基于PCA和PSO-ELM的煤与瓦斯突出软测量研究

针对煤与瓦斯突出预测效率和准确率不高这一问题,提出将主成分分析(PCA)法与改进的极端学习机(PSO-ELM)相结合的方法对煤与瓦斯突出进行预测。根据某煤矿地质动力区划方法,在划分活动断裂,岩体应力计算等工作基础上获取影响突出的相关数据;通过主成分分析法对原始数据进行降维处理,消除变量间的线性相关性;利用粒子群算法(PSO)对极端学习机(ELM)的输入权值和隐层阈值进行优化,建立PSO-ELM预测模型,将提取的主成分作为该模型的输入,煤与瓦斯突出强度作为模型输出。实验结果表明,该方法的预测精度高、结构简化,具有较强的泛化性能力强。

Research on the soft sensor of coal and gas outburst based on improved pca-elm

For the coal and gas outburst prediction efficiency and the accuracy is not high, proposed to primary component analysis (PCA) combined with improved extreme learning machine (PSO-ELM) method for prediction of the coal and gas outburst. For a coal mine geology dynamic division method to extract relevant data highlight the impact of work-based division of active faults, the rock mass stress calculation. By PCA to reduce the dimension of the original data, remove the linear correlation volume. Establish PSO-ELM prediction model, the principal components of the extract as the input of the prediction model, coal and gas outburst intensity as the model output, tested with test samples. The results show that the predicted in accord with the actual situation at the same time, simplify the model structure, reducing the predicted time and improving the prediction accuracy and generalization performance.