基于RS-PSO-ELM的深部煤与瓦斯突出安全评价研究

Research on Safety Evaluation of Deep Coal and Gas Outburst Based on RS-PSO-ELM

针对深部煤矿瓦斯突出高维、非线性等特点,提出一种基于RS-PSO-ELM的深部煤与瓦斯突出安全评价模型。首先通过粗糙集(RS)进行指标降维处理,其次运用PSO优化ELM的初始权重和阈值,构建出一种能够运用于深部煤矿瓦斯突出评价系统的PSO-ELM模型。数据拟合显示,标准PSO模型识别准确率80%,而PSO-ELM模型识别准确率可达90%,提升了10个百分点,能够显著改善深部煤与瓦斯突出探测精度,这为科学评价深部煤与瓦斯突出危险性提供了一种新思路,对促进深部煤矿安全管理有重要参考价值。

Aiming at the high-dimensional and nonlinear characteristics of gas outburst in deep coal mines, proposes a safety evaluation model for deep coal and gas outburst based on RS-PSO-ELM.First, rough set(RS) is used to reduce the dimensionality of indicators, and secondly, PSO is used to optimize the initial weight and threshold of ELM to construct a PSO-ELM model that can be applied to the evaluation system of gas outburst in deep coal mines. Data fitting shows that the recognition accuracy of the standard PSO model is 80%, while the recognition accuracy of the PSO-ELM model can reach 90%, an increase of 10%, which can significantly improve the detection accuracy of deep coal and gas outbursts. This is a scientific evaluation of deep coal. And the danger of gas outburst provides a new way of thinking, which has important reference value for promoting the safety management of deep coal mines.