共查询到18条相似文献,搜索用时 187 毫秒
1.
2.
基于计算机视觉与SVM的水质异常监测方法 总被引:1,自引:0,他引:1
针对水质异常监测问题,本文提出了一种基于计算机视觉技术和支持向量机相结合的生物式水质异常监测方法。首先通过计算机视觉获取可以反映水质状况的鱼类行为运动特征参数,对其进行预处理;然后建立样本集并获得基于SVM的水质异常监测模型;最后利用模型对未知水质下的鱼类行为特征参数分析评价,间接监测水质异常状况。鉴于支持向量机核函数类型和参数优化对模型优劣有重大影响,本文对不同类型的核函数进行实验对比,其次分别采用粒子群优化算法(PSO)、遗传算法(GA)以及网格搜索法(Grid Search)对参数进行优化选择。实验结果表明该方法可以快速有效的进行水质异常监测。 相似文献
3.
目的 解决快递包裹物流过程中暴力分拣问题的前提是对暴力分拣行为进行有效识别,为此提出一种基于加速度分布特征的快递包裹暴力分拣行为智能识别方法。方法 利用集成三轴加速度传感器的数据采集设备实时采集并截取潜在异常操作情况下快递包裹的加速度数据。然后将潜在异常数据上传服务器,在服务器端执行分布特征的提取。最后将特征矩阵送入神经元网络分类器,得到当前包裹所受操作类别的结果。结果 实验证明,文中提出的多阈值截取方法可以有效截取潜在异常数据,使用加速度分布作为特征可以有效对暴力分拣行为进行分类。其中,使用BP网络作为模式识别分类器时,分类正确率可以达到93.6%;使用CNN作为模式识别分类器时,分类正确率可以达到95.3%。结论 文中提出的暴力分拣识别方法准确、快速,具有良好的在线实时性。基于此方法可以构建暴力分拣行为识别数据库,为进一步完善快递企业服务水平定量化评价体系提供数据支撑。这些数据还可以用于对暴力分拣产生的原因进行深入分析,从而提出减少暴力分拣行为的针对性解决方案。 相似文献
4.
5.
6.
基于相空间重构方法,从海底回波信号的相平面和相空间中提取了三个特征量:一阶距、相似序列重复度和熵,应用于海底底质分类。通过对海上实验数据的分析表明:这三个特征参数能有效地将两类海底分开,结果与海底采样分析吻合良好。 相似文献
7.
目的 有效分析和探索海洋船舶时空轨迹行为模式,提高船舶轨迹聚类的效率与质量,更好地检测真实船舶的异常行为。方法 针对当前船舶轨迹数据研究中存在的对多维特征信息利用不足、检测效率不高、检测精度较差等问题,提出一种精确度高、能自主识别分析多维特征的船舶异常轨迹识别方法。首先利用随机森林分类器评估多维特征重要性,构建轨迹特征的最优组合;然后提出一种降维密度聚类方法,将T–分布随机邻域嵌入(T–SNE)和自适应密度聚类(DBSCAN)模型结合,通过构建特征选择层和无监督聚类层实现对数据元素非线性关系的高效提取以及对聚类参数的智能选择;最后根据聚类结果构建类簇特征向量,计算距离阈值判别轨迹相似度,实现轨迹异常检测模型的构建。结果 以UCI数据集为例,降维密度聚类方法对4、13、30、64维特征数据集的F1分数能达到0.9 048、0.9 534、0.8 218、0.6 627,多个聚类指标均优于DBSCAN、K–Means等常见聚类算法的。结论 研究结果表明,降维密度聚类方法能有效提取数据多维特征结构,实现聚类参数自适应,弥补密度聚类中参数难以确定的问题,有效实现对多种类型船舶轨迹异常的识别。 相似文献
8.
在有效提取特征参数后,结合具体的应用环境,提出一种模糊判决算法,依据运动物体的面积和运动物体的运动距离等特征参数,对目标进行识别报警判断,捕获并存储异常现象,最后发出报警信号.研究表明,通过异常识别及报警模糊判决方法可以使监控系统有效地消除日光灯频闪光线,部分运动阴影以及局部小扰动带来的区域干扰. 相似文献
9.
