Deep Learning Based Automatic Charging Identification and Positioning Method for Electric Vehicle

Electric vehicle charging identification and positioning is critically important to achieving automatic charging.In terms of the problem of automatic charging for electric vehicles,a dual recognition and positioning method based on deep learning is proposed.The method is divided into two parts:global recognition and localization and local recognition and localization.In the specific implementation process,the collected pictures of electric vehicle charging attitude are classified and labeled.It is trained with the improved YOLOv4 networkmodel and the corresponding detectionmodel is obtained.The contour of the electric vehicle is extracted by the BiSeNet semantic segmentation algorithm.The minimum external rectangle is used for positioning of the electric vehicle.Based on the location relationship between the charging port and the electric vehicle,the rough location information of the charging port is obtained.The automatic charging equipment moves to the vicinity of the charging port,and the camera near the charging gun collects pictures of the charging port.The model is detected by the Hough circle,the KM algorithmis used for featurematching,and the homography matrix is used to solve the attitude.The results show that the dual identification and location method based on the improved YOLOv4 algorithm proposed in this paper can accurately locate the charging port.The accuracy of the charging connection can reach 80%.It provides an effective way to solve the problems of automatic charging identification and positioning of electric vehicles and has strong engineering practical value.

A Dual Source Power Based EV Wireless Charging System

Recently,there has been a huge increase in the usage of fuel resources for automobiles which is severely affecting the climate and causing global warming.The use of electric vehicle(EV)is an effective way to protect the environment and reduce travel costs.However,the EV charging system has a single charging source,and the charging rate is limited.In this paper,an EV wireless charging system based on dual source power supply has been developed.It realizes intelligent switching between 12 V photovoltaic output and 220 V AC dual source power,and has wireless transmission function.Based on the proposed power supply architecture,the micro wireless charging model is built,which enables the EV model to store power and realize static and mobile control through the wireless induction charging system.

Automatic SOC Equalization Strategy of Energy Storage Units with DC Microgrid Bus Voltage Support

In this paper,an improved sag control strategy based on automatic SOC equalization is proposed to solve the problems of slow SOC equalization and excessive bus voltage fluctuation amplitude and offset caused by load and PV power variations in a stand-alone DC microgrid.The strategy includes primary and secondary control.Among them,the primary control suppresses the DC microgrid voltage fluctuation through the I and II section control,and the secondary control aims to correct the P-U curve of the energy storage system and the PV system,thus reducing the steady-state bus voltage excursion.The simulation results demonstrate that the proposed control strategy effectively achieves SOC balancing and enhances the immunity of bus voltage.The proposed strategy improves the voltage fluctuation suppression ability by approximately 39.4%and 43.1%under the PV power and load power fluctuation conditions,respectively.Furthermore,the steady-state deviation of the bus voltage,△U_(dc) is only 0.01–0.1 V,ensuring stable operation of the DC microgrid in fluctuating power environments.

Advanced Metering Infrastructure for Electric Vehicle Charging

The widely adoption of Electric Vehicle (EV) has been identified as a major challenge for future development of smart grids. The ever increasing electric vehicle charging further increases the energy demand. This paper reports the development of an Advanced Metering Infrastructure (AMI) as an effective tool to reshape the load profile of EV charging by adopting appropriate demand side management strategy. This paper presents a total solution for EV charging service platform (EVAMI) based on power line and internet communication. It must be stressed that the development of Third Party Customer Service Platform in this investigation facilitates a single bill to be issued to EV owners. Hence, EV owners understand their energy usage and thus may perform energy saving activity efficiently. Experiment and evaluation of the proposed system show that the throughput achieved is about 5 Mbps at 10 ms end to end delay in Power line Communication. By introducing two dimensional dynamic pricing and charging schedule, the proposed EVAMI successfully reduces 36% peak consumption and increases the “off peak” consumption by 54%. Therefore the EVAMI does not only reduce the peak consumption but also relocates the energy demand effectively.

