回归分析在房地产市场方面的应用

本文通过建立的回归模型，对商品住宅的销售量进行了预测。     

高超声速飞行器前体/进气道参数重要性测度

针对机体推进高度一体化的吸气式高超声速飞行器前体/进气道相关参数对其性能指标的独立和交互作用问题,基于回归模型和二阶混合中心矩理论,以总压恢复系数为性能指标,提出了参数重要性测度新方法。设计了二维混压楔形前体/进气道变几何构型方案并给出重要性测度模型,定量和定性地对参数重要性进行了对比和分析。研究结果表明:前体/进气道相关参数间具有强的非线性作用,交互作用非常显著,独立作用可以忽略不计,且重要性测度模型易于扩展。     

航空发动机研制费估算工作的现状与展望

针对在立项论证阶段对航空发动机项目经费进行快速并有效的估算的问题,基于中国航空发动机的研制现状和型号数据的积累情况,分析了发动机研制经费估算工作的重点与难点以及相应的解决途径,并采用偏最小二乘法建立了航空发动机研制经费估算模型。计算结果表明:该发动机模型精度较高,已经应用于国产某型涡扇发动机的经费测算工作中,并可用于中国未来航空发动机型号的研制经费估算。     

基于高斯过程的航天器自适应滑模姿态控制

针对存在模型不确定性和外界干扰的刚性航天器,提出了一种基于高斯过程回归(GPR)的新型自适应滑模姿态控制算法。该算法具有自学习能力,在不同的姿态控制任务下都能够实现高精度、强鲁棒和高效率的姿态跟踪。首先,在航天器的四元数标称系统动态模型基础上,应用在线稀疏高斯过程回归(SOGP)方法学习系统的未知动态;其次,结合高斯过程的预测均值设计滑模控制算法,利用高斯过程的预测方差自适应调节控制增益,并应用李雅普诺夫方法严格证明闭环系统的稳定性,保证了航天器姿态跟踪误差的渐进收敛性;最后,通过数值仿真验证了所设计控制器的有效性。结果表明,该自学习控制算法与自适应滑模控制(ASMC)与神经网络自适应控制等算法相比,具有更快的收敛速度、更高的跟踪精度以及更低的控制成本。     

The relationship between TEC and Earth’s magnetic field during quiet and disturbed days over Istanbul,Turkey

In this study, the impact of Earth’s magnetic field on total electron content (TEC) was studied by using statistical multiple linear regression model and co-integration method. TEC values were measured over the Turkey-Istanbul (ista) station using date of global positioning system (GPS), and the magnetic field components of the Earth were measured from Boğaziçi University, Kandilli Observatory and Earthquake Research Institute, Geomagnetic observatory Istanbul (ISK) station. This examination has been carried out during the dates of March 14–19, 2015 covering the dates of March 17–18, 2015 known in the literature as St. Patrick's Day geomagnetic storm. The three days before the storm (March 14–16) were named as quiet days, whereas the other days (March 17–19) were named as disturbed days after which the two periods were examined separately. It was observed as a result of the examination that the x-component (south-north direction) of the magnetic field had a negative impact on TEC on quiet days, whereas the impact was positive on disturbed days. However, the y-component (east–west direction) of the magnetic field had an inverse relationship of the x-component on the quiet and disturbed days. In addition, it was deduced that the impact coefficient of the x and y-component of the magnetic field was higher on disturbed days in comparison with those on quiet days. The correlation coefficient between the TEC and the components of the Earth’s magnetic field was 0.11 on quiet days and 0.95 on disturbed days. Therefore, it can be stated that the relationship of the TEC values with the geomagnetic field are higher on disturbed days.     

定时截尾数据回归分析方法

提出定时截尾数据回归分析方法,建立定时截尾数据回归方程,给出回归系数和标准差的最佳无偏整体估计、百分位值的点估计及其置信限估计.详细讨论了工程中常见的极值分布、Weibull分布、正态分布以及一般位置-尺度分布场合下定时截尾数据的回归分析问题.该方法可以充分利用截尾时刻的试验信息,并将各个状态下的定时截尾数据作为一个整体进行统计分析,具有信息量大、精度高的特点,从而可以在试验时间、经费等有限的情况下对产品进行高精度的寿命预测和可靠性评估.     

周向局部处理机匣对压气机影响的数值研究

为了分析周向非均匀处理槽对压气机的影响,对一台单级跨声速轴流压气机进行了周向局部处理机匣与全周处理机匣的非定常数值研究.结果显示,具有相同处理槽数的周向局部处理机匣比全周处理机匣能获得更好的压气机性能.由于处理槽的周向非均匀性,前者给叶尖流场产生大尺度的周向非均匀特征,因而能提供后者所不具备的低频非定常作用.此外,提供了高、低频两种非定常作用的周向局部处理机匣能够同时改善叶尖泄漏涡与尾缘分离涡.      

粒子群优化在直升机旋翼动平衡调整中的应用

传统的直升机旋翼调整方法没有考虑调整参数与振动信号之间的非线性关系,针对这一缺点,提出将广义回归神经网络(GRNN,General Regression Neural Network)和粒子群算法相结合的旋翼调整方法,采用GRNN网络建立旋翼动平衡调整模型,以桨叶的调整参数作为神经网络的输入,以旋翼转轴和机身的三向的加速度测量值作为网络输出,建立调整参数与直升机振动信号间的模型.以直升机振动作为目标函数,采用粒子群优化算法对桨叶的调整参数进行寻优,获得当直升机振动最小时的桨叶的调整量. 飞行实验结果表明,此方法可通过飞行测试获得的新数据对神经网络进行更新,使系统在使用过程中不断完善,并可在较少的飞行调整下完成旋翼的动平衡调整.      

基于变权重最小二乘法的发动机气路故障诊断

针对航空发动机气路部件故障诊断中存在的严重故障诊断问题,提出基于变权重最小二乘法进行发动机故障诊断.该方法在发动机仿真实验的基础上采用加权最小二乘法进行故障诊断,并对算法进行了改进,根据初期诊断结果对故障权重系数矩阵进行修正,使诊断结果更加合理可信.仿真表明,基于变权重最小二乘法的发动机气路故障诊断能快捷有效地诊断气路部件严重故障.      

Comparison of hindlimb unloading and partial weight suspension models for spaceflight-type condition induced effects on white blood cells

Animal models are frequently used to assist in the determination of the long- and short-term effects of space flight. The space environment, including microgravity, can impact many physiological and immunological system parameters. It has been found that ground based models of microgravity produce changes in white blood cell counts, which negatively affects immunologic function. As part of the Center of Acute Radiation Research (CARR), we compared the acute effects on white blood cell parameters induced by the more traditionally used animal model of hindlimb unloading (HU) with a recently developed reduced weightbearing analog known as partial weight suspension (PWS). Female ICR mice were either hindlimb unloaded or placed in the PWS system at 16% quadrupedal weightbearing for 4 h, 1, 2, 7 or 10 days, at which point complete blood counts were obtained. Control animals (jacketed and non-jacketed) were exposed to identical conditions without reduced weightbearing. Results indicate that significant changes in total white blood cell (WBC), neutrophil, lymphocyte, monocyte and eosinophil counts were observed within the first 2 days of exposure to each system. These differences in blood cell counts normalized by day 7 in both systems. The results of these studies indicate that there are some statistically significant changes observed in the blood cell counts for animals exposed to both the PWS and HU simulated microgravity systems.