基于VMD和BSA-KELM的高陡边坡位移预测模型研究

边坡位移的时间序列曲线存在复杂的非线性特性,传统的预测模型精度不足以满足预测要求。为此提出了基于变分模态分解的鸟群优化-核极限学习机的预测模型,并用于河北省某水泥厂的边坡位移预测。该方法首先采用VMD把边坡位移序列分解为一系列的有限带宽的子序列,再对各子序列分别采用相空间重构并用核极限学习机预测,采用鸟群算法优化相空间重构的嵌入维度和KELM中惩罚系数和核参数三个数值,以取得最优预测模型。最后将各个子序列预测值叠加,得到边坡位移的最终预测值。结果表明：和KELM、BSA-KELM、EEMD-BSA-KELM模型相比,基于VMD的BSA-KELM预测精度更高,为边坡位移的预测提供一种有效的方法。     

北斗星历解析及实时卫星位置解算实现

利用 C 语言编程进行北斗卫星星历数据的实时读取，更新结构体的卫星轨道参数， 从而实现北斗卫星位置的解算，并与武汉大学数据中心提供的北斗精密星历作比较，对解算的卫星位置结果进行评估，最大误差不超过 3.5 米，满足实际应用需要。     

金针菇多糖对微冻大黄鱼及其鱼片品质变化的影响

为研究金针菇多糖（polysaccharide from Flammulina velutipes，FVP）对微冻大黄鱼及鱼片在贮藏期间肌原纤维蛋白性质的变化及水分分布的影响，实验分别选用0.03、0.06、0.09 g/L FVP浸渍处理大黄鱼和鱼片，以无菌水处理为对照组，分析微冻贮藏期间样品的感官指标得分、总挥发性盐基氮含量、总巯基含量、Ca2＋-ATPase活性、蛋白流变学性质以及水分迁移变化规律。结果表明：FVP可有效抑制整鱼总挥发性盐基氮含量上升和感官得分的下降；减缓整鱼及鱼片在微冻过程中总巯基含量、Ca2＋-ATPase活性下降和水分流失；此外FVP还能够延缓大黄鱼因腐败而出现的蛋白凝胶能力减弱。在本实验选取的多糖浓度范围内，0.09 g/L FVP处理组保鲜效果较强。该研究结果可为FVP用于水产品贮运保鲜提供理论参考。     

Hydrogeochemical Processes and Inverse Modeling for a Multilayer Aquifer System in the Yuaner Coal Mine,Huaibei Coalfield,China

Coal mining can dramatically change hydrogeological conditions and induce serious environmental problems. Fifty groundwater samples were collected from the main aquifers in the Yuaner coal mine (Anhui Province, China). The results show that the main hydrogeochemical processes in the mine include dissolution, precipitation, pyrite oxidation, desulfurization, and cation exchange. The Neogene porous aquifer is affected by groundwater flow conditions; its main hydrogeochemical processes are dissolution of carbonate minerals and gypsum, and cation exchange. The Permian coal measure’s fractured sandstone aquifer was confirmed to be controlled by the region’s geological structure; its main hydrogeochemical processes are desulfurization and cation exchange. The Carboniferous Taiyuan limestone aquifer was determined by both groundwater flow conditions and regional geological structure; its main hydrogeochemical processes are dissolution of carbonate minerals and gypsum, pyrite oxidation, and cation exchange. Additionally, hydrogeochemical inverse modeling of the groundwater flow path confirm the hydrochemistry results and principal component analysis.

     

定距螺旋桨对船用主机外特性的要求分析

为解决定距螺旋桨与船用主机在船舶运行工况的机桨匹配问题,结合船舶系泊和航行试验的相关标准,分析和归纳船舶运行数据,将实船测试与船机桨匹配理论计算相结合,得出运输船和拖轮在常用工况及特殊工况下定距螺旋桨对主机外特性的定量要求,为配套不同细分市场时船用主机的优化和开发提供参考依据。     

床温及SNCR脱硝对CFB锅炉NOx和N2O排放影响的试验研究

为了研究循环流化床（CFB）锅炉燃用无烟煤时床温及选择性非催化还原（SNCR）脱硝对于NO和N2O排放的影响，在1 MW CFB试验装置上开展了试验研究。结果表明:床温由880 ℃提高到970 ℃，NO排放质量浓度由119.5 mg/m3上升到226.0 mg/m3，N2O排放质量浓度由216.0 mg/m3降低到102.2 mg/m3；在氨氮摩尔比（NSR）为0~3.7之间，随着NSR的提高，脱硝效率从0上升到50.72%；进一步提高NSR到5.2，脱硝效率升至53.61%，增加较为缓慢；随着NSR从0提高到1.7，N2O排放质量浓度由84.3 mg/m3上升至118.3 mg/m3，增长较为缓慢；进一步提高NSR至2.0，N2O排放质量浓度上升至187.7 mg/m3，增长速度提高；继续提高NSR至5.2，N2O排放质量浓度上升至381.4 mg/m3；CFB锅炉采用以尿素为还原剂的SNCR脱硝工艺时，单纯通过加大NSR来提高脱硝效率不仅效果有限，过量喷入的还原剂会造成N2O排放量的显著提高。     

A self-adaptive synthetic over-sampling technique for imbalanced classification

Traditionally, in supervised machine learning, (a significant) part of the available data (usually 50%-80%) is used for training and the rest—for validation. In many problems, however, the data are highly imbalanced in regard to different classes or does not have good coverage of the feasible data space which, in turn, creates problems in validation and usage phase. In this paper, we propose a technique for synthesizing feasible and likely data to help balance the classes as well as to boost the performance in terms of confusion matrix as well as overall. The idea, in a nutshell, is to synthesize data samples in close vicinity to the actual data samples specifically for the less represented (minority) classes. This has also implications to the so-called fairness of machine learning. In this paper, we propose a specific method for synthesizing data in a way to balance the classes and boost the performance, especially of the minority classes. It is generic and can be applied to different base algorithms, for example, support vector machines, k-nearest neighbour classifiers deep neural, rule-based classifiers, decision trees, and so forth. The results demonstrated that (a) a significantly more balanced (and fair) classification results can be achieved and (b) that the overall performance as well as the performance per class measured by confusion matrix can be boosted. In addition, this approach can be very valuable for the cases when the number of actual available labelled data is small which itself is one of the problems of the contemporary machine learning.