Magnetic properties prediction of NdFeB magnets by using support vector regression

2014 ◽  
Vol 28 (23) ◽  
pp. 1450177
Author(s):  
Wende Cheng
Keyword(s):  
Magnetic Properties ◽  
Support Vector Regression ◽  
Magnetic Energy ◽  
Practical Method ◽  
Percentage Error ◽  
Support Vector ◽  
Ndfeb Magnets ◽  
Energy Product ◽  
Experimental Process ◽  
Leave One Out

A novel model using support vector regression (SVR) combined with particle swarm optimization (PSO) was employed to construct mathematical model for prediction of the magnetic properties of the NdFeB magnets. The leave-one-out cross-validation (LOOCV) test results strongly supports that the generalization ability of SVR is high enough. Predicted results show that the mean absolute percentage error for magnetic remanence Br, coercivity Hcj and maximum magnetic energy product (BH) max are 0.53%, 3.90%, 1.73%, and the correlation coefficient (R2) is as high as 0.839, 0.967 and 0.940, respectively. This investigation suggests that the PSO-SVR is not only an effective and practical method to simulate the properties of NdFeB , but also a powerful tool to optimatize designing or controlling the experimental process.

Magnetic Remanence Prediction of NdFeB Magnets Based on a Novel Machine Learning Intelligence Approach Using a Particle Swarm Optimization Support Vector Regression

2014 ◽  
Vol 6 (4) ◽  
pp. 72-81 ◽  
Author(s):  
WenDe Cheng
Keyword(s):  
Magnetic Properties ◽  
Particle Swarm Optimization ◽  
Support Vector Regression ◽  
Particle Swarm ◽  
Support Vector ◽  
Chemical Compositions ◽  
Swarm Optimization ◽  
Ndfeb Magnets ◽  
Magnetic Remanence ◽  
The Mean

Studies have shown that the chemical compositions affecting the magnetic properties of NdFeB magnets. In order to get the right NdFeB magnets, it is advantageous to have an accurate model with which one can predict the magnetic properties with different components. In this paper, according to an experimental dataset on the magnetic remanence of NdFeB, a predicting and optimizing model using support vector regression (SVR) combined with particle swarm optimization (PSO) was developed. The estimated result of SVR agreed with the experimental data well. Test results of leave-one-out cross validation show that the mean absolute error does not exceed 0.0036, the mean absolute percentage error is solely 0.53%, and the correlation coefficient () is as high as 0.839. This implies that one can estimate an available combination of different proportion components by using support vector regression model to get suitable magnetic remanence of NdFeB.

Prediction of Glass Transition Temperature of Polymer by Support Vector Regression

2012 ◽  
Vol 455-456 ◽  
pp. 436-442
Author(s):  
J.F. Pei ◽  
C.Z. Cai ◽  
X.J. Zhu ◽  
G.L. Wang ◽  
B. Yan
Keyword(s):  
Glass Transition ◽  
Transition Temperature ◽  
Glass Transition Temperature ◽  
Support Vector Regression ◽  
Density Functional ◽  
Absolute Error ◽  
Percentage Error ◽  
Support Vector ◽  
Quantum Chemical Descriptors ◽  
Leave One Out

. Based on two quantum chemical descriptors (the thermal energy Ethermal and the total energy of the whole system EHF) calculated from the structures of the repeat units of polyacrylamides by density functional theory (DFT), the support vector regression (SVR) approach combined with particle swarm optimization (PSO), is proposed to establish a model for prediction of the glass transition temperature (Tg) of polyacrylamides. The prediction performance of SVR was compared with that of multivariate linear regression (MLR). The results show that the mean absolute error (MAE=4.65K), mean absolute percentage error (MAPE=1.28%) and correlation coefficient (R2=0.9818) calculated by leave-one–out cross validation (LOOCV) via SVR models are superior to those achieved by QSPR (MAE=14.25K, MAPE=4.39% and R2=0.9211) and QSPR-LOO (MAE=17.01K, MAPE=5.66% and R2=0.8823) models for the identical samples, respectively. The prediction results strongly demonstrate that the modeling and generalization abilities of SVR model consistently surpass those of QSPR and QSPR-LOO models. It is revealed that the established SVR model is more suitable to be used for prediction of the Tg values for unknown polymers possessing similar structure than the conventional MLR approach. These suggest that SVR is a promising and practical methodology to predict the glass transition temperature of polyacrylamides.

scholarly journals Multi-State Load Demand Forecasting Using Hybridized Support Vector Regression Integrated with Optimal Design of Off-Grid Energy Systems—A Metaheuristic Approach

Processes ◽  
2021 ◽  
Vol 9 (7) ◽  
pp. 1166
Author(s):  
Bashir Musa ◽  
Nasser Yimen ◽  
Sani Isah Abba ◽  
Humphrey Hugh Adun ◽  
Mustafa Dagbasi
Keyword(s):  
Support Vector Regression ◽  
Mean Square Error ◽  
Prediction Accuracy ◽  
Demand Forecasting ◽  
Load Forecasting ◽  
Coefficient Of Determination ◽  
Percentage Error ◽  
Support Vector ◽  
Mean Square ◽  
Hybrid Renewable Energy System

