优化极限学习机的煤与瓦斯突出预测方法  

A Prediction Method of Coal and Gas Outburst Based on Optimized Extreme Learning Machine

作　　者：王雨虹[1] 孟瑶瑶 付华[1] 屠乃威[1] 徐耀松[1] WANG Yu-hong;MENG Yao-yao;FU Hua;TU Nai-wei;XU Yao-song(Faculty of Electrical and Control Engineering,Liaoning Technical University,Huludao 125105,China)

机构地区：[1]辽宁工程技术大学电气与控制工程学院,辽宁葫芦岛125105

出　　处：《控制工程》2022年第11期2131-2137,共7页Control Engineering of China

基　　金：国家自然科学基金资助项目(51974151,61601212);辽宁省教育厅科学技术研究项目(LJ2019QL015)。

摘　　要：为提高煤与瓦斯突出的预测精度、实现快速预测,提出了一种基于自适应天牛须搜索算法(ABAS)和极限学习机(ELM)的瓦斯突出预测模型ABAS-ELM。采用核主成分分析法(KPCA)对煤与瓦斯突出的高维、非线性特征进行提取,将提取后的主特征作为预测模型的输入,使用ABAS对ELM的输入权重和隐层偏差进行寻优,建立ABAS-ELM瓦斯突出预测模型,实现对瓦斯突出风险的预测。实验结果表明,与ELM、粒子群优化的极限学习机(PSO-ELM)和遗传算法优化的极限学习机(GA-ELM)预测模型相比,该方法在提高模型泛化能力和预测精度方面效果显著。In order to improve the prediction accuracy of coal and gas outburst and achieve rapid prediction, a gas outburst prediction model ABAS-ELM based on the adaptive beetle antennae search(ABAS) algorithm and the extreme learning machine(ELM) is proposed. The kernel principal component analysis(KPCA) is used to extract the high-dimensional and non-linear features of coal and gas outburst. The extracted main features are used as the input of the prediction model, and the ABAS algorithm is used to optimize the input weight and hidden layer deviation of the ELM. The ABAS-ELM model for gas outburst prediction is established to predict the gas outburst risk. The experimental results show that compared with the prediction models such as ELM,particle swarm optimization-ELM(PSO-ELM) and genetic algorithm-ELM(GA-ELM), the method proposed in this paper has significant effect in improving the generalization ability of the model and the prediction accuracy.

关 键 词：煤与瓦斯突出 特征提取 自适应天牛须算法 极限学习机 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]