优化强化学习路径特征分类的脉象识别法

脉象识别是中医诊断的重要手段之一。长期以来,依据个人经验进行的脉诊制约了中医的推广与发展。因此,利用传感设备进行脉象识别的研究正在逐步展开。针对神经网络识别脉象的相关研究中,存在需要大量训练数据集,以及存在处理“黑箱”和时间花销较大等问题,在强化学习的框架下,提出了一种采用马尔可夫决策和蒙特卡罗搜索的脉象图分析法。首先依据中医理论对特定的脉象进行路径分类,然后在此基础上为不同的路径选择代表性特征,最终通过对代表性特征的阈值对比完成对脉象的识别。实验结果表明,所提方法可缩减训练时间和所需资源,并可保留完整的经验轨迹;且在提高脉象识别的准确率的同时,还可解决数据处理过程中的“黑箱”问题。     

基于模型的测试用例生成方法

在大量软件出现的今天,除开软件的功能是否完善外,对软件本身提出了更高的安全性和稳定性要求;一款软件在上线前需要进行大量的测试,以便提升软件的质量;由于开发人员参与了软件的研发及上线流程,导致了看待软件问题的局限性,而测试人员在编写测试用例时,往往由于依据文档的不一致性,使得测试用例的价值大打折扣;并且在实际软件的开发流程中,测试环节与开发严重脱节;往往只是为了出相应的测试报告而去测试,偏离了测试的初衷;针对以上问题,提出基于模型的用例生成方法,能够基于工作流程图、判定表、状态转换等多种测试方法,并在该方法中应用边界值与等价类的思想,够贯穿整个软件研发的生命周期,在软件研发初期就能够参与测试,提出设计方案的不足;并且能够自动生成测试用例,提高测试人员的效率.     

Variable sorting based on fault tree structure adjustment for multi-valued decision diagrams

The dynamic fault tree does not have the ability of fault calculation when analyzing the reliability of the system, so it needs to be modeled and analyzed by means of multi-valued decision diagrams and so on. The dynamic fault tree is translated into a multi-valued decision diagram according to the ordering of variables of basic events which affects the size of the generated multi-valued decision diagram and the cost of traversal to get cut sequences. An adjustment method of the dynamic fault tree structure is proposed based on the importance degree of repeated events, dynamic gates and the locations of events of the dynamic fault tree. By taking the fact that the basic events at the same level are equally important into account, an improved dynamic variable ordering method and ordering generation algorithm for the multi-valued decision diagram are presented in this paper. The result analysis of an example shows that the improved dynamic variable ordering method can reduce the size of the multi-valued decision diagram and space and time complexity of the reliability calculation compared to the similar methods.     

基于宽带时频图的多路摩尔斯信号自动检测

针对现有算法没有涉及的宽带环境下多路摩尔斯信号自动检测问题,提出一种基于宽带时频图和集成学习分类器的算法.首先,通过提出一种基于宽带时频图的信号快速窄带滤波方法,实现噪声背景中各类型信号窄带时频图的快速获取;然后,为从上述窄带时频图中识别出多路摩尔斯信号,提出3个新特征与局部二值模式特征构成特征向量;最后,采用集成学习算法设计分类器实现摩尔斯信号的自动检测.与现有算法对比实验结果表明:针对多组实际数据,该算法的正确率均可达95%以上,同时误检率低于10%,具有良好的鲁棒性和应用价值.     