The prediction accuracy of support vector regression (SVR) is highly influenced by a kernel function. However, its performance suffers on large datasets, and this could be attributed to the computational limitations of kernel learning. To tackle this problem, this paper combines SVR with the emerging Harris hawks optimization (HHO) and particle swarm optimization (PSO) algorithms to form two hybrid SVR algorithms, SVR-HHO and SVR-PSO. Both the two proposed algorithms and traditional SVR were applied to load forecasting in four different states of Nigeria. The correlation coefficient (R), coefficient of determination (R2), mean square error (MSE), root mean square error (RMSE), and mean absolute percentage error (MAPE) were used as indicators to evaluate the prediction accuracy of the algorithms. The results reveal that there is an increase in performance for both SVR-HHO and SVR-PSO over traditional SVR. SVR-HHO has the highest R2 values of 0.9951, 0.8963, 0.9951, and 0.9313, the lowest MSE values of 0.0002, 0.0070, 0.0002, and 0.0080, and the lowest MAPE values of 0.1311, 0.1452, 0.0599, and 0.1817, respectively, for Kano, Abuja, Niger, and Lagos State. The results of SVR-HHO also prove more advantageous over SVR-PSO in all the states concerning load forecasting skills. This paper also designed a hybrid renewable energy system (HRES) that consists of solar photovoltaic (PV) panels, wind turbines, and batteries. As inputs, the system used solar radiation, temperature, wind speed, and the predicted load demands by SVR-HHO in all the states. The system was optimized by using the PSO algorithm to obtain the optimal configuration of the HRES that will satisfy all constraints at the minimum cost.

SUPPORT VECTOR REGRESSION MODEL FOR DIRECT METHANOL FUEL CELL

2012 ◽  
Vol 23 (07) ◽  
pp. 1250055 ◽  
Author(s):  
J. L. TANG ◽  
C. Z. CAI ◽  
T. T. XIAO ◽  
S. J. HUANG
Keyword(s):  
Fuel Cell ◽  
Prediction Model ◽  
Support Vector Regression ◽  
Direct Methanol Fuel Cell ◽  
Cell Voltage ◽  
Percentage Error ◽  
Support Vector ◽  
Absolute Percentage Error ◽  
Direct Methanol ◽  
Methanol Fuel Cell

The purpose of this paper is to establish a direct methanol fuel cell (DMFC) prediction model by using the support vector regression (SVR) approach combined with particle swarm optimization (PSO) algorithm for its parameter selection. Two variables, cell temperature and cell current density were employed as input variables, cell voltage value of DMFC acted as output variable. Using leave-one-out cross-validation (LOOCV) test on 21 samples, the maximum absolute percentage error (APE) yields 5.66%, the mean absolute percentage error (MAPE) is only 0.93% and the correlation coefficient (R2) as high as 0.995. Compared with the result of artificial neural network (ANN) approach, it is shown that the modeling ability of SVR surpasses that of ANN. These suggest that SVR prediction model can be a good predictor to estimate the cell voltage for DMFC system.

Microstructure and Magnetic Properties of Hot-Pressed and Hot-Deformed Composite Magnets Produced by Spark Plasma Sintering Method

2011 ◽  
Vol 686 ◽  
pp. 740-744 ◽  
Author(s):  
Yi Long Ma ◽  
Deng Ming Chen ◽  
Qian Shen ◽  
Peng Jun Cao
Keyword(s):  
Magnetic Properties ◽  
Spark Plasma Sintering ◽  
Hot Pressing ◽  
Magnetic Energy ◽  
Pressing Temperature ◽  
Energy Product ◽  
Plasma Sintering ◽  
Spark Plasma ◽  
Energy Products ◽  
Fe Addition

Bulk isotropic and anisotropic Nd13.5Fe80.4Ga0.5B5.6 and Nd13.5Fe80.4Ga0.5B5.6/Fe magnets were synthesized by applying spark plasma sintering (SPS) technique. The effect of hot-pressing temperature on the magnetic properties of hot-pressed (HP) and hot-deformed (HD) magnets without additive and with 5% Fe addition was investigated. With increasing sintering temperature for HP magnets, the grain grew gradually. For HD magnets, the optimal magnetic properties could be obtained at hot-pressing temperature 680°C due to the development of desired c-axis texture and uniform microstructure, which resulted from the appropriate and uniform grain size in HP magnets. Fe addition could enhance remanence (Br) and magnetic energy products ((BH)m) of HP and HD magnets. However, the maximum magnetic energy product of HD magnets decreased when hot-pressing temperature was higher than 650°C.

