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.

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.

scholarly journals A COMPARISON STUDY OF DIFFERENT KERNEL FUNCTIONS FOR SVM-BASED CLASSIFICATION OF MULTI-TEMPORAL POLARIMETRY SAR DATA

2014 ◽  
Vol XL-2/W3 ◽  
pp. 281-285 ◽  
Author(s):  
B. Yekkehkhany ◽  
A. Safari ◽  
S. Homayouni ◽  
M. Hasanlou
Keyword(s):  
Kernel Function ◽  
Temporal Integration ◽  
Experimental Tests ◽  
Kernel Functions ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Svm Classifier ◽  
Rbf Kernel ◽  
Multi Temporal ◽  
Dimension Space

In this paper, a framework is developed based on Support Vector Machines (SVM) for crop classification using polarimetric features extracted from multi-temporal Synthetic Aperture Radar (SAR) imageries. The multi-temporal integration of data not only improves the overall retrieval accuracy but also provides more reliable estimates with respect to single-date data. Several kernel functions are employed and compared in this study for mapping the input space to higher Hilbert dimension space. These kernel functions include linear, polynomials and Radial Based Function (RBF). <br><br> The method is applied to several UAVSAR L-band SAR images acquired over an agricultural area near Winnipeg, Manitoba, Canada. In this research, the temporal alpha features of H/A/α decomposition method are used in classification. The experimental tests show an SVM classifier with RBF kernel for three dates of data increases the Overall Accuracy (OA) to up to 3% in comparison to using linear kernel function, and up to 1% in comparison to a 3rd degree polynomial kernel function.

Research of a New SVM Kernel Function

2014 ◽  
Vol 543-547 ◽  
pp. 1659-1662
Author(s):  
Juan Du ◽  
Wen Long Zhang ◽  
Meng Meng Xie
Keyword(s):  
Kernel Function ◽  
Homogeneous Polynomial ◽  
Information Filtering ◽  
Kernel Functions ◽  
Learning Ability ◽  
New Combination ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Text Information ◽  
Information Recognition

The kernel was the key technology of SVM; the kernel affected the learning ability and generalization ability of support vector machine. Aiming at the specific application of harmful text information recognition, combining traditional kernel function the paper structured a new combination kernel, modeling for the independent harmful vocabulary and co-occur vocabularies, and then evaluation the linear kernel, homogeneous polynomial kernel, non homogeneous polynomial kernel and combination kernel function in the sample experiment. The experimental results of combination kernel function showed that the effect has increased greatly than other kernel functions for the application of harmful text information filtering. Especially the Rcall value achieved satisfactory results.

scholarly journals A Model-Based Design Floating-Point Accumulator. Case of Study: FPGA Implementation of a Support Vector Machine Kernel Function

Sensors ◽  
2020 ◽  
Vol 20 (5) ◽  
pp. 1362 ◽  
Author(s):  
Marco Bassoli ◽  
Valentina Bianchi ◽  
Ilaria De Munari
Keyword(s):  
Support Vector Machine ◽  
Kernel Function ◽  
Code Generation ◽  
Wearable Sensors ◽  
Machine Learning Algorithms ◽  
Floating Point ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Practical Case ◽  
Model Based

Recent research in wearable sensors have led to the development of an advanced platform capable of embedding complex algorithms such as machine learning algorithms, which are known to usually be resource-demanding. To address the need for high computational power, one solution is to design custom hardware platforms dedicated to the specific application by exploiting, for example, Field Programmable Gate Array (FPGA). Recently, model-based techniques and automatic code generation have been introduced in FPGA design. In this paper, a new model-based floating-point accumulation circuit is presented. The architecture is based on the state-of-the-art delayed buffering algorithm. This circuit was conceived to be exploited in order to compute the kernel function of a support vector machine. The implementation of the proposed model was carried out in Simulink, and simulation results showed that it had better performance in terms of speed and occupied area when compared to other solutions. To better evaluate its figure, a practical case of a polynomial kernel function was considered. Simulink and VHDL post-implementation timing simulations and measurements on FPGA confirmed the good results of the stand-alone accumulator.

