基于CRNN的汽车发动机声纹个体识别方法

为提高声纹个体识别率,提出了一种基于卷积神经网络(CNN)和深度循环神经网络(RNN)的声纹个体识别方案CRNN,用于发动机声纹个体识别.该方法通过优化CRNN网络参数,挖掘声谱图"纹路"特征和时序特征,解决现有方法不能充分利用声音信号特征的问题.基于实采汽车发动机声音信号的仿真结果表明,相对于传统方法,改进CRNN能获得更高识别率,达到了98.75％.     

Reaction degree of composition B explosive with multi-layered compound structure protection subjected to detonation loading

The explosive reaction degree and protection from explosions are concerns in the military field.In this work,the reaction degree of the composition B explosive was investigated experimentally.Multi-layered compound structures were used as barriers to weaken the blast loads.A comprehensive experiment using a high-speed camera and image processing techniques,side witness plates,and bottom witness plates was presented.Using the experimental fragment velocities,fragment piercing patterns,and damage characteristics,the reaction degree of the explosive impeded by different multi-layered com-pound structures could be precisely differentiated.Reaction parameters of the explosive obstructed by compound structures were obtained by theoretical analysis and numerical simulations.Unlike the common method in which the explosive reaction degree is only distinguished based on the initial pressure amplitude transmitted into the explosive,a following shock wave reflected from the side steel casing was also considered.Different detonation growth paths in the explosive formed.Therefore,all these shock wave propagation characteristics must be considered to analyze the explosive response impeded by compound structures.     

A novel DOA estimation algorithm using directional antennas in cylindrical conformal arrays

In this paper, a novel direction of arrival (DOA) estimation algorithm using directional antennas in cy-lindrical conformal arrays (CCAs) is proposed. To eliminate the shadow effect, we divide the CCAs into several subarrays to obtain the complete output vector. Considering the anisotropic radiation pattern of a CCA, which cannot be separated from the manifold matrix, an improved interpolation method is investigated to transform the directional subarray into omnidirectional virtual nested arrays without non-orthogonal perturbation on the noise vector. Then, the cross-correlation matrix (CCM) of the sub-arrays is used to generate the consecutive co-arrays without redundant elements and eliminate the noise vector. Finally, the full-rank equivalent covariance matrix is constructed using the output of co-arrays, and the unitary estimation of the signal parameters via rotational invariance techniques (ESPRIT) is performed on the equivalent covariance matrix to estimate the DOAs with low computational complexity. Numerical simulations verify the superior performance of the proposed algorithm, especially under a low signal-to-noise ratio (SNR) environment.     

中法战争中的晚清外交

本文阐述了晚清法越问题的历史渊源,对中法战争中清政府的内外处境和应对措施,以及与之有关的外交政策进行了客观中肯的评述。     

ESD对微电子器件造成潜在性失效的研究综述

静电放电(ESD)潜在性失效问题是当前微电子工业面临的可靠性问题之一,并且越来越引起人们的重视。国内外学者在微电子器件ESD潜在性失效的检测及探讨失效机理方面的研究取得了较大的进展。研究表明:MOS电路等微电子器件,在ESD作用下确实存在潜在性失效问题。因此,开展ESD潜在性失效研究具有重要意义。     

浅析不良学术行为对军校学报的影响及对策

在遏制学术不良行为的过程中,学报编辑部和编辑人员肩负着预防和纠正不良学术风气侵袭的重要防线。通过对当前社会和军校中不良学术行为主要表现的分析,进一步明确学术研究的本质属性,充分认识不良学术行为的危害性,提高学报编辑部和编辑人员的自律引领作用,强化规范办刊、质量办刊理念,从根源上遏制不良学术行为。     

激光平行光幕的爆炸成型弹丸形貌测试技术

针对目前爆炸成型弹丸形貌测试普遍使用的脉冲X光摄影法成本昂贵、结构复杂、测试困难的缺点,提出了激光平行光幕形貌测试系统。该系统中,由启动网靶、停止网靶和计时仪组成的区截测速装置测试EFP的速度,激光平行光幕和示波器测试EFP弹丸通过光幕时直径随时间的变化过程。然后将上述测试结果用Matlab软件进行仿真,得出EFP弹丸的形貌。测试与仿真表明:激光平行光幕形貌测试系统可以测试EFP弹丸的速度与形貌,而且成本低廉、可靠性高,可以在大威力战斗部试验中使用。     

效用函数的装备保障效能分析与评估

论述了装备保障效能及其评估的内涵,分析了效用函数的概念和构成方法,以ARINC系统效能模型为基础,结合我军装备保障工作的特点,系统地研究了影响装备保障效能的指标,建立了科学合理的装备保障效能指标体系,应用效用函数分析了每个效能评估指标,建立出装备保障效能评估的数学模型,并应用具体实例对其进行了论证。     

萃取-絮凝组合精制再生废润滑油

根据溶剂精制再生废润滑油环保、经济、高效的特点,采用单因素实验方法,应用极性溶剂为萃取剂、乙二胺为絮凝剂,组合精制再生废润滑油。最佳工艺条件为:萃取剂为正丁醇,精制时间为15 min,精制温度为25℃,剂/油质量比为5∶1,絮凝剂添加比例为1.0%。以该精制工艺操作,再生油性能指标得到明显改善,黏温指数达130以上,闪点达200℃,酸值为0.05 mg.g-1,灰分质量分数降低到0.01%以下,金属元素含量显著下降,再生油产率为80.6%,各项性能基本上符合HVI150基础油指标,表明该精制工艺再生废润滑油可行,应用前景广阔。     

一类不确定时滞混沌系统的全局鲁棒自适应神经网络同步控制器设计

研究一类不确定时滞混沌系统的全局鲁棒自适应神经网络同步控制器设计,其系统中的不确定时滞项不是简单的线性有界条件,而是允许其存在高阶项,因此具有全局特性．在控制器的设计上;首先通过选取合适的径向基函数（RBF）神经网络的权向量去逼近时滞系统中的未知连续有界部分;然后在RBF神经网络输出的基础上,选用一个鲁棒自适应控制器来趋近时滞系统的不确定部分;同时,利用Lyapunov稳定性理论对混沌同步的条件给出了论证;最后,数据仿真的结果表明该方法的有效性．