Modeling satellite battery aging for an operational satellite simulator

During the satellite’s operations, simulation tools perform an important role in ensuring the space mission success. In this sense, the models implemented in the context of an operational satellite simulator that enables analysis of health status and maintenance during operations shall reflect the current satellite behavior with high fidelity. Moreover, it is complicated to obtain all analytical models of a satellite’s disciplines, considering its aging. This paper proposes an Artificial Neural Network (ANN) to reproduce the battery voltage behavior of a large sun-synchronous remote sensing satellite, the CBERS-4, currently in operation. Using the genetic algorithm to find the best network architecture of ANN, the neural model for this application presented an error of less than 1%, demonstrating its feasibility to obtain a high fidelity model for an operational simulator enabling extend analyses. The paper addresses advanced techniques aligned with the space industry’s future, increasing the ability to analyze a large amount of data and improve the space system’s operation.     

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.     

A new method for improving the performance of an ionospheric model developed by multi-instrument measurements based on artificial neural network

There are remarkable ionospheric discrepancies between space-borne (COSMIC) measurements and ground-based (ionosonde) observations, the discrepancies could decrease the accuracies of the ionospheric model developed by multi-source data seriously. To reduce the discrepancies between two observational systems, the peak frequency (foF2) and peak height (hmF2) derived from the COSMIC and ionosonde data are used to develop the ionospheric models by an artificial neural network (ANN) method, respectively. The averaged root-mean-square errors (RMSEs) of COSPF (COSMIC peak frequency model), COSPH (COSMIC peak height model), IONOPF (Ionosonde peak frequency model) and IONOPH (Ionosonde peak height model) are 0.58 MHz, 19.59 km, 0.92 MHz and 23.40 km, respectively. The results indicate that the discrepancies between these models are dependent on universal time, geographic latitude and seasons. The peak frequencies measured by COSMIC are generally larger than ionosonde’s observations in the nighttime or middle-latitudes with the amplitude of lower than 25%, while the averaged peak height derived from COSMIC is smaller than ionosonde’s data in the polar regions. The differences between ANN-based maps and references show that the discrepancies between two ionospheric detecting techniques are proportional to the intensity of solar radiation. Besides, a new method based on the ANN technique is proposed to reduce the discrepancies for improving ionospheric models developed by multiple measurements, the results indicate that the RMSEs of ANN models optimized by the method are 14–25% lower than the models without the application of the method. Furthermore, the ionospheric model built by the multiple measurements with the application of the method is more powerful in capturing the ionospheric dynamic physics features, such as equatorial ionization, Weddell Sea, mid-latitude summer nighttime and winter anomalies. In conclusion, the new method is significant in improving the accuracy and physical characteristics of an ionospheric model based on multi-source observations.     

关于BP网络算法的输电线速断保护

建立人工神经网络BP算法，利用计算运行方式的变化改进传统的电力输电线系统的保护措施，可以实时跟踪故障点并同步实施控制。利用人工神经网络技术的快速性、自适应性和容错性，在一个周期内准确地定位区内、区外故障点，实现对输电线的速断保护。     

人工智能在矢量推力现场动态校准中的应用研究

基于航天工程中对于发动机试车台矢量推力现场动态校准需求,以摆锤式动态力加载装置为力源,研制了发动机试车台矢量推力现场动态校准装置。在发动机试车台试验校准点有限的情况下,将人工智能技术应用在校准工作中,对矢量推力的动态响应特性进行校准与补偿。验证结果表明,该方案动态性能优异,响应迅速,满足试车台矢量推力校准的需求,为后续进一步准确测试矢量推力提供了依据。     

基于神经网络的旁路活门自适应控制

ＦＬ－７风洞旁路活门非线性控制系统稳Ｍ数神经网络自适应控制中的网络拓扑结构，权值调整，自构性学习，及其实现方法表明，整个系统控制性能优良，不仅控制精度高，而且节省燃油，可靠性性能良好。     

多级涡轮多目标气动优化设计流程

在准三维设计基础上,采用多目标优化设计方法,给出一个多级涡轮气动优化设计流程,优化联合采用人工神经网络和遗传算法,流场计算采用全三维粘性流N-S方程求解。此优化设计流程有三个特点:针对每列叶栅的气动特性进行局部优化;各列叶栅反复多次优化;粗细网格交替使用。并采用此设计流程对一三级涡轮进行优化设计,效率提高1%,说明此方法可以有效的用于多级涡轮气动优化设计。     

卫星转动惯量测量方法

介绍了用扭摆,通过倾斜安装测量卫星三个方向转动惯量的一种方法。分析了IYY测量准确度和测量倾斜角大小、IYY/IXX的比值、倾斜角误差之间的关系。当倾斜角度θ〉45°时,IYY能够达到较高的测量准确度。     

人工智能可解释性评估研究综述CSCD

近年来,可解释人工智能(XAI)发展迅速,成为当前人工智能领域的研究热点,已出现多种人工智能解释方法。如何量化评估XAI的可解释性以及解释方法的效果,对研究XAI具有重要意义。XAI的可解释性评估涉及主、客观因素,是一个复杂且有挑战性的工作。综述了XAI的可解释性评估方法,首先,介绍了XAI的可解释性及其评估的概念和分类;其次,总结和梳理了一些可解释性的特性;在此基础上,从可解释性评估方法和可解释性评估框架两方面,综述和分析了当前可解释性评估工作;最后,总结了当前人工智能可解释性评估研究的不足,并展望了其未来发展方向。     

石英晶振老化的建模与模型求解

为预测石英晶振的频率老化，提出了一种非线性时变模型。在一阶马尔可夫假设下，利用多层前向神经网络进行迭代逼近求解。对四种晶体的全部或部分实验数据进行了学习和预测试验。结果表明该模型不仅能拟合函数，而且可在存在野值时，根据以往的数据预测目前的频率。与其他线性模型相比，该模型的预测能力更佳，适用于多种类型的晶振老化模式，预测误差小，有很好的抗噪声能力。