基于模糊综合评价的关联性能分析

针对单一指标无法较完整的对数据融合中的数据关联效果进行评估的问题,本文提出应用模糊综合评价法,综合多个指标、多个场景对数据关联的性能进行综合评估.实验表明,该模型可以对数据关联的性能进行定量评价,并且能够对不同关联算法的性能进行比较.     

基于模糊故障树和因子化分析的重复使用火箭发动机失效模式

为确定发动机薄弱环节,指导重复使用火箭发动机可靠性设计,以航天飞机主发动机为研究对象,通过模糊故障树分析法和因子化分析法对发动机主要组件的关键失效模式进行研究.结果表明:模糊故障树分析法给出关键重要度最高的底事件为由剥落、凹坑、磨损和腐蚀致高压氧化剂涡轮泵的轴承失效;因子化分析法通过考虑风险、时间和概率3种因素综合评估出发动机系统中的综合因子最高的失效模式为涡轮叶片失效.      

基于SVM和SNN的航空发动机气路故障诊断

为了区分航空发动机气路故障诊断过程中出现的相似故障,提高诊断准确率,提出了一种支持向量机(SVM)和协同神经网络(SNN)相结合的故障诊断方法.首先利用参数优化后的SVM对测量数据进行初步故障诊断分类,对诊断结果进行分析统计,得出难以区分的相似故障类型,并根据SNN对这些相似故障进一步地区分判断,最后根据实际数据对此故障模型进行仿真.结果显示:基于SVM的初步故障诊断准确率达到96%;而经过SNN进一步地相似故障区分后,诊断准确率提升到100%.     

Two-stage open-loop velocity compensating method applied to multi-mass elastic transmission system

In this paper, a novel vibration-suppression open-loop control method for multi-mass system is proposed, which uses two-stage velocity compensating algorithm and fuzzy I ＋ P control- ler. This compensating method is based on model-based control theory in order to provide a damp- ing effect on the system mechanical part. The mathematical model of multi-mass system is built and reduced to estimate the velocities of masses. The velocity difference between adjacent masses is cal- culated dynamically. A 3-mass system is regarded as the composition of two 2-mass systems in order to realize the two-stage compensating algorithm. Instead of using a typical PI controller in the velocity compensating loop, a fuzzy I ＋ P controller is designed and its input variables are decided according to their impact on the system, which is different from the conventional fuzzy PID controller designing rules. Simulations and experimental results show that the proposed veloc- ity compensating method is effective in suppressing vibration on a 3-mass system and it has a better performance when the designed fuzzy I ＋ P controller is utilized in the control system.     

A fuzzy PID-controlled SMA actuator for a two-DOF joint

Shape memory alloy(SMA) actuator is a potential advanced component for servosystems of aerospace vehicles and aircraft. This paper presents a joint with two degrees of freedom(DOF) and a mobility range close to ±60 when driven by SMA triple wires. The fuzzy proportional-integral-derivative(PID)-controlled actuator drive was designed using antagonistic SMA triple wires, and the resistance feedback signal made a closed loop. Experiments showed that, with the driving responding frequency increasing, the overstress became harder to be avoided at the position under the maximum friction force. Furthermore, the hysteresis gap between the heating and cooling paths of the strain-to-resistance curve expanded under this condition. A fuzzy logic control was considered as a solution, and the curves of the wires were then modeled by fitting polynomials so that the measured resistance was used directly to determine the control signal. Accurate control was demonstrated through the step response, and the experimental results showed that under the fuzzy PID-control program, the mean absolute error(MAE) of the rotation angle was about 3.147. In addition, the investigation of the external interference to the system proved the controllable maximum output.     

基于小波变换的容差电路故障诊断

针对目前模拟电路中电子元器件存在的容差与非线性导致电路故障难以检测的现状,设计了适用于诊断由器件超出容差所引起的模拟电路故障的小波分析诊断方法。通过设定故障进行蒙特卡罗容差实验,采用小波神经网络,对故障输出信号进行小波分析提取其小波高频系数参量,经PCA分析和归一化后形成训练特征向量,并经过BP神经网络训练后,故障信号通过小波神经网络后能够快速精准的对故障器件进行定位。通过大量样本进行仿真计算表明所设计的小波特征参量故障诊断法对于模拟电路具有很好的故障分辨率。     

柔性机翼承载能力的试验与预测

对柔性机翼进行了承载能力的试验及预测研究,首先对柔性机翼的翼型结构进行建模,并对充气机翼的结构进行了分析和优化;其次应用正交试法确定出影响柔性机翼承载能力的主要影响因素,以优化后的结果建立实物模型和主要影响因素为变量进行试验;最后以大量的试验数据为训练样本建立改进的神经网络模型,并进行承载能力预测.试验与预测结果对比研究表明:在初始阶段,柔性机翼在压强一定时,载荷与挠度近似呈线性关系;在同一气压值下,载荷增加到一定值时,载荷与挠度的关系曲线呈近似线性关系,而是斜率突然减小;神经网络测试值和试验实测值最大相对误差与标准方差只有12%和0.39%,人工神经网络解析方法可以用于对充气机翼抗弯刚度的分析.      

基于模糊综合评价与灰色关联分析法的多工艺方案评价

为了使企业能够选择最佳的工艺方案指导实际生产,提出了基于模糊综合评价与灰色关联分析法的多工艺方案评价方法.该方法将模糊综合评价与灰色关联分析法融合在一起建立多工艺方案评价方法.在工艺方案优选结构图中通过对影响工艺方案质量的多种影响因素进行层次化分析,建立各影响因素的层次化模型;在数据标准化阶段,采用隶属度进行数据标准化操作;在计算权重时,在权重误差平方和最小的条件下采用主客观权重相结合的权重计算方法来代替传统灰色关联分析中的均值权重方法;最后通过关联系数和组合权重确定工艺方案的排序.以某航空发动机叶片零件来建立实例,结果表明:该方法具有良好的实用效果,满足多工艺方案优选的实际要求.      

径向基神经网络在非线性非定常气动力建模中的应用研究

基于南航NH-2风洞中某飞机模型大迎角大振幅单自由度偏航、滚转及偏航-滚转耦合的谐波、阶跃运动实验数据,应用径向基神经网络,研究人工神经网络描述非线性非定常气动力特性的能力.研究结果表明,所建立的径向基神经网络模型的预测结果与训练数据和验证数据都符合得很好,说明神经网络建模方法可以有效地对高度非线性的气动力进行建模.研究还表明,用神经网络建立模型时所需要的风洞实验数据可以减少,从而提高风洞实验效率、减少风洞实验的时间和成本.     

基于模糊理论老龄飞机结构腐蚀损伤评判

对老龄飞机在复杂环境发生结构腐蚀损伤的情况进行综合评判,提出了一种基于故障树分析的手段和理论方法.通过举例分析,证明所提方法的有效性.