检索结果-内蒙古大学图书馆

sequential approximate optimization on projectile disturbances of the moving tank based on BP neural network

JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY 2021年第3期35卷 935-944页

作者： Chen, Yu Yang, Guolai Zhou, Honggen Sun, Quanzhao Jiangsu Univ Sci & Technol Sch Mech Engn Zhenjiang Jiangsu Peoples R China Nanjing Univ Sci & Technol Sch Mech Engn Nanjing Peoples R China

For the firing accuracy problem of the moving tank with different speed and different road level, the modelling and optimization method of the projectile disturbances of the moving tank under the general driving conditions were studied. A high-dimensional multi-objective optimization method for the projectile disturbances of the moving tank considering the different driving conditions was proposed based on the sequential approximate optimization method. Therein, a projectile disturbance multi-disciplinary simulation model of the moving tank considering multiple nonlinear factors was built and the sliced Latin hypercube design method was introduced to apply the experimental design. On the basis, the BP neural network surrogate model of the projectile disturbances at muzzle-exit of the moving tank under the general driving conditions was established. With the genetic algorithm and the potential optimal criterion, the sample points were updated to improve the accuracy of the surrogate model during the optimization. The optimization results show that the projectile disturbances at muzzle-exit of the moving tank under the general driving conditions were reduced effectively, and the comprehensive firing accuracy of the moving tank was improved. The research can provide a reference for realizing the reasonable match between firing accuracy and mobility of the tank.

关键词： Moving tank Projectile disturbance Multi-disciplinary simulation BP neural network sequential approximate optimization

来源：评论

学校读者我要写书评

暂无评论

Numerical optimization of baffle configuration in header of heat exchanger using sequential approximate optimization

引用

SIMULATION MODELLING PRACTICE AND THEORY 2022年第0期115卷 102429-102429页

作者： Kitayama, Satoshi Miyamoto, Kohei Izutsu, Rihito Tabuchi, Satoshi Yamada, Sayaka Kanazawa Univ Kakuma Machi Kanazawa Ishikawa 9201192 Japan Kanazawa Univ Grad Sch Nat Sci & Technol Kakuma Machi Kanazawa Ishikawa 9201192 Japan Kobe Steel Ltd 1-5-5 Takatsukadai Kobe Hyogo 6512271 Japan

To enhance the performance of heat exchangers (HEs), it is important to make the flow uniform and is to reduce the pressure. To achieve them simultaneously, baffle with small holes is often installed in the header of HEs, but the configuration is completely determined by the engineer's experience. In this paper, the baffle configuration under 2D fluid flow is optimized so as to minimize the flow nonuniformity and the pressure drop. Therefore, multi-objective design optimization is performed. The computational fluid dynamics (CFD) is so intensive that sequential approximate optimization that response surface is repeatedly constructed and optimized is adopted to identify the pareto-frontier. It is found from the numerical result that the optimal baffle configuration can drastically improve the flow nonuniformity and the pressure drop, compared to the conventional one. Compared to the conventional configuration, 34% improvement of the flow nonuniformity and the 23% improvement of the pressure drop are achieved by the design optimization. In addition, the size of large vortex can drastically be reduced. In particular, it is clarified that the inclined baffle plays an important role for improving the flow nonuniformity.

关键词： Heat exchanger Baffle configuration Multi-objective design optimization sequential approximate optimization

来源：评论

学校读者我要写书评

暂无评论

Numerical optimization of variable blank holder force trajectory and blank shape for twist springback reduction using sequential approximate optimization

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2019年第1-4期103卷 63-75页

作者： Kitayama, Satoshi Ishizuki, Ryoto Yokoyaka, Masaki Kawamoto, Kiichiro Natsume, Shinji Adachi, Kazuaki Noguchi, Takahiro Ohtani, Toshio Kanazawa Univ Kakuma Machi Kanazawa Ishikawa 9201192 Japan Kanazawa Univ Grad Sch Nat Sci & Technol Kakuma Machi Kanazawa Ishikawa 9201192 Japan Komatsu Ind Corp 1-1 Ono Machi Shinmachi Kanazawa Ishikawa 9200225 Japan Komatsu Ltd 3-1-1 Ueno Hirakata Osaka 5731011 Japan

