基于FSVM改进隶属度的发动机振动性能分析

为了更有效地掌握航空发动机振动性能的影响因素,提出了改进FSVM信息熵的融合定量分析方法.首先,对模糊支持向量机(FSVM)的模糊隶属度函数进行改进,建立多类模糊隶属度计算模型.再将该方法应用到航空发动机整机振动性能评估,计算出振动故障模式与故障原因之间的权值,建立了一个多参数的发动机振动性能分析模型;并对各类振动原因对发动机整体性能的影响进行定量分析,为发动机的振动抑制提供量化参考指标.最后,通过与实际经验作比较,验证了该方法是可行和有效的.     

An adaptive turbo-shaft engine modeling method based on PS and MRR-LSSVR algorithms

In order to establish an adaptive turbo-shaft engine model with high accuracy, a new modeling method based on parameter selection (PS) algorithm and multi-input multi-output recursive reduced least square support vector regression (MRR-LSSVR) machine is proposed. Firstly, the PS algorithm is designed to choose the most reasonable inputs of the adaptive module. During this process, a wrapper criterion based on least square support vector regression (LSSVR) machine is adopted, which can not only reduce computational complexity but also enhance generalization performance. Secondly, with the input variables determined by the PS algorithm, a mapping model of engine parameter estimation is trained off-line using MRR-LSSVR, which has a satisfying accuracy within 5&. Finally, based on a numerical simulation platform of an integrated helicopter/ turbo-shaft engine system, an adaptive turbo-shaft engine model is developed and tested in a certain flight envelope. Under the condition of single or multiple engine components being degraded, many simulation experiments are carried out, and the simulation results show the effectiveness and validity of the proposed adaptive modeling method.     

毫米波制导导弹系统误差及捕获概率研究

分析了毫米波制导导弹系统误差源及其分布特性,该误差直接决定所需导引头动态视场的大小;对导引头动态视场的影响因素进行了分析,并计算了导引头在不同条件下的动态视场,基于此计算了导引头捕获概率。研究结果可以直接应用于毫米波制导导弹的工程研制,并且可以对同类的自寻的导弹工程研制起借鉴作用。     

Influence of fuel injection position and equivalent mixture ratio on chemical non-equilibrium effects of single expansion ramp nozzle

Chemical non-equilibrium flow was investigated for the scramjet single expansion ramp nozzle(SERN) with a strut-based liquid-kerosene-fueled combustor.Two-dimensional Reynolds-averaged Navier-Stokes(RANS) equations were solved with the species conservation equation for continuous phase and the renormalization group(RNG) k-ε turbulence model.Lagrangian discrete-phase model was analyzed for liquid-kerosene droplets behavior in the supersonic stream.Combustion was simulated by kerosene surrogate fuel's 10-species and 13-step reduced reaction kinetics mechanism with use of Arrhenius's laminar finite rate model.Parametric studies were carried out to estimate the influence of different fuel injection positions and equivalent mixture ratios on the SERN chemical non-equilibrium effects.Numerical calculation results show that the strut-based combustor enables convenient modeling of various SERN entry conditions,which is similar with many preceding investigations,by changing the injector strut position and controlling the mass flow rate of each injector.Chemical non-equilibrium effects function in the whole SERN,especially in the initial flow expansion region,leads to obviously higher SERN performance of the non-equilibrium flow than that of the frozen flow.Furthermore,the distributed fuel injection pattern plays a significant role in enhancing the combustion efficiency in combustor,but weakening the chemical non-equilibrium effects funciton in SERN.Additionally,while the equivalent mixture ratio increases,the SERN thrust coefficient and lift coefficient rise gradually,and the increment of non-equilibrium flow in relation to frozen flow becomes higher as well.To be specific,the equivalent mixture ratio is 0.6,the maximum increment of thrust coefficient and lift coefficient are 11.6% and 25% respectively.      

基于WCFSE-FSVM的转子振动故障诊断方法

为了提高含有噪声和野值的转子振动故障样本诊断精度,提出了基于WCFSE-FSVM的故障诊断方法。充分融合小波相关特征尺度熵(WCFSE)特征提取方法和FSVM故障诊断方法的优点,建立WCFSE-FSVM故障诊断模型。基于转子实验台模拟4种典型故障,获得原始故障数据;并利用WCFSE方法提取这些故障数据的WCFSE值,选取故障信号高频段中的尺度1和尺度2上的小波相关特征尺度熵W1和W2构造出振动信号的故障向量作为故障样本,建立FSVM诊断模型。实例分析显示:WCFSE-FSVM方法的转子故障诊断精度最高,即故障类别诊断精度为94.49%,故障严重程度的诊断精度为95.58%,二者都优于其它故障诊断方法。验证了WCFSE-FSVM方法的可行性和有效性。      

基于小波变换的图像低通去噪

提出了一种利用小波变换的多分辨率特性对图像进行低通去噪的方法,系统的阐述了其基本原理和核心算法,并对加噪后的图像实现了低通去噪处理。     

跑道容量的运行优化

从战略流量管理的观点出发,研究了预期交通需求超过机场跑道系统容量情况下,跑道容量的运行优化问题。在满足跑道容量曲线限制下,建立了恒定容量和变化容量下的整数规划数学模型,并以数值例子对两种模型进行了对比计算分析。     

涡轮泵试车数据单类支持向量机检测算法

为了在缺乏故障样本的情况下检测某型液体火箭发动机涡轮泵故障,实现基于不完整信息的状态决策,建立了基于v-支持向量分类器的单类支持向量机新异类检测模型。在分析了模型决策边界、支持向量和约束条件之间关系的基础上,为单类支持向量机引入并改进了序贯最小优化算法,提高了训练效率,解决了大样本训练问题。通过对某型液体火箭发动机涡轮泵历史试车数据的分析,结果表明,所建模型的训练速度得到了很大提高,对涡轮泵状态的检测效果良好。     

航空发动机的智能神经网络自适应控制研究

针对结构复杂、模型不确定、强非线性的航空发动机对象,提出一种综合模糊推理、神经网络自适应和PID简单控制各自优点的控制方案.在改进模糊PID控制器的基础上,进行了新型智能型神经网络控制器的设计,并提出离线混沌蚁群优化与在线误差反传调整相结合的优化方法.应用具有良好泛化能力的最小二乘支持向量机进行系统辨识,对某型航空发动机进行了设计点处的线性和非线性模型控制仿真.结果表明:控制系统具有满意的动、静态性能和较好的鲁棒性,验证了该方案的可行性和有效性.      

旋翼气动提前操纵角研究

为了保证某型直升机操纵系统设计的顺利进行,本文基于国内外相关资料对气动提前操纵角进行了深入的研究,得出该角度主要取决于桨叶挥舞基阶固有频率ωβ1.而ωβ1与挥舞铰外伸量e、桨叶根部弹性约束Kβ和挥舞调节系数Kp密切相关.通过分析e,Kβ和Kp对气动提前操纵角△ψ的影响,推导出计算该角度的具体公式.采用该公式对几个型号进行计算,经校核与验证后,表明本文提供的计算方法可行,能满足工程精度,可应用于工程研究,从而为布置助力器提供理论依据.