A nonlinear background removal method for seismo-ionospheric anomaly analysis under a complex solar activity scenario: A case study of the M9.0 Tohoku earthquake

A precise determination of ionospheric total electron content (TEC) anomaly variations that are likely associated with large earthquakes as observed by global positioning system (GPS) requires the elimination of the ionospheric effect from irregular solar electromagnetic radiation. In particular, revealing the seismo-ionospheric anomalies when earthquakes occurred during periods of high solar activity is of utmost importance. To overcome this constraint, a multiresolution time series processing technique based on wavelet transform applicable to global ionosphere map (GIM) TEC data was used to remove the nonlinear effect from solar radiation for the earthquake that struck Tohoku, Japan, on 11 March, 2011. As a result, it was found that the extracted TEC have a good correlation with the measured solar extreme ultraviolet flux in 26–34 nm (EUV_26–34) and the 10.7 cm solar radio flux (F_10.7). After removing the influence of solar radiation origin in GIM TEC, the analysis results show that the TEC around the forthcoming epicenter and its conjugate were significantly enhanced in the afternoon period of 8 March 2011, 3 days before the earthquake. The spatial distributions of the TEC anomalous and extreme enhancements indicate that the earthquake preparation process had brought with a TEC anomaly area of size approximately 1650 and 5700 km in the latitudinal and longitudinal directions, respectively.     

一种基于粗糙K-均值的椭球基函数神经网络

改进了一种椭球基函数神经网络,它与经典椭球单元神经网络的结构不同,而与径向基函数神经网络结构类似,即它有一个隐含层,并且隐层单元采用椭球基函数,区别于RBF网络的高斯函数。本文采用粗糙K-均值方法求取椭球函数的中心,并给出了该方法中确定初始阈值的步骤。这种改进方法不但使对输入空间的划分局部作用,而且划分区域封闭有界。因此,改进的神经网络具有较好的函数逼近能力和模式识别能力。仿真实验验证了该椭球基函数神经网络的正确性和有效性。     

成组技术中计算机辅助零件分类方法的探讨

成组技术是有效实现CAD/CAM的基础之一,是提高多品种、中小批量生产水平的重要手段。本文提出了在成组技术中应用模糊数学理论进行计算机辅助零件分类的新方法,并对回转零件进行了分类试验,取得了满意的结果。采用这种方法,不需要对零件进行编码,可以对零件相似性进行定量分析,使得零件分类更具有柔性,为成组技术中零件分类提供了新的方法。     

低轨卫星缺失时序数据的模式识别方法

在航天应用中，低轨卫星经常会由于原始数据缺失而影响卫星时序数据模式识别结果，降低准确率。针对该问题提出了一种新型MR-GRU模型，可有效处理缺失时序数据，并获得较好的模式识别准确率。区别于传统模型的补全缺失数据的方法，MR-GRU模型直接在缺失时序数据上运用循环神经网络进行训练，对传统门控循环单元结构进行了改进，增加了两个新变量：掩蔽项和衰减项。掩蔽项作用于输入，衰减项作用于输入和隐层单元输出。MR-GRU模型不仅能够保持时序数据固有的时间特性，还能有效提高模式识别精度。在卫星时序数据上的模式识别试验表明，MR-GRU模型准确率优于传统模型。     

基于改进的卷积神经网络的步态识别

为了提高惯性传感器采集到的序列数据中步态识别的准确率,建立了一个激励层改进的卷积神经网络(CNN)模型。针对三轴加速度传感器对运动太过敏感导致步态周期划分不准确的问题,采用加速度传感器与弯曲度传感器组合获取人体运动信息。将CNN模型中激励层的线性整流函数(ReLU)改进为带泄露线性整流函数(Leaky ReLU),以解决遇到卷积输出数据小于0时神经元被抑制的问题,进而达到提高步态识别准确率的目的。实验结果表明激励层优化的CNN模型在行走、上下楼和上下坡五种步态模式下识别率达到了95.79%,与未采用弯曲度传感器的改进CNN模型和未进行激励层改进的CNN模型相比,步态识别率有所提高。     

