A New Algorithmic Approach for Detection and Identification of Vehicle Plate Numbers

This work proposes a method for the detection and identification of parked vehicles stationed. This technique composed many algorithms for the detection, localization, segmentation, extraction and recognition of number plates in images. It is acts of a technology of image processing used to identify the vehicles by their number plates. Knowing that we work on images whose level of gray is sampled with (120×180), resulting from a base of abundant data by PSA. We present two algorithms allowing the detection of the horizontal position of the vehicle: the classical method “horizontal gradients” and our approach “symmetrical method”. In fact, a car seen from the front presents a symmetry plan and by detecting its axis, that one finds its position in the image. A phase of localization is treated using the parameter MGD (Maximum Gradient Difference) which allows locating all the segments of text per horizontal scan. A specific technique of filtering, combining the method of symmetry and the localization by the MGD allows eliminating the blocks which don’t pass by the axis of symmetry and thus find the good block containing the number plate. Once we locate the plate, we use four algorithms that must be realized in order to allow our system to identify a license plate. The first algorithm is adjusting the intensity and the contrast of the image. The second algorithm is segmenting the characters on the plate using profile method. Then extracting and resizing the characters and finally recognizing them by means of optical character recogni-tion OCR. The efficiency of these algorithms is shown using a database of 350 images for the tests. We find a rate of lo-calization of 99.6% on a basis of 350 images with a rate of false alarms (wrong block text) of 0.88% by image.

基于深度学习的雾霾天气下的车牌号码识别方法

针对雾霾天气下车牌识别存在的精确度低、漏检等问题,提出了一种基于深度学习的雾霾天气下的车牌号码识别方法。首先用AOD-Net算法对车辆图像进行去雾预处理。然后,基于YOLOv5网络设计一种车牌检测网络ACG_YOLOv5s。ACG_YOLOv5s是在YOLOv5s网络的基础上,融入CBAM注意力机制,提高模型的抗干扰能力;引入自适应特征融合网络ASFF,根据模型自适应学习到的权重赋予网络不同特征层不同比重的权值,从而突出重要特征信息;使用Ghost卷积模块替换传统卷积,在保证模型效果的同时减少了网络训练过程中的参数量。最后通过LPRNet对检测到的车牌图像进行识别。实验结果表明,改进后的ACG_YOLOv5s网络车牌检测准确率达到99.6%,LPRNet识别准确率达96%且内存占比小。实验证明AOD-Net算法和YOLO算法结合可更加有效地检测雾霾天气下车牌图像中的车牌号码。

基于YOLOv8-OCR的井下人员检测算法

为提高井下昏暗环境的目标检测性能,将行人属性应用到井下,将反光号码牌贴在安全帽和工作服上作为属性进行识别。针对井下小目标检测率低的缺点,提出了一种将YOLOv8检测算法与光学字符识别(Optical Character Recognation, OCR)技术相结合的方法。通过添加卷积块注意力模块(Convolutional Block Attention Module, CBAM),提高了网络对不同尺度的特征提取能力;将YOLOv8中的CBS模块改进为CBF模块,提高了目标的识别准确率;对检测到的反光号码牌区域用OCR技术对区域内数字进行识别,进一步提高了模型的检测精度。实验结果表明,提出的方法在自建数据集上获得了93.2%的识别准确率和每张24.4 ms的检测速度,相比YOLOv8模型有着更高的准确率,能够有效地应对井下环境中的光照变化和干扰因素并且满足实时检测的要求。

平头孔板的初生空化特性定量分析

随着现代水利水电工程的日益优化创新,高坝设计中需要解决的重大技术瓶颈是消杀高坝泄放洪流所携带的超大能量。利用水流的突扩、突缩消能的孔板制造简便,并且消能效率高。孔板的抗空化特性跟它的最小壁面压强系数大小紧密相关,其作为孔板设计制造的一个关键性指标。通过数值模拟和物理模型试验的方法,研究了平头孔板初生空化数与相关体型要素和水力要素之间的关系,并得到了经验表达式。研究结果表明,平头孔板初生空化数的经验表达式与实际吻合较好,为孔板的工程应用提供了参考。

