A Mixed-Kernel-Based Support Vector Regression Model for Automotive Body Design Optimization Under Uncertainty

2017 ◽  
Vol 3 (4) ◽  
Author(s):  
Yudong Fang ◽  
Zhenfei Zhan ◽  
Junqi Yang ◽  
Xu Liu
Keyword(s):  
Design Optimization ◽  
Support Vector Regression ◽  
Kernel Function ◽  
Optimization Under Uncertainty ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Fe Model ◽  
Support Vector Regression Model ◽  
Automotive Body ◽  
Body Design

Finite element (FE) models are commonly used for automotive body design. However, even with increasing speed of computers, the FE-based simulation models are still too time-consuming when the models are complex. To improve the computational efficiency, support vector regression (SVR) model, a potential approximate model, has been widely used as the surrogate of FE model for crashworthiness optimization design. Generally, in the traditional SVR, when dealing with nonlinear data, the single kernel function-based projection cannot fully cover data distribution characteristics. In order to eliminate the application limitations of single kernel SVR, a method for reliability-based design optimization (RBDO) based on mixed-kernel-based SVR (MKSVR) is proposed in this research. The mixed kernel is constructed based on the linear combination of radial basis kernel function and polynomial kernel function. Through the particle swarm optimization (PSO) algorithm, the parameters of the mixed kernel SVR are optimized. The proposed method is demonstrated through a representative analytical RBDO problem and a vehicle lightweight design problem. And the comparitive studies for SVR and MKSVR in application indicate that MKSVR surpasses SVR in model accuracy.

A Mixed-Kernel-Based Support Vector Regression Model for Automotive Body Design Optimization

2016 ◽  
Author(s):  
Yudong Fang ◽  
Zhenfei Zhan ◽  
Junqi Yang ◽  
Jun Lu ◽  
Chong Chen
Keyword(s):  
Design Optimization ◽  
Kernel Function ◽  
Optimization Design ◽  
Approximate Model ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Fe Model ◽  
Support Vector Regression Model ◽  
Automotive Body ◽  
Body Design

Finite Element (FE) models are commonly used for automotive body design. However, even with increasing speed of computers, the FE-based simulation models are still too time-consuming when the models are complex. To improve the computational efficiency, SVR, a potential approximate model, has been widely used as the surrogate of FE model for crashworthiness optimization design. Generally, in the traditional SVR, when dealing with nonlinear data, the single kernel function based projection can’t fully cover data distribution characteristics. In order to eliminate the limitations of single kernel SVR, a mixed-kernel-based SVR (MKSVR) is proposed in this research. The mixed kernel is constructed based on the linear combination of radial basis kernel function and polynomial kernel function. Through the particle swarm optimization algorithm, the parameters of the mixed kernel SVR are optimized. Then the proposed MKSVR is applied to automotive body design optimization. The application of MKSVR is demonstrated by a vehicle design problem for weight reduction while satisfying safety constraints on X direction acceleration and Crush Distance. A comparison study for SVR and MKSVR in application indicates MKSVR surpasses SVR in model accuracy.

State estimation for the electro-hydraulic actuator based on particle filter with an improved resampling technique

2019 ◽  
Vol 234 (1) ◽  
pp. 41-51
Author(s):  
Runxia Guo ◽  
Zhile Wei ◽  
Ye Wei
Keyword(s):  
Probability Density Function ◽  
State Estimation ◽  
Support Vector Regression ◽  
Probability Density ◽  
Density Function ◽  
Kernel Function ◽  
Particle Filters ◽  
Support Vector ◽  
Hydraulic Actuator ◽  
Support Vector Regression Model

State estimation for the electro-hydraulic actuator of civil aircraft is one of the most valuable but intractable issues. Recently, the state estimation approach based on particle filters has widely attracted attention. We pursue the benefits of the data-driven approach when physical model is deficienct, and put forward some improvements that are triggered by the shortcomings of particle filters algorithm. In order to solve the particles’ degeneracy phenomenon in particle filters, a kernel function that integrates the information of probability distribution is constructed; then, the established probability kernel function is designed to represent the probability density function of resampling and the regularization form of probability density function in Hilbert space is defined. Consequently, the probability density function of resampling is obtained by solving the support vector regression model. The novel resampling method based on support vector regression-particle filters can keep the diversity of particles as well as relieve the degeneracy phenomenon and eventually make the estimated state more realistic. The approach is simulated and applied to an electro-hydraulic actuator model. The estimation results validate the effectiveness of the proposed algorithm.

