Alternate solutions for mine ventilation network to keep a preassigned fixed quantity in a working place

In underground constructions, a good ventilation design not only delivers fresh air to establish good working environment, but also provides a scientific and reliable basis to prevent disasters. In emergency cases, unexpected closure of the main airways may occur, providing the workers with alternative airways is substantial. This is important not only to sustain personnel lives, but also to prevent the mine ventilation system from damage. In this research, alternate solutions were introduced in case of failure in the underground construction to keep a pre-assigned fixed quantity in a working place for mine ventilation network. Eight different collapse scenarios were proposed to study their effect on the air quantity distribution among the branches in the ventilation circuit. From these scenarios, it is found that providing a sufficient air quantity in the working places could be achieved through modification of the network topology and adjusting the values of the regulators pressure. It is also indicated that the distance between the collapse and working places has a great effect on the amount of air delivered to it. A reduction in the power consumption could be done by re-arrange the installed regulators and decreasing the number of nodes and branches inside the network. A relationship representing the effect of changing the network topology on the total network power consumption was deduced through regression analysis. It is found that the total network power is quadratic dependent on the number of regulators and number of branches while it is directly dependent on the regulator power.

Analysis of Mine Ventilation Network Using Genetic Algorithm

Aim To determine the global optimal solution for a mine ventilation network under given network topology and airway characteristics. Methods\ The genetic algorithm was used to find the global optimal solution of the network. Results\ A modified genetic algorithm is presented with its characteristics and principle. Instead of working on the conventional bit by bit operation, both the crossover and mutation operators are handled in real values by the proposed algorithms. To prevent the system from turning into a premature problem, the elitists from two groups of possible solutions are selected to reproduce the new populations. Conclusion\ The simulation results show that the method outperforms the conventional nonlinear programming approach whether from the viewpoint of the number of iterations required to find the optimum solutions or from the final solutions obtained.

GIS-Based Mine Ventilation Network and Safety Analysis

This paper constructed the mine ventilation network model using the powerful function of attribute management and display of GIS based on the study of GIS and mine ventilation network. In a mine ventilation network, a specified result can be obtained by defining weight values for attribute fields as the constraint condition. It is of great importance for mines to determine the best rescue and leaving route by the analyses of mine ventilation network routes, nodes and loops when a mine accident happens.

The stability indexes of branched airflow of ventilation network in coal mine

The stability of branched airflow of ventilation network is guarantee of safety in production of coal mine. Two indexes which stand for the stability of branches of ventilation network in coal mine were put forward in this paper, that are airflow intensity and sta- bility index of branched airflow, The airflow stability of working place was divided into different grade according to the stability index. The conclusion has great significance for safety in production of coal mine.

Stability of multiple fans in mine ventilation networks

In large mines,single fan is usually not enough to ventilate all the working areas.Single mine-fan approach cannot be directly applied to multiple-fan networks because the present of multiple pressures and air quantities associated with each fan in the network.Accordingly,each fan in a multiple-fan system has its own mine characteristic curve,or a subsystem curve.Under some consideration,the conventional concept of a mine characteristic curve of a single-fan system can be directly extended to that of a particular fan within a multiple-fan system.In this paper the mutual effect of the fans on each other and their effect on the stability of the ventilation network were investigated by Hardy Cross algorithm combined with a switching-parameters technique.To show the validity and reliability of this algorithm,the stability of the ventilation system of Abu-Tartur Mine(one of the largest underground mine in Egypt)has been studied.

Junction Pressure Composing MethodCalculating the Total Resistance of Mine Ventilation Network

In mine ventilation network calculation, the total ventilatiou perameters, such as total specific resistance and total natural veutilatiou pressure of an overall mine ventilation system, play an important role on selecting main fan and regulating its operating point. This paper explains the critical effect of network’ s total parameter calculation on the above two aspects and presents a new method, the junction pressure composing method(JPC method), which can be applied to calculate the total resistance.of an overall, complex and multi-fan ventilation network. Based on the total ressistance and airflow rate of main fan, total specific resistance of a natwork is easily calculated. This method gets rid of those shortcomings in the route airflow working mathod(RAW method), greatly improves computing speed and adaptability, and can calculate the total parameters of a mine ventilation network rapidly and conveniently. This method is proved to be correct and reliable by example tests.

