基于异构网络表示学习的评分预测模型

深入分析电商行业的用户个性化数据并提供推荐服务近年来已成为业界的热点。推荐服务的基础是对用户的潜在兴趣进行挖掘，并对商品的感兴趣程度进行预测。因此，以此为背景，研究用户对商品的评分预测。对电商业的关系型数据在推荐系统中的应用进行了研究，提出了通过使用网络表示学习进行评分预测的方法。首先，将关系型数据构建成异构网络，用户和商品为网络中的节点。然后，设计了兼顾网络结构信息和节点之间相似性的个性化异构网络采样方法，并对节点进行表示学习。最后，将学习到的用户、商品表示向量输入到神经网络中进行训练，利用优化后的神经网络模型进行评分预测。实验结果表明:所提方法在YELP 13、Movielens 100k、Movielens 1m数据集上都有较高的准确率，对比常用方法，准确率提升6.5%以上。      

PBT弹性体微相分离及对其力学性能的影响研究

为了获得微相分离对宽温PBT叠氮聚醚弹性体力学性能的影响规律,用红外光谱分析法(FT-IR)和动态热力学分析法(DMA)研究了PBT叠氮聚醚弹性体产生微相分离的机理和影响因素。用调节硬段含量、交联参数的方法调控其微相分离,控制适当的微相分离程度可显著改善推进剂的力学性能。研究结果表明:在二元醇扩链的弹性体体系中,当硬段含量约为15%时,弹性体发生相对最大比例的微相分离,体现出较佳的综合力学性能。通过微相分离的调控可获得宽温范围内综合力学性能较好的叠氮聚醚推进剂用粘合剂基体材料。     

Fault self-repair strategy based on evolvable hardware and reparation balance technology

In the face of harsh natural environment applications such as earth-orbiting and deep space satellites, underwater sea vehicles, strong electromagnetic interference and temperature stress,the circuits faults appear easily. Circuit faults will inevitably lead to serious losses of availability or impeded mission success without self-repair over the mission duration. Traditional fault-repair methods based on redundant fault-tolerant technique are straightforward to implement, yet their area, power and weight cost can be excessive. Moreover they utilize all plug-in or component level circuits to realize redundant backup, such that their applicability is limited. Hence, a novel selfrepair technology based on evolvable hardware（EHW） and reparation balance technology（RBT） is proposed. Its cost is low, and fault self-repair of various circuits and devices can be realized through dynamic configuration. Making full use of the fault signals, correcting circuit can be found through EHW technique to realize the balance and compensation of the fault output-signals. In this paper, the self-repair model was analyzed which based on EHW and RBT technique, the specific self-repair strategy was studied, the corresponding self-repair circuit fault system was designed, and the typical faults were simulated and analyzed which combined with the actual electronic devices. Simulation results demonstrated that the proposed fault self-repair strategy was feasible. Compared to traditional techniques, fault self-repair based on EHW consumes fewer hardware resources, and the scope of fault self-repair was expanded significantly.     

粗糙表面偏振二向反射分布函数的影响参数及其反演

针对目标偏振二向反射特性研究中模型参数难以准确确定的问题,分析了粗糙表面偏振二向反射分布函数的影响参数,并通过理论推导和仿真计算,研究了各参数对粗糙表面散射特性的作用机理。总结分析了现有参数反演方法,针对现有方法存在的理论缺陷,在P-G(Preist-Germer)模型的基础上,提出了利用"相对偏振分量-角度"的相关关系进行参数反演的方法,设计了参数反演算法,进行了标准反射板和绿漆表面的偏振二向反射特性测试实验,并根据实验数据进行了参数反演和模型验证。实验结果表明,改进的参数反演方法可准确反演所有模型参数。利用反演参数进行模型验证,结果显示模型预测数据与实验数据具有较好的吻合度,验证了模型的准确性。     

Kriging模型在机翼气动外形优化中的应用

针对粒子群等随机优化算法计算量大的缺点,发展了基于Kriging模型的优化方法.采用改进的量子粒子群算法对Kriging模型的相关模型参数进行优化,以提高代理模型预测精度,并与具有双层结构的粒子群算法相结合.采用雷诺平均N-S方程流场求解器与多目标非线性适应值加权方法,对高维度多目标多约束的跨声速机翼进行了优化,设计的机翼具有理想的压力分布,降低了机翼阻力系数,并且有效控制了低头力矩和翼根弯矩,表明该方法具有较强的工程实用性.     

