Model Predictive Control for Cascaded H-Bridge PV Inverter with Capacitor Voltage Balance

We designed an improved direct-current capacitor voltage balancing control model predictive control(MPC)for single-phase cascaded H-bridge multilevel photovoltaic(PV)inverters.Compared with conventional voltage balanc-ing control methods,the method proposed could make the PV strings of each submodule operate at their maximum power point by independent capacitor voltage control.Besides,the predicted and reference value of the grid-connected current was obtained according to the maximum power output of the maximum power point tracking.A cost function was con-structed to achieve the high-precision grid-connected control of the CHB inverter.Finally,the effectiveness of the proposed control method was verified through a semi-physical simulation platform with three submodules.

基于改进Cascade R-CNN算法的船舶目标检测方法

为了解决实际场景下船舶目标检测精度低的问题,本文在Cascade R-CNN算法的基础上,提出一种船舶目标检测方法 Boat R-CNN。Boat R-CNN使用带自注意力机制的Swin-Transformer Tiny网络提取图像特征,使用Soft-NMS非极大值抑制方法提升候选框过滤精度,使用Smooth_L1损失函数加速模型收敛并减少梯度爆炸情况,使用CIOU边界框回归损失提高候选框回归质量,并针对船舶目标的形状特征优化锚框的长宽比,提高锚框的生成质量。实验结果表明,Boat R-CNN算法的精度相比原版Cascade R-CNN算法提高了21.8%,相比主流Faster R-CNN算法提高了30.3%,有效提升了实际场景下的船舶目标检测精度。

基于改进Cascade R-CNN的安全帽检测算法

针对安全帽检测中,目标形状、尺度变化大,易出现漏检、误检等问题,提出了一种基于改进级联基于区域的卷积神经网络(Cascade R-CNN)的安全帽检测算法。首先,对ResNet50进行改进形成D-ResNet50,利用可变形卷积仅增加少量参数就可增大感受野的特性,对特征提取网络的C2~C5卷积层进行重塑,提高网络对目标几何变换的适应能力和特征提取能力。其次,将D-ResNet50作为主干网络引入Cascade R-CNN,形成级联目标检测器,在每个阶段对正负样本重采样,抑制误检问题。再次,对递归特征金字塔进行改进,更高效地进行多尺度特征融合,并且基于反馈信息对特征进行二次处理,增强特征表达,提高网络的分类和定位能力。最后,使用Soft-非极大值抑制(Soft-NMS)进行后处理,进一步解决漏检问题。提出的方法在Hard hat workers数据集上的AP值相比检测基线提高了3.5%,与Sparse R-CNN、TridentNet、VFnet等先进算法相比分别提升了4.7%、5.9%、2.3%等。

Pluggable multitask diffractive neural networks based on cascaded metasurfaces

Optical neural networks have significant advantages in terms of power consumption,parallelism,and high computing speed,which has intrigued extensive attention in both academic and engineering communities.It has been considered as one of the powerful tools in promoting the fields of imaging processing and object recognition.However,the existing optical system architecture cannot be reconstructed to the realization of multi-functional artificial intelligence systems simultaneously.To push the development of this issue,we propose the pluggable diffractive neural networks(P-DNN),a general paradigm resorting to the cascaded metasurfaces,which can be applied to recognize various tasks by switching internal plug-ins.As the proof-of-principle,the recognition functions of six types of handwritten digits and six types of fashions are numerical simulated and experimental demonstrated at near-infrared regimes.Encouragingly,the proposed paradigm not only improves the flexibility of the optical neural networks but paves the new route for achieving high-speed,low-power and versatile artificial intelligence systems.

基于Local Cascade Ensemble方法的胎儿健康自动分类

为更好地自动评估胎儿宫内状态,提出一种基于local cascade ensemble(LCE)方法的胎儿健康状态分类模型。选用UCI数据集,使用ADASYN方法对不平衡数据集进行填充平衡,接着结合随机森林算法对数据特征进行选择,最后使用LCE方法对胎儿状态进行自动分类。实验结果表明,所提出模型使用的方法平均准确率、精确率、召回率和F1分数分别达到了0.9554、0.9054、0.9557和0.9290,对比传统的机器学习算法能得到更好的分类效果,有效降低了误判率。

Phase-locked single-mode terahertz quantum cascade lasers array

We demonstrated a scheme of phase-locked terahertz quantum cascade lasers(THz QCLs)array,with a single-mode pulse power of 108 mW at 13 K.The device utilizes a Talbot cavity to achieve phase locking among five ridge lasers with first-order buried distributed feedback(DFB)grating,resulting in nearly five times amplification of the single-mode power.Due to the optimum length of Talbot cavity depends on wavelength,the combination of Talbot cavity with the DFB grating leads to better power amplification than the combination with multimode Fabry-Perot(F-P)cavities.The Talbot cavity facet reflects light back to the ridge array direction and achieves self-imaging in the array,enabling phase-locked operation of ridges.We set the spacing between adjacent elements to be 220μm,much larger than the free-space wavelength,ensuring the operation of the fundamental supermode throughout the laser's dynamic range and obtaining a high-brightness far-field distribution.This scheme provides a new approach for enhancing the single-mode power of THz QCLs.

Multi-dimensional multiplexing optical secret sharing framework with cascaded liquid crystal holograms

Secret sharing is a promising technology for information encryption by splitting the secret information into different shares.However,the traditional scheme suffers from information leakage in decryption process since the amount of available information channels is limited.Herein,we propose and demonstrate an optical secret sharing framework based on the multi-dimensional multiplexing liquid crystal(LC)holograms.The LC holograms are used as spatially separated shares to carry secret images.The polarization of the incident light and the distance between different shares are served as secret keys,which can significantly improve the information security and capacity.Besides,the decryption condition is also restricted by the applied external voltage due to the variant diffraction efficiency,which further increases the information security.In implementation,an artificial neural network(ANN)model is developed to carefully design the phase distribution of each LC hologram.With the advantage of high security,high capacity and simple configuration,our optical secret sharing framework has great potentials in optical encryption and dynamic holographic display.

