Microseismic monitoring technique is an important means of ground pressure monitoring to ensure safe, high-efficient and sustainable development of mines. Microseismic data obtained by sensors in mines are easily influenced by non-stationary noises with a wide frequency band, resulting in the lack of available high-quality data for microseismic monitoring. Instead of traditional analysis in frequency domain, this paper introduces a new method, synchrosqueezed wavelet transform (SSWT), which provides a way to decompose data into time domain and frequency domain simultaneously. With higher time-frequency resolution of SSWT spectrum, purer microseismic signals can be extracted from raw data. Besides, two wavelet bases, Morlet wavelet and bump wavelet, are compared to match the microseismic signal in this paper. Two field data with different signal-noise rate (SNR) are used to show the application of the algorithm in the mine industry. The results of data graphical filtering method show that the SSWT has great practical value to extract the microseismic signal from raw data and improves SNR of signals effectively than traditional methods.
Purpose:Long-term irrational use of mine resources leads to soil erosion,the reduction of cultivated land area and the destruction of the ecosystem.To make rational use of mineral resources and restore and control the geological environment of mines,the northwest of Hunan Province is taken as the research object.Method:The methods are as follows:By considering eight evaluation factors of three evaluation types(population density,surface slope,rainfall,engineering rock group,geological structure,mine area,geological disaster,and forest coverage rate),the expert evaluation weight was evaluated,and Q value was obtained through calculation.The innovation was to carry out local mine geological environment evaluation by using vector polygon method and GIS analysis.Based on geographic information system(GIS)technology,the mining environment of each district and county in the study area was graded.Result:The results showed that the mining environment in the northwest Hunan region was generally evaluated intuitively.Significance:It could provide a certain reference basis for mine environmental management and ecological restoration in northwest Hunan Province,and provide theoretical basis for other mine evaluations.
为准确预测矿井粉尘浓度,有效防治矿井粉尘危害,运用遗传算法优化的BP神经网络预测模型(GA-BP模型)对某矿山工作面时间序列粉尘浓度进行预测,以预测结果的相对误差、平均绝对百分比误差来评判模型的预测准确性.再利用BP神经网络预测模型、卷积神经网络预测模型(CNN 模型)的预测结果同 GA-BP 预测模型的预测结果进行对比验证,以均方根误差来评价三种模型的预测效果.结果表明,应用 GA-BP 预测模型,相对误差最大为 4.27%,最小为 0.14%,相对误差都在 10%以内,预测样本的平均绝对百分比误差(MAPE)小于 10%,达到了高精度预测要求.CNN、BP、GA-BP三种预测模型的RMSE值分别为 1.100 7、1.000 8、0.935 4,GA-BP预测模型对于该矿山工作面粉尘浓度预测效果最好.实现了利用 GA-BP神经网络预测模型对只有单一时间影响因素且样本数量较少条件下的矿井粉尘浓度预测.
为简化模型结构、解决迭代训练拖延问题,利用海鸥(SOA)算法进行核极限学习机(KELM)重要参数择优,建立基于数据插补和 SOA-KELM的岩爆风险预测模型.综合岩爆预测过程中多因素影响,选取单轴抗压强度、单轴抗拉强度等 6 种指标作为岩爆风险评价指标,搜集 93 组岩爆实测样本.一方面采用随机过采样补充少数类别样本数据,一方面采用 ELMAN神经网络进行缺失数据插补,构建高质量岩爆风险预测样本数据库.最终将预处理后的数据输入 4 种模型中进行分类预测.结果表明:数据插补后,各模型预测准确率提升 5.56～16.66 个百分点.不同情况下,SOA-KELM预测准确率均为最高数值,且数据随机过采样处理并未影响模型预测准确率,融合 ELMAN神经网络和 SOA-KELM的预测模型可有效应用于岩爆风险预测,为实际岩爆预测提供了新思路.
为考察烧结法微晶玻璃形核机制,试验以铜尾矿为基,设计了 R2O-CaO-SiO2-Al2O3-CaF2 体系微晶玻璃,通过分步取样、XRD、IR、SEM等手段分析并论证了基础玻璃形核机制,明确了基础玻璃晶核形成过程及机理,初步确定了C曲线.结果表明,本试验同时存在两种形核机制:异相诱导形核和分相诱导形核.形核阶段发生在550～650℃,基础玻璃在晶核形成初期会处于一种介于基础玻璃与晶核析出时的特殊状态,即在纳米和微米尺度范围内,基础玻璃内部粒子逐渐发生有序化行为.明晰形核机制对微晶玻璃的受控析晶过程具有重要的指导意义,可为消除烧结法微晶玻璃表面龟裂玻璃相提供依据.