Stress evaluation in seven-wire strands based on singular value feature of ultrasonic guided waves

2021 ◽  
pp. 147592172110053
Author(s):  
Qian Ji ◽  
Li Jian-Bin ◽  
Liu Fan-Rui ◽  
Zhou Jian-Ting ◽  
Wang Xu
Keyword(s):  
Dispersion Curve ◽  
Support Vector Regression ◽  
Stress Level ◽  
Guided Waves ◽  
Guided Wave ◽  
Singular Value ◽  
Support Vector ◽  
Support Vector Regression Model ◽  
Various Boundary Conditions ◽  
Wave Methods

The seven-wire strands are the crucial components of prestressed structures, though their performance inevitably degrades with the passage of time. The ultrasonic guided wave methods have been intensely studied, owing to its tremendous potential for full-scale applications, among the existing nondestructive testing methods, for evaluating the stress status of strands. We have employed the theoretical and finite element methods to solve the dispersion curve of single wire and steel strands under various boundary conditions. Thereafter, the singular value decomposition was adopted to work with the simulated and experimental signals for extracting a feature vector that carries valuable stress status information. The effectiveness of the vector was verified by analyzing the relationship between the vector and the stress level. The vector was also used as an input to establish a support vector regression model. The accuracy of the model has been discussed for different sample sizes. The results show that the fundamental mode dispersion curve offset on the high-frequency part and cut-off frequency increases as the boundary constraints enhance. Simulated and experimental results have demonstrated the effectiveness and potential of the proposed support vector regression method for evaluating the stress level in the strands. This method performs well even at low stress levels and the reliability can be enhanced by adding more samples.

scholarly journals Hotspot Temperature Prediction of Dry-Type Transformers Based on Particle Filter Optimization with Support Vector Regression

Symmetry ◽  
2021 ◽  
Vol 13 (8) ◽  
pp. 1320
Author(s):  
Yuanyuan Sun ◽  
Gongde Xu ◽  
Na Li ◽  
Kejun Li ◽  
Yongliang Liang ◽  
...  
Keyword(s):  
Particle Filter ◽  
Support Vector Regression ◽  
Heat Dissipation ◽  
Hot Spot ◽  
Load Capacity ◽  
Regression Method ◽  
Support Vector ◽  
Temperature Prediction ◽  
Support Vector Regression Model ◽  
Load Rate

Both poor cooling methods and complex heat dissipation lead to prominent asymmetry in transformer temperature distribution. Both the operating life and load capacity of a power transformer are closely related to the winding hotspot temperature. Realizing accurate prediction of the hotspot temperature of transformer windings is the key to effectively preventing thermal faults in transformers, thus ensuring the reliable operation of transformers and accurately predicting transformer operating lifetimes. In this paper, a hot spot temperature prediction method is proposed based on the transformer operating parameters through the particle filter optimization support vector regression model. Based on the monitored transformer temperature, load rate, transformer cooling type, and ambient temperature, the hotspot temperature of a dry-type transformer can be predicted by a support vector regression method. The hyperparameters of the support vector regression are dynamically optimized here according to the particle filter to improve the optimization accuracy. The validity and accuracy of the proposed method are verified by comparing the proposed method with a traditional support vector regression method based on the real operating data of a 35 kV dry-type transformer.

Support Vector Regression-Based Multidisciplinary Design Optimization for Ship Design

2012 ◽  
Author(s):  
Dongqin Li ◽  
Yifeng Guan ◽  
Qingfeng Wang ◽  
Zhitong Chen
Keyword(s):  
Design Optimization ◽  
Support Vector Regression ◽  
Design Process ◽  
Multidisciplinary Design Optimization ◽  
Initial Point ◽  
Ship Design ◽  
Collaborative Optimization ◽  
Multidisciplinary Design ◽  
Support Vector ◽  
Independent Design

The design of ship is related to several disciplines such as hydrostatic, resistance, propulsion and economic. The traditional design process of ship only involves independent design optimization within each discipline. With such an approach, there is no guarantee to achieve the optimum design. And at the same time improving the efficiency of ship optimization is also crucial for modem ship design. In this paper, an introduction of both the traditional ship design process and the fundamentals of Multidisciplinary Design Optimization (MDO) theory are presented and a comparison between the two methods is carried out. As one of the most frequently applied MDO methods, Collaborative Optimization (CO) promotes autonomy of disciplines while providing a coordinating mechanism guaranteeing progress toward an optimum and maintaining interdisciplinary compatibility. However there are some difficulties in applying the conventional CO method, such as difficulties in choosing an initial point and tremendous computational requirements. For the purpose of overcoming these problems, Design Of Experiment (DOE) and a new support vector regression algorithm are applied to CO to construct statistical approximation model in this paper. The support vector regression algorithm approximates the optimization model and is updated during the optimization process to improve accuracy. It is shown by examples that the computing efficiency and robustness of this CO method are higher than with the conventional CO method. Then this new Collaborative Optimization (CO) method using approximate technology is discussed in detail and applied in ship design which considers hydrostatic, propulsion, weight and volume, performance and cost. It indicates that CO method combined with approximate technology can effectively solve complex engineering design optimization problem. Finally, some suggestions on the future improvements are proposed.

Sign in / Sign up

Export Citation Format

Share Document