谱峭度和Vold-kalman阶比跟踪在风电机组齿轮箱故障诊断中的应用

针对风电机组齿轮箱在时变工况下的振动信号具有非平稳特性,提出一种谱峭度和Vold-kalman阶比跟踪(Vold-Kalman Filter Based Order Tracking,VKF-OT)相结合的故障特征提取方法。以转频和啮合频率作为VKF-OT的提取频率,获得随转速变化的阶比信号,通过阶比信号复包络直接求两种频率分量的幅值、相位,经实验分析这种方法能保留齿轮箱的瞬变信息。而后计算两种频率分量的谱峭度,以最大谱峭度对应的频率带能量与原阶比信号总能量之比作为故障特征,最后采用高斯混合模型对风电机组齿轮箱在不同工况下的150组振动信号进行特征描述,运用最大贝叶斯分类器实现故障识别。故障识别率表明该方法可有效地识别任意时变工况下的齿轮早期局部微弱故障。

无线信道统计模型识别

为准确地找到最符合快衰落特性的统计分布模型,论文基于概率论和信息论设计了Kullback-Leibler距离及信息准则表达式,对几种主要的统计分布模型进行了仿真和实验,得到了各统计分布模型的正确识别率,通过统计的方式对比了各种识别模型,发现基于直方图的KL方法识别模型的可靠性比其他方法要高,而韦伯衰落模型更加适合用来对无线信道进行建模。

非约束环境下基于小样本的人脸特征精确定位

针对非约束环境下的人脸特征定位问题,在概率框架下提出一种基于小样本的精确定位策略.通过对比分析,提取人脸主要特征的颜色和灰度信息及人脸特征之间的几何约束信息,利用混合高斯模型分别对其进行概率建模.之后建立定位融合策略,不仅考虑每种人脸特征的概率分布,还考虑其周围元素的概率分布特性,及各元素之间的几何约束.实验结果表明,该方法能在少量训练样本图像且样本个体较为单一的条件下,实现人脸主要特征的精确定位,且定位精度高于现有方法.

Immune adaptive Gaussian mixture particle filter for state estimation

The particle filter （PF） is a flexible and powerful sequen- tial Monte Carlo （SMC） technique capable of modeling nonlinear, non-Gaussian, and nonstationary dynamical systems. However, the generic PF suffers from particle degeneracy and sample im- poverishment, which greatly affects its performance for nonlinear, non-Gaussian tracking problems. To deal with those issues, an improved PF is proposed. The algorithm consists of a PF that uses an immune adaptive Gaussian mixture model （IAGM） based immune algorithm to re-approximate the posterior density. At the same time, three immune antibody operators are embed in the new filter. Instead of using a resample strategy, the newest obser- vation and conditional likelihood are integrated into those immune antibody operators to update the particles, which can further im- prove the diversity of particles, and drive particles toward their close local maximum of the posterior probability. The improved PF algorithm can produce a closed-form expression for the posterior state distribution. Simulation results show the proposed algorithm can maintain the effectiveness and diversity of particles and avoid sample impoverishment, and its performance is superior to several PFs and Kalman filters.

基于DM642的混合高斯模型运动目标检测系统设计与实现

运动目标检测是智能视频监控技术的重要环节,精确的分割出运动目标是后续监控技术得以实现的重要基础。该文以强大运算能力的DM642为核心搭建了运动目标检测系统硬件平台,实现和优化了基于混合高斯模型的检测算法。实验表明,该系统能有效地检测出运动目标,实时性较高。

A quasi single-phase model for debris flows and its comparison with a two-phase model

A depth-averaged quasi single-phase mixture model is proposed for debris flows over inclined bed slopes based on the shallow water hydrosediment-morphodynamic theory with multi grain sizes. The stresses due to fluctuations are incorporated based on analogy to turbulent flows, as estimated using the depth-averaged k-? turbulence model and a modification component. A fully conservative numerical algorithm, using wellbalanced slope limited centred scheme, is deployed to solve the governing equations. The present quasi single-phase model using four closure relationships for the bed shear stresses is evaluated against USGS experimental debris flow and compared with traditional quasi single-phase models and a recent physically enhanced two-phase model. It is found that the present quasi single-phase model performs much better than the traditional models, and is attractive in terms of computational cost while the two-phase model performs even better appreciably.

基于Markov随机场理论的鼠脑切片显微图像的分割研究

鼠脑中的神经细胞是生物学家的一个重要研究对象.随着计算机视觉技术的飞速进步,研究者们利用图像分割技术从鼠脑切片显微图像自动提取细胞,为进一步分析提供便利.文中提出一种基于马尔可夫随机场理论的鼠脑切片细胞分割算法.相对于传统的算法,文中创新是利用已有的专家标记图和原始图像的灰度特征,结合期望最大化算法,初步估计高斯混合模型的参数,作为条件迭代模式算法的初始值,不仅提高分割精度,且减少迭代次数;并将像素的灰度特征和像素间的距离加入到传统的Potts随机场模型中,更加合理地描述像素间的定量关系.实验结果表明,与传统方法相比,此方法具有较高的计算效率和分割精度.

Coherent Point Drift Registration Combined with Image Feature and its Application

A key step of constructing active appearance model is requiring a set of appropriate training shapes with well-defined correspondences.In this paper,we introduce a novel point correspondence method(FB-CPD),which can improve the accuracy of coherent point drift(CPD) by using the information of image feature.The objective function of the proposed method is defined by both of geometric spatial information and image feature information,and the origin Gaussian mixture model in CPD is modified according to the image feature of points.FB-CPD is tested on the 3D prostate and liver point sets through the simulation experiments.The registration error can be reduced efficiently by FB-CPD.Moreover,the active appearance model constructed by FB-CPD can obtain fine segmentation in 3D CT prostate image.Compared with the original CPD,the overlap ratio of voxels was improved from 88.7% to 90.2% by FB-CPD.

典型干旱区甘肃民勤光合/非光合植被覆盖度时空演变分析

光合植被(Photosynthetic Vegetation, PV)和非光合植被(Non-Photosyntletic Vegetation, NPV)是用于描述干旱区植物生存状态和监测植物生产力的重要因子,及时监测PV/NPV的覆盖度是研究植被衰退驱动机制的必要条件。鉴于此,以中国西部甘肃省民勤县荒漠过渡带为研究区,采用线性光谱混合模型,通过Google Earth Engine地理云计算平台上Landsat系列的年NDVI(归一化植被指数Normalized Difference Vegetation Index)最大合成影像数据生成一套1987年—2017年的PV与NPV覆盖度产品(1期/年)。通过数据分析发现近30 a间民勤的PV和NPV覆盖度均明显增加,2007年—2008年是PV大量向NPV转化的时间节点;PV覆盖度增加主要是在石羊河两侧耕地范围内及其南部腾格里沙漠区域,而NPV覆盖度增加分布于绿洲外的整个民勤境内的荒漠区域,此结论可作为研究区PV与NPV覆盖度变化及其发生的根源分析的依据。