《计量技术》2021,(9)
针对力值测量中进回程分布对不确定度的影响进行研究。在实际测量中,尽管在ISO376中定义了1.732这一包含因子,但力传感器的进回程分布并非是已知常见的分布,因此无法根据分布性质确定包含因子k。为了探究力传感器进回程特性,将采用包含因子的原始计算定义式对其进行计算分析。通过对严格控制实验条件得到的进、回程测量值,采用离散、连续两种分析方法,讨论进回程差实际分布特征,进而计算进回程差的包含区间,并最终确定包含因子k。通过核密度估计近似模拟,将离散型随机变量转变为连续型随机变量,得到未知分布的概率密度函数,并使用中心法以及最短包含区间进行分类讨论,最终获得95%与99%置信区间内的包含因子分别为1.846 3与2.221 6。 相似文献
10.
触屏手机按键设计新参数-最小按键中心距研究 总被引:1,自引:0,他引:1
目的研究手机触屏中两个相邻按键之间的最小中心距离。方法记录不同按键中心距条件下,四个典型任务情景下(拇指离散、食指离散、拇指系列和食指系列)的输入操作绩效和主观评价结果,并由绩效结果来动态调整下一轮操作需要的按键中心距,反复循环直至获取最小中心距。结果拇指离散、拇指系列、食指离散和食指系列四个任务下的最小按键中心距分别为:4.17 mm、6.30 mm、3.38 mm和5.40 mm。结论研究中以按键中心距参数代替按键尺寸和按键间距这两个参数的方法不仅保证了界面设计的简单高效,而且研究结果同时兼顾了稳定性和用户任务操作上的差异性。因此,研究结果可以为以手机为代表的小型触屏界面中的按键及其布局的标准化设计提供科学依据。 相似文献
11.
12.
目的 建立评价卷烟包装材料外观质量的检测方法,用于对卷烟包装材料的表面印刷适用性进行预判,以提高印刷效率。方法 以水雾面积作为对卷烟包装材料外观质量的主要评价对象,筛选卷烟包装材料印刷面的表观特性。对烟标表面粗糙度、平滑度、亮度、摩擦因数、粗糙度、表面形貌与水雾面积的相关性进行分析。结果 卷烟包装材料外观质量(水雾面积)与粗糙度、亮度等参数相关,与平滑度、摩擦因数等参数不直接相关。在433~818 nm的微观粗糙度内,水雾面积随着粗糙度的增加逐渐减小,当微观粗糙度大于818 nm时,水雾现象不存在。结论 基于白光干涉仪的微观粗糙度可作为卷烟包装材料外观质量(水雾现象)的定量和定性评价指标,该方法为解决烟包印刷行业的水雾问题提供了有益的理论支持。 相似文献
13.
Correspondence analysis and establishment of evaluation model of classification performance indices for a turbo air classifier
下载免费PDF全文
![点击此处可从《Materialwissenschaft und Werkstofftechnik》网站下载免费的PDF全文](/ch/ext_images/free.gif)
The operational parameters of a turbo air classifier including feeding speed, rotor cage's rotary speed and air inlet velocity affect its classification performance directly, such as cut size, classification precision, classification efficiency, fine powder yield, particle fineness and degree of dispersion. Current methods of optimizing operational parameters and improving the classification performance of a turbo air classifier are almost single objective decision only for one of the classification performance indices. In this paper, the multi‐objective programming (MOP) model on classification performance for a turbo air classifier is established to evaluate these performance indices comprehensively and achieve optimal classification performance. To minimize the effect of repeatability within these classification performance indices, correspondence analysis is applied to determine the evaluation indices of this MOP model. According to correspondence analysis on the fine talc classification experimental data as well as the calcium carbonate classification experimental data, there is a very strong correlation between cut size and D90; there is also a very strong correlation between cut size and fine powder yield. Thus D90 and fine powder yield are filtered out and they aren't discussed in the evaluation model. The variation coefficient method is introduced to calculate weights of the evaluation function, and the dimensionless transformation method is used to eliminate the effects of different dimension. Thus, the optimal solution among the experimental data is obtained through solving the evaluation function. For the talc classification experiments, the optimal operational parameter combinations are: the feeding speed is 40 kg · h–1, the air inlet velocity is 5 m · s–1 and the rotor cage's rotary speed is 1200 ? min–1. The classification performance indices are: cut size is 16.5 μm, classification precision index is 0.59, Newton classification efficiency is 57% and degree of dispersion is 2.13. For the calcium carbonate classification experiments, the optimal operational parameter combinations are: the feeding speed is 92 kg · h–1, the air inlet velocity is 12 m · s–1 and the rotor cage's rotary speed is 1200 ? min–1. The classification performance indices are: cut size is 31.4 μm, classification precision index is 0.74, Newton classification efficiency is 74% and degree of dispersion is 1.27. This evaluation model avoids the limitation of evaluation for the single classification performance index and incomplete information got by the means of single factor experiment of operational parameters. It also provides the quantitative evaluating criteria for classification performance of a turbo air classifier, which offers a theoretical basis for effective production. This multi‐objective programming optimizing method and evaluation model on classification performance can be applied to other dynamic air classifiers as well. 相似文献
14.