Experiment on Boiling Heat Transfer of Refrigerant R134a in Mini-channels

The flow boiling heat transfer characteristics of refrigerant R134 a flowing inside two different kinds of minichannels are investigated. One channel is multi-port extruded with the hydraulic diameter of 0.63 mm,and the other one is rectangular with offset fins and a hydraulic diameter of 1.28 mm. The experiments are performed with a mass flow rate between 68 and 630 kg/(m~2·s),a heat flux between 9 and 64 kW/m~2,and a saturation pressure between 0.24 and 0.63 MPa,under the constant heat flux heating mode. It is found that the effect of mass flow rate on boiling heat transfer is related to heat flux,and that with the increase of heat flux,the effect can only be efficient in higher vapor quality region. The effects of heat flux and saturation pressure on boiling heat transfer are related to a threshold vapor quality,and the value will gradually decrease with the increase of heat flux or saturation pressure. Based on these analyses,a new correlation is proposed to predict the boiling heat transfer coefficient of refrigerant R134 a in the mini-channels under the experimental conditions.     

压电致动器扑翼结构动力学仿真

采用传统扑动机构的微型扑翼,气动效率低、扑动能耗大。采用压电致动器的微型扑翼通过压电材料进行致动使机翼产生上下扑动,有效地将扑动机构和机翼两个主要系统进行集成,不仅节省重量,同时它具有任务变形自适应能力强、气动效率高和扑动能耗小的特点。通过PCL语言建立采用压电致动器的扑翼有限元模型,结合同尺寸扑翼气动力试验数据,进行采用压电致动器扑翼结构仿真。利用仿真结果研制采用压电致动器扑翼原理样机,研究表明,采用压电致动器后扑翼扑动频率得到明显提高,压电片可有效控制机翼的弯扭变形,有助于提高扑翼的气动效率。     

基于点击反应改善叠氮推进剂/丁羟衬层界面粘接性能的研究

针对极性差异较大的叠氮推进剂和丁羟衬层界面粘接体系,采用红外光谱及二维相关光谱分析、凝胶含量、粘接性能测试等方法研究了三种炔基化合物的引入对其界面粘接性能的改善效果。结果表明,在丁羟衬层中引入三种不同分子结构的炔基化合物AC-1,AC-2和AC-3均可提高叠氮推进剂/丁羟衬层的界面粘接强度,当AC-1,AC-2和AC-3的炔基参数RA分别为0.097~0.127、0.051和0.097~0.141时,叠氮推进剂/丁羟衬层界面粘接的剥离强度可分别提高约80%,40%和70%。     

注射成型和注射压缩成型角窗的残余应力比较

基于粘性流体力学基本方程和粘度模型,建立了注射成型和注射压缩成型的残余应力计算模型,然后对角窗的注射成型和注射压缩成型进行了计算模拟,结果表明,注射成型角窗的残余应力大,且分布范围宽;注射压缩成型角窗的残余应力相对较小,且分布范围较窄,这种特征与注射压缩成型时熔体流动阻力小、型腔压力和体积温度分布均匀有关。最后采用偏振光法对实际注射成型和注射压缩成型角窗的应力分布进行了测试,进一步验证了注射压缩成型制品的低残余应力特点。     

一种非线性飞行控制律评估方法研究

研究了一种基于改进遗传算法的非线性评估方法。将非线性准则转换成简单的适应度函数,通过寻优找到最坏情况,在其基础上实现评估。仿真结果表明,该方法不仅能在各个飞行状态对飞行控制律进行非线性准则评估,而且能找出飞行包线内的最坏飞行状态,细化飞行包线,方法使用灵活,结果可靠。