This paper proposes an approach for twist springback reduction using variable blank holder force (VBHF) trajectory that the blank holder force (BHF) varies through the stroke. In addition, the blank shape is optimized. Therefore, design optimization of VBHF trajectory and blank shape for twist springback reduction is performed. Springback of U-shaped product is a simple deformation, whereas the one of S-rail-shaped product shows more complicated behavior due to twisting. As the result, compared with the springback of U-shaped product, it is difficult to evaluate the twist springback. A novel evaluation method for the twist springback is proposed, and the optimal VBHF trajectory and blank shape for the twist springback reduction are determined under several design constraints. Numerical simulation of the S-rail-shaped product is so intensive that response surface approach is valid. In particular, a sequential approximate optimization that the response surface is repeatedly constructed and optimized is used to determine the optimal VBHF and blank shape. Through numerical result, the validation of the proposed approach is examined.

关键词： Twist springback reduction Variable blank holder force trajectory Blank shape sequential approximate optimization Numerical simulation

来源：评论

学校读者我要写书评

暂无评论

Hypersonic vehicle aerodynamic design using modified sequential approximate optimization

引用

ADVANCES IN SPACE RESEARCH 2019年第11期63卷 3706-3720页

作者： Wang, Wen-jie Wu, Ze-ping Wang, Dong-hui Zhang, Wei-hua Zhao, Kun Okolo, Patrick N. Bennett, Gareth J. Natl Univ Def Technol Coll Aerosp Sci & Engn Changsha 410073 Hunan Peoples R China China Aerodynam Res & Dev Ctr State Key Lab Aerodynam Mianyang 621000 Sichuan Peoples R China Univ Dublin Trinity Coll Dublin Dept Mech & Mfg Engn Dublin D02 PN40 Ireland

Hypersonic vehicles are receiving increased attention within the aerospace community due to their high cruise speed and long-range capabilities. In this paper, a modified sequential approximate optimization method is proposed for an optimized aerodynamic design of a hypersonic vehicle. As part of this approach, a constrained experimental design method is developed to handle the constraints more efficiently. A radial basis function is used to surrogate time-consuming CFD analysis. An efficient and more robust numerical mesh morphing scheme for the hypersonic vehicle is developed for the generation of high-quality meshes. Within this paper, a novel adaptive infilling strategy is proposed which uses an inaccurate search technique coupled with an elite archive. This allows the location of a more promising sample region and hence improves the surrogate accuracy, thereby further enhancing the optimization efficiency. A hypersonic vehicle aerodynamic design problem is solved using the proposed approach and satisfactory results are obtained at much lower computational costs. The lift-to-drag ratio is increased by 23.8% when compared with the base configuration while also satisfying the volume and lift constraints. The pressure and Mach contours have been compared with those of the base configuration and the results demonstrate the strength of the optimized configuration. The modified sequential approximate optimization for designing an improved hypersonic vehicle is worth referencing in future work. (C) 2019 COSPAR. Published by Elsevier Ltd. All rights reserved.

关键词： Hypersonic vehicle Aerodynamic optimization sequential approximate optimization Constrained experimental design Mesh morphing Inaccurate search Adaptive infilling strategy

来源：评论

学校读者我要写书评

暂无评论

Improved sequential approximate optimization for Aerodynamic Design Benchmark Problem

Improved Sequential Approximate Optimization for Aerodynamic...

