共查询到19条相似文献,搜索用时 218 毫秒
1.
电容层析成像系统的传感器具有"软场"特性,即敏感场分布受被测介质的影响。为获得高质量的重建图像,利用COMSOL软件快速求解油气润滑测试系统ECT的灵敏度矩阵,运用COMSOL和MATLAB联合仿真,对该管道内层流和环状流2种典型流型的灵敏度场的软场效应进行分析,并且应用LBP算法和OTSU算法,分别在考虑和忽略软场效应的情况下对2种流型进行图像重建。仿真结果表明,软场效应改变了灵敏度分布;润滑油介质靠近管壁时,检测敏感度较高;采用软场效应改变的灵敏度矩阵进行图像重建,将有效提高重建图像精度。 相似文献
2.
3.
卷积神经网络凭借其较强的非线性拟合能力,在电容层析成像图像重建中逐渐得到应用。本文针对卷积神经网络模型超参数调节问题,研究了模型参数对卷积神经网络电容层析成像图像重建的影响。首先,通过数值方法构建了包含80 000组随机流型与40 000组典型流型的"电容矩阵-介质分布"数据集;然后,通过该数据集中的训练集对不同超参数的卷积神经网络模型进行训练和验证,并系统研究了网络初始化、网格密度、卷积核数、全连接层神经元数以及隐藏层结构等超参数对图像重建精度的影响;接着,利用额外生成的12 000组数据作为测试集对各网络模型性能进行评价;最后通过静态实验,对不同网络模型的图像重建效果进行了比较和分析。结果表明:网络隐藏层结构对图像重建精度影响较大,而网络初始化、网格密度、卷积核数以及全连接层神经元数等超参数对重建精度影响较小。 相似文献
4.
5.
6.
分析了叶片一般通用扭曲规律,在此基础上拓展了一般通用扭曲规律。提出了叶片抛物线流型,适当增加了叶片均径附近的能量头,减小了叶尖与叶根附近的能量头。利用通用扭曲规律的拓展形式,通过选择不同的控制系数,能够获得传统常用流型以及不同能量头分布的抛物线流型。对比了抛物线流型与等环量、等反动度流型,结果表明,抛物线流型改善了反动度、入口相对速度马赫数、气流出口角、气流折转角的分布,克服了传统流型叶根易出现负反动度、叶尖入口相对速度马赫数过大等缺点,缓解了叶根气流出口角和气流折转角过大等问题。 相似文献
7.
粒子滤波算法在ECT图像重建中的应用 总被引:2,自引:1,他引:1
针对电容层析成像技术(ECT)的图像重建质量精度较低的问题,提出了一种基于粒子滤波的ECT图像重建方法。首先,分析了ECT图像重建基本原理,以系统状态估计的方式描述了ECT图像重建最优解的搜索过程,并建立了状态空间模型。然后,以线性反投影(LBP)算法的图像重建结果作为初始状态,利用测量信息对从状态空间中获取的随机样本进行最优加权,以获得重建图像的最小方差估计。最后,对5种不同的流型进行了仿真实验。实验结果表明,利用本文方法获得的重建图像误差平均值为42.93%,相关系数平均值为0.813 9,比LBP算法、Landweber迭代算法和IMN-SNOF算法得到的相应指标要好。本文方法是一种有效、精度较高的ECT图像重建方法,为ECT图像重建技术提供了新的途径和手段。 相似文献
8.
电站空冷风机的设计与流场数值计算 总被引:1,自引:0,他引:1
介绍了火电厂直接空冷风机采用5次方流型的设计过程,使用三维N-S方程对所设计的空冷风机在设计点的性能进行了计算,并与采用等α流型的风机性能进行了比较,计算结果表明:采用5次方流型设计,其全压效率要比等α流型的风机高10%左右. 相似文献
9.
10.
11.
Flow regime is one of the key characteristics of gas-liquid two-phase pipe-flows and its identification is essential for several industrial applications. In this paper, the ultrasonic phased array technology is used to identify flow regimes of two-phase (air-water) vertical flow. The ultrasonic phased array can perform multi-point, omnidirectional detection to obtain high-resolution data suitable for image processing. The scanned images, which have distinctive features, are subjected to a series of image-treatment techniques, such as principle component analysis, to extract information necessary for flow regime identification. The K-nearest neighbors (KNN) classification algorithm is then used to identify flow regimes with high accuracy. 相似文献
12.
The width of the emission spectrum of a common fluorophore allows only for a limited number of spectral distinct fluorescent markers in the visible spectrum, which is also the regime where CCD-cameras are used in microscopy. For imaging of cells or tissues, it is required to obtain an image from which the morphology of the whole cell can be extracted. This is usually achieved by differential interference contrast (DIC) microscopy. These images have a pseudo-3D appearance, easily interpreted by the human brain. In the age of high throughput and high content screening, manual image processing is not an option. Conventional algorithms for image processing often use threshold-based criteria to identify objects of interest. These algorithms fail for DIC images as they have a range from dim to bright with an intermediate intensity equal to the background, so as to produce no clear object boundary. In this article we compare different reconstruction methods for up to 100 MB-large DIC images and implement a new iterative reconstruction method based on the Hilbert Transform that enables identification of cell boundaries with standard threshold algorithms. 相似文献
13.
