| 摘要:为有效预防煤与瓦斯突出灾害，针对煤与瓦斯突出预测精度和效率不高问题，提出基于小波核主成分分析（KPCA）和改进的极限学习机（IQGA-ELM）的煤与瓦斯突出预测方法。通过小波核主成分分析法对原始致突指标进行非线性降维处理，提取出致突指标主成分序列，将其作为极限学习机（ELM）网络神经的输入，利用改进量子遗传算法（IQGA）对ELM的输入层权值和隐含层阈值进行优化，建立小波KPCA-IQGA-ELM预测模型，模型的输出为煤与瓦斯突出强度的预测结果。研究结果表明，该模型泛化能力强，可以对煤与瓦斯突出强度进行有效预测。 |
| 关键词: 煤与瓦斯突出预测 小波核主成分分析 改进量子遗传算法 极限学习机 |
|
| Based on the Wavelet KPCA with IQGA –ELM Coal and Gas Outburst Prediction research |
|
|
| Abstract:In order to prevent the coal and gas outburst disaster effectively, this paper presents a method of combining wavelet principal component analysis (KPCA) and improved extreme learning machine (IQGA-ELM) for the problem of low accuracy and efficiency of coal and gas outburst prediction to predict coal and gas outbursts. The principal component sequence of the primate index is extracted by wavelet principal component analysis (KPCA), which is used as the input of ELM neural network, using the improved quantum genetic algorithm (IQGA) to optimize the input weight and the hidden layer threshold of the extreme learning machine (ELM),and establishing the wavelet KPCA-IQGA-ELM prediction model. The output of the model is the prediction of coal and gas outburst strength. The results show that the model has strong generalization performance and can be used to predict the strength of coal and gas outburst effectively. |
| Key words: Prediction of Coal and Gas Outburst wavelet kernel principal component analysis improved quantum genetic algorithm extreme learning machine |