引用

IEEE Congress on Evolutionary Computation (IEEE CEC)

作者： Wang, Wenjie Wu, Zeping Wang, Donghui Zhang, Weihua Natl Univ Def Technol Coll Aeronaut & Astronaut Changsha Hunan Peoples R China

ISBN: (纸本)9781728121536

A modified surrogate-based optimization method based on sequential approximate optimization (SAO) is proposed to purposively improve the efficiency of aerodynamic shape optimization. In this method, a specific initial sampling approach is proposed to obtain the initial sampling set of excellent properties of space-filling and orthogonality in the shape space, a field approximate model is presented to predict the flow field parameters of interest for the specific aerodynamic optimization problems. Moreover, a novel and efficient infill strategy is proposed, which uses the inaccurate search technique in cooperation with an elite archive to locate the promising region and improve the surrogate accuracy. Consequently, the optimization efficiency is well enhanced. Two benchmark aerodynamic optimization problemsare performed using the proposed method. Results reveal that the proposed method presents much better performances comparing to conventional SAO and the stochastic optimization methods, in terms of solution quality and convergence rate.

关键词： aerodynamic optimization sequential approximate optimization field approximate model adaptive infilling strategy

来源：评论

学校读者我要写书评

暂无评论

sequential approximate optimization of industrial hammer peening using finite element simulations

引用

STRUCTURAL AND MULTIDISCIPLINARY optimization 2017年第3期55卷 767-778页

作者： Luk-Cyr, Jacques El-Bawab, Rayan Champliaud, Henri Lanteigne, Jacques Vadean, Aurelian Ecole Polytech Montreal Montreal PQ Canada Ecole Technol Super Montreal PQ Canada Inst Rech Hydro Quebec Varennes PQ Canada

In this paper, the industrial hammer peening process is optimized using multi-objective, sequential approximate optimization, which is a mathematics-plus finite element-based algorithm. Since the number of design and objective variables is significant, the global optimization problem is split into two, more manageable multi-objective subproblems. The use of surrogate modelling together with an intensification and diversification strategy for solving the optimization subproblems allows for significant computational cost savings without loss of accuracy. Additionally, we propose a Bayesian inference criterion-based sensitivity approach for "filtering-out" design variables which do not significantly affect objectives variables. Finally, guidelines for selecting appropriate Pareto optima are given using N - 1 Pareto diagrams, where N is the number of objective variables.

关键词： Hammer peening sequential approximate optimization Pareto optima Finite element

来源：评论

学校读者我要写书评

暂无评论

optimization of blank shape and segmented variable blank holder force trajectories in deep drawing using sequential approximate optimization

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2017年第5-8期91卷 1809-1821页

作者： Kitayama, Satoshi Koyama, Hiroki Kawamoto, Kiichiro Miyasaka, Takuji Yamamichi, Ken Noda, Takuya Kanazawa Univ Kakuma Machi Kanazawa Ishikawa 9201192 Japan Kanazawa Univ Grad Sch Nat Sci & Technol Kakuma Machi Kanazawa Ishikawa 9201192 Japan Komatsu Ind Corp 1-1 Ono Machi Shinmachi Kanazawa Ishikawa 9200225 Japan

Blank holder force (BHF) is one of the important process parameters for successful sheet metal forming. Variable blank holder force (VBHF) that the BHF varies through the forming process is recognized as an advanced forming technology. It has also been reported that segmented VBHF (S-VBHF) is valid to a complex shape forming, but the optimal S-VBHF trajectories are rarely discussed and used. In addition to BHF, blank shape has an influence on the product quality. The blank shape minimizing the earing is still an important issue in sheet metal forming. Simultaneous optimization of both S-VBHF trajectories and blank shape is one of the crucial issues in industries. This paper proposes a method to simultaneously optimize both the segmented VBHF trajectories and the blank shape. Numerical simulation in sheet metal forming is so intensive that a sequential approximate optimization (SAO) using a radial basis function (RBF) network is adopted for the simultaneous design optimization. Based on the numerical result, the experiment using the AC servo press (H2W300, Komatsu Industry Corp.) that can conduct the optimal S-VBHF trajectories is carried out. It has been confirmed from the numerical and experimental result that the proposed approach is valid.