An optimized control of ventilation in coal mines based on artificial neural network

According to the nonlinear and time dependent features of the ventilation systems for coal mines, a neural network method is applied to control the ventilator for coal mines in real time. The technical processes of coal mine ventilation system are introduced, and the principle of controlling a ventilation fan is also explained in detail. The artificial neutral network method is used to calculate the wind quantity needed by work spots in coal mine on the basis of the data collected by the system, including ventilation conditions, environmental temperatures, humidity, coal dust and the contents of all kinds of poisonous and harmful gases. Then the speed of ventilation fan is controlled according to the required wind which is determined by an overall integration of data. A neural network method is presented for overall optimized solution or the genetic algorithm of simulated annealing.

Stability of mine ventilation system based on multiple regression analysis

In order to overcome the disadvantages of diagonal connection structures that are complex and for which it is difficult to derive the discriminant of the airflow directions of airways, we have applied a multiple regression method to analyze the effect, of changing the rules of mine airflows, on the stability of a mine ventilation system. The amount of air （ Qj ） is determined for the major airway and an optimum regression equation was derived for Qi as a function of the independent variable （ Ri ）, i.e., the venti- lation resistance between different airways. Therefore, corresponding countermeasures are proposed according to the changes in airflows. The calculated results agree very well with our practical situation, indicating that multiple regression analysis is simple, quick and practical and is therefore an effective method to analyze the stability of mine ventilation systems.

Study on unidirectional circuit problem in multi-fan-station ventilation type of Jinchuan No.2 mine

The calculating methods for path number and path matrix of ventilation net- works without unidirectional circuits were introduced,and the inapplicability problem of the matrix algorithm to determine paths in a ventilation network with unidirectional circuit was brought forward,and a depth-first search method based algorithm to determine path ma- trix by means of modifying search strategies was discussed.The method is suitable for ventilation networks with unidirectional circuits and ventilation networks without unidirec- tional circuits,moreover the complexity is less than the complexities of matrix based algo- rithms.A series of methods and means to avoid and to reduce the negative effects of un- idirectional circuits such as the optimum of the positions of fan stations,the increase or de-crease of fan station numbers,the optimum regulation of network and the analysis of diagonal structures were put forward.

THE LEAST SQUARES COMPREHENSIVE ADJUSTMENT FOR MINE VENTILATION MEASUREMENTS

This paper systematically introduced the method of direct, indirect and free-network adjustments and their application in data process of minewide ventilation measurements. The direct adjustment is suitable for errors collating of the measurements of airflow rates. The indirect method is suitable for the adjustment of ventilation resistance. The free-net method is adapted to the combined adjustment of the measurements of both the ventilation in branches of the air network and the air pressure at nodes of the ventilation network, the partial adjustment is also introduced here to be used for saving the storage locations in computer required for the adjustment for large scale mine ventilation measurements.

基于YOLOv8改进的脑癌检测算法

自动检测脑部肿瘤在磁共振成像中的位置是一个复杂、繁重的任务,需要耗费大量时间和资源。传统识别方案经常出现误解、遗漏和误导的情况,从而影响患者的治疗进度,对患者的生命安全产生影响。为了进一步提高鉴定的效果,引入了4项关键改进措施。首先,采用了高效的多尺度注意力EMA(Efficient Multi-scale Attention),这种方法既可以对全局信息进行编码,也可以对信息进行重新校准,同时通过并行的分支输出特征进行跨维度的交互,使信息进一步聚合。其次,引入了BiFPN(Bidirectional Feature Pyramid Network)模块,并对其结构进行改进,以便缩短每一次检测所需要的时间,同时提升图像识别效果。然后采用MDPIoU损失函数和Mish激活函数进行改进,进一步提高检测的准确度。最后进行仿真实验,实验结果表明,改进的YOLOv8算法在脑癌检测中的精确率、召回率、平均精度均值均有提升,其中Precision提高了4.48%,Recall提高了2.64%,mAP@0.5提高了2.6%,mAP@0.5:0.9提高了7.0%。

