Machine learning algorithm selection for windage alteration fault diagnosis of mine ventilation system

Machine learning algorithms have been widely used in mine fault diagnosis. The correct selection of the suitable algorithms is the key factor that affects the fault diagnosis. However, the impact of machine learning algorithms on the prediction performance of mine fault diagnosis models has not been fully evaluated. In this study, the windage alteration faults (WAFs) diagnosis models, which are based on K-nearest neighbor algorithm (KNN), multi-layer perceptron (MLP), support vector machine (SVM), and decision tree (DT), are constructed. Furthermore, the applicability of these four algorithms in the WAFs diagnosis is explored by a T-type ventilation network simulation experiment and the field empirical application research of Jinchuan No. 2 mine. The accuracy of the fault location diagnosis for the four models in both networks was 100%. In the simulation experiment, the mean absolute percentage error (MAPE) between the predicted values and the real values of the fault volume of the four models was 0.59%, 97.26%, 123.61%, and 8.78%, respectively. The MAPE for the field empirical application was 3.94%, 52.40%, 25.25%, and 7.15%, respectively. The results of the comprehensive evaluation of the fault location and fault volume diagnosis tests showed that the KNN model is the most suitable algorithm for the WAFs diagnosis, whereas the prediction performance of the DT model was the second-best. This study realizes the intelligent diagnosis of WAFs, and provides technical support for the realization of intelligent ventilation.     

因素空间理论下基点分类算法研究

目前，基于因素空间理论的背景基提取算法计算过程复杂，初始化必须依赖各因素极值，基点数量提取冗余等原因，未能在应用中取得很好效果。为此，结合内点判别法和知识可继承、可扩展的思想，提出一种计算简单、初始化独立、基点数量小的改进的背景基提取算法。然后，利用改进的背景基提取算法构造出一种全新的数据分类算法-基点分类算法，基点分类算法以提取每一类样本的背景基为预测模型，再通过新定义的λ-背景基，优化预测模型。数值实验表明:基点分类算法原理简单、构造难度小、分类模型泛化能力强，预测能力准确率高，同时严格的模型限定区域又能为识别新类别提供新方法。     

同安煤矿4101综放工作面煤氧化自燃的标志性气体研究

煤自然火灾严重威胁着煤炭工业的安全。为了遏制该类火灾的发生,煤自然火灾指标气体的预测预报功能越来越受到人们的重视。本文通过煤氧化反应生产气体的红外光谱实验,分析了同安煤矿4101综放面煤样在升温氧化过程中,在不同温度下煤氧化自燃产生气体的红外光谱图谱,确定了此煤样在氧化自燃过程中在不同温度下出现的标志性气体。建立了标志性气体的预报模型,研究分析了煤样氧化自燃生产的CO、CH_4和C_2H_4气体的浓度与温度的关系。结果表明,4101综放工作面实验煤样氧化自燃生成的气体产物有H_2O、CO_2、CO、CH_4和C_2H_4等5种,CH_4、CO和C_2H_43种气体的浓度随温度的升高有着不同的变化规律。对矿井自燃火灾的预测预报具有重要的指导意义。     

柔性注压锚杆锚固段阻抗摩擦应力分布规律模拟研究

针对柔性注压锚杆解析及实验比较困难,采用有限元方法,模拟研究其锚固段阻抗摩擦应力的分布规律。数值模拟显示:沿锚杆环向呈近似正弦或余弦函数的循环分布形态;沿锚杆轴向应力分布可划分成波浪段、平台段以及突降段3个阶段。柔性注压锚杆锚固段最大阻抗摩擦应力沿轴向分布近似是均匀的,可实现真正的全长锚固。     

Caking property and active components of coal based on group component separation

The content and the caking index of the heavy,the dense medium and the loose medium components of coal,obtained by extraction and stripping with CS_2/N-methyl-2-pyrrolidinone mixed solvent(1:1 by volume),were studied and correlated with the caking property of raw coals.Images of the three group components after heat treatment were analyzed.The results show that both caking index(G) and maximum thickness of plastic layer(Y) of coals have a good linear relationship with the content of the medium component;the dense medium and the loose medium components are the two key factors to determine the caking property of raw coals-they are the source materials of fluidity and swelling of coal,respectively;the heavy component without the swelling and fluidity was cohered by the other components;two new indexes,which can extend current understanding of the caking properties,were introduced.     

A new design of foaming agent mixing device for a pneumatic foaming system used for mine dust suppression

To overcome the drawbacks of the conventional foam technology used for dust suppression,including large pressure loss,high water pressure and low driving pressure,a new pneumatic foaming system is introduced.Then an original design of foaming agent mixing device is proposed,and its performance is investigated and evaluated under different pressure compensations.Experimental results show that the maximum absorption amount increases by 2.9-6.7 times at a pressure compensation of 0.04-0.2 MPa compared with no pressure compensation.The pressure loss and pressure fluctuation both reduce significantly with increasing pressure compensation.The critical outlet pressure increases by30.4-240%.Field application indicates that the proposed mixing device ensures the reliable addition of foaming agent used for foam dust suppression.The effect of foam on dust suppression is remarkable,and the economic cost of foam is low.Therefore,there is reason to believe that the new mixing device will greatly promote foam technology to be widely used for suppressing dust in underground coal mines.     