基于机器视觉的手写钢板号图像增强及矫正算法研究与应用

钢板号的正确识别检查是实现生产线自动化生产的重要基础条件之一。近年来,许多生产线在备料位置配备了喷印机用于自动标记物料编号。喷印的字迹清晰且耐高温,在没有涂抹的情况下使用钢板号识别设备可以实现接近100%的识别率。然而,由于喷印设备故障或受限于资金和空间等原因,有时无法安装喷印设备,只能依赖人工手写的方式在钢板表面标记编号。与喷印编号相比,手写编号存在书写随意、连笔、字迹歪斜扭曲等复杂情况,这些因素限制了识别系统的准确性。鉴于识别效果较差,通常需要依赖人工目测来辅助识别,从而影响了物料跟踪自动化的实施效果。为了提升手写钢板号的识别效果,对传统机器学习光学字符识别(OCR)文本区域检测算法进行改进研究,并针对手写钢板号的特征,提出一种图像增强和扭曲矫正处理的算法。应用结果表明,该算法可以改善手写钢板号的图像质量和形状,提高识别的准确性。该研究旨在提升手写钢板号识别效果,以解决自动化生产中的难题。通过图像增强和矫正处理,使识别系统更好地处理手写钢板号,推动物料跟踪的自动化实施。

基于板-梁理论的FGM双轴对称箱形截面组合扭转理论与有限元验证

基于板梁理论研究FGM双轴对称箱形截面组合扭转理论与有限元验证.首先,选取弹性模量变化函数,建立能量变分模型,引入无量纲参数,获得双轴对称箱形截面组合扭转的近似解析解;然后,利用微分方程模型计算双轴对称箱形截面组合扭转的精确解析解,给出微分方程解答;最后,利用ANSYS有限元分析软件进行验证,将本文研究所得解析解和ANSYS有限元分析软件得出的解析解进行对比,对比结果验证了本文理论推导及所给出的自由扭转刚度、约束扭转刚度表达式的正确性.

基于YOLOv7-Tiny的车牌及放大号检测研究

由于大型车辆的后车牌容易污损和遮挡,目前车牌号的识别对于这种情况有明显缺陷。提出将车牌放大号和车牌共同检测后再识别,提升车牌识别算法的适用性。本文基于YOLOv7-Tiny检测,算法先后采用更换主干网络和卷积模块实现模型轻量化,通过改进损失函数来提升精度。实验表明,在YOLOv7-Tiny更换Mobilenetv3主干网络、GSConv卷积核和Focal-EIoU后,实现模型体积下降35%,参数量下降37%,运算量下降58%,从而实现一种轻量化的模型。

催化裂解装置液化石油气分离系统脱丙烷方案优化

随着催化裂解装置裂解深度的增加,液化石油气中二烯烃含量增加。液化石油气分离常规流程中脱丙烷塔底温度约108℃,较高的温度增加了二烯烃聚合的可能性,影响装置运行周期和经济效益,国内几家催化裂解液化石油气分离装置的脱丙烷塔普遍存在塔釜和重沸器结焦堵塞的情况。在实际生产中为了缓解脱丙烷塔底结焦引起的停工等问题,通常在进料和塔底物料中加入阻聚剂,以降低物料聚合速率。文中分析了压力对脱丙烷体系相对挥发度和塔底温度的影响,得出较低的塔压有利于降低塔釜温度、提高轻重关键组分的相对挥发度,使分离更容易。塔压在0.9~1.1 MPa范围内较为合适,可将塔釜温度控制在80℃以下,在满足脱丙烷塔分离要求的前提下,减少因塔釜结焦造成的装置非计划停工。另外,文中从能耗和设备投资两方面对优化方案和常规方案进行了对比,优化方案能耗比常规方案降低约37%,主要设备投资也比常规方案低。

引力波探测中惯性传感器的残余气体动力学特性机理研究

作为空间引力波探测的核心系统,惯性传感器在轨运行时的噪声干扰诱发机制解析是迫切需要解决的关键科学问题。惯性传感器中检验质量(TM)的残余加速度噪声是限制探测器灵敏度的最大噪声源。作为残余气体噪声的直接表征手段,惯性传感器复杂拓扑构型下气体分子逃逸时间动态特性解析亟待解决。文章首先考虑了狭小空间下检验质量块与周围壁面间的材料属性、放气特性等差异性,建立了异质空间复杂拓扑结构下的惯性传感器数理模型;其次解析出残余气体噪声与气体分子逃逸时间之间的定量约束关系,提取了逃逸时间核心影响因素;随后以蒙特卡洛模拟技术为切入点,得到约束条件下气体分子从板间扩散出去所需的逃逸时间及碰撞次数的模拟解。文章研究发现:不同气体成分、壁面性质对残余气体噪声有较大影响;考虑气体分子在壁面的滞留时间会大幅增加逃逸时间、降低碰撞频率。

