A beetle antennae search improved BP neural network model for predicting multi-factor-based gas explosion pressures

A gas explosion in an underground structure may cause serious damage to the human body and ground buildings and may result in huge economic losses. The pressure of the gas explosion is an important parameter in determining its severity and designating an emergency plan. However, existing empirical and computational fluid dynamics (CFD) methods for pressure prediction are either inaccurate or inefficient when considering multiple influencing factors and their interrelationships. Therefore, for a more efficient and reliable prediction, the present study developed a multifactorial prediction model based on a beetle antennae search (BAS) algorithm improved back propagation (BP) neural network. A total of 317 sets of data which considered factors of geometry, gas, obstacle, vent, and ignition were collected from previous studies. The results showed that the established model can predict pressures accurately by low RMSE (43.4542 and 50.7176) and MAPE (3.9666% and 4.9605%) values and high R² (0.7696 and 0.7388) values for training and testing datasets, respectively. Meanwhile, the BAS algorithm was applied to improve both the calculation efficiency and the accuracy of the proposed model by enabling a more intelligent hyperparameter tuning method. Furthermore, the permutation importance of input variables was investigated, and the length (L) and the ratio of length and diameter (L/D) of geometry were found to be the most critical factors that affect the explosion pressure level.     

基于ATG实报的空中颠簸预防管理系统设计

在对颠簸伤害事件原因分析的基础上,设计了基于ATG实报的空中颠簸预防管理系统,该系统设计主要包括:开发QAR计算EDR程序,通过EDR指标提高颠簸预报精度;开发颠簸管理平台,实现颠簸信息的有效传递;利用ATG技术使颠簸预报向颠簸实报提升,提高颠簸信息的实时性。该解决方案可实现空地高精度颠簸风险实时自动预警,有效降低颠簸伤害。     

基于遗传-蚁群算法的单层建筑火灾疏散路径规划研究

为解决如何快速、有效地找出单层建筑火灾最佳疏散路径问题,分析火灾发生时可能影响人员逃生及最佳路径生成的因素。提出基于遗传-蚁群算法求解火灾时期人员疏散路径。运用遗传算法的快速全局搜索能力,对蚁群算法初期所需要的信息素进行快速处理;利用蚁群算法的正反馈机制,快速找出可行路径,缩短搜索时间;并运用Matlab软件对其进行仿真。结果表明:遗传-蚁群算法所求得的路径生成质量有明显提高,并缩短路径生成时间,有助于提高人员逃生效率,降低人员伤亡率。     

1种基于CCRP火灾情况下的动态疏散算法

为在火灾发生时给逃生人群规划最优的安全疏散方案,基于CCRP算法开发1种火灾情况下受容量限制的动态疏散算法。该算法模型将发生火灾的建筑布局信息表达成节点连接弧形式,鉴于可预测危害蔓延对火灾逃生过程中疏散通道封锁时间的影响,为建筑网络图上的节点赋予“危险时刻”属性,逃生人员通过节点的时刻必须小于该节点的“危险时刻”才能规避火灾危险;基于eclipse软件平台,通过动态疏散算法与相似Dinesh算法应用实例对比仿真分析,验证基于CCRP的动态疏散算法的可行性与优越性。结果表明:通过该算法计算出的逃生路径保证逃生人员在最短时间疏散出去;且其具有安全性高和耗时少等优点。     

1种机器人工作区域协同搜索避障巡检策略

为解决工作区域搜索待操作目标的不确定性以及单一策略无法解决障碍物区域多搜索目标遍历与避障的问题,提出1种随机与固定搜索相结合的协同巡检策略。该策略在重点监测点通过引入非线性收敛因子及动态权重策略的改进灰狼优化算法遍历多任务点进行固定路线搜索;在非重点监测区域为差速转向移动机器人赋予三视野扫描线,并运用其灵活转动的特点进行随机路线搜索;通过交互式人工标记的方法定位搜索目标点并对其进行标记,运用改进灰狼优化算法对标记出的多目标点进行遍历顺序规划及D*算法避障到达;通过5个国际通用工程函数仿真测试改进的灰狼优化算法。结果表明:改进的灰狼优化算法能加快收敛速度,增强模型的求解精度,加强算法的稳定性,同时验证随机与固定相结合的区域协同搜索避障巡检策略的有效性。     