H.L. Hu J. Dong J. Zhang Y.J. Cheng T.M. Xu 《Flow Measurement and Instrumentation》2011,22(5):482-487
In the gas/solid two-phase system, solid particles can accumulate a large number of electrostatic charges because of collision, friction and separation between particles or between particles and the wall. Through the detection and processing of the induced fluctuation charge signal, a measuring system can obtain two-phase flow parameters, such as flow regime, concentration and velocity. A novel methodology via introducing the characteristics of speech emotion recognition into flow regime identification is proposed for improving the recognition rate in gas/solid two-phase flow systems. Three characteristics of electrostatic fluctuation signals detected from an electrostatic sensor are extracted as the input of back propagation (BP) neural networks for flow regime identification. They are short-term average energy, Mel-frequency cepstral coefficients (MFCC) and cepstrum. The results show that the method based on each characteristic of the electrostatic fluctuation signal and BP neural networks can identify the three flow regimes of gas/solid two-phase flow in a horizontal pipe, and the identification rate of the method based on the three characteristics and BP neural networks is up to 97%, much higher than the methods based on a single characteristic. 相似文献
14.
数码相机的彩色图像预处理过程 总被引:3,自引:2,他引:1
结合数码相机图像采集特性和人眼视觉误差,讨论了彩色图像预处理过程.通过分析彩色图像的数据格式,将八叉树量化方法用于彩色图像的颜色信息量化,并采用矢量中值滤波消除彩色图像噪声,以实现对彩色图像的合理预处理.结合实验讨论分析了矢量中值滤波法的滤波器窗口参数,并结合颜色信息相似度理论提出了彩色图像预处理效果的评价方法.实验获得了合理的颜色量化方法和滤波器窗口参数,处理得到的图像最大色差变化控制在3个CIELAB色差单位.结果表明,用八叉树结构量化和矢量中值滤波对数码相机采集到的彩色图像进行预处理可达到较理想的效果. 相似文献
15.
The most crucial task of petroleum geology is to explore oil and gas reservoirs in the deep underground. As one of the analysis techniques in petroleum geological research, rock thin section identification method includes particle segmentation, which is one of the key steps. A conventional sandstone thin section image typically contains hundreds of mineral particles with blurred boundaries and complex microstructures inside the particles. Moreover, the complex lithology and low porosity of tight sandstone make traditional image segmentation methods unsuitable for solving the complex thin section segmentation problems. This paper combines petrology and image processing technologies. First, polarised sequence images are aligned, and then the images are transformed to the HSV colour space to extract pores. Second, particles are extracted according to their extinction characteristics. Last, a concavity and corner detection matching method is used to process the extracted particles, thereby completing the segmentation of sandstone thin section images. The experimental results show that our proposed method can more accurately fit the boundaries of mineral particles in sandstone images than existing image segmentation methods. Additionally, when applied in actual production scenarios, our method exhibits excellent performance, greatly improving thin section identification efficiency and significantly assisting experts in identification. 相似文献
16.
根据概率论的基本原理 ,分析了图形的矩表示法 ,利用七个不变矩作为图形的描述子 (特征量 ) ,提出基于七个不变矩及模糊神经网络的螺纹识别方法 ,采用了L M(Levenberg Marquardt)算法训练网络。七个不变矩可以作为一幅图形的特征量进行图像识别 ,模糊L MBP网络收敛较快。 相似文献
17.
基于遗传算法/神经网络组合技术的气液两相流型辨识 总被引:3,自引:1,他引:2
通过采用遗传算法训练BP神经网络、优化网络权值的技术,对气液两相流的流型进行了辨识研究,在此基础上建立了基于遗传算法/神经网络组合技术的气液两相流流型的预测模型,从而为发动机轴承腔内润滑油气液两相流流型识别提供了技术支持,也为考虑轴承腔气液两相流的相关设计和实验工作提供了技术条件。 相似文献
18.
Computerized tomography (CT) has been applied to multi-phase flow measurement in recent years. Image reconstruction of CT often involves repeatedly solving large-dimensional matrix equations, which are computationally expensive, especially for the case of on-line flow regime identification. In this paper, a minimum cross-entropy (MCE) reconstruction based on wavelet multi-resolution processing, i.e., an MRMCE method, is proposed for fast reconstruction of CT images. Each row of the system’s matrix is transformed by 1-D wavelet decomposition. A regularized MCE solution is obtained using the simultaneous multiplicative algebraic reconstruction technique (SMART) at a coarse resolution level, where important information of the reconstructed image is contained. Then the solution in the finest resolution is obtained by inverse fast wavelet transformation (IFWT). Both computer simulation and experimental work were carried out for oil-gas two-phase flow regimes. Results obtained indicate that the MRMCE method improves the resolution of the reconstructed images and dramatically reduces the computation time compared with the traditional linear back-projection (LBP), MCE and algebraic reconstruction technique (ART) methods. Furthermore, the new method can also be used to accurately estimate the local time-averaged void fraction of dynamic two-phase flow. It is suitable for on-line multi-phase flow measurement. 相似文献
19.
《Flow Measurement and Instrumentation》2005,16(2-3):135-144
Gas–solids flows in the risers of circulating fluidised beds (CFBs) and cyclones exhibit complex physical behaviour, such as local backflow and recirculation. The difficulties in accurate measurement of gas–solids flows stem from various flow regimes, which exist in multi-phase flows in pipelines and vessels. It is necessary to investigate the solids’ fraction profile, flow regime identification, image reconstruction, flow acceleration and flow velocity. Electrical capacitance tomography (ECT) is regarded to be a successful technology for imaging industrial processes containing dielectric materials. ECT would help understanding of gas–particle interaction, particle–boundary interaction and the influence of gas on the solids’ flow turbulence.The first part of this paper covers some new developments in ECT, i.e., algorithms for 3D image presentation and on-line iterative image reconstruction. The second part presents a novel non-intrusive technique for measuring axial and angular velocities. Theoretical and experimental studies, carried out using cross-correlation techniques in a cyclone separator dipleg, confirm the feasibility of on-line velocity measurement. Experimental results from various gas–solids flow facilities, CFB and cyclone, are presented. 相似文献