共查询到20条相似文献,搜索用时 78 毫秒
1.
2.
《中国航空学报》2023,36(3):303-315
Imbalanced data classification is an important research topic in real-world applications, like fault diagnosis in an aircraft manufacturing system. The over-sampling method is often used to solve this problem. It generates samples according to the distance between minority data. However, the traditional over-sampling method may change the original data distribution, which is harmful to the classification performance. In this paper, we propose a new method called Conditional Self-Attention Generative Adversarial Network with Differential Evolution (CSAGAN-DE) for imbalanced data classification. The new method aims at improving the classification performance of minority data by enhancing the quality of the generation of minority data. In CSAGAN-DE, the minority data are fed into the self-attention generative adversarial network to approximate the data distribution and create new data for the minority class. Then, the differential evolution algorithm is employed to automatically determine the number of generated minority data for achieving a satisfactory classification performance. Several experiments are conducted to evaluate the performance of the new CSAGAN-DE method. The results show that the new method can efficiently improve the classification performance compared with other related methods. 相似文献
3.
本文建立了由进气道节流特性风洞实验数据和发动机流量特性求其共同工作点的计算法.应用此法能准确计算任意给定飞行条件、大气条件和发动机工作条件下进气道性能数据.与国内进气道设计中常使用的图解法相比,这个计算法便于建立推进系统一体化的数学模型,并能提高数据的准确性,减轻工作量. 相似文献
4.
涡轮风扇发动机的风扇特性图在试验的基础上绘制,是发动机建模、仿真以及研究发动机工作性能的重要依据。从试验中只能得到有限的数据,为了充分利用试验数据,讨论了风扇在等换算转速下入口总温、出口总温、以及发动机转速间的增量关系,在此基础上得出特性数据间的关系,建立等换算转速下风扇特性拟合的约束条件。考虑此约束条件,构造风扇特性的拟合函数,并给出了计算机仿真结果。 相似文献
5.
通过总结某型发动机的使用经验,提出了表征该型发动机工作状况的特征参数,并利用样本数据对所提出的特征参数进行了验证。结果表明,所提出的特征参数能够较为有效地反映发动机的工作状况,为发动机的状态监测和故障诊断提供了依据。 相似文献
6.
7.
8.
9.
民机概念设计阶段性能分析程序快速开发方法 总被引:1,自引:1,他引:0
张陈力子祝雯生余雄庆 《民用飞机设计与研究》2016,(1):28
为了在概念设计阶段快速准确地分析民航客机性能,提出一种基于MATLAB/SIMULINK 联合仿真的性能分析程序快速开发方法。从数据库文件中读取已有的气动、重量、推进、飞行剖面等数据,在SIMULINK中分别求解已建立的各飞行阶段运动微分方程,将结果保存至原数据库。整个求解及前后处理过程由MATLAB脚本控制。以波音737-800型客机性能分析为例,验证了该方法的有效性。与经验公式法相比,本文算法更为准确,流程更加清晰,不需要编写大量代码,实现与维护更加简便,适用于民机概念设计阶段性能分析程序的快速开发。 相似文献
10.
11.
Q-Flex quartz flexure suspension technology has evolved to produce a world class accelerometer with thousands of units delivered in 1991. The Sundstrand Model QA3000 Q-Flex design achieves a new level of inertial grade performance while maintaining a competitive market price. The specification for the QA3000, supported by actual performance data, depicts performance characteristics superior in both bias and scale factor. Long term measurements display bias and scale factor repeatability obtained across temperature over a period of three years. These data exhibit improved thermal behavior with reduced errors. Reaction time and radiation data highlight the performance of the hybrid position detector circuit 相似文献
12.
为了研究雷诺数对涡扇发动机性能的影响并提升稳态性能模型在工作包线内的计算精度,提出了一种基于整机试验数据辨识的计算分析方法。选取用于气路分析的测量参数,提升辨识算法的收敛性和计算结果的有效性;结合非线性气路分析算法辨识计算出各试验点的部件性能修正因子,统计分析雷诺数和各部件性能修正因子的变化关系,定量得到雷诺数对发动机各部件性能的影响程度;修正基线稳态性能模型,并对计算精度进行验证对比。结果表明:对比试验结果,修正后的稳态性能模型各参数计算偏差不大于2.5%。对比基线稳态性能模型各参数计算结果,计算精度平均提升2.3%,最大提升9.2%。 相似文献
13.