基于Ventsim的王家塔煤矿通风系统优化研究

针对王家塔煤矿存在的多煤层、多盘区、供风线路长和通风阻力分布不协调等特点,尤其是随着4^(#)煤开拓和3^(#)煤3盘区的准备,通风系统的不合理性更加凸显。在获取可靠通风基础参数的基础上,利用Ventsim建立王家塔煤矿全矿井三维可视化模型并完成仿真模拟,按照调风操作可行、简单、可靠的原则,提出优化调整方案并模拟分析了调风效果。调风实践表明,优化后的通风系统稳定性增强,通风总阻力降低,阻力分布趋于合理,既实现了企业通风的节能降耗和成本开支,又全面提升了矿井的通风管理水平及决策能力,对矿井通风管理有较好的指导作用。

深部通风三维仿真模拟研究

随着矿井开采深度的不断增加,井下深部高温热害问题严重,由于深部的恶劣条件导致相关现场研究十分困难,利用通风三维仿真模拟技术进行深部通风系统分析是合理可靠的科学选择。应用Ventsim通风仿真模拟软件对河西金矿通风系统进行三维仿真模拟和系统能量损失分布模拟、河西金矿深部通风系统总需风量的相关计算,在模拟结果与理论计算的基础上,对模拟风量结果与临界需风量结果进行对比分析。为相似条件的深部矿井通风系统的模拟分析研究和降本节能增效提供了案例借鉴和数据参考。

基于PCA-BP神经网络的巷道通风摩擦阻力系数预测模型

根据实测巷道通风摩擦阻力系数数据的特点,建立了主成分分析PCA-BP神经网络预测模型。采用PCA法对影响巷道通风摩擦阻力系数的支护类型、断面形状、巷道宽、巷道高、支护部分周边长、巷道断面积和巷道长度7个因素进行降维。将降维后因素的贡献率进行排序筛选,得到3个主成分指标(F_(1)、F_(2)和F_(3)),作为BP神经网络输入层的神经元。利用实测数据对PCA-BP神经网络模型进行训练和测试,并将测试结果与支持向量机回归(SVM)模型和BP神经网络模型的测试结果进行对比,结果显示:全因素的BP神经网络预测模型和SVM预测模型的平均精度分别为92.9420%、93.0235%,而PCA-BP预测模型的平均精度达到了96.4325%。PCA-BP神经网络模型不但简化了网络结构,更提高了网络的泛化能力,使预测误差更小、精度更高,为更准确地获得巷道通风摩擦阻力系数提供了一种有效的方法。

汽轮发电机带有交替径向风道的转子流体与传热耦合分析

针对汽轮发电机带有交替径向通风道的转子发热冷却问题,以一台350 MW水氢氢冷汽轮发电机为研究对象,依据流体力学和传热学的基本理论,首先建立计及旋转的电机全域通风网络模型,采用逐次迭代法计算得到各支路流量和节点压力。其次,建立了带有交替径向风道的发电机转子流体-传热三维物理模型和数学模型,给出了基本假设和相应的边界条件,同时将通风网络计算得到的风速和压力作为转子求解域的耦合边界,采用有限体积法进行求解,计算结果与实测值吻合。然后分析了交替径向风道内流量分配和氢气流动情况,研究了转子内部氢气温度分布和槽楔出风口风温变化规律,探明了转子绕组和铁心轴向温度分布特性,讨论了副槽入口流量和槽楔出口直径对转子流体和温度的影响。得出副槽入口流量应控制在0.1~0.16 m^(3)/s范围内,且选择较小的槽楔出口直径,可以提高通风系统的效率与风量分配均匀性,降低转子轴向热不平衡。

