Open AccessPrediction of Spontaneous Combustion Tendency Grade of Sulfide Ore Based on Decision Tree Combined Classifier
Author(s) -
Nianping Liu,
Siqi Huang,
Xiaojun Xie
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1302/4/042060
Subject(s) - decision tree , spontaneous combustion , sulfide , combustion , classifier (uml) , decision tree learning , decision tree model , computer science , artificial intelligence , chemistry , materials science , metallurgy , organic chemistry
Based on the related theories of decision tree and its classifier, a decision tree combiner model for spontaneous combustion of sulfide ores was established. Based on the analysis of the influencing factors of spontaneous combustion of sulfide ore, the three most representative measured characteristics, such as oxidation rate, self-hot spot, and auto-ignition point, were selected as predictors of the decision tree classifier model. Using the actual measured data of spontaneous combustion of sulfide ore as a training sample, a decision tree model for establishing spontaneous combustion of sulfide ores was used to predict the spontaneous combustion tendency grades, and verified with other measured data that did not participate in training. The results show that the decision tree combined classifier model is simple and feasible, with high prediction accuracy and simplified data processing. It is one of the effective methods to solve the problem of predicting the spontaneous combustion grade of sulfide ore.