Design and Application of Automatic Test System of Soil Water Characteristic Curve

[Objective] In order to better meet the requirement of crops on a more and more accurate water content under various planting environment of modern agri-culture, an automatic test system of soil water characteristic curve was designed by combining the conceptions of soil moisture content and soil water potential. [Method] Electronic soil moisture tension meter was used to determine the real-time tension value of soil moisture in the tested container, and the electronic Weigh sensor was used to determine soil Weigh. Minusing method was used to calculate soil moisture content, based on which the soil water characteristic curve was plotted. [Result] Through the filed survey of 2 different kinds of soil in Jiangsu Province, the results were as fol ows： soil of different composition showed different trend in soil water characteristic curve that the soil water characteristic relation of the sandy soil in the old course of the Yel ow River in Xuzhou was Y=-0.000 2X3＋0.027 7X2-1.644 5X＋38.161, R2=0.991 9; while the soil water characteristic relation of the saline-alkali soil in Jinhai Farm of Dafeng was Y=-0.00 2X2-0.426X＋39.905, R2=0.991 3. [Con-clusion] The automatic test system of soil water characteristic curve soil water char-acteristics curve could reflect soil moisture content and soil water potential, as wel as reflect the effectiveness of soil water to plant growth, providing basis for the sci-entific irrigation.

机车充风能力对重载列车缓解性能及车钩力影响研究

机车充气与排气性能是列车制动系统重要指标,目前机车制动系统验收指标仅对排气性能有明确要求,对充气性能无要求。机车供风能力不仅影响重载列车缓解特性和车钩力,而且严重制约重载列车在循环制动中的操纵方法。了解机车充气能力对缓解特性和车钩力的影响规律,以及重载列车安全运行和制动系统设计具有重要意义。通过建立列车空气制动系统仿真模型,分析机车充风能力对重载列车缓解特性和车钩力的影响。分析发现,机车充风能力对列车再充风时间、缓解波传播和车钩力都有明显影响;充风能力越弱,则缓解波传递越慢,车钩力越大。在本文研究范围内,合适的充气能力将比弱充风能力首尾车缓解时间差缩短3 s,最大车钩力降低16.2%。建议机车验收时增加机车充风能力检测,并给出了建议检测标准。针对重载列车充风能力,建议多部门联合系统性开展实验与仿真研究,制订重载列车制动系统检测标准与方法。

简易数字频率计的设计与仿真

简易数字频率计主要由前端采集处理模块、计数控制模块和显示模块组成。输入信号通过可调放大电路放大,有源低通滤波器滤波选频,电压比较器整形后,给计数控制模块计数,进行测频,并通过显示模块显示其测量频率的大小。仿真结果表明:该数字频率计实现了自动测频、自动清零、数据显示和保持功能,具有成本低,性价比高的优势。

基于改进DeepLabV3+的指针式仪表智能识别方法设计

针对现有仪表识别方法存在的诸如对表盘差异敏感、环境干扰严重以及图像质量依赖性强导致识别准确率不高的问题,提出了一种基于改进DeepLabV3+的指针式仪表智能识别算法。通过引入GhostNetV2作为主干网络进行特征提取,并添加注意力模块CBAM,有效提升了模型在仪表语义分割任务的精度;同时设计了多类仪表的示值识别算法,实现了对多类仪表的指针读数。通过在构建的指针式仪表识别数据集上对算法进行评估,结果表明,仪表智能识别算法能够适应多种仪表类型和复杂环境,识别准确率最高达99.67%,且改进的DeepLabV3+模型平均IoU达79.8%,性能优于原始模型,能够满足实际工业应用需求。

汽车衡全自动无接触计量的应用

鞍钢股份有限公司鲅鱼圈钢铁分公司汽车衡计量发展经历了手动计量、联网计量、自助计量到现在的全自动计量的发展过程,目前采用的全自动汽车衡的计量方式将整个称重流程进行了优化,称重速度显著提高,适应了日益增长的汽车衡称重需求。

