The automated prediction of solar flares from SDO images using deep learning

In the last few years, there has been growing interest in near-real-time solar data processing, especially for space weather applications. This is due to space weather impacts on both space-borne and ground-based systems, and industries, which subsequently impacts our lives. In the current study, the deep learning approach is used to establish an automated hybrid computer system for a short-term forecast; it is achieved by using the complexity level of the sunspot group on SDO/HMI Intensitygram images. Furthermore, this suggested system can generate the forecast for solar flare occurrences within the following 24 h. The input data for the proposed system are SDO/HMI full-disk Intensitygram images and SDO/HMI full-disk magnetogram images. System outputs are the “Flare or Non-Flare” of daily flare occurrences (C, M, and X classes). This system integrates an image processing system to automatically detect sunspot groups on SDO/HMI Intensitygram images using active-region data extracted from SDO/HMI magnetogram images (presented by Colak and Qahwaji, 2008) and deep learning to generate these forecasts. Our deep learning-based system is designed to analyze sunspot groups on the solar disk to predict whether this sunspot group is capable of releasing a significant flare or not. Our system introduced in this work is called ASAP_Deep. The deep learning model used in our system is based on the integration of the Convolutional Neural Network (CNN) and Softmax classifier to extract special features from the sunspot group images detected from SDO/HMI (Intensitygram and magnetogram) images. Furthermore, a CNN training scheme based on the integration of a back-propagation algorithm and a mini-batch AdaGrad optimization method is suggested for weight updates and to modify learning rates, respectively. The images of the sunspot regions are cropped automatically by the imaging system and processed using deep learning rules to provide near real-time predictions. The major results of this study are as follows. Firstly, the ASAP_Deep system builds on the ASAP system introduced in Colak and Qahwaji (2009) but improves the system with an updated deep learning-based prediction capability. Secondly, we successfully apply CNN to the sunspot group image without any pre-processing or feature extraction. Thirdly, our system results are considerably better, especially for the false alarm ratio (FAR); this reduces the losses resulting from the protection measures applied by companies. Also, the proposed system achieves a relatively high scores for True Skill Statistics (TSS) and Heidke Skill Score (HSS).     

Experimental and numerical analysis of non-symmetric breakage of liquid columns in an axial gravitational field rotating around an eccentric axis

An experiment in microgravity conditions aboard the TEXUS-23 mission was performed to obtain the deformation up to breakage of a cylindrical liquid column in isorotation around an eccentric axis. In previous work, breakage rotation speed was predicted by a numerical method. This method was validated by comparison with analytical and experimental results. The non-symmetric breakage of the liquid column observed in the experiment, however, was not explained by the combined effect of rotation and eccentricity.     

A novel stability prediction approach for thin-walled component milling considering material removing process

The milling stability of thin-walled components is an important issue in the aviation manufacturing industry,which greatly limits the removal rate of a workpiece.However,for a thin-walled workpiece,the dynamic characteristics vary at different positions.In addition,the removed part also has influence on determining the modal parameters of the workpiece.Thus,the milling stability is also time-variant.In this work,in order to investigate the time variation of a workpiece's dynamic characteristics,a new computational model is firstly derived by dividing the workpiece into a removed part and a remaining part with the Ritz method.Then,an updated frequency response function is obtained by Lagrange's equation and the corresponding modal parameters are extracted.Finally,multi-mode stability lobes are plotted by the different quadrature method and its accuracy is verified by experiments.The proposed method improves the computational efficiency to predict the time-varying characteristics of a thin-walled workpiece.     

基于eN-数据库方法复杂构型飞机转捩预测

为探索边界层转捩对大型运输机在起降条件和有较大层流区的巡航条件下的气动力精确计算问题，通过在三维RANS求解器中引入eN-数据库方法来预测飞行器表面的转捩位置，并探索转捩对气动力的影响规律。方法与目前流行的基于间歇因子控制方程的转捩预测方法相比，具有计算效率高、易于工程应用、且考虑TS不稳定性转捩因素的特点。在此基础上，通过计算NASA梯形翼来分析起降构型条件下气动力受转捩影响的规律，并通过计算DLR－F6翼身组合体来探索三维构型在巡航条件下的气动力精度。使用eN-数据库转捩判断方法的计算结果与实验值吻合较好，验证了所构建的基于RANS求解器的eN-数据库转捩预测方法的有效性，并为大型运输机气动力精确计算提供了分析工具。     

基于灰色理论的飞机结构疲劳寿命预测

对飞机结构疲劳寿命进行预测研究,具有重要的军事意义与凸显的经济价值,本文以某型军用飞机关键结构部件——水平尾翼为具体研究对象,采用通过飞机结构疲劳寿命试验专用平台得到的水平尾翼疲劳寿命的真实试验数据,运用灰色相关理论建立非等间距GM（1,1）模型,应用此模型预测飞机结构部件的疲劳寿命,并通过试验对所建模型的准确性与有效性进行验证。试验表明,非等间距的GM（1,1）模型能准确地预测飞机结构部件的疲劳寿命,降低TOM（1,1）模型的预测误差,拓宽‘TGM（1,1）模型在飞机结构疲劳寿命预测领域的应用范围,具有很好的工程实用价值。     

武器装备可靠性工程研究现状与最新进展

介绍国内外武器装备可靠性工程理论模型的发展现状与最新研究进展,主要包括提高系统可靠性经常应用到的冗余配置问题,系统失效分析采用的最短路径的旅行商问题,小样本数据条件下的动态故障树问题,复杂系统可靠性预测的随机约束与虚拟最短路径以及NASA对高技术项目进行评价和排序过程中采用的一种多学科群决策模型等。     

多元混合数据回归分析方法

针对加速寿命试验中经常遇到完全数据、定数截尾数据和定时截尾数据混合的情况,提出一种多元混合数据回归分析方法,建立了多元混合回归模型,给出回归系数和标准差的最佳无偏估计,以及百分位值的点估计和置信限估计.该方法不但适用于正态分布,而且还适用于Weibull分布、极值分布等其他各种位置-尺度分布,从而将传统只适用于完全数据...     

模型确认热传导挑战问题求解的贝叶斯方法

为了进一步推动模型确认方法的发展并明确其具体实施步骤,以圣地亚国家实验室提出的模型确认热传导挑战问题为例,建立了模型确认的贝叶斯框架,并阐述模型确认的思想以及实现的一般过程.模型确认不仅是一个评定仿真模型准确度的过程,而且是一个通过确认结果提高模型预测精度的过程.首先介绍了贝叶斯及不确定性量化的基本理论,强调了模型修正...