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

Autor:	WenDe Cheng
Rok vydání:	2014
Předmět:	Correlation coefficient Computer science business.industry Particle swarm optimization Regression analysis Machine learning computer.software_genre Cross-validation Support vector machine Mean absolute percentage error Remanence Magnet Artificial intelligence business computer
Zdroj:	International Journal of Software Science and Computational Intelligence. 6:72-81
ISSN:	1942-9037 1942-9045
Popis:	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.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::d487b6d929874143a4ca57c80aa87a3c https://doi.org/10.4018/ijssci.2014100105 Zobrazit plný text záznamu