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.

An integrated fuzzy support vector regression and the particle swarm optimization algorithm to predict indoor thermal comfort

2016 ◽  
Vol 25 (8) ◽  
pp. 1248-1258 ◽  
Author(s):  
Fayçal Megri ◽  
Ahmed Cherif Megri ◽  
Riadh Djabri
Keyword(s):  
Particle Swarm Optimization ◽  
Thermal Comfort ◽  
Support Vector Regression ◽  
Thermal Sensation ◽  
Particle Swarm ◽  
Pso Algorithm ◽  
Support Vector ◽  
Statistical Regression ◽  
Swarm Optimization ◽  
Comfort Indices

The thermal comfort indices are usually identified using empirical thermal models based on the human balanced equations and experimentations. In our paper, we propose a statistical regression method to predict these indices. To achieve this goal, first, the fuzzy support vector regression (FSVR) identification approach was integrated with the particle swarm optimization (PSO) algorithm. Then PSO was used as a global optimizer to optimize and select the hyper-parameters needed for the FSVR model. The radial basis function (RBF) kernel was used within the FSVR model. Afterward, these optimal hyper-parameters were used to forecast the thermal comfort indices: predicted mean vote (PMV), predicted percentage dissatisfied (PPD), new standard effective temperature (SET*), thermal discomfort (DISC), thermal sensation (TSENS) and predicted percent dissatisfied due to draft (PD). The application of the proposed approach on different data sets gave successful prediction and promising results. Moreover, the comparisons between the traditional Fanger model and the new model further demonstrate that the proposed model achieves even better identification performance than the original FSVR technique.

Sign in / Sign up

Export Citation Format

Share Document