Spatial transformation of general sampling-aliasing frequency region for rotating-blade parameter identification with emphasis on single-probe blade tip-timing measurement

Blade-health monitoring is intensely required for turbomachinery because of the high failure risk of rotating blades. Blade-Tip Timing (BTT) is considered as the most promising technique for operational blade-vibration monitoring, which obtains the parameters that characterize the blade condition from recorded signals. However, its application is hindered by severe undersampling and stringent probe layouts. An inappropriate probe layout can make most of the existing methods invalid or inaccurate. Additionally, a general conflict arises between the allowed and required layouts because of arrangement restrictions. For the sake of economy and safety, parameter identification based on fewer probes has been preferred by users. In this work, a spatial-transformation-based method for parameter identification is proposed based on a single-probe BTT measurement. To present the general Sampling-Aliasing Frequency (SAFE) map definition, the traditional time–frequency analysis methods are extended to a time-sampling frequency. Then, a SAFE map is projected onto a parameter space using spatial transformation to extract the slope and intercept parameters, which can be physically interpreted as an engine order and a natural frequency using coordinate transformation. Finally, the effectiveness and robustness of the proposed method are verified by simulations and experiments under uniformly and nonuniformly variable speed conditions.     

边缘检测技术在火箭发动机实验诊断中的应用

对高速运动分析仪拍摄的Ｕ型燃气发生器固体装药燃烧和双组元液体喷嘴雾化图像进行了边缘检测图像分析,根据被分析实物边缘层次性较强的特点,在简单边缘检测的基础上采用自动门限、二次门限和最佳滤波的方法,获得了固体燃气发生器在燃烧过程中的内部结构、推进剂瞬态燃速、绝热隔板烧蚀率等参数,获得了双组元液体喷嘴的雾化角、粒子分布等特性。     

高斯模糊下舰船图像的矩特征

针对舰船目标图像受到自身运动、环境和图像预处理的影响出现模糊,丢失轮廓信息,造成像素点阵模糊和矩特征变化的问题,在高斯模糊低阶矩特征分析的基础上,提出并证明了Hu矩、仿射不变矩特征在高斯模糊作用下的变化定理;通过2个仿真实验验证了定理的正确性;为了保证舰船目标的识别效率,提出了建立多尺度特征库的建议。     

改进BA优化的MKSVDD航空发动机工作状态识别

为了提高航空发动机工作状态识别准确率和效率,避免人工识别中存在的误判和耗时耗力问题,提出了基于混沌脉冲蝙蝠算法（CRBA）优化的多核支持向量数据描述（CRBA-MKSVDD）智能识别方法。研究了多核支持向量数据描述（MKSVDD）改进策略,引入混沌脉冲发射率提高了蝙蝠算法（BA）的收敛速度和收敛精度,得到了CRBA;通过CRBA优化MKSVDD的惩罚因子和核参数,同时对飞参数据进行了特征提取;基于特征飞参数据训练了CRBA-MKSVDD分类器,并对某型发动机一个飞行架次的工作状态进行了识别。结果表明,该方法识别准确率达到97.547 9%,可用于与发动机工作状态的相关研究和应用。      

通用航空机队设备可靠性动态识别模型

通用航空机队设备可靠性是通航单位安全运行的前提条件,是影响运营单位经济效益的重要因素之一。根据通航单位机队设备可靠性数据统计、分析及实际使用情况,采用ATA100章节名称作为指标源。综合可变模糊识别方法和权重阶梯朴素贝叶斯分类器模型的优势,构建了通用航空机队设备可靠性动态识别模型。为了避免主观给定指标权重导致的不合理,应用熵权法客观获取指标权重。最后利用实例测试样本验证了权重阶梯朴素贝叶斯分类器的合理性,并基于该方法对待识别样本进行了可靠性状态识别。实例分析表明：基于权重阶梯朴素贝叶斯分类器的通用航空机队设备可靠性状态识别模型具有较强的可行性和合理性,为通用航空机队设备可靠性状态提供了一种科学的识别方法。