多级变孔径孔板装置水力特性研究

孔板消能装置具有结构简单、消能效率高和经济实用等优点,在水利工程中已得到广泛应用。本文以传统的多级等直径孔板消能装置为基础,构建了一种变孔径孔板消能装置,通过数值模拟对该装置在不同的收缩角、扭转角和雷诺数下空化特性和流场特性的变化情况进行了分析研究。结果表明:多级变孔径孔板的扭转角及收缩角对空化数沿程变化的影响不大,而雷诺数对空化数沿程变化的影响较大,并且空化数随雷诺数的增大而增大;在同一雷诺数及同一收缩角下,多级变孔径孔板扭转角越大,形成的螺旋流越明显;多级变孔径孔板的存在对管道内流体轴向、切向、径向速度大小与方向的影响较大,在变径孔板后形成四股强烈的螺旋状流束。

基于有限元法泥水盾构机刀盘的设计与优化

针对地层中复杂多变的软土环境,通过设计原理与仿真试验,提高了大泥水盾构机刀盘的强度与刚度。以盾构机刀盘为研究对象,建立辐条、辐板个数等因素为变量的刀盘三维结构模型,通过二次正交旋转试验确定辐条个数与辐板个数最优配比的刀盘。结果证明:当辐条个数为8个、辐板个数为8个时,质量指数为267250 kg,总变形指数为22.1 mm,应力指数为736.4 MPa,与优化结果基本一致,得到性能最优的刀盘。

平板计数法检测化妆品中需氧细菌总数的不确定度评估

文章将不确定度原理引入平板计数中,以测量需氧细菌总数检测过程中平皿计数法的检测误差。检测方法参照USP 2023<61>中的“非无菌产品微生物限度检查”,采用微生物计数法定量检测化妆品中的需氧细菌总数,并参照JJF1059.1-2012《测量不确定度评定与表示》中的要求,用需氧细菌总数对数值表示,通过评定需氧细菌总数检测中平皿计数法测量的不确定度,探讨平皿计数的检测误差[1]。结果表明,平皿法检测需氧菌总数的测量误差主要由A类评定的不确定度所致,而B类评定不确定度造成的误差可以忽略不计,因而据此得出可以扩展不确定度。研究所得的通过对需氧细菌总数检测中平皿计数结果的测量进行不确定度评定,可用于评估平皿计数法的检测误差[2]。

Experimental investigation of crossflow characteristics in multi-jets system at small nozzle-to-plate spacing

To further extend knowledge about the detailed knowledge on the crossflow characteristics in a multi-jets system under a confined space,particle image velocimetry (PIV) was employed to investigate the flow structures together with the distributions of the mean velocity components for Reynolds numbers (Re) ranging from 6 213 to 13 418,nozzle-to-plate spacing (H/D) varying from 0. 20 to1. 25,respectively. Results show that the crossflow configuration is significantly different from those of large nozzle-to-plate spacing. In addition,a turning point H/D=0.50 is revealed in the profile of the normalized maximum radial velocity which is associated with the heat transfer distribution on the impingement plate.

Effects of magnetohydrodynamic flow past a vertical plate with variable surface temperature

An analysis is performed to study the magnetohydrodynamic flow of an electrically conducting, viscous incompressible fluid past a semi-infinite vertical plate with variable surface temperature under the action of transversely applied magnetic field. The heat due to viscous dissipation and the induced magnetic field are assumed to be negligible. The dimensionless governing equations are unsteady, two-dimensional, coupled and non-linear governing equations. It is found that the magnetic field parameter has a retarding effect on the velocities of air and water.

Simulation and Experimental Study on Influence of Multi⁃port Integrated Hydraulic Transformer Port Number on Transformer Ratio Characteristics

The integrated hydraulic transformer has a compact structure and no throttling loss in the process of pressure regulation.It is widely used in the common pressure rail hydrostatic transmission system.The integrated hydraulic transformer is realized by designing more than three ports on the distribution plate,and the voltage transformation characteristics of the integrated hydraulic transformer with different port numbers are different.In this paper,the influence of port number on the pressure ratio of integrated hydraulic transformer was studied,and the pressure ratio characteristics of 3⁃ports,4⁃ports,and 5⁃ports integrated hydraulic transformer were obtained,and an experimental platform was built for experimental verification,which shows that the simulation results are consistent with the experimental results and provides a theoretical basis for the design of integrated hydraulic transformer.

