl Rotor–Stator System , 1997 .

[64]  J. A. Edwards,et al.  Analysis of unsteady supersonic cavity flow employing an adaptive meshing algorithm , 1996 .

[65]  Bernard Widrow,et al.  Adaptive switching circuits , 1988 .

[66]  Theodore H. Okiishi,et al.  The Influence of Shrouded Stator Cavity Flows on Multistage Compressor Performance , 1998 .

[67]  Maureen B. Tracy,et al.  Cavity Unsteady-Pressure Measurements at Subsonic and Transonic Speeds , 1997 .

[68]  E. Covert,et al.  Flow-Induced Pressure Oscillations in Shallow Cavities , 1971 .

[69]  James L. Rogers,et al.  Aerodynamic performance optimization of a rotor blade using a neural network as the analysis , 1992 .

[70]  D. Ronneberger,et al.  The dynamics of shearing flow over a cavity— A visual study related to the acoustic impedance of small orifices , 1980 .

[71]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[72]  Dennis Gabor,et al.  Communication Theory and Cybernetics , 1954 .

[73]  M. L. Celestina,et al.  A model for closing the inviscid form of the average−passage equation system , 1986 .