Open AccessPSO-SVM Model for Classifying Spontaneous Combustion Tendency Grade of Sulfide Ores
Author(s) -
Liu Nian-ping,
Xiaojun Xie,
Siqi Huang
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/611/1/012024
Subject(s) - support vector machine , particle swarm optimization , sulfide , spontaneous combustion , combustion , point (geometry) , biological system , artificial intelligence , computer science , pattern recognition (psychology) , chemistry , mathematics , machine learning , materials science , metallurgy , geometry , biology
Three main factor indexes that most reflect spontaneous combustion tendency of sulfide ores were selected such as oxidation increment of ore sample under low temperature, self-heating point temperature and self-burning point temperature as the basic discriminate factors of the classification model. Based on the theory of cross validation and particle swarm optimization(PSO) to optimize the parameters of support vector machine (SVM),the PSO-SVM model for classifying spontaneous combustion tendency grade of sulfide ores was built by using training samples from measured data, and was verified by engineering data. It shows that the model has high predication accuracy, which also is scientific and feasible, it provides a new approach to evaluate the spontaneous combustion tendency grade of ores in any sulfide mines.