Application and Experimental Study of Support Vector Machine in Rolling Bearing Fault

2011 ◽  
Vol 48-49 ◽  
pp. 241-245
Author(s):  
Hong Bing Gao ◽  
Liao Yang ◽  
Xian Zhang ◽  
Chen Cheng
Keyword(s):  
Support Vector Machine ◽  
Kernel Function ◽  
Rolling Bearing ◽  
Fault Analysis ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Dimension Theory ◽  
Bearing Failure ◽  
Machine Method ◽  
Bearing Condition Monitoring

A brief introduction of the basic concepts of the classification interval, the optimal classification surface and support vector; explained derivation of SVM based on Lagrange optimization method; Sigmoid kernel function and so on. It describes three methods of C-SVM、V-SVM and least squares SVM based on Sigmoid kernel function. To a bearing failure as a example to compare three results of SVM training of the kernel linear function, polynomial kernel function, Sigmoid kernel function, The results show that satisfactory fault analysis demand the appropriate kernel function selection. Fault in the gear box, the bearing failure is 19%, In addition, the rate is as high as 30% in other rotating machinery system failure [1,2].Thus, rolling bearing condition monitoring and fault diagnosis are very important to production safety, and many scholars have done numerous studies [3,4]. Support vector machine method is a learning methods based on statistical learning theory Vapnik-Chervonenkis dimension theory and structural risk minimization [5,6].

scholarly journals New Mixed Kernel Functions of SVM Used in Pattern Recognition

2016 ◽  
Vol 16 (5) ◽  
pp. 5-14 ◽  
Author(s):  
Hao Huanrui
Keyword(s):  
Support Vector Machine ◽  
Kernel Function ◽  
Kernel Methods ◽  
Pattern Analysis ◽  
New Technology ◽  
Wavelet Function ◽  
Kernel Functions ◽  
Good Time ◽  
Polynomial Kernel ◽  
Support Vector

Abstract The pattern analysis technology based on kernel methods is a new technology, which combines good performance and strict theory. With support vector machine, pattern analysis is easy and fast. But the existing kernel function fits the requirement. In the paper, we explore the new mixed kernel functions which are mixed with Gaussian and Wavelet function, Gaussian and Polynomial kernel function. With the new mixed kernel functions, we check different parameters. The results shows that the new mixed kernel functions have good time efficiency and accuracy. In image recognition we used SVM with two mixed kernel functions, the mixed kernel function of Gaussian and Wavelet function are suitable for more states.

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.

scholarly journals Day-Ahead Wind Speed Forecasting Using Relevance Vector Machine

2014 ◽  
Vol 2014 ◽  
pp. 1-6 ◽  
Author(s):  
Guoqiang Sun ◽  
Yue Chen ◽  
Zhinong Wei ◽  
Xiaolu Li ◽  
Kwok W. Cheung
Keyword(s):  
Wind Speed ◽  
Kernel Function ◽  
Back Propagation ◽  
Relevance Vector Machine ◽  
Back Propagation Neural Network ◽  
Gaussian Kernel ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Stable Operation ◽  
Wind Speed Forecasting

With the development of wind power technology, the security of the power system, power quality, and stable operation will meet new challenges. So, in this paper, we propose a recently developed machine learning technique, relevance vector machine (RVM), for day-ahead wind speed forecasting. We combine Gaussian kernel function and polynomial kernel function to get mixed kernel for RVM. Then, RVM is compared with back propagation neural network (BP) and support vector machine (SVM) for wind speed forecasting in four seasons in precision and velocity; the forecast results demonstrate that the proposed method is reasonable and effective.

Sign in / Sign up

Export Citation Format

Share Document