抽油机故障诊断的分布驱动主动学习算法

抽油机示功图直观显示了抽油机工作情况，但实际工况情况呈现典型的长尾分布特性，类别严重不平衡。传统方法无法准确识别小类别工况，也无法获得井下工作状态准确识别。针对这一问题，提出一种基于分布驱动的多类别长尾数据代价敏感主动学习算法（Cost-sensitive active learning algorithm based on distribution -driven multi-class long-tailed data， CALA）。首先，考虑数据分布特性，以最小化代价为优化目标确定数据的最佳聚类簇数；其次，通过加入预分类误差代价来更新之前得到的最佳聚类簇数；然后，构建集成分类模型作为分类器；最后，通过迭代来平衡数据分布。采用某油田真实的示功图数据进行测试，显著性实验分析证明CALA在小类别工况诊断上具有更好的性能。     

Electrochemical behavior of Ti-6.5Al-2Zr-1Mo-1V alloy under rotating condition with periodically fluctuating current density

Titanium alloy plays a crucial role in the electrochemical field due to its excellent corrosion resistance. The passivation and dissolution behaviors of Ti-6.5Al-2Zr-1Mo-1V（TA15） alloy in Na Cl solution were studied by simulating the electrochemical machining process in a rotating condition, which made the anode in a state with alternating high and low current density. Electron probe micro analysis, ultra-depth microscope, scanning electron microscope, and X-ray photoelectron spectrometer were u...     

双列调心滚子轴承摩擦力矩的特性

基于滚动轴承的动力学理论，建立了双列调心滚子轴承动力学微分方程与摩擦力矩数学模型，采用预估-校正GSTIFF(gear stiff)变步长积分算法求解其动力学微分方程，研究了结构参数和工况参数对双列调心滚子轴承摩擦力矩特性的影响。研究结果表明:较小的内滚道密合度与较大的外滚道密合度有利于降低轴承的摩擦力矩；过大、过小的保持架兜孔曲率半径都不利于轴承摩擦力矩的降低，存在一个合理的保持架兜孔曲率半径使轴承摩擦力矩最小；保持架兜孔间隙对轴承的摩擦力矩影响较小，适当增大保持架引导间隙可有效减小轴承的摩擦力矩；适量的增大双列调心滚子轴承径向游隙有利于降低轴承的摩擦力矩。      

民用飞机电传飞控系统功能危害性评估方法研究

民机系统级功能危害性评估（Functional Hazard Assessment, 简称FHA）是指对系统功能进行系统性的综合分析过程，即依据系统功能失效状态对飞机安全性影响严重程度进行评估，从而实现对功能的等级进行识别和分类的过程，是系统顶层关键的设计过程。在分析大量相关资料和实际型号经验的基础上，得出适用于民机电传飞控系统的功能定义、功能失效状态分析和确定功能失效影响等级并对其进行确认的思路和方法，以及保证民机电传飞控系统级FHA正确性和完整性的具体可行的措施等，该方法已应用到某民机电传飞控系统级FHA的评估工作中，取得了良好的效果。     

基于改进蚁群算法和Mann-Kendall法的涡桨发动机性能预测

针对涡桨发动机复杂、非线性的工作环境，利用层次分析（AHP）法提取发动机工作状态特征参数，考虑各特征参数对工作状态识别的影响，以特征参数加权的改进蚁群算法为基础，进行发动机同一工作状态识别、聚类，并采用Mann-Kendall法开展发动机性能预测分析。利用多台涡桨发动机性能参数飞参数据进行验证，结果表明：该方法能准确识别发动机起飞、额定工作状态，巡航以下工作状态识别准确率达84%以上；此外，发动机性能预测效率提升了近50%，而预测错误率小于10%，可以满足航空兵部队维修保障工作的实际需要。     

模具表面状态对复合材料构件固化变形的影响

为查明不同模具表面状态下的复合材料构件应变演变规律及其对固化变形的影响,采用热电偶和光纤光栅传感器对不同模具表面状态下的复合材料构件在热压罐成型工艺过程中的温度和应变进行在线监测,获得不同模具表面状态下构件应变的变化规律。结果表明:升温阶段脱模布的使用能够有效屏蔽模具-构件界面相互作用,使构件在升温阶段的应变很小。三层脱模剂模具表面条件下构件中的应变明显小于一层脱模剂;降温阶段三种实验条件下在构件中都出现了较大的压应变,其中一层脱模剂模具表面状态下模具-构件相互作用力最大,在固化工艺完成后构件发生翘曲变形,且翘曲变形以沿纤维方向为主。     

