CFD-Based Optimization of Fluid Flow Product Aided by Artificial Intelligence and Design Space Validation

Li, Lei; Cheng, Zhengrong; Lange, Carlos F.

doi:10.1155/2018/8465020

Cited by 8 publications

(6 citation statements)

References 42 publications

(51 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 2 shows a flow chart for the CFD simulation, which consists of mainly three steps: model formation, solver setup, and postprocessing. The given algorithm is based on the studies mentioned in the literature 20,21 …”

Section: Design Methodologymentioning

confidence: 99%

See 1 more Smart Citation

Numerical optimization for fluid flow in turboexpander wheel of helium liquefaction plant

2020

View full text Add to dashboard Cite

A radial turbine is one of the vital components of a helium liquefaction plant. The design of a turbine becomes critical due to its compact size and high‐speed configuration. In this study, numerical optimization has been performed for the three‐dimensional steady flow of helium gas in the radial inflow turbine of a helium liquefaction plant at a nominal condition. The mean line design is an appropriate method to obtain the approximate results. The computational fluid dynamics simulation algorithm is adopted in this study to reach the final results and Ansys CFX is used for the simulation. From the analysis, it has been reported that the number of rotor blades was overestimated in the mean line design. Performance parameters like total‐to‐static efficiency and velocity ratio were also found to be optimum numerically under a preliminary design condition. Finally, power of 1.7 kW was achieved at total‐to‐static efficiency of 71.4%. The deviation in analytical and numerical results is within ± 10 % for performance as well as geometric parameters.

show abstract

Section: Design Methodologymentioning

confidence: 99%

“…The given algorithm is based on the studies mentioned in the literature. 20,21 The physical model consists of selection of turbulence model, fluid properties, and so forth. The CFD results are approached by performing grid independence test and obtaining optimum number of blades, and finalized after the validation.…”

Section: Mean Line Designmentioning

confidence: 99%

Numerical optimization for fluid flow in turboexpander wheel of helium liquefaction plant

2020

View full text Add to dashboard Cite

show abstract

“…Based on the previous research on the intelligent CFD simulation system [14,39,40], the intelligent FSI simulation system is proposed, as illustrated in Figure 2. This system is composed of CFD simulation and structure simulation, with the interface between FS domains as the medium of the data transfer.…”

Section: Intelligent Fsi Simulation Systemmentioning

confidence: 99%

Intelligent Design Optimization System for Additively Manufactured Flow Channels Based on Fluid–Structure Interaction

Zou

et al. 2022

Micromachines

Self Cite

View full text Add to dashboard Cite

Based on expert system theory and fluid–structure interaction (FSI), this paper suggests an intelligent design optimization system to derive the optimal shape of both the fluid and solid domain of flow channels. A parametric modeling scheme of flow channels is developed by design for additive manufacturing (DfAM). By changing design parameters, a series of flow channel models can be obtained. According to the design characteristics, the system can intelligently allocate suitable computational models to compute the flow field of a specific model. The pressure-based normal stress is abstracted from the results and transmitted to the solid region by the fluid–structure (FS) interface to analyze the strength of the structure. The design space is obtained by investigating the simulation results with the metamodeling method, which is further applied for pursuing design objectives under constraints. Finally, the improved design is derived by gradient-based optimization. This system can improve the accuracy of the FSI simulation and the efficiency of the optimization process. The design optimization of a flow channel in a simplified hydraulic manifold is applied as the case study to validate the feasibility of the proposed system.

show abstract

“…Response surface models, kriging and feedforward ANNs have proven to be useful in the field of metamodeling-assisted design optimization (among others) and some of them are available even in commercial software nowadays. Though new techniques have been invented and many improvements have been done, state-of-the-art research [9,10] utilizes the same core idea as presented in the introductory paper of DACE [3].…”

Section: Related Workmentioning

confidence: 99%

Accelerating Convergence of Fluid Dynamics Simulations with Convolutional Neural Networks

Hajgató

Gyires-Tóth

Paál

2019

Period. Polytech. Mech. Eng.

View full text Add to dashboard Cite

A novel technique to accelerate optimization-driven aerodynamic shape design is presented in the paper. The methodology of optimization-driven design is based on the automated evaluation of many similar shapes which are generated according to the output of an optimization algorithm. The vast amount of numerical simulations makes this process slow but the resource-intensive simulation part can be changed to so-called surrogate models or metamodels. However, there isn’t any guarantee of this solution’s accuracy.The motivation of this work was to develop an acceleration method to speedup optimization sessions without losing accuracy. Accordingly, the numerical simulation is kept in the pipeline but it is initialized with a velocity field that is close to the expected solution. This velocity field is generated by a predictive initializer that is based on a convolutional deep neural network. The network has to be trained before using it for initializing numerical simulations; the data generation, the training and the testing of the network are described in the paper as well.The performance of predictive initializing is presented through a test problem based on a deformable u-bend geometry. It has been found that the speedup in the convergence speed of the numerical simulation depends on the resolution of the predictive initializer and on the handling of velocities in the near-wall cells. A speedup of 13 % was achieved on a test set of 500 geometries that were not seen by the initializer before.

show abstract

CFD-Based Optimization of Fluid Flow Product Aided by Artificial Intelligence and Design Space Validation

Cited by 8 publications

References 42 publications

Numerical optimization for fluid flow in turboexpander wheel of helium liquefaction plant

Numerical optimization for fluid flow in turboexpander wheel of helium liquefaction plant

Intelligent Design Optimization System for Additively Manufactured Flow Channels Based on Fluid–Structure Interaction

Accelerating Convergence of Fluid Dynamics Simulations with Convolutional Neural Networks

Contact Info

Product

Resources

About