Periodic attitude motions along planar orbits in the elliptic restricted three-body problem

A way to improve the accuracy of the three-body problem model is taking into account the eccentricity of primary attractors. Elliptic Restricted Three-Body Problem (ER3BP) is a model for studying spacecraft trajectory within the three-body problem such that the orbital eccentricity of primaries is reflected in it. As the principal cause of perturbation in the employed dynamical model, the primaries eccentricity changes the structure of orbits compared to the ideal Circular Restricted Three-Body Problem (CR3BP). It also changes the attitude behavior of a spacecraft revolving along periodic orbits in this regime. In this paper, the coupled orbit-attitude dynamics of a spacecraft in the ER3BP are exploited to find precise periodic solutions as the spacecraft is considered to be in planar orbits around Lagrangian points and Distant Retrograde Orbits (DRO). Periodic solutions are repetitious behaviors in which spacecraft whole dynamics are repeated periodically, these periodic behaviors are the main interest of this study because they are beneficial for future mission designs and allow delineation of the system’s governing dynamics. Previous studies laid the foundation for spacecraft stability analysis or studying pitch motion of spacecraft in the ER3BP regime. While in this paper, at first, initial guesses for correction algorithms were derived through verified search methods, then correction algorithms were used to refine calculated orbit-attitude periodic behaviors. Periodic orbits and full periodic solutions are portrayed and compared to previous studies and simpler models. Natural periodic solutions are valuable information eventuate in the longer functional lifetime of spacecraft. Since the problem assumption considered in this paper is much closer to real mission conditions, these results may be the means to use natural bounded motions in the actual operational environment.     

A serialized civil aircraft R&D cost estimation model considering commonality based on BP algorithm

The common design of serial civil aircraft, an important strategy of modern civil aircraft research and develop-ment, minimizes the whole life cycle cost of civil aircraft through asset reuse and resource sharing. However, the existing estimating model for the R&D cost of civil aircraft ignores the effects of common design, so the value estimated by estimating derivative models is significantly inconsistent with the actual one. To solve this problem, a novel assessment method for civil aircr...     

SGKW轨道在线生成技术研究

天基对地打击动能武器(SGKW)用于从太空对地面高价值战略目标进行快速、准确的打击.针对作战实时性要求,探讨了SGKW的轨道在线生成技术.首先,利用庞特里亚金极大值原理将时间最短打击轨道的最优控制问题转化为两点边值问题.由于约束条件中存在优化参数,一种基于"遗传算法+序列二次规划"的组合优化算法被用于求解伴随变量初值和再入点参数.为了提高轨道生成的速度,在大量离线优化数据的基础上建立了BP神经网络预测模型,其预测值通过序列二次规划算法稍加修正,即可满足相应任务的落点精度要求.仿真结果验证了上述方案的有效性.     

一种实用的边缘强度互相关匹配可信度分析方法

匹配可信度是衡量匹配质量的重要指标，针对归一化边缘强度互相关匹配算法，研究了基于神经网络的匹配可信度判别方法。通过对参考图进行加噪实验获得训练样本，对BP网络进行训练，并将训练后的网络用于匹配可信度的判别。针对实际卫片与航片图像对的实验结果，平均判决正确率达到90％以上，证实了该方法的有效性。     

BP神经网络在惯导系统传递对准中的应用

针对系统阶次较高时卡尔曼滤波实时性较差的特点,将多层BP神经网络替代卡尔曼滤波应用于舰载机惯导系统的传递对准。利用卡尔曼滤波的输入、输出作为BP神经网络滤波的样本对值进行训练,得到了神经网络的输出值,实现了惯导传递对准中的滤波功能。仿真结果表明,将BP神经网络用于传递对准,既获得了与卡尔曼滤波相当的精度,又有效地降低了系统的解算时间,提高了系统的实时性。     

一种研究逆向卸荷膜片式减压器稳定性的BP神经网络改进算法

为更好地研究多结构参数耦合变化下减压器PPR(pressure reducing regulator)的稳定性,使用BFGS (Broyden-Fletcher-Goldfarb-Shanno)拟牛顿法替换梯度下降法,实现了基于Wolfe条件的一维线搜索变步长BP(back propagation)算法.结果表明:改进的BP算法使迭代次数减少了1~2个数量级,且易于收敛到最小点.该算法用于逆向卸荷膜片式减压器时,能适应2~3个结构参数的耦合,可预测大于106个数据点的数据集.多结构参数同时变化时,更容易找到使得减压器稳定的结构参数组合.更重要的是这些结构参数同时变化时减压器的稳定性比仅其中一个参数变化时更好.      

基于故障检测的某涡扇发动机维修决策方法

为有效解决某涡扇发动机过度维修造成发动机性能衰减、维修周期长、维修成本高的难题,以某涡扇发动机大修手册和维修工艺为依据,研究了基于故障检测的发动机维修流程和修理模式,建立专家诊断系统和基于BP(back propagation)神经网络的故障诊断模型,并用数台涡扇发动机真实性能数据验证故障诊断模型的可靠性,其诊断准确率高达95%,综合两者的诊断信息,制定可靠的维修方案,优化维修流程,提出了一种基于故障检测的维修决策方法.通过某涡扇真实排气温度高发动机应用验证表明:所提出的维修决策方法,有效排除故障,提高发动机的修理质量,降低维修成本,具有良好的工程应用价值.      

基于深度学习的滑油监测方法研究

针对传统的数据特征提取方法难以提取航空发动机滑油监测数据有效特征的缺陷,提出了一种基于多尺度卷积神经网络(Multi-scales convolutional neural network,MSCNN)、长短期记忆(Long short-term memory,LSTM)神经网络和BP网络的单通道网络模型MSCNN-LSTM-BP。将多尺度学习融入CNN,MSCNN和LSTM以串行方式提取数据在空间维度和时间维度的二维特征。实验结果表明:3尺度的MSCNN-LSTM-BP对数据样本的分类准确率达到98.2%,单组电容数据采集测试时间仅为2.1986ms,综合分类率F1达到98.57%,总体性能优于CNN,LSTM和传统的多尺度特征提取方法。MSCNN-LSTM-BP满足航空发动机滑油监测对于实时性和准确性的要求,具有良好的适用性。     

一种BP MFN逆模型补偿的复合控制结构方案研究

由于对结构未知和不确定的非线性系统还没有形成一种通用有效的辨识和控制方法，为此首先对非线性系统逆模型辨识和控制的结构方案进行分析，然后基于复合控制思想，对基于神经网络的非线性系统逆模型补偿的复合控制结构方案进行研究。设计了一种基于BP MFN（Multilayer Feedforward Network）逆模型补偿的复合控制结构方案，并基于不同BPMFN逆模型结构进行了仿真。仿真结果显示，基于神经网络的非线性系统逆模型补偿的复合控制结构方案是有效的，且在满足辨识建模精度要求前提下，采用相对简单的BPMFN逆模型结构，对提高逆模型的泛化能力和非线性系统的控制效果是有益的。     

基于神经网络的电子线路故障诊断

分析了故障字典法在实际应用中存在的不足，提出将单位BP算法应用到电子线路的故障诊断中。对基于该方法的航空装备电子线路故障诊断进行了计算机仿真，并分析了网络参数的变化对训练结果的影响。仿真结果表明了该方法的合理性和有效性。