15.
目的为了提高枸杞分选效率且使分选结果便于统一包装,提出一种在机器视觉技术下多特征组合的枸杞精选方法。方法枸杞的形状和饱满度是精选的2个重要特征和依据,首先通过数字图像处理技术获取枸杞图像的横径纵径数据比值,并将其作为形状特征参数;其次获取枸杞质量和枸杞图像面积的比值,将其作为饱满度特征参数。基于这2类特征参数进行聚类分析,建立BP神经网络的枸杞多特征精选分类器。结果枸杞的形状类型不同,其形状特征和饱满度特征值也不同,通过BP神经网络分类器显示不同形状类型的枸杞聚类。该方法可以有效地对枸杞形状类型进行精选,精选准确率达到97.6%。结论根据形状和饱满度特征组合的分选效果最佳,该方法可以实现枸杞形状类型的精选。 相似文献
16.
Z.Q. Feng Y.Q. Yang B. Huang X. Luo M.H. Li Y.X. Chen M. Han M.S. Fu J.G. Ru 《Materials Letters》2011,65(17-18):2808-2811
The high angle annular dark field scanning transmission electron microscopy (STEM-HAADF) tomography technique was applied to understand the three dimensional (3D) morphology and distribution characteristic of grain boundary precipitate (GBP) in peak-aged Al–Cu–Mg alloy. The results indicate that GBPs show both spherical and lenticular shapes and triangularly distribute along grain boundary (GB). Based on 3D observations from various directions, the values of GBP relevant parameters such as GBP size, center to center distance, number of GBPs per unit GB area and area fraction of GB covered by GBPs are further determined. The 3D method for GBP relevant parameter determination seems an effective way to avoid misunderstandings in the conventional two dimensional (2D) methods induced by GBP overlapping and projection effect as well as curved GB surface. 相似文献
17.
本文通过对拉深件成型状态的声发射测试,进行了拉深过程AE特征参数信号的提取。对采集到的信号进行局域波分解后提取各IMF(Intrinsic Mode Function)的能量值作为初始特征参数,应用遗传算法对初始特征参数进行优化,生成最优特征参数。采用简单的马氏距离方法,将正常状态和微裂纹状态两种质量状态下的实验数据进行计算,比较两种状态下马氏距离的大小,取其中最小判别距离对应的状态为测试样本的状态类型。研究结果说明了该方法可以有效地识别出拉深件的微裂纹AE信号,从而判断出拉深件的初始裂纹状态,实现AE信号特征参数的优化及对金属拉深件成型质量状态的识别。 相似文献
18.
It is known that pollutants can be dispersed from the emission sources by the wind, or settled on the ground. Particle size, stack height, topography and meteorological conditions strongly affect particulate matter (PM) dispersion. In this work, an impact distance calculation methodology considering different particulate sizes is presented. A Gaussian-type dispersion model for PM that handles size particles larger than 0.1 μm is used. The model considers primary particles and continuous emissions. PM concentration distribution at every affected geographical point defined by a grid is computed. Stochastic uncertainty caused by the natural variability of atmospheric parameters is taken into consideration in the dispersion model by applying a Monte Carlo methodology. The prototype package (STRRAP) that takes into account the stochastic behaviour of atmospheric variables, developed for risk assessment and safe distances calculation [Godoy SM, Santa Cruz ASM, Scenna NJ. STRRAP SYSTEM - A software for hazardous materials risk assessment and safe distances calculation. Reliability Engineering and System Safety 2007;92(7):847-57] is enlarged for the analysis of the PM air dispersion. STRRAP computes distances from the source to every affected receptor in each trial and generates the impact distance distribution for each particulate size. In addition, a representative impact distance value to delimit the affected area can be obtained. Fuel oil stack effluents dispersion in Rosario city is simulated as a case study. Mass concentration distributions and impact distances are computed for the range of interest in environmental air quality evaluations (PM2.5-PM10). 相似文献