Ionic liquid modified graphene oxide for enhanced flame retardancy and mechanical properties of epoxy resin

In this work, to improve its dispersion and flame retardancy, graphene oxide (GO) was functionalized by silane coupling agent KH550 and 1-butyl-3-methylimidazole hexafluorophosphate (PF₆-ILs), and characteristics of the PF₆-ILs@GO was obtained by transmission electron microscopy (TEM), energy dispersive spectroscopy (EDS), Fourier transform infrared spectroscopy (FTIR), X-ray diffraction (XRD), and thermogravimetric analysis (TGA). Then, the synergistic flame retardant of GO or PF₆-ILs@GO and melamine pyrophosphate (MPP) were applied for epoxy resin (EP) materials. Specifically, the limiting oxygen index (LOI) value of EP with 0.1 wt% PF₆-ILs@GO was increased to 29.2% from 27.5% of EP/MPP composites, and the UL-94 test reached the V-0 rating. The CCT results showed that the total heat release (THR) and total smoke release (TSP) of EP/MPP/PF₆-ILs@GO composites were significantly 24.4% and 53.4% lower than that of EP/MPP composites. Besides, the thermal behavior investigated by TGA indicated that the char-forming effect of GO and PF₆-ILs@GO was great, the residual char of EP/MPP/PF₆-ILs@GO composites was as high as 19.5% at 700°C, and its thermal stability was higher than that of EP/MPP composites. On the other hand, the tensile strength of EP/MPP/GO and EP/MPP/PF₆-ILs@GO composites were increased by 15.6% and 28.3% compared with EP/MPP composites. According to SEM analysis, the EP/MPP/GO composites formed a good protective char layer, which can effectively improve flame retardancy of EP. This research represents a new method of flame retardant modified GO to improve the flame retardancy and mechanical properties of polymers.     

Study on improvement of conductivity of Cu-Cr-Zr alloys

The influence of alloying, heat treatment, and plastic working on the performance of Cu-Cr-Zr alloys was investigated. The precipitated phases were characterized as Cr, Cu51Zr14 and Cu5Zr. Cu-Cr-Zr alloys demonstrate combination properties of high strength and high conductivity after solution treatment, aging treatment, and plastic deformation. Precipitation course of Cr is the main factor that influences the conductivity of Cu-Cr-Zr alloys, while adding Zr in the alloys adjusts the orientation relationship between Cr and matrix, and tends to increase the conductivity of aged Cu-Cr-Zr alloys after deformation.     

高压切割喷嘴冲击磨损的数值分析

以复用矿井含煤颗粒的水对高压切割喷嘴的磨损物理问题为研究对象,采用计算流体力学理论进行数值计算,分析讨论了质量浓度为10、15、20、25、30、40 mg/L条件下速度、剪应力、磨损的分布以及变化关系。计算、分析结果表明:磨损主要发生在出口部位和锥体的后半部份,入口部份和锥体前半部份磨损较小;入口部位、锥体部位磨损量、剪应力随质量浓度增加变化较小;出口部位磨损量在质量浓度为10～20 mg/L减小较快,超过20 mg/L后变化不大;出口部位流体速度、磨损量、剪应力与质量浓度间存在对应关系。煤粒入口速度与混合物速度相同、锥体部位煤粒流体速度低于锥体部位混合物速度(平均值)约79.4%;煤粒出口部位速度随质量浓度的增大而呈现先增加后减小的趋势,速度最大值发生在浓度20 mg/L。     

椭圆管外流动熵产及放热系数的数值分析

以椭圆管加热水流动为研究对象,对椭圆管加热水流动系统进行了二维数值模拟。通过联立求解流体力学基本方程和熵产方程,获得了熵产、放热系数与雷诺数和纵、横向间距的变化关系。数值分析结果表明:熵产主要发生在管壁表面附近,而在系统内部区域熵产较小,可以忽略;熵产随雷诺数的增大而增大,随纵、横向间距增加而减小,熵产与雷诺数、纵、横向间距存在对应关系,纵、横向间距宜在1.75～2.0间;在相同的雷诺数值时,熵产、放热系数沿流动方向呈现单调减小的趋势;不同的雷诺数值,熵产、放热系数不同,单调减小的趋势相同。放热系数随Re的增大而增大,且与雷诺数存在对应关系。纵向总放热系数随纵、横向间距增大而减小,且存在对应关系。