利用BP网络进行发动机故障诊断的研究

探讨了利用人工神经网络的ＢＰ网络进行发动机故障诊断的特点。通过发动机实际故障样本和模拟故障样本对ＢＰ网络的故障诊断功能进行了研究，并且对ＢＰ网络与主因子模型两种算法进行了比较。     

Moment equation description of interstellar hydrogen

The flow of interstellar hydrogen in the heliosphere can be studied using the moment equation approach. The Boltzmann equation is integrated over the velocity space to obtain the moment equations, the moment equations are then solved directly for the flow conditions. We present a closed system of moment equations. This approach can include anisotropic pressure when the distribution function is distorted into skewed ellipsoid.     

THE WIDE-BAND PLASMA WAVE INVESTIGATION

As part of the Cluster Wave Experiment Consortium (WEC), the Wide-Band (WBD) Plasma Wave investigation is designed to provide high-resolution measurements of both electric and magnetic fields in selected frequency bands from 25 Hz to 577 kHz. Continuous waveforms are digitised and transmitted in either a 220 kbit s^-1 real-time mode or a 73 kbit s^-1 recorded mode. The real-time data are received directly by a NASA Deep-Space Network (DSN) receiving station, and the recorded data are stored in the spacecraft solid-state recorder for later playback. In both cases the waveforms are Fourier transformed on the ground to provide high-resolution frequency-time spectrograms. The WBD measurements complement those of the other WEC instruments and also provide a unique new capability for performing very-long-baseline interferometry (VLBI) measurements.     

Effects of polarization and resolution on SAR ATR

Lincoln Laboratory is investigating the detection and classification of stationary ground targets using high resolution, fully polarimetric, synthetic aperture radar (SAR) imagery. A study is summarized in which data collected by the Lincoln Laboratory 33 GHz SAR were used to perform a comprehensive comparison of automatic target recognition (ATR) performance for several polarization/resolution combinations. The Lincoln Laboratory baseline ATR algorithm suite was used, and was optimized for each polarization/resolution case. Both the HH polarization alone and the optimal combination of HH, HV, and VV were evaluated; the resolutions evaluated were 1 ft/spl times/1 ft and 1 m/spl times/1 m. The data set used for this study contained approximately 74 km/sup 2/ of clutter (56 km/sup 2/ of mixed clutter plus 18 km/sup 2/ of highly cultural clutter) and 136 tactical target images (divided equally between tanks and howitzers).     

采用内积原理建立航空发动机神经网络辨识模型

根据样本空间的内积特性,提出一种无需迭代学习内积神经网络。以某型航空发动机的机载记录数据为例,对发动机进行了建模,结果表明该方法具有自学习速度快、抗干扰能力强、准确性高的特点。     

液体推进剂一甲肼与水二元物系汽液相平衡的研究

一甲肼是一种重要的液体推进剂,分离反应过程所生成的水是确保一甲肼质量的关键。测定了甲基肼－水（ＭＭＨ－Ｈ２Ｏ）物系在１０１．３３ｋＰａ下的汽液平衡,以及电解质对其汽液平衡的影响。采用盐效应和溶剂化的方法,研究了不同电解质对ＭＭＨ－Ｈ２Ｏ汽液平衡的盐效应。     

发动机故障诊断主状态量模型的数学模型

发动机故障诊断的一种主要方法是根据故障方程和发动机性能参数的测量值确定故障的类别和故障程度,故障方程组通常是亚定的。主状态量模型是求解亚定的故障方程的有效方法。主状态量模型的主要内容是根据最少故障原理,利用最优化方法求解然后根据合理性准则选择合理最优解。本文详细地讨论了主状态量模型可能采用的数学模型,并且指出:(1)主状态量模型可以采用不同的数学模型求解;(2)并非所有的数学模型都能给出合理的结果。本文的研究结果表明,约束或无约束超定最小二乘法和单个优选的散度法是发动机故障诊断主状态量模型的理想算法,而本文中所讨论的其他算法都或多或少存在一定的问题。     

发动机故障诊断主状态量模型合理解的选择

主状态量模型是基于发动机故障方程的发动机故障诊断的一种十分有效的方法,它在发动机故障诊断上的成功应用已为大量实例所证实。发动机故障诊断主状态量模型的一个技术关键就是合理解的选择问题。本文给出了选择合理解的基本原则。这些原则可以有效地提高合理解选择的确定性和故障诊断的故障分辨率。对于JT9D发动机的大量故障实例利用主状态量模型(加权最小二乘法)进行了检验。故障诊断的成功率达90%以上,并且得到了许多有用的信息,文中给出了24个实例的故障诊断结果以及故障趋势分析的典型例子。     

导弹水下点火的流体动力研究

对轴对称导弹水下点火这一非线性瞬态流动提出以下数学模型及求解方法。水流场假设为理想不可压势流,用边界积分方程法求解;喷管中的燃气流动按准一维非定常无粘完全气体流动处理,用逆步有限差分格式的特征线法求解;喷入水中的燃气流采用简化的等压泡模型,用Euler-Lagrange方法模拟气泡的演化。按照时间步进方法实现了水、气流动和物体运动的数值耦合求解。数值实验结果反映出导弹水下点火时水气流动的一些重要特性。