向阳 《民用飞机设计与研究》2021,(2):67-72
针对飞机辅助动力装置(Auxiliary Power Unit,简称APU)性能评估研究中单参数评估不全面的问题,提出了基于逻辑回归模型的方法,融合多参数来对飞机APU性能状况进行全面评估。首先,对APU参数数据来源进行分析,选择基于实时报文数据的APU性能评估方法,并结合APU的工作原理以及实际工作情况,挑选出可以反映APU性能状态的特征参数,然后利用主成分分析法(Principal Component Analysis,简称PCA)对原始特征参数进行降维处理。其次,以APU正常性能状态历史数据和性能严重衰退状态历史数据建立逻辑回归模型。最后,根据回归模型得到APU全寿命周期的健康指数(Health Index,简称HI)并对其进行验证。结果表明,APU性能健康指数曲线能很好的反映APU各个阶段的性能变化情况,可以为后续的视情维修策略的制定提供技术参考。 相似文献
14.
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. 相似文献
15.
依据某型燃气轮机动态试车性能数据,应用VBA平台编制稳态性能处理程序,提出数据特征点的提取方法、参数速率计算方法和升降状态判断方法,在提取出特征点的基础上,通过分析动态过程得到某次燃气轮机试车性能参数变化率的变化最大值,并对单次试车性能参数阶跃段和平稳段进行了比较。 相似文献
16.
本文提出用首飞期描述直升机综合性能的思想,给出其性能综合评价及发展态势估算方法和模型,运用实际样本资料给出算例,为时序多属性高技术产品性能综合评价及发展态势估算提供思路。 相似文献
17.
Tonissen S.M. Evans R.J. 《IEEE transactions on aerospace and electronic systems》1996,32(4):1440-1451
“Track-Before-Detect” (TBD) is a target tracking technique where no threshold is applied at each measurement frame. Instead, data are processed over a number of frames before decisions on target existence are made. The track is returned simultaneously with the detection. A simple algorithm is presented and demonstrated via simulations. A detailed analysis enables detection and tracking performance to be predicted for particular algorithm parameters. Good performance is observed at low signal-to-noise ratio (SNR), with rapid degradation as SNR is reduced further. For some cases the detection performance does not improve regardless of how many frames of data are processed. Tracking performance may also be poor even though detection performance is good 相似文献
18.
19.
Li F. Liu H. Vaccaro R.J. 《IEEE transactions on aerospace and electronic systems》1993,29(4):1170-1184
Subspace based direction-of-arrival (DOA) estimation has motivated many performance studies, but limitations such as the assumption of an infinite amount of data and analysis of individual algorithms generally exist in these performance studies. The authors have previously proposed a unified performance analysis based on a finite amount of data and achieved a tractable expression for the mean-squared DOA estimation error for the multiple signal classification (MUSIC). Min-Norm, estimation of signal parameters using rotational invariance techniques (ESPRIT), and state-space realization algorithms. However, this expression uses the singular values and vectors of a data matrix, which are obtained by the highly nonlinear transformation of the singular value decomposition (SVD). Thus the effects of the original data parameters such as numbers of sensors and snapshots, source coherence and separations were not explicitly analyzed. The authors unify and simplify this previous result and derive a unified expression based on the original data parameters. They analytically observe the effects of these parameters on the estimation error 相似文献
20.
基于RF-SVR的燃油计量装置性能衰退检测和剩余寿命估计方法 总被引:1,自引:0,他引:1
为了实现航空发动机燃油系统的安全状态监测和健康管理,开展了燃油系统性能衰退检测和剩余使用寿命估计方面的研究。以燃油系统燃油计量装置为例,分析了其主要的性能衰退模式,设计了基于电流-速度数据的健康指标(HIs)选取方案,并考虑环境及模型参数不确定性,进行模型不确定性仿真,基于健康数据与性能衰退数据间的马氏距离对部件性能衰退进行检测。提出了基于随机森林-支持向量回归(RF-SVR)的剩余使用寿命(RUL)估计方法,利用通过RF特征选择优化的SVR模型实现部件RUL估计。最后基于某型民用涡扇发动机机械液压模型仿真数据对该方法进行了验证,结果表明:该方法的性能衰退检测虚警率及漏报率低于2%,RUL估计误差低于3%,可为航空发动机燃油系统的预测性维护提供参考。 相似文献