空气预热器实时监控系统堵塞可视化性能研究

针对电站锅炉回转式空气预热器运行时上下表面不可见的问题，本文提出了一种视频监控与故障分析系统，可直接监测转子表面情况。该系统通过视频监控获取图像，结合改进的Retinex算法对其进行处理，实现了以下2个功能:1）能分析积灰程度以判断转子堵塞 情况；2）与温度场融合实时显示转子表面热点分布以预防二次燃烧。该系统已应用于某600 MW机组，实现了在热态环境下对空气预热器转子积灰程度、热点分布、堵塞程度的估算与可视化，大大提高了空气预热器运行的可靠性。     

火电机组负荷分配中多源不确定性因素影响分析

不确定性因素存在于火电机组负荷分配中，影响机组负荷分配、节能环保目标。本文综合考虑负荷预测不确定性、机组煤耗率不确定性与其CO2排放系数不确定性，分别构建火电机组一次能源消耗成本与CO2排放量最小目标下的火电机组负荷优化分配模型；以此为基础，引入析因分析方差分解方法，量化多源不确定性因素单独与交互作用下对节能、环保目标的影响程度。结果表明:负荷预测不确定性对火电机组节能、环保目标影响最为显著，相对影响程度分别为51.13%、62.70%；机组煤耗特性及其CO2排放系数影响次之，相对影响程度分别为47.58%、34.95%。此研究结果对不确定性条件下电力系统负荷分配具有借鉴价值。     

Automatic breast tumor detection in ABVS images based on convolutional neural network and superpixel patterns

Breast cancer is one of the most common female malignancies, as well as the second leading cause of mortality for women. Early detection and treatment can dramatically decrease the mortality rate. Recently, automated breast volume scanner (ABVS) has become one of the most frequently used diagnose methods for breast tumor screening because of its operator-independent and reproducible advantages. However, it is a challenging job to obtain the tumors’ accurate locations and shapes by reviewing hundreds of ABVS slices. In this paper, a novel computer-aided detection (CADe) system is developed to reduce clinicians’ reading time and improve the efficiency. The CADe system mainly contains three parts: tumor candidate acquisition, false-positive reduction and tumor segmentation. Firstly, a local phase-based approach is built to obtain breast tumor candidates for further recognition. Subsequently, a convolutional neural network (CNN) is applied to reduce false positives (FPs). The introduction of CNN can help to avoid complicated feature extraction as well as elevate the accuracy and efficiency. Finally, superpixel-based segmentation is used to outline the breast tumor. Here, superpixel-based local binary pattern (SLBP) is proposed to assist the segmentation, which improves the performance. The methods were evaluated on a clinical ABVS dataset whose abnormal cases were manually labeled by an experienced radiologist. The experiment results were mainly composed of two parts. At the FP reduction stage, the proposed CNN achieved 100% and 78.12% sensitivity with FPs/case of 2.16 and 0. At the segmentation stage, our SLBP obtained 82.34% true positive, 15.79% false positive and 83.59% Dice similarity. In summary, the proposed CADe system demonstrated promising potential to detect and outline breast tumors in ABVS images.

     

In-situ crystal growth and photoluminescence properties of YBO3: Tb3+ microstructures

Three-dimensional (3D) YBO₃:Tb³⁺ flower-like and dense flower-like hierarchitecture constituted of nanoflakes are solvothermally synthesized in the presence of polyborate precursors in the mixture of ethanol and water. The growth process of the YBO₃:Tb³⁺ flowers and dense flowers was explored based on the time-dependent experiment and the results showed that the growth mechanism follows an in situ growth rather than self-assembly process as reported previously. YBO₃:Tb³⁺ morphologies composed of nanoflakes are achieved by controlling the concentration of ethanol and dependence of photoluminescence on morphology was studied. Remarkable photoluminescence enhancement was observed for YBO₃:Tb³⁺ with flower-like morphology demonstrating the potential of the microstructure in future applications as a green phosphor. Such a synthetic method and growth mechanism may be applied to fabricate complex 3D architectures of other materials.     

水文序列相依变异识别的RIC定阶准则——以自回归模型为例

水文过程相依性是水文变异的主要表现形式之一,应用自回归模型对其进行拟合时合理确定模型阶数是一个难点问题。本文在分析AIC和BIC准则的基础上,提出了一种以原序列与其相依成分的相关系数作为拟合度指标,同时借用信息熵形式的函数式,作为模型不确定性度量指标的自回归模型定阶准则(简称RIC准则)。以AR(1)、AR(2)、AR(3)和AR(4)模型为例进行统计试验,将不同序列长度下该准则的定阶准确率与其他定阶准则进行比较,试验结果表明,RIC准则对于上述模型均具有较好的适应性,且定阶准确率远高于AIC准则,其中对于前三阶模型RIC准则优于BIC准则,但四阶模型略低于BIC准则。RIC准则的优势是可以同时满足模型定阶、相依程度分级与模型检验的需求,将其应用于实测水文序列分析,结果显示,该准则能较准确地识别自回归模型的阶数,且符合提出的"相依有变异而残差无变异的最小阶数"的检验标准。     

马钢张庄矿高压辊磨机装配工艺研究

针对马钢张庄矿高压辊磨机辊套疲劳断裂严重、对辊精度不能满足生产要求等问题，马钢重机公司根据张庄矿实际生产要求对对辊进行国产化，国产化内容包括辊轴、辊套等零部件的新制以及装配工艺攻关，通过技术研发同时结合实际生产经验，成功对高压辊磨机辊套与辊轴以及辊轴与轴承进行装配，完成了张庄矿高压辊磨机整对对辊的国产化，为该型设备后续生产及优化提供了理论和实践参考依据。     

基于注意力机制与文本信息的用户关系抽取

随着社交媒体的发展,用户之间的关系网络对于社交媒体的分析有很大的帮助。因此,该文主要研究用户好友关系检测。以往的关于用户好友关系抽取的研究主要基于社交媒体上的结构化信息,比如其他好友关系,用户的不同属性等。但是,很多时候用户本身并没有大量的好友信息存在,同时也不一定有很多确定的属性。因此,我们希望基于用户发表的文本信息来对用户关系进行预测。不同于以往的潜在好友推荐算法,该文提出了一种基于注意力机制以及长短时记忆网络(long short-term memory,LSTM)的好友关系预测模型,将好友之间的评论分开处理,通过分析用户之间的评论来判断是否具备一定的好友关系。该模型将好友双方信息拼接后的结果作为输入,并将注意力机制应用于LSTM的输出。实验表明,用户之间的评论对于好友关系预测确实有较大的实际意义,该文提出的模型较之于多个基准系统的效果,取得了明显的提升。在不加入任何其它非文本特征的情况下,实验结果的准确率达到了77%。