Free form deformation and symmetry constraint‐based multimodal brain image registration using generative adversarial nets

Multi‐modal brain image registration has been widely applied to functional localisation,neurosurgery and computational anatomy.The existing registration methods based on the dense deformation fields involve too many parameters,which is not conducive to the exploration of correct spatial correspondence between the float and reference images.Meanwhile,the unidirectional registration may involve the deformation folding,which will result in the change of topology during registration.To address these issues,this work has presented an unsupervised image registration method using the free form deformation(FFD)and the symmetry constraint‐based generative adversarial networks(FSGAN).The FSGAN utilises the principle component analysis network‐based structural representations of the reference and float images as the inputs and uses the generator to learn the FFD model parameters,thereby producing two deformation fields.Meanwhile,the FSGAN uses two discriminators to decide whether the bilateral registration have been realised simultaneously.Besides,the symmetry constraint is utilised to construct the loss function,thereby avoiding the deformation folding.Experiments on BrainWeb,high grade gliomas,IXI and LPBA40 show that compared with state‐of‐the‐art methods,the FSGAN provides superior performance in terms of visual comparisons and such quantitative indexes as dice value,target registration error and computational efficiency.

Development of 3D Female Breast Model Library for Bra Design

As the maturity of female costume concept as well as the social consuming activities, a new and higher requirement is imposed on female underwear design. Human body model is the basic of many applications on 3D garment CAD. This paper delivered a novel approach for modeling a human body which could be driven by related body dimensions to form a female breast model library based on the free form deformatioll technologies. The 3D female breast shape reserve has a strong potential of being used for bra design, bra flttins, virtual try-on and exhibition to meet ＂made-tomeasure＂ demand of the booming bra market in the world.

Shape Optimization for A Conventional Underwater Glider to Decrease Average Periodic Resistance

As a type of autonomous underwater vehicle(AUV),underwater gliders(UG)are getting increasing attention in ocean exploration.To save energy and satisfy the mission requirements of a longer voyage,shape optimization for UGs has become a key technique and research focus.In this paper,a conventional UG,including its fuselage and hydrofoil,is optimized,which aims to decrease the average resistance in one motion cycle.To operate the optimization progress for the complex object,multiple free form deformation(FFD)volumes are established for geometric parameterization.High-fidelity simulation models are employed for objective function evaluation and gradients calculation.And sequential quadratic programming(SQP)method is adopted as an optimization algorithm.The optimization results show that there exists a UG with symmetrical and non-horizontal hydrofoils that has lower resistance.

Robust design of NLF airfoils

A robust optimization design approach of natural laminar airfoils is developed in this paper. First, the non-uniform rational B-splines （NURBS） free form deformation method based on NURBS basis function is introduced to the airfoil parameterization. Second, aerodynamic characteristics are evaluated by solving Navier-Stokes equations, and theγ-Reθt transition model coupling with shear-stress transport （SST） turbulent model is introduced to simulate boundary layer transition. A numerical simulation of transition flow around NLF0416 airfoil is conducted to test the code. The comparison between numerical simulation results and wind tunnel test data approves the validity and applicability of the present transition model. Third, the optimization system is set up, which uses the separated particle swarm optimization （SPSO） as search algorithm and combines the Kriging models as surrogate model during optimization. The system is applied to carry out robust design about the uncertainty of lift coefficient and Mach number for NASA NLF-0115 airfoil. The data of optimized airfoil aerodynamic characteristics indicates that the optimized airfoil can maintain laminar flow stably in an uncertain range and has a wider range of low drag.

Aeroacoustic and aerodynamic optimization of propeller blades

It is of great significance to develop a high-efficiency and low-noise propeller optimization method for new-generation propeller aircraft design.Coupled with free form deformation method,dynamic mesh interpolation technology,optimization algorithm,surrogate model,aerodynamic calculation and aeroacoustic prediction model module,the integrated aerodynamic and aeroacoustic design method of propeller is built.The optimization design for the six-blade propeller is carried out.The non-reduction in efficiency,thrust coefficient and the minimum of aerodynamic noise is treated as the optimization design objective.The spatial vorticity distribution of the propeller before and after the design is also analyzed by using unsteady computational fluid dynamics method.The results show that the optimized propeller can effectively reduce the aerodynamic noise level.The maximum total sound pressure level can be reduced by 5 dB without reducing its aerodynamic performance.The developed method has good application potential in low-noise optimization design of propeller and other rotating machinery.

Aerodynamic design optimization of nacelle/pylon position on an aircraft

The arbitrary space-shape free form deformation （FFD） method developed in this paper is based on non-uniform rational B-splines （NURBS） basis function and used for the integral parameterization of nacelle-pylon geometry. The multi-block structured grid deformation technique is established by Delaunay graph mapping method. The optimization objects of aerodynamic characteristics are evaluated by solving NavierStokes equations on the basis of multi-block structured grid. The advanced particle swarm optimization （PSO） is utilized as search algorithm, which com-bines the Kriging model as surrogate model during optimization. The optimization system is used for optimizing the nacelle location of DLR-F6 wing-body-pylon-nacelle. The results indicate that the aerodynamic interference between the parts is significantly reduced. The optimization design system established in this paper has extensive applications and engineering value.