Multi-objective optimization of suspension parameters for rail vehicles based on a virtual prototype surrogate model

2016 ◽  
Vol 39 (6) ◽  
pp. 746-754 ◽  
Author(s):  
Yue Yang ◽  
Wei Zeng ◽  
Ting Wang ◽  
Yun Liao
Keyword(s):  
Surrogate Model ◽  
Virtual Prototype ◽  
Multi Objective Optimization ◽  
Multi Objective ◽  
Suspension Parameters ◽  
Rail Vehicles

scholarly journals Multi-Objective Optimization of a High Specific Speed Centrifugal Volute Pump Using 3D Inverse Design Coupled With CFD Simulations

2019 ◽  
Author(s):  
Luying Zhang ◽  
Gabriel Davila ◽  
Mehrdad Zangeneh
Keyword(s):  
Surrogate Model ◽  
Design Method ◽  
Inverse Design ◽  
Multi Objective Optimization ◽  
Blade Angle ◽  
Multi Objective ◽  
Specific Speed ◽  
Meridional Shape ◽  
Inverse Design Method ◽  
Conventional Optimization

Abstract This paper presents three different multi-objective optimization strategies for a high specific speed centrifugal volute pump design. The objectives of the optimization consist of maximizing the efficiency and minimizing the cavitation while maintaining the Euler head. The first two optimization strategies use a 3D inverse design method to parametrize the blade geometry. Both meridional shape and 3D blade geometry is changed during the optimization. In the first approach Design of Experiment method is used and the efficiency computed from CFD computations, while cavitation is evaluated by using minimum pressure on blade surface predicted by 3D inverse design method. The design matrix is then used to create a surrogate model where optimization is run to find the best tradeoff between cavitation and efficiency. This optimized geometry is manufactured and tested and is found to be 3.9% more efficient than the baseline with little cavitation at high flow. In the second approach the 3D inverse design method output is used to compute the efficiency and cavitation parameters and this leads to considerable reduction to the computational time. The resulting optimized geometry is found to be similar to the more computationally expensive solution based on 3D CFD results. In order to compare the inverse design based optimization to the conventional optimization an equivalent optimization is carried out by parametrizing the blade angle and meridional shape. Two different approaches are used for conventional optimization one in which the blade angle at TE is not constrained and one in which blade angles are constrained. In both cases larger variation in head is obtained when compared with the inverse design approach. This makes it impossible to create an accurate surrogate model. Furthermore, the efficiency levels in the conventional optimization is generally lower than the inverse design based optimization.

Multi-Objective Optimization for the Micro-Milling Process With Adaptive Data Modeling

2011 ◽  
Author(s):  
Xinyu Liu ◽  
Weihang Zhu ◽  
Victor Zaloom
Keyword(s):  
Surrogate Model ◽  
Data Modeling ◽  
Milling Process ◽  
Machining Process ◽  
Micro Milling ◽  
Machining Parameters ◽  
Multi Objective Optimization ◽  
Multi Objective ◽  
Optimization Study ◽  
Machining Parameter

This paper presents a multi-objective optimization study for the micro-milling process with adaptive data modeling based on the process simulation. A micro-milling machining process model was developed and verified through our previous study. Based on the model, a set of simulation data was generated from a factorial design. The data was converted into a surrogate model with adaptive data modeling method. The model has three input variables: axial depth of cut, feed rate and spindle speed. It has two conflictive objectives: minimization of surface location error (which affects surface accuracy) and minimization of total tooling cost. The surrogate model is used in a multi-objective optimization study to obtain the Pareto optimal sets of machining parameters. The visual display of the non-dominated solution frontier allows an engineer to select a preferred machining parameter in order to get a lowest cost solution given the requirement from tolerance and accuracy. The contribution of this study is to provide a streamlined methodology to identify the preferred best machining parameters for micro-milling.

scholarly journals Low-Cost Multi-Objective Optimization of Multiparameter Antenna Structures Based on the l1 Optimization BPNN Surrogate Model

Electronics ◽  
2019 ◽  
Vol 8 (8) ◽  
pp. 839
Author(s):  
Dong ◽  
Qin ◽  
Mo
Keyword(s):  
Surrogate Model ◽  
Communication Systems ◽  
Low Cost ◽  
Computational Cost ◽  
Optimization Method ◽  
Antenna Design ◽  
Multi Objective Optimization ◽  
Compact Structure ◽  
Multi Objective ◽  
L1 Optimization

The development of modern wireless communication systems not only requires the antenna to be lightweight, low cost, easy to manufacture and easy to integrate but also imposes requirements on the miniaturization, wideband, and multiband design of the antenna. Therefore, designing an antenna that quickly and effectively meets multiple performance requirements is of great significance. To solve the problem of the large computational cost of traditional multi-objective antenna design methods, this paper proposes a backpropagation neural network surrogate model based on l1 optimization (l1-BPNN). The l1 optimization method tends to punish larger weight values and select smaller weight values so as to preserve a small amount of important weights and reset relatively unimportant weights to zero. By using l1 optimization method, the network mapping structure can be automatically adjusted to achieve the most suitable and compact structure of the surrogate model. Furthermore, for multi-parameter antenna design problems, a fast multi-objective optimization framework is constructed using the proposed l1-BPNN as a surrogate model. The framework is illustrated using a miniaturized multiband antenna design case, and a comparison with previously published methods, as well as numerical validation, is also provided.

Sign in / Sign up

Export Citation Format

Share Document