关键词： Deep drawing Blank shape Segmented variable blank holder force trajectories Numerical simulation sequential approximate optimization

来源：评论

学校读者我要写书评

暂无评论

Rapid Simulation-Driven Design of Compact Photonic Y-Junction By Variable-Dimensional sequential approximate optimization

Rapid Simulation-Driven Design of Compact Photonic Y-Junctio...

引用

IEEE/ACES International Conference on Wireless Information Technology (ICWITS) and System and Applied Computational Electromagnetics (ACES)

作者： Bekasiewicz, Adrian Koziel, Slawomir Ogurtsov, Stanislav Reykjavik Univ Sch Sci & Engn Reykjavik Iceland

ISBN: (纸本)9781509012596

In this paper, a technique for expedited design optimization of a compact photonic Y-junction has been proposed. We utilize sequential approximate optimization where local response surface approximation (RSA) models are constructed and optimized to yield a sequence of designs that converge towards the optimum. The junction geometry is parameterized using splines. In order to reduce the design cost, dimensionality of the design space is gradually increased by adding the number of control points for the spline curves in the subsequent algorithm iterations. The final design exhibits transmission of over 49.5 percent and return loss below 0.3 percent over the wavelength range from 1500 nm to 1580 nm.

关键词： Integrated photonics Y-junctions computer-aided design simulation-driven design sequential approximate optimization

来源：评论

学校读者我要写书评

暂无评论

Determination of back-pressure profile for forward extrusion using sequential approximate optimization

引用

STRUCTURAL AND MULTIDISCIPLINARY optimization 2015年第1期51卷 225-237页

作者： Okada, Masato Kitayama, Satoshi Kawamoto, Kiichiro Chikahisa, Junpei Yoneyama, Takeshi Kanazawa Univ Kanazawa Ishikawa 9201192 Japan Komatsu Ind Corp Kanazawa Ishikawa 9200225 Japan Kanazawa Univ Grad Sch Nat Sci & Technol Kanazawa Ishikawa 9201192 Japan

This paper proposes a method for determining optimal back-pressure profile in forging of aluminum alloy using a sequential approximate optimization (SAO). In forging, it is important to improve the mold filling for the product quality. In addition, it is preferable to produce a product with a minimum forming energy. To achieve these objectives simultaneously, a forging method with back-pressure profile is proposed. Here, the back-pressure profile implies that the back-pressure varies through the stroke. In this paper, a multi-objective optimization (MOO) problem is formulated. To improve the mold filling, an unfilled area is taken as the first objective function. Furthermore, a forming energy during the forging is taken as the second objective function. Numerical simulation in the forging is so expensive that the SAO using the radial basis function (RBF) network is adopted, and the pareto-frontier is identified with a small number of simulation runs. Based on the numerical result, the experiments are also conducted. It can be found from these results that, the back-pressure profile approach is valid for improving the mold filling as well as the forming energy.

关键词： Multi-objective optimization sequential approximate optimization Forging Back-pressure profile

来源：评论

学校读者我要写书评

暂无评论

A novel sequential approximate optimization approach using data mining for engineering design optimization

引用

optimization METHODS & SOFTWARE 2015年第6期30卷 1255-1275页

作者： Ye, Pengcheng Pan, Guang Northwestern Polytech Univ Sch Marine Sci & Technol Xian 710072 Peoples R China

For most engineering design optimization problems, it is hard or even impossible to find the global optimum owing to the unaffordable computational cost. To overcome this difficulty, a sequential approximate optimization (SAO) approach that integrates the hybrid optimization algorithm with data mining and surrogate models is proposed to find the global optimum in engineering design optimization. The surrogate model is used to replace expensive simulation analysis and the data mining is applied to obtain the reduced search space. Thus, the efficiency of finding and quality of the global optimum will be increased by reducing the search space using data mining. The validity and efficiency of the proposed SAO approach are examined by studying typical numerical examples.

关键词： engineering design optimization sequential approximate optimization data mining surrogate model

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：