首页|Louisiana State University Researcher Yields New Study Findings on Machine Learn ing (Deep Learning-Based Eddy Viscosity Modeling for Improved RANS Simulations o f Wind Pressures on Bluff Bodies)
Louisiana State University Researcher Yields New Study Findings on Machine Learn ing (Deep Learning-Based Eddy Viscosity Modeling for Improved RANS Simulations o f Wind Pressures on Bluff Bodies)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators discuss new findings in artificial intelligence. According to news originating from Baton Rouge, Louisia na, by NewsRx correspondents, research stated, “Accurate prediction of wind pres sures on buildings is crucial for designing safe and efficient structures. Exist ing computational methods, like Reynolds-averaged Navier-Stokes (RANS) simulatio ns, often fail to predict pressures accurately in separation zones.” Our news editors obtained a quote from the research from Louisiana State Univers ity: “This study proposes a novel deep-learning methodology to enhance the accur acy and performance of eddy viscosity modeling within RANS turbulence closures, particularly improving predictions for bluff body aerodynamics. A deep learning model, trained on large eddy simulation (LES) data for various bluff body geomet ries, including a flat-roof building and forward/backward facing steps, was used to adjust eddy viscosity in RANS equations. The results show that incorporating the machine learning-predicted eddy viscosity significantly improves agreement with LES results and experimental data, particularly in the separation bubble an d shear layer. The deep learning model employed a neural network architecture wi th four hidden layers, 32 neurons, and tanh activation functions, trained using the Adam optimizer with a learning rate of 0.001. The training data consisted of LES simulations for forward/backward facing steps with width-to-height ratios r anging from 0.2 to 6. The study reveals that the machine learning model achieves a balance in eddy viscosity that delays flow reattachment, leading to more accu rate pressure and velocity predictions than traditional turbulence closures like k-o SST and k-e. A sensitivity analysis demonstrated the pivotal role of eddy v iscosity in governing flow separation, reattachment, and pressure distributions. ”
Louisiana State UniversityBaton RougeLouisianaUnited StatesNorth and Central AmericaCyborgsEmerging Technolo giesMachine Learning
NETL
NSTL
