支持向量机用于液体火箭发动机的故障诊断

支持向量机（Support Vector Machine,简称SVM）是一种基于机器学习的模式分类算法,其在解决小样本、非线性及高维模式识别等问题中都表现出许多特有的优势。用SVM对液体火箭发动机的故障数据进行检测和诊断。通过对发动机仿真模型的9种故障数据的学习,能检测出18组故障数据中的17组,但有4组出现误报,对误报故障进行二次学习和再检测,能对这4种故障正确检测。经过对C75试车4种故障数据的学习,能正确检测其故障类型,进一步验证了该方法的正确性和可行性。     

航空发动机高压转子试验模型的动力学相似设计

为了获得能够替代航空发动机转子原型进行动力学试验的模型，提出了发动机转子系统试验模型的动力学相似设计方法。采用相似理论推导了转子系统缩比模型的动力学相似准则，继而建立缩比模型与原型的动力学相似关系。通过动力学优化方法对转子缩比模型的动力学等效模型进行修正，目标函数由固有频率、临界转速和振型组成。以双转子发动机高压转子系统的动力学相似设计为例，通过有限元仿真对设计方法的有效性进行了验证。结果表明，在设计转速范围内，动力学相似模型与原型的前两阶临界转速相似误差分别为3.92%和0.86%，对应振型的相关性均大于0.98，且模型与原型的模态应变能分布基本一致。通过该方法获得的动力学相似模型能够较好地预测原型的动力学特性，并有效降低模型试验的成本和难度。     

一种航天器图像分类模型快速学习方法

为了有效分类空间目标,提出了一种航天器图像分类模型快速学习方法。分类模型的学习过程利用了分治思想,首先利用无监督聚类方法将图像数据集散列为类别桶,然后利用每个类别桶中的图像样本训练支持向量机完成学习过程。分类时利用支持向量机对待分类图像样本进行分类。实验结果表明,所提方法具有较好的实时性和准确率,能够为空间应用打下良好基础。     

概率有限状态机在动态效能评估中的应用

为了反映作战过程中实时战场变化对武器作战效能的影响，本文对武器作战动态效能评估(DEE)方法进行研究，提出一种基于概率有限状态机(PFSM)的动态效能评估方法。利用该方法对武器作战过程进行动态效能评估的同时，能够快速准确地分析影响武器作战效能的关键因素，为作战方案决策及武器研发提供依据。该方法考虑了武器装备、战场环境、作战方案及作战目标这四个战场信息空间对武器效能的影响，能够根据实时战场信息输出动态效能变化曲线。本文以反舰导弹为例，对其进行动态效能评估，结果表明,本文所提出的方法能够动态评估不同战场信息对效能的影响，并快速找到影响其效能的关键因素，从而为作战方案优化提供参考。     

改进模拟退火算法的喷管动力学模型修正

为获得液体火箭发动机喷管高精度的结构动力学有限元模型，提出一种基于改进模拟退火算法（Improved Simulation Annealing Algorithm，ISAA）的有限元模型修正方法。首先，将复杂的薄壁夹层板喷管等效为复合材料层合壳，建立喷管的参数化有限元模型；在此基础上，以结构模态参数为参考基，构造出联合使用模态频率及模态振型的目标函数，并运用灵敏度分析提取设计变量，从而建立其优化模型；提出带记忆、局部搜索功能的改进模拟退火算法，运用ISAA在设计空间进行多目标全局寻优；最后，采用基于MSC Patran/Nastran软件平台二次开发的结构动力学模型修正软件ZDXZ V1.0进行模型修正，并对模型修正方法的有效性进行了校验。结果表明，修正后喷管的前3阶计算模态频率与试验值相对误差小于2%，振型相关性最小MAC值大于0.9，大大提升了喷管模型的动力学符合性，模型精度满足工程应用要求；表明所述模型修正策略的有效性，该方法具有高效、强鲁棒性等特点，适合于大型复杂结构的模型修正。     

Best practices for model-based and simulation-aided engineering of power transmission and motion control systems

This paper deals with the modelling and simulation of aircraft systems, in particular for power transmission and control. It is intended to review, propose and disseminate best practices for making model-based/simulation-aided engineering more efficient at any phase of the system life cycle. The proposals are aimed at creating value, not only by increasing the performance of the product under study but also by shortening the time to market, capitalizing knowledge, mitigating risks and facilitating concurrent engineering. The needs associated with the engineering activities are firstly identified to define a set of requirements for the models. Then, these requirements are used to drive the considerations leading to model development, focusing in particular on the process, modelled physical effects, modelling level, model architecting and concurrent engineering. The third part deals with the model implementation, giving special consideration to the different types of models, causalities, parameterization, implementation and verification. Each part is illustrated by examples related to safety critical actuators.     

Non-intrusive reduced-order model for predicting transonic flow with varying geometries

A Non-Intrusive Reduced-Order Model (NIROM) based on Proper Orthogonal Decomposition (POD) has been proposed for predicting the flow fields of transonic airfoils with geometry parameters. To provide a better reduced-order subspace to approximate the real flow field, a domain decomposition method has been used to separate the hard-to-predict regions from the full field and POD has been adopted in the regions individually. An Artificial Neural Network (ANN) has replaced the Radial Basis Function (RBF) to interpolate the coefficients of the POD modes, aiming at improving the approximation accuracy of the NIROM for non-samples. When predicting the flow fields of transonic airfoils, the proposed NIROM has demonstrated a high performance.     

Reliability estimation of mechanical seals based on bivariate dependence analysis and considering model uncertainty

The reliability estimation of mechanical seals is of crucial importance due to their wide applications in pumps in various mechanical systems. Failure of mechanical seals might cause leakage, and might lead to system failure and other relevant consequences. In this study, the reliability estimation for mechanical seals based on bivariate dependence analysis and considering model uncertainty is proposed. The friction torque and leakage rate are two degradation performance indicators of mechanical seals that can be described by the Wiener process, Gamma process, and inverse Gaussian process. The dependence between the two indicators can be described by different copula functions. Then the model uncertainty is considered in the reliability estimation using the Bayesian Model Average (BMA) method, while the unknown parameters in the model are estimated by Bayesian Markov Chain Monte Carlo (MCMC) method. A numerical simulation study and fatigue crack study are conducted to demonstrate the effectiveness of the BMA method to capture model uncertainty. A degradation test of mechanical seals is conducted to verify the proposed model. The optimal stochastic process models for two performance indicators and copula function are determined based on the degradation data. The results show the necessity of using the BMA method in degradation modeling.     

基于图像识别技术的火箭飞行时序判读

在运载火箭开展射前综合测试时,控制系统在预先指定的飞行时序向末端发送一系列指令,指示末端设备做出相应动作,以达成对应的目标。这些动作主要依赖火工品完成,这些动作变化会体现在火工品等效器指示灯上。当前控制系统无法检测到末端等效器的电流情况变化,因此无法对末端动作进行有效监测,测试缺乏可靠性、准确性与可追溯性的问题亟需改善。通过综合运用人工智能、数字图像处理与计算机视觉技术,经由特征匹配、指示灯定位、指示灯状态建模等步骤,可对末端火工品等效器状态变化实现精准监测,进而实现飞行时序自动判读。与标准判据比对后,本文提出的火箭飞行时序判读系统准确率可达98.89%。