The Prediction of Pulverized Coal Ignition Property Based on Piecewise Least Squares Support Vector Machine

摘要：

Aimed at the quantitative analysis of pulverized coal ignition temperature, this paper presents a piecewise least squares support vector machine modeling method, where several sub-models are created according to the burning characteristics of lignite, bituminous coal, lean coal and anthracite coal etc. and the parameters of each sub-model are optimized independently. By implementing the piecewise LSSVM and the global LSSVM on coal fuel samples obtained from certain company, we find that the piecewise LSSVM behaves better than the global LSSVM on mean-square error and correlation coefficient, etc.

关键词： subsection model least squares support vector machine, blending coal igniting temperature

作者: CHANG Aiying WU Tiejun XIN Bao

作者单位: State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China

会议类型: 国际会议

会议名称: 2010 3rd IEEE International Conference on Computer Science and Information Technology(第三届IEEE计算机科学与信息技术国际会议 ICCSIT 2010)

会议地点: 成都

会议语种:英文

页码: 251-254

在线出版日期: 2010-07-07（万方平台首次上网日期，不代表论文的发表时间）