基于LSTM和CNN的高速柱塞泵故障诊断

针对高速轴向柱塞泵容易发生空化，且目前空化故障诊断方法存在依赖手工特征提取、鲁棒性不高的问题，提出了一种基于长短时记忆（LSTM）和一维卷积神经网络（1D-CNN）相结合的空化故障诊断方法。搭建了柱塞泵故障实验台，采集柱塞泵在不同空化等级下的壳体振动信号。利用LSTM和1D-CNN搭建的分类模型对不同进口压力情况下的振动信号进行空化等级识别。实验结果表明：提出的方法能够准确地识别出4类不同的空化等级，准确率高达99.5%，同时在不附加降噪方法的情况下，具有良好的鲁棒性，在0 dB信噪比的情况下，识别准确率高达87.3%。     

Spatial Reorientation: Effects of Verbal and Spatial Shadowing

ABSTRACT

Spatially disoriented adults flexibly conjoin geometric information (macroscopic shape) and nongeometric information (e.g., the color of a wall) to re-establish their bearings. It has been proposed that non-geometric information is incorporated into a geometric frame of reference through the use of spatial language. Support for this assumption comes from dual-task studies in which participants failed to use non-geometric features when they shadowed a verbal message concurrent to the reorientation task. These studies were performed in small rectangular spaces. In contrast, our study was performed in a large square room. Experiment 1 showed that verbal shadowing did not disrupt non-geometric feature use in this environment. In Experiment 2, we found that a spatial shadowing task that required the encoding of frequently changing spatial directions impaired reorientation behavior. Our study shows that nongeometric information can be used for reorientation without recourse to linguistic processes, and suggests that the use of non-geometric features is dependent upon a spatial coding process.     

Combining Locations from Working Memory and Long-Term Memory into a Common Spatial Image

Abstract

This research uses a novel integration paradigm to investigate whether target locations read in from long-term memory (LTM) differ from perceptually encoded inputs in spatial working-memory (SWM) with respect to systematic spatial error and/or noise, and whether SWM can simultaneously encompass both of these sources. Our results provide evidence for a composite representation of space in SWM derived from both perception and LTM, albeit with a loss in spatial precision of locations retrieved from LTM. More generally, the data support the concept of a spatial image in working memory and extend its potential sources to representations retrieved from LTM.     

C++Builder语言的虚拟设备驱动程序VxD的开发

本文介绍了虚拟设备驱动程序的基本概念和用C Builder开发VxD程序的方法，并以在证券业务屏中普遍采用内存映射卡为例进行简略说明。     

一种采用衰减记忆滤波的环月航天器自主导航方法研究

针对环绕月球运行的深卒探测航天器提出了一种新的自主导航方案，该方案是以两个环月航天器之间的相对位置矢量信息作为量测量，结合轨道动力学方程，对航天器的轨道自主估计确定，方案中考虑了符合实际的复杂摄动影响，并对描述动力学特性的数学模型与噪声的统计模型不准确而导致的滤波发散问题，提出利用一种经过衰减记忆改进的平方根非线性滤波（SRUKF）算法进行解决。对所提方案做了大量的计算机仿真，同时洋尽的分析和比较了由于衰减因子及采样周期变化所带来的影响。从仿真结果上看，衰减记忆滤波处理能够很好得抑制非线性状态转移条件下的滤波发散趋势。     

Fe—Mn—Si—Cr—Ni形状记忆合金的研究

利用电子显微镜对Ｆｅ－１５Ｍｎ－５．５Ｓｉ－１２Ｃｒ－７Ｎｉ（质量分数）形状记忆合金的物理本质进行了研究。结果表明：该合金的记忆效应是靠应力诱发ε－马氏体相变及其逆转变而产生的。ε－马氏体是在应力诱发下由奥氏体基体（１１１）γ面层错处形核产生的。通过热处理和训练处理后，该合金的记忆效应明显提高。     

频率源的短期频率稳定度及相位噪声测量

叙述了频率源的重要特性—频率稳定度及相位噪声的表征和测量；比较了各种测量方法的优缺点；分析了测量中存在的问题，影响测量结果的因素及其引入的误差；给出了避免这些影响和修正误差的方法；最后介绍了国内外频率稳定度和相位噪声测量的最新进展。     

塑性变形提高形状记忆合金相变滞后机制的探讨

形状记忆合金经适当温度下的塑性变形可以有效地提高马氏体的稳定性,从而使相变滞后得以大幅度提高.本文根据马氏体相变热力学和动力学,并结合相关的实验结果,研究了弹性应变能弛豫和相变滞后的关系.结果表明,塑性变形产生的位错以及变形的第二相颗粒对逆马氏体相变温度的提高具有一定作用,但塑性变形导致应变能释放才是形变提高形状记忆合金相变滞后的主导因素.     

PE—3284中型计算机内存扩充

介绍了ＰＥ—３２８４中型计算机内存扩充的方法，包括硬件电路设计，操作系统和应用软件的改进．     

最大应变记忆元件

 本文介绍的新型的应变测试元件——最大应变记忆元件,具有记忆构件上曾经历过的最大应变值的功能。在不跟踪测量的情况下,可以得知构件上曾经历过的最大应变值,使用方便,灵敏度高。