一种改进的极限学习机煤与瓦斯突出预测模型

发布时间：2018-03-07 20:38

本文选题：煤与瓦斯突出　切入点：预测模型　出处：《传感技术学报》2016年01期 　论文类型：期刊论文

【摘要】：较高精度的煤与瓦斯突出预测是煤矿安全生产的必要前提和保证。为了提高煤与瓦斯突出预测模型的预测精度,提出了一种改进的极限学习机煤与瓦斯突出预测模型。首先利用核主成分分析法对煤与瓦斯突出的影响指标进行降维简化处理,提取指标数据的主成分序列;把主成分序列分为训练样本和验证样本,然后在训练阶段,使用训练样本通过结合了全局搜索和局部搜索的文化基因算法对极限学习机的输入权值和隐含层偏差进行优化,得到最佳预测模型;最后,在最佳预测模型中,用验证样本对煤与瓦斯突出强度进行预测。通过实例验证,该模型能够有效预测煤与瓦斯突出强度。与BP、SVM、ELM、KPCA-ELM等预测模型相比,该模型具有更高的预测精度。
[Abstract]:High precision prediction of coal and gas outburst is the prerequisite and guarantee of coal mine safety production. In order to improve the prediction accuracy of coal and gas outburst prediction model, An improved prediction model of coal and gas outburst is presented in this paper. Firstly, the influence index of coal and gas outburst is reduced by kernel principal component analysis, and the principal component sequence of index data is extracted. The principal component sequence is divided into training samples and verification samples. Then, in the training stage, the input weights and hidden layer deviations of the learning machine are optimized by using the cultural gene algorithm which combines global search and local search. Finally, in the best prediction model, the strength of coal and gas outburst is predicted by using the verification sample. The model can effectively predict the strength of coal and gas outburst, compared with the BPSVM / ELMKPCA-ELM prediction model. The model has higher prediction accuracy.
【作者单位】：辽宁工程技术大学电气与控制工程学院;辽宁工程技术大学机械工程学院;
【基金】：国家自然科学基金项目(51274118;70971059) 辽宁省科技攻关项目(2011229011) 辽宁省教育厅基金项目(L2012119)
【分类号】：TD713

【相似文献】