共查询到19条相似文献,搜索用时 46 毫秒
1.
2.
3.
4.
5.
6.
以可模拟非线性保守结构体系的一个计算模型为例,重点分析、对比了判别结构动力稳定性的拟静力刚度准则和能量判别准则。拟静力刚度准则依靠切线刚度非正定判定结构发生动力失稳可能导致误判。能量判别准则适用于具有屈曲后不稳定平衡路径的结构,利用屈曲后不稳定平衡路径上鞍点处的总势能作为动力失稳临界能量,结构总能量超越临界能量则判定为动力失稳。振动极值位移随荷载变化的曲线可以作为一种动力平衡路径,在接近临界荷载时,荷载的微小增量会导致结构振动极大位移显著增大,最终在临界点发生跃越失稳。 相似文献
7.
小波基特征提取的复合材料损伤检测 总被引:7,自引:0,他引:7
借助小波函数良好的时频带通性,利用B样条小波级数展开提取信号特征,并使之输入到自适应B样条小波神经网络进行学习和识别。最后从损伤检测领域中特征信号模式识别的应用角度,给出了利用上述理论进行复合材料无损检测的实例 相似文献
8.
通过引入频谱幅值修正系数改进了通常的谐波小波包变换。改进的谐波小波包变换使得信号分解前后各子带的频谱幅值保持不变,能精确提取相应子带故障调制信号的强度与频率,为机械故障诊断带来了方便。仿真实验和轴承故障诊断实例不仅表明谐波小波包具有一般正交小波包无法比拟的完美的带通滤波性能和极强的微弱特征信号提取能力,而且还表明改进的谐波小波包变换确实使得信号分解前后各子带的频谱幅值保持不变,能精确提取相应子带故障调制信号的强度与频率,有一定的工程应用价值。 相似文献
9.
心音信号特征提取小波包算法研究 总被引:2,自引:5,他引:2
为了准确地提取心音信号的病理特征信息,在研究小波包分析的基础上,提出一种心音信号分频带能量特征提取的算法.基于心音信号频谱分析,采用能量集中度高、局部特性好的db6小波函数作为小波包母函数并选取适合心音信号分析的最优基,对不同的心音信号进行4层小波包分解,得到最优基的小波包系数.根据小波包系数与信号能量在时域上的等价关系,提取最优基频带的归一化能量作为心音信号的特征向量.采用类别可分离性判据,计算出该算法对正常和心脏疾病患者的心音特征的可分性测度均值为3.934 9,表明该算法能有效地识别不同的心音信号. 相似文献
10.
11.
为了对蝙蝠回声定位声波进行种类识别,论文基于离散小波包分解的特征提取方法,对飞行状态下短翼菊头蝠与鲁氏菊头蝠的回声定位声波进行三层小波包分解,提取两种菊头蝠在不同频率带内声波信号的能量作为特征参数,并根据U检验结果选取参数作为识别特征向量,进行BP神经网络识别。其中短翼菊头蝠和鲁氏菊头蝠回声定位声波训练样本分别为95个和102个,测试样本分别为44个和68个。对现有测试样本识别率达到100%。结果表明.基于小波包分析和神经网络的分类方法对蝙蝠回声定位声波进行识别是可行的。 相似文献
12.
为了使增强的Fisher鉴别准则(EFDC)避免因PCA降维带来的鉴别信息丢失问题,本文将其进行二维推广,提出基于二维类内差异信息保持(2D-IDP)的人脸识别方法,该方法建立了一个鲁棒性更强的鉴别准则,使得投影后不同类的样本点尽量远离的同时,类内紧致性和差异信息都得到有效保持,避免了过学习现象的产生.同时对EFDC近邻图中的参数t作了重新定义,使其能根据不同的输入样本自适应的变化,避免了t选择不当导致的识别性能下降的问题.在YALE和AR人脸库上的实验表明了本文方法的有效性. 相似文献
13.
舰船辐射噪声频域特征提取是舰船目标识别的关键技术之一。为提高舰船目标识别率 ,采用小波包和 112维谱对舰船辐射噪声进行多小波包空间调制谱和噪声谱特征提取及融合研究。并用提取的特征对五类舰船目标辐射噪声进行了分类识别实验 ,结果表明所提特征具有很好的分类识别效果 相似文献
14.