Assessing the hydromorphological condition of the Sub-Himalayan Mahananda-Balason system using the hydromorphological quality Index

An evaluation of the hydromorphological condition of the Mahananda-Balason River system of the sub-Himalayan foothills, West Bengal, India was attempted using a multiparameter-based Hydromorphological Quality Index (HQI). After segmenting these rivers based on continuity, bed material and channel planform, a total of 18 indicators, divided into 3 subgroups Continuity (C), Planform (P), and Floodplain Morphology (FM), were quantified reach-wise and scaled upon the level of alteration (1 for highly altered and 5 for no alteration). The derived overall HQI (3.6) exhibited a moderate hydromorphological quality of the system, however, significant differences between the HQIs of confined and unconfined reaches were witnessed. Students ‘t-test and Multiple Correspondence Analysis both portrayed vast dissimilarities among the confined and unconfined reaches and the clustering was depending on their confinement. The deviations measured from the system’s mean and least altered conditions portrayed that the confined reaches with lesser human interventions were in comparatively more pristine hydromorphological conditions. Conversely, unconfined reaches showed moderate to very poor hydromorphological conditions chiefly due to intense human-induced alterations regarding urbanization, embanking and sediment extraction. Restorations on these aspects should initiate with immediate effect to avoid a shortage of riverine resources such as fluvial sediment, fish and groundwater. Overall, this methodology was found suitable for continuous monitoring of the river systems along with the precise identification of areas and aspects to be restored for upgrading the hydromorphological quality. More testing of this methodology would eventually help in validating the hydromorphological quality assessment protocol for Indian rivers.     

引入稀疏原子特征融合的滑动轴承摩擦故障状态监测

从信息融合理论出发，将特征的稀疏表达作为特征融合参数，提出一种结合K奇异值分解(KSVD）和最大相关最小冗余准则(mRMR）的轴承摩擦故障特征融合算法。该算法采用KSVD对信号稀疏化，将稀疏系数对应的字典原子作为特征融合的参数，用以表达非线性故障信息；针对字典原子集的优化选择问题，基于互信息的mRMR提出一种确定最优原子集的原子数目的准则；最后，通过最大化原则融合稀疏系数，提取故障状态监测的有效信息。轴承摩擦故障模拟实验的结果表明，所提方法能够更好地融合不同特征的故障信息，相比于单特征和其他融合特征方法，提高了约12%的故障识别率。      

Gaussian process regression model incorporated with tool wear mechanism

Cutting tool condition directly affects machining quality and efficiency. In order to avoid severely worn tools used during machining process and fully release the remaining useful life in the meanwhile, a reliable evaluation method of remaining useful life of cutting tools is quite necessary. Due to the variation of cutting conditions, it is a challenge to predict remaining useful life of cutting tools by a unified model. In order to address this issue, this paper proposes a method for predicting the remaining useful life of cutting tools in variable cutting conditions based on Gaussian process regression model incorporated with tool wear mechanism, where the predicted value at adjacent moments is constrained to a linear relationship by the covariance matrix of Gaussian model based on the assumption of progressive tool wear process, so the wear process under continuous changing conditions can be modelled. In addition to that, the input feature space and the output of the model are also enhanced by considering the tool wear mechanism for improving prediction accuracy. Machining experiments are performed to verify the proposed method, and the results show that the proposed could improve the prediction of tool remaining useful life significantly.     

高空来流条件下航空发动机双旋流燃烧室点火特性数值模拟

为深入了解真实航空发动机燃烧室极端条件下点火性能，在自有CFD平台上对不同高空来流条件下典型航空发动机双旋流燃烧室点火过程进行了数值模拟。为保证模拟精度，对模型包括全部气膜冷却小孔在内的所有精细结构均进行了完全仿真，并完整再现了燃烧室内从燃油雾化到点火燃烧全过程。结果表明3种高空来流条件下单次点火均失败。点火过程显示高温燃气越过旋流杯中心向上回流区扩张是点火的关键时空区域，在此时补充点火可推动火焰顺利传播到整个主燃区。对8km和6km两种状态分别增加点火次数到3次和5次后最终点火成功，结果表明前者着火极限油气比约为0.057，后者为0.038~0.042。