The effect of multi-orifice plate configuration on bubble detachment volume

The multi-orifice plate gas sparger, mainly composed of a multi-orifice plate and a gas chamber, is one of the most common sparger facilities.The aeration performance of multi-orifice plate has a close relation with the multiorifice plate configuration.In addition, the weeping phenomenon has a considerable influence on the gas chamber condition which affects the bubble detachment volume directly.This paper conducts a set of visual experiments to study the influence of multi-orifice configuration and gas chamber condition on the aeration performance of gas sparger.For multi-orifice plate, an improved theoretical model is proposed which considers the wave effect of the previous bubbles generated from adjacent orifices and the variance of the number of active bubbling orifice.A parameter is proposed to evaluate the aeration performance in order to overcome the difficulty caused by the randomness of bubble formation process.The experimental results suggest that the gas chamber filled with water is in favor of large bubble formation.The influence of the pitch of orifice on aeration performance can only be observed in high-restricted case.According to the theoretical model and experimental results, the influences of gas flow rate and the number of open orifices on the aeration performance are analyzed and a design criterion for the number of open orifice is proposed.

Run-Up Flow of a Maxwell Fluid through a Parallel Plate Channel

We consider the flow of an incompressible viscous Maxwell fluid between two parallel plates, initially induced by a constant pressure gradient. The pressure gradient is withdrawn and the upper plate moves with a uniform velocity while the lower plate continues to be at rest. The arising flow is referred to as run-up flow. The unsteady governing equations are solved as initial value problem using Laplace transform technique. The expression for velocity, shear stresses on both plates and discharge are obtained. The behavior of the velocity, shear stresses and mass flux has been discussed in detail with respect to variations in different governing flow parameters and is presented through graphs.

CFD Simulations of Oscillating Flow around Solid and Perforated Plates

Damping plates have been used for truss spars in gulf of Mexico to reduce the heave motions. The plates are usually perforated with holes for the passage of marine risers, but the effects of the perforation have not been examined thoroughly. In the present study, a computational fluid dynamics investigation into the hydrodynamic forces is carried out by using FLUENT, which is on two-dimensional perforated plates with varying degrees of perforation in oscillating flow under small Keulegan-Carpenter (KC) number. The numerical results of the hydrodynamic coefficients are presented. The effects of both the perforation ratio (PR) and KC number on the hydrodynamic coefficients of the plates are discussed. Some results of the simulated flow patterns around the plates were also given and discussed.

Dufour Effects on Unsteady Hydromagnetic Radiative Fluid Flow past a Vertical Plate through Porous Medium

The objective of the present study is to investigate diffusion-thermo (Dufour effect) and radiation effects on unsteady MHD free convection flow past an impulsively started infinite vertical plate with variable temperature and uniform mass diffusion in the presence of transverse applied magnetic field through porous medium. At time t > 0, the plate is given an impulsive motion with constant velocity in the vertical upward direction against to the gravitational field. At the same time the plate temperature is raised linearly with time t and the level of concentration near the plate is raised to . A magnetic field of uniform strength is applied normal to the direction to the flow. The dimen- sionless governing equations are solved in closed form by Laplace-transform technique. The effect of flow parameters on velocity, temperature, concentration, the rate of heat transfer and the rate of mass transfer are shown through graphs.

基于深度学习的有遮挡车牌的识别方法研究

针对遮挡车牌图像中车牌识别存在的车牌号码识别不准确、识别准确率低等问题,提出一种车牌检测网络YOLOv5s_BCG和车牌识别网络CRNN_Den。在车牌检测网络中,使用BiFPN(BI-directional Feature Pyramid Network)替代原YOLOv5网络中的PANet结构,使网络能够自适应学习不同特征层的重要性权重;融入CBAM(Convolutional Block Attention Module)注意力机制,加强网络对关键特征信息的提取;使用Ghost卷积替换传统卷积降低参数量。在车牌识别网络中,用DenseNet模块替换CRNN(Convolutional Recurrent Neural Network)网络中的特征提取部分,实现特征重用,提升网络性能。实验结果表明,车牌检测网络YOLOv5s_BCG相较于原始YOLOv5网络mAP@0.5提升4.2%,可达99.1%。车牌识别网络CRNN_Den能达到94.35%的识别准确率。所提方法能够更加充分地提取车牌图像中的特征信息,可有效识别被遮挡车牌图像中的车牌号码。