基于卷积神经网络的燃气表信息自动识别方法研究

提出了一种基于改进的LeNet-5卷积神经网络的识别方法。通过加装摄像头和通信线路的方式,实时采集图像信息,并对图像进行部分预处理。引入Gabor滤波器、ReLU-Softplus函数、SVM分类器等优化传统LeNet-5模型,并根据图像数据的不均衡性,运用Grid Loss函数优化CNN网络,由此,实现燃气表自动化识别方法的构建。在Caffe深度学习框架下进行实验测评,结果表明该方法整体的识别准确性高达99.60%、整个样本集及单幅字码的训练总时间均优于其他识别方法,且对于不完整表码字的识别准确率也达到了99.21%。

基于STM32单片机的太阳能自动跟踪锂电池充电系统设计

随着经济全球化和世界经济的迅猛发展,人们对煤炭、石油等传统能源的需求越来越高,但该类资源不仅储藏有限,而且容易污染环境。与此同时,以太阳能为代表的新能源逐渐进入人们的视野。在此背景下,为进一步提高太阳能的利用率,文章提出一种基于STM32单片机的太阳能自动跟踪锂电池充电系统的设计方案,利用光照传感器采集四个方向的光照强度将其转换为电信号,通过AD转换将电信号转化为数字信号,再由STM32单片机进行数据处理分析,并根据四个方向的光照强度驱动电机旋转,使太阳能电池板与太阳光尽量保持垂直,最大限度提高太阳能的吸收效率。

立式金属储罐计量软件的开发与应用

随着我国经济高速发展,新建炼厂的建成投产及扩建项目的完成,国内炼油能力大幅提升,大宗化工品产量增多,化工品进出口规模逐年增大,贸易交接次数增多随之,因此要求储罐计量结果的准确性要大大提高,有助于进出口贸易的顺利交接。而传统的“手工计算”除了会增加工作量、效率会降低之外难免会出现差量等情况,会导致储罐计量结果的准确性大大降低,既浪费作业时间更不利于进出口贸易交接。为了解决“手工计算”带来的工作量大、效率低、准确性不高等不利因素,阐述了“自动计算”对于目前石油化工行业的必要性。通过对比“手工计算”不足,突出“自动计算”在研发和运用中的重要性,目的是以更加便捷、更加准确的理念提出此项研究。

考虑充电的多层级货架自动小车存取系统的资源配置优化

自动小车存取系统是近年来新兴的自动化物流技术,依托自动导引小车(AGV)和升降机的灵活配置,该系统具备较高的吞吐能力与柔性。随着物流需求的不断增长,如何在保持高效运作的同时,最小化系统的投资和能耗成本,成为亟待解决的问题。因此,提出最小化投资成本和平均任务能耗成本的优化目标,构建了以平均任务周期时间和平均空闲AGV数量为双重约束的随机非线性整数规划模型。模型考虑了AGV运行过程中能耗与充电情况的相互影响,并通过排队网模型来近似求解分析系统性能指标。同时为了进一步优化系统配置,将排队网模型的近似求解算法嵌入到启发式算法中进行求解,提升求解效率和解的质量。算例结果验证了所提方法的有效性和准确性,此外,敏感性分析结果为AGV和升降机的参数优化提供了有价值的参考,进一步验证了所提方法的适用性。

基于高增益观测器的火炮药协调臂位置控制

针对火炮协调输药机在协调过程中药协调臂运动到位精度不足的问题,提出了一种基于高增益观测器的火炮药协调臂自适应滑模控制策略,设计高增益观测器来估计火炮药协调臂伺服系统的未知状态并对其进行有效的在线跟踪和补偿,设计滑模控制器来消除所观测状态的误差,从而实现药协调臂机电伺服系统的快速高精度控制。针对滑模控制过程中出现的高频抖振现象,设计了一种自适应律并与滑模控制器相结合,从而极大地削弱了控制量的抖振。仿真实验结果表明,在输药机装满药的极端工况下,该控制策略能够大幅提高药协调臂的到位精度,具有较强的鲁棒性。