基于采矿工程安全的MGWO在矿井风网风量优化调节中的应用

针对当前采矿工程中矿井风网风量优化调节效果不够理想的缺陷,研究提出一种风量优化调节模型,并采用优化的灰狼优化算法(Grey Wolf Optimization,GWO)对其进行求解,完成矿井风网风量智能优化调节。结果显示,MGWO算法求解的风量优化平均值为216.4kW,平均运行时间为132.6s,均优于其他两种算法。上述结果说明,研究提出的MGWO对矿井风网风量优化调节模型的求解效率与精度更高,对风网风量优化调节的效果更好,能够有效调节风网风量,保证采矿工程安全性。

矿井传感器风量最小平衡修正量研究

在智能化开采时代,高性能的实时通风网络解算对于矿山通风系统的安全管理至关重要,而初始迭代风量对解算性能具有显著影响。由于传感器难以避免地存在测量误差且布置稀疏,利用传感器监测数据难以分配全风网初始风量。首先,将矿井通风网络视为网络流模型,并对传统的有上下界网络流模型进行改进,以使之能够基于存在测量误差的传感器风量进行全风网风量分配。其次,用风量平差模型对传感器误差导致的节点风量不平衡进行最小平衡量修正。试验模拟和现场试验均表明了研究方法的可行性和有效性。在现场试验中,传感器分支的风量平均修正率为0.66%,平均风量修正值为0.09 m^(3)/s。该方法能够对任意位置布置且存在测量误差的传感器的风量进行全风网的风量初始化分配。

某大型铝土矿地下矿山通风系统存在问题分析及优化调控方法探讨

随着某大型铝土矿地下矿山井下生产的展开,矿井通风系统的问题逐步凸显,对现场风质进行测定后发现生产巷道中有害气体会出现较严重的超限等通风故障现象。通过对矿井风量、通风设备设施和通风网络结构的分析,研究了矿井通风系统故障的原因,并提出了消除通风系统故障、改进通风系统的方法;对保障地下矿山安全生产,有效防范矿井中毒窒息事故,坚决遏制重特大事故的发生具有非常重要的指导意义。

基于回路风量法的矿井通风网络解算算法

基于当前矿井通风网络解算算法的不足,深入研究回路法、Scott-Hinsley和Seidel法,设计出一种能够快速解算复杂风网的算法,主要步骤包括确定风网结构、赋权边并选取最小生成树、圈划独立回路、进行网络解算。该方法用Kruskal法来选取最小生成树,思路清晰、易于理解,方便计算机程序的实现;用试探回溯法来圈划独立回路,对于反复出现的子问题,无需进行二次求解;用改进Scott-Hinsley法进行风量解算,计算收敛速度更快,提高了算法的执行效率。将该优化算法应用于“黄坊煤矿通风智能决策系统”迭代解算模块。结果表明:风量解算结果与实测值误差均小于5%,能满足工程应用要求,为矿井通风网络解算提供了一种新思路。

基于人工神经网络的老年单肺通气患者术后谵妄预警模型的构建与评价

目的 构建基于人工神经网络(ANN)的老年单肺通气(OLV)患者术后谵妄(POD)的风险预警模型并评价其预警效能。方法纳入542例接受OLV的老年患者,其中POD组242例,非POD组300例。数据集按照7:3随机分为训练集(POD=169例,非POD=210例)和验证集(POD=73例,非POD=90例),利用训练集分别构建ANN和Logistic回归风险预警模型,并在验证集中评价两模型预警效能。结果两模型的Hosmer and Lemeshow检验差异均无统计学意义(P>0.05);ANN风险预警模型的曲线下面积、灵敏度、特异度、阴性预测值和净重新分类指数高于Logistic回归风险预警模型(P<0.05);ANN风险预警模型的约登指数、F1 score、阳性似然比、阴性似然比优于Logistic回归风险预警模型;两模型准确率和阳性预测值比较差异无统计学意义(P>0.05)。结论 基于ANN的风险预警模型对老年OLV患者POD的预警效能优于Logistic回归风险预警模型。