十字路口处长车交通状态相图

如今,相图被广泛用于交通科学领域的研究,取得了重要成果。根据理论分析和计算机模拟,本文构建了十字路口处交通流量相图。该相图是由五个基本区域构成的,本文分析并推导出每个区域的具体流量公式。在周期边界条件下,采用确定性 Fukui－Ishibashi元胞自动机交通模型进行数值模拟,其模拟结果与理论分析精确一致。     

由二元合金相图提取无限稀活度系数（英文）

提出了由二元相图提取定温下无限稀活度系数的方法,分别在正规溶液和Richardson假设条件下,计算了31个二元液态合金体系两组元无限稀活度系数,并与相应的实验值比较,所获得的平均相对误差为:共晶体系为23.2%和20.7%;含固溶体体系为19.4%和18.3%;含化合物体系为39.5%和46.1%;分层体系为25.8%和14.3%.结果表明:由共晶相图、含固溶体相图提取无限稀活度系数,有效性较好,由含化合物相图提取无限稀活度系数有效性较差.引入Richardson假设后,对计算值的精度有所提高.研究表明,运用二元相图提取无限稀活度系数方法提取二元合金体系无限稀活度系数是可行的.     

智能投币机在城市公交上使用的改进分析

通过鱼骨图的方法对现有智能公交投币机存在识别率偏低的问题进行了分析,提出在智能投币机中采用闭式五角叶轮或增加硬币预处理部分,对现有的智能公交投币机进行改进,使智能公交投币机的硬币辨识率得到提高.     

基于拟三元等温图对宁东粉煤灰高温熔融流动特性的研究

在气流床气化炉的实际运行中,经常需要寻求最优的进料煤调配方案以调控煤灰的熔融流动特性。借助SiO₂-Al₂O₃-AAEM(CaO+MgO+Na₂O+K₂O)拟三元等温图,分析了不同组成的宁东煤灰熔融特性,并结合X-射线衍射(XRD)探究了灰在熔化过程中的矿物质转化规律。发现熔融温度在拟三元等温图中呈现U型分布。当SiO₂、Al₂O₃和AAEM质量分数分别为37.5%、25.0%和37.5%时,灰的熔融温度达到最低,流动温度比宁东煤灰降低40 ℃。对灰熔化过程中矿物质转化分析发现,熔化过程中石英与氧化钙会发生矿物质转化反应生成低熔点的钙黄长石和长石,对其熔化具有明显的促进作用;对灰熔化后形成液态熔渣的黏-温特性曲线分析发现,该比例下灰样品同时具有最低的临界黏性温度(T_CV=1107 ℃)和最低的黏性流动活化能(E_a=282.86 kJ/mol),可有效降低气化炉的操作温度。研究表明,拟三元等温图对于气化原料配煤方案可起到一定的指导作用。     

Immobilizing chromium in stainless steel slags with MnO addition

This work investigates the stabilizing impact of MnO on the leaching behavior of hazardous Cr-containing CaO-SiO₂-Al₂O₃-Cr₂O₃-MnO stainless steel slags after equilibrating at various elevated temperatures and evaluates the potential immobilization of Cr into a MnCr₂O₄ spinel phase from the existing Cr₂O₃ phase. The MnCr₂O₄ spinel phase was found to be an excellent Cr-stabilizer in stainless steel slags, where the leaching tendency of potentially hazardous Cr-related ions decreased with higher MnO content and lower equilibration temperatures within the range of 0 to 15 mass pct. and 1500 to 1300°C, respectively. Thermodynamic calculations by conducting the phase stability diagram also showed that the MnCr₂O₄ spinel phase was relatively stable and the Ca₃Si₂O₇ (Ca_3-xMn_xSi₂O₇) phase was relatively unstable compared with other crystal phases in acid extractant with pH value of 3.2. Combined with the scanning electron microscopy and X-ray powder diffraction results along with the thermodynamic calculations, the leached Cr-related ions was predominantly originating from the unstable amorphous glass phase.     

Low-temperature phase formation in the SrF2–LaF3 system

Phase formation in the SrF₂–LaF₃ system was studied at temperatures ranging from 300°C to 450°C using nitrate flux. The solubility of LaF₃ in SrF₂ decreases with decreasing temperature. The equilibrium width of the solid solution region Sr_1−xLa_xF_2+x at 400°C, it is 44.6 ± 0.4 mol% LaF₃ (x = 0.446), at 350°C — 38.3 ± 0.7 mol% LaF₃ (x = 0.383), and decreases almost to zero at 300°C.