矿井通风网络压能图节点分层算法研究

为解决人工绘制矿井通风网络图与压能图工作量繁重的问题,基于对矿井通风网络图与矿井通风压能图的特点与作用的研究,提出了具有通风网络图与压能图部分特点的矿井通风网络压能图的概念及其特点与作用。采用分层算法实现对矿井通风网络压能图中各节点纵向相对位置的确定,为避免巷道两端节点压能值因取整相等时被分到同一层的问题,提出运用最长路径算法对各巷道节点进行第1次分层,再利用各节点的相对压能值进行2次分层的绘制方法。构造以分层算法绘制通风网络压能图的整体框架,为实现矿井通风网络压能图的自动绘制提供了技术支持。     

Precipitation as the Primary Driver of Variability in River Nitrogen Loads in the Midwest United States

Nitrogen (N) losses from agricultural lands in the Midwest United States are contributing to the expansion of the hypoxic zone in the Gulf of Mexico. This study evaluated the importance of inter‐annual variability in precipitation, land cover, and N fertilizer use on NO₃ + NO₂‐N loads in seven United States Midwestern Rivers using the backward stepwise regression analysis. At the annual scale, fluctuations in the current and previous years’ precipitations explained much of the variation in streamflow, baseflow, and N‐load. Previous years precipitation effects were associated with fillable soil porosity. In some years, higher residual soil N from previous dry years also contributed to an increase in N‐load. Area under soybean production (SOY), a surrogate for replacement of prairies and small grains was generally not a significant explanatory variable. Fertilizer use from 1987 to 2012 was also not a significant explanatory variable in the annual analysis. Precipitation in both the current and previous months and previous year were important in explaining variation in monthly streamflow, baseflow, and N‐load. SOY was significant in one or two months from June to August, but had a higher p‐value than precipitation. We conclude recent increases in river N‐loads are primarily due to wet climate and minimally due to the changes in land cover or N fertilizer use. Under current cropping systems and agronomic N application rates, tile water remediation will be necessary to reduce river N‐loads.     

方钢管混凝土柱-钢梁竖向加劲板连接节点抗震性能分析

在合理选择材料本构关系、破坏准则的基础上,采用通用有限元软件ANSYS对方钢管混凝土柱-钢梁竖向加劲板式节点进行了低周反复荷载试验,以及在低周反复荷载下的抗震性能分析。结果表明:有限元分析得到的滞回曲线和骨架曲线与试验结果吻合较好;试件破坏为梁端破坏,塑性铰出现在梁端,在梁变截面附近出现了局部屈曲,也与试验结果一致。     

腺病毒气溶胶的实时荧光定量PCR检测和绿色荧光蛋白活细胞检测

将带有绿色荧光蛋白的复制缺陷型重组腺病毒,作为模拟病毒建立一种检测病毒侵袭力的方法.在钢化玻璃箱中通过TK-3型微生物气溶胶发生器将腺病毒形成气溶胶,用FA-1型多级撞击式空气微生物采样器进行气溶胶采样,对采样样品分别进行实时荧光定量PCR检测和表达了绿色荧光蛋白的PK15活细胞定时检测.实时荧光定量PCR检测可测定病毒在大气中存在的相对基因拷贝数,通过在荧光显微镜下计数带绿色荧光的PK15细胞数可直观检测病毒的感染力及活力.结果表明,重组腺病毒气溶胶主要分布在采样器第五级,腺病毒气溶胶与病毒粒子相比较大.     

基于AGNES算法优化BP神经网络和GIS系统的大气污染物浓度预测

建立了大气污染物浓度与影响因子之间的BP神经网络,对城市中各监测点位的次日大气污染物浓度进行预测,采用GIS的插值分析进行污染物空间分布预测,其中BP神经网络的输入向量采用AGNES算法进行处理。以太原市区SO2、PM10浓度预测为例,选择气温、湿度、降水量、大气压强、风速和前5天的污染物浓度等10个参数训练BP神经网络,结果表明,BP神经网络的训练效果较好,预测结果与实际浓度显著相关,R2分别为0.988、0.976;结合太原市8个监测点位的污染物浓度预测值,运用GIS空间差值法绘出SO2、PM10的浓度分布预测图,该图与实际情况大体符合,并且与国控大气污染企业的分布显著相关,Pearson相关系数分别为0.969、0.949。