基于小波包和1(1/2)维谱的舰船辐射噪声频域特征提取及融合 总被引:6,自引:0,他引:6
舰船辐射噪声频域特征提取是舰船目标识别的关键技术之一。为提高舰船目标识别率,采用小波包和1 1/2维谱对舰船辐射噪声进行多小波包空间调制谱和噪声谱特征提取及融合研究。并用提取的特征对五类舰船目标辐射噪声进行了分类识别实验,结果表明所提特征具有很好的分类识别效果。 相似文献
15.
为了改进舰船辐射噪声分类系统的性能,进一步提高识别准确率,文章提出了一种基于多特征的小波包分解在长短期记忆(LongShort-TermMemory,LSTM)网络中分类的方法。该方法首先通过小波包分解技术,分频段提取舰船辐射噪声的多种特征,将提取的特征利用主成分分析法(Principal Component Analysis, PCA)进行数据降维,通过添加注意力机制(Attention Mechanism)算法的LSTM网络,对辐射噪声结果分类,提高了学习效率和识别准确率。为了更精细地提取特征,分频段提取了舰船辐射噪声的时频域特征、小波变换特征和梅尔倒谱系数等特征,并将分频段与不分频段的特征、多特征与单一特征、不同信噪比间的算法性能进行对比。实验结果表明,基于小波包分解和PCA-Attention-LSTM的模型可以有效地提高舰船辐射噪声分类的性能,是一种可行的分类方法。 相似文献
16.
爆破振动信号是典型的短时非平稳随机信号。应用多分辨率特点的小波包变换对爆破振动信号进行多层分解,得到信号能量分布的细节信息。根据建立在概率统计基础上的信息熵概念,推导得到爆破振动信号能量熵计算方法。分析了4种类型爆破振动信号的能量熵,熵值由大到小为:隧道爆破、管道爆炸、台阶爆破、塌落振动。结果表明,能量熵能够反映不同类型爆破对振动信号的影响。提出将能量熵作为爆破振动信号的新特征量,为爆破振动信号特征提取、不同爆破类型振动信号识别和爆破振动预测提供一种新思路。 相似文献
17.
18.
Ultrasonic techniques for evaluating the quality of solid-state weld interfaces have been investigated over the past several years. Promising results have been obtained on a variety of solid-state welds by extracting features from the ultrasonic wave forms and applying pattern recognition algorithms to separate acceptable from unacceptable welds. The general conclusion is that the ultrasonic features most sensitive to interfacial bonding are those dependent on high frequencies. However, no single feature has been discovered that is adequate to yield separation of good vs. poor welds, since the microstructural response is also frequency dependent.Given the increase in sensitivity and resolution with high-frequency ultrasonic evaluation, selected specimens have been examined with acoustic microscopy. These specially prepared samples were inspected with focused transducers at frequencies in the 35–75 MHz range. The reflections observed indicated bond quality to vary in discrete regions with good and poor regions distributed across the diameter. Corresponding variations in the degree of bonding have been observed on the fracture surfaces of mechanically-tested specimens. The development of both low- and high-frequency acoustic microscopy has led to the possibility of sensing and imaging subtle changes in the reflection coefficient of the bond line. These acoustic images will improve our understanding of the mechanisms involved in evaluating solid-state bonds. 相似文献
19.
Automatic identification of bird targets with radar via patterns produced by wing flapping.
下载免费PDF全文

Serge Zaugg Gilbert Saporta Emiel van Loon Heiko Schmaljohann Felix Liechti 《Journal of the Royal Society Interface》2008,5(26):1041-1053
Bird identification with radar is important for bird migration research, environmental impact assessments (e.g. wind farms), aircraft security and radar meteorology. In a study on bird migration, radar signals from birds, insects and ground clutter were recorded. Signals from birds show a typical pattern due to wing flapping. The data were labelled by experts into the four classes BIRD, INSECT, CLUTTER and UFO (unidentifiable signals). We present a classification algorithm aimed at automatic recognition of bird targets. Variables related to signal intensity and wing flapping pattern were extracted (via continuous wavelet transform). We used support vector classifiers to build predictive models. We estimated classification performance via cross validation on four datasets. When data from the same dataset were used for training and testing the classifier, the classification performance was extremely to moderately high. When data from one dataset were used for training and the three remaining datasets were used as test sets, the performance was lower but still extremely to moderately high. This shows that the method generalizes well across different locations or times. Our method provides a substantial gain of time when birds must be identified in large collections of radar signals and it represents the first substantial step in developing a real time bird identification radar system. We provide some guidelines and ideas for future research. 相似文献