直流充电桩电能计量关键技术设计

针对当前直流(DC)充电桩电能计量存在计量效率低、误差大、电源纹波大、无法远程监控的问题,设计了充电桩计量电路。通过硬件乘法器级联原理实现三相交流有功功率的瞬时值硬件电路,能够快速获取交流(AC)有功功率在时域上输出的数据信息。将原始的多种信息输出变成单一的DC信号,为双通道模数转换器(ADC)同步测量提供了μs级别的AC有功功率信号。通过增量补偿控制输出模块对电网电压和实际输出电压的差值进行补偿,提高了充电桩测试电源的精度。DC充电桩能够远程无线通信,实现了多地区多客户端界面和现场操作终端界面的操作流程和数据的实时同步,大幅提升了DC充电桩电能计量能力。试验结果证明,该设计误差低、计量效率高。

扫地机器人的自动回充技术专利综述

【目的】梳理扫地机器人自动回充涉及的主要技术,为我国扫地机器人自动回充领域的创新发展提供参考。【方法】从国内、国外的专利申请人国家、主要申请人的分布等多方面对扫地机器人的自动回充技术进行全面的数据统计及分析。【结果】扫地机器人自动回充领域相关的专利的申请量不断上升,其中中国、韩国的申请量最大。【结论】国内外对该技术的研究已经相对较成熟,现阶段的改进点大多在于将已有的多种方式结合及分步骤地进行引导,提高自动回充的准确性、可靠性。

基于工艺设计的无线远传水表自动化装配设备研制

传统水表制造由人工装配完成,存在生产周期长、生产效率低、生产费用高等问题。分析了水表的结构组成和各零件之间的相互配合,以国内主流的无线远传水表为例,设计了一款由6个设备组成的自动化装配生产线。完成了生产线的整体布局和物料在各个设备之间的流转,经过现场安装和运行调试,实现了自动化生产装配线的可靠稳定运行。有效提高了生产效率和装配精度,适应企业产业升级的需求,为自动化生产装配线提供了设计新思路,具有实际借鉴意义。

光功率计功率校准能力扩展与自动校准系统的实现

光功率计是光通信网络中用于测量光功率的仪器。为了保证光功率计测量结果准确,必须对光功率计进行校准。现有计量检定规程适用于-80~27 dBm范围内光功率参数的检定和校准,为了满足大于27 dBm功率的校准并提高光功率计的校准效率,设计了一套光功率自动校准系统,并将光功率参数的校准能力扩展至34dBm。介绍了该系统的硬件组成、软件的设计思路和实现方法,并给出了不确定度评定结果。经过与中国计量科学研究院(NIM)的校准结果比较,该方法在提高校准效率的同时保证了校准结果的准确可靠。

基于P-V自动调节的活塞式气体流量装置研究

为研究超声波、热式燃气表在空气介质与天然气介质条件下的流量特性及差异,设计了一种基于压力-体积(P-V)自动调节的活塞式气体循环流量标准装置。介绍了装置基本架构、工作原理。分析了流体流动闭合回路中影响测量精度的原因。建立了实现定常流的P-V自动调节控制数学模型。该装置采用主动盘形活塞式流量标准器,体积扩展不确定度U r=0.07%;配置柱形活塞作为容积补偿,通过监测气体压力变化调节活塞运动方向及速度,以达到压力恒定的目的。装置配置了六表位工装台架,并设置最大工作压力为0.1 MPa、最大流量为10 m^(3)/h、量程比为1000∶1;通过测试六台G2.5超声波燃气表,得出压力波动小于5 Pa、流量稳定性优于0.02%。在流量测试领域,P-V自动调节方法可以为实现定常流提供新的解决思路。

新型电力系统场景下网侧规模化储能二次调频控制策略

针对大规模新能源并网时造成的新型电力系统频率波动问题,在新型电力系统场景下兼顾电网调频需求及储能调频能力提出一种网侧规模化储能二次调频控制策略。基于电网调频需求,对储能系统响应自动发电控制指令时的双信号自适应切换控制进行研究,在充分发挥两种调频信号优势的同时使储能系统更好地配合响应调频指令;考虑储能机组的技术特性,利用模糊控制对各储能单元的出力深度进行均衡控制,在维持其荷电状态的同时能够将频率偏差的波动以更快的速度控制在更小的范围内;最后在Matlab/Simulink中对所提控制策略进行仿真验证。结果表明,所提控制策略能够快速抑制频率偏差在更小的范围内、避免储能系统过充过放以及有效维持各组储能单元荷电水平。