Modeling and predicting the tensile strength of poly (lactic acid)/graphene nanocomposites by using support vector regression

2016 ◽  
Vol 30 (10) ◽  
pp. 1650052
Author(s):  
W. D. Cheng ◽  
C. Z. Cai ◽  
Y. Luo ◽  
Y. H. Li ◽  
C. J. Zhao
Keyword(s):  
Tensile Strength ◽  
Lactic Acid ◽  
Support Vector Regression ◽  
Process Parameters ◽  
Poly Lactic Acid ◽  
Percentage Error ◽  
Support Vector ◽  
Graphene Nanocomposites ◽  
Absolute Percentage Error ◽  
Rsm Model

According to an experimental dataset under different process parameters, support vector regression (SVR) combined with particle swarm optimization (PSO) for its parameter optimization was employed to establish a mathematical model for prediction of the tensile strength of poly (lactic acid) (PLA)/graphene nanocomposites. Four variables, while graphene loading, temperature, time and speed, were employed as input variables, while tensile strength acted as output variable. Using leave-one-out cross validation test of 30 samples, the maximum absolute percentage error does not exceed 1.5%, the mean absolute percentage error (MAPE) is only 0.295% and the correlation coefficient [Formula: see text] is as high as 0.99. Compared with the results of response surface methodology (RSM) model, it is shown that the estimated errors by SVR are smaller than those achieved by RSM. It revealed that the generalization ability of SVR is superior to that of RSM model. Meanwhile, multifactor analysis is adopted for investigation on significances of each experimental factor and their influences on the tensile strength of PLA/graphene nanocomposites. This study suggests that the SVR model can provide important theoretical and practical guide to design the experiment, and control the intensity of the tensile strength of PLA/graphene nanocomposites via rational process parameters.

Mechanical properties prediction for carbon nanotubes/epoxy composites by using support vector regression

2015 ◽  
Vol 29 (05) ◽  
pp. 1550016 ◽  
Author(s):  
W. D. Cheng ◽  
C. Z. Cai ◽  
Y. Luo ◽  
Y. H. Li ◽  
C. J. Zhao
Keyword(s):  
Mechanical Properties ◽  
Carbon Nanotubes ◽  
Support Vector Regression ◽  
Correlation Coefficients ◽  
Epoxy Composites ◽  
Percentage Error ◽  
Support Vector ◽  
Data Set ◽  
Highly Nonlinear ◽  
Mechanical Properties Prediction

Studies have shown there are several process/geometry parameters affecting the mechanical properties of the carbon nanotubes/epoxy composites. The relationship between the response and process/geometry parameters is highly nonlinear and quite complicated. It is very valuable to have an accurate model to estimate the response under different process/geometry parameters. In this paper, the support vector regression (SVR) combined with particle swarm optimization (PSO) for its parameter optimization was employed to construct mathematical models for prediction of mechanical properties of the carbon nanotubes/epoxy composites according to an experimental data set. The leave-one-out cross-validation (LOOCV) test results by SVR models support that the generalization ability of SVR model is high enough. The statistical mean absolute percentage error for tensile strength, elongation and elastic modulus are 3.96%, 3.14% and 2.62%, the correlation coefficients (R2) achieve as high as 0.991, 0.990 and 0.997, respectively. This study suggests that the established SVR model can be used to accurately foresee the mechanical properties of carbon nanotubes/epoxy composites and can be used to optimize designing or controlling of the experimental process/geometry in practice.

scholarly journals Classificação do Risco de Quedas em Idosos com Least Squares Support Vector Regression Utilizando Sinais Eletromiográficos e Dinamométricos

2021 ◽  
Author(s):  
Daniele Alves Silva ◽  
Laiana Sepúlveda de Andrade Mesquita ◽  
Luan Marinho Morais Pereira ◽  
Nayra Ferreira Lima Castelo Branco ◽  
Hermes Manoel Galvão Castelo Branco ◽  
...  
Keyword(s):  
Radial Basis Function ◽  
Least Squares ◽  
Support Vector Regression ◽  
Basis Function ◽  
Support Vector ◽  
Radial Basis ◽  
Leave One Out

A determinação do risco de cair é de suma importância na assistência à saúde do idoso, pois a ocorrência de quedas nessa população trazem consequências em vários aspectos. Ferramentas de aprendizado de máquinas têm sido cada vez mais empregadas com este fim. Portanto, o objetivo deste estudo foi investigar a viabilidade da utilização de sinais eletromiográficos e dinamométricos na classificação do risco de quedas em idosos via modelo least squares support vector regression (LSSVR). Trinta e um voluntários idosos foram avaliados com a Escala de Equilíbrio de Berg (EEB), eletromiografia e dinamometria do membro inferior dominante. Para o modelo LSSVR foram utilizados kernels do tipo linear, polinomial e radial basis function (RBF), além de validações cruzadas pelos métodos leave one out e K-fold. Ambos os sinais apresentaram erros médios baixos na maioria das execuções realizadas. Dessa forma, verificou-se que é possível classificar o risco de quedas em idosos por meio de sinais eletromiográficos e dinamométricos aplicados ao modelo LSSVR.

Sign in / Sign up

Export Citation Format

Share Document