A distributed VSG control method for a battery energy storage system with a cascaded H-bridge in a grid-connected mode

With the high penetration of renewable energy,new challenges,such as power fluctuation suppression and inertial support capability,have arisen in the power sector.Battery energy storage systems play an essential role in renewable energy integration.In this paper,a distributed virtual synchronous generator(VSG)control method for a battery energy storage system(BESS)with a cascaded H-bridge converter in a grid-connected mode is proposed.The VSG is developed without communication dependence,and state-of-charge(SOC)balancing control is achieved using the distributed average algorithm.Owing to the low varying speed of SOC,the bandwidth of the distributed communication networks is extremely slow,which decreases the cost.Therefore,the proposed method can simultaneously provide inertial support and accurate SOC balancing.The stability is also proved using root locus analysis.Finally,simulations under different conditions are carried out to verify the effectiveness of the proposed method.

THD Analysis of Cascaded H-Bridge Inverter with Fuzzy Logic Controller

In recent days, the multilevel inverter technology is widely applied to domestic and industrial applications for medium voltage conversion. But, the power quality issues of the multilevel inverter limit the usage of much sensitive equipment like medical instruments. The lower distortion level of the output voltage and current can generate a quality sinusoidal output voltage in inverters and they can be used for many applications. The harmonics can cause major problems in equipments due to the nonlinear loads connected with the power system. So, it is necessary to minimize the losses to raise its overall efficiency. In this paper, a new topology of seven level asymmetrical cascaded H-bridge multilevel inverter with a Fuzzy logic controller had been implemented to reduce the Total Harmonic Distortion (THD) and to improve the overall performance of the inverter. The proposed model is well suited for use with a solar PV application. In this topology, only six IGBT switches are used with three different voltage ratings of PV modules (1:2:4). The lower number of semiconductor switches leads to minimizing overall di/dt ratings and voltage stress on each switches and switching losses. The gate pulses generated by Sinusoidal Pulse Width Modulation (SPWM) technique with a Fuzzy logic controller are also introduced. A buck-boost converter is used to maintain the constant PV voltage level integrated by an MPPT technique followed by Perturb and Observer algorithm is also implemented. The MPPT is used to harness the maximum power of solar radiations under its various climatic conditions. The new topology is evaluated by a Matlab/Simulink model and compared with a hardware model. The results proved that the THD achieved by this topology is 1.66% and realized that it meets the IEEE harmonic standards.

改进的Cascade R-CNN算法在目标检测上的应用

针对Cascade R-CNN目标检测算法中存在检测精度较低以及目标遮挡问题,本文提出一种改进的Cas-cade R-CNN网络目标检测算法.该算法在主干网络ResNet101中引入可切换空洞卷积模块(Switchable Atrous Convolu-tion,SAC),该模块主要由两个全局上下文模块以及SAC组件构成,采用SAC组件以不同的空洞卷积率对特征进行卷积,并使用Switch函数收集特征来提高特征提取能力.同时,在ResNet101残差网络中引入坐标注意力机制(Coordi-nate Attention,CA),该机制将位置信息嵌入通道注意力中,用于更好地获取方向感知和位置感知信息,进而提高目标检测精度.此外,针对目标遮挡问题,引入Repulsion Loss损失函数.该损失函数主要由吸引项和排斥项组成,吸引项使得预测框和匹配上的目标框尽可能接近,排斥项使得预测框远离错误目标,进而减少非极大值抑制(Non-Maximum Suppression,NMS)的误检,提高目标检测中遮挡问题的检测精度.实验结果表明,在公开的科大讯飞AI挑战赛数据集上,与原算法测试性能相比,改进的Cascade R-CNN网络对该数据集检出率增长了2.39%,改进算法的识别精度有一定的提高.

基于改进Cascade RCNN的输电线路防振锤脱落检测方法

无人机巡检输电线路时,因拍摄角度和距离问题,容易出现被输电线遮挡和远距离拍摄的防振锤脱落目标,导致目标特征被遮挡且分辨率较低,且部分防振锤出现滑移现象,导致目标识别准确率降低。针对以上问题,提出一种基于改进Cascade RCNN的防振锤脱落检测网络。第一,设计了对比学习网络,将正负样本与真实样本的特征进行对比学习,利用对比损失函数训练网络,使其能更加关注到被遮挡的防振锤脱落目标,提升其特征提取能力;第二,进行了分类器增强操作,筛选出网络级联结构中回归效果较好的感兴趣区域并送入最后的分类回归队列中,提高了分类器的分类能力,进而提升检测目标的分类分数;第三,设计了并行注意力机制模块,整合网络提取的特征,增大关键特征的权重,使网络关注到图像中更关键的区域;在特征金字塔中,将双线性插值方法代替为反卷积,提升特征还原能力。经交叉验证实验结果表明,改进后的模型召回率、精确率和平均精度达到了97.5%,91.0%和92.0%,相比基线模型分别提高了6.9%,28.4%和8.0%。

基于改进Cascade R-CNN的探地雷达管线目标检测

针对人工识别探地雷达管线图像时效率低、误差大和成本高昂等问题,本文提出了一种基于改进Cascade R-CNN的管线目标智能化检测方法.首先对探地雷达管线图像数据集进行预处理,提升数据质量.然后采用ResNeXt代替ResNet作为主干网络提取目标特征信息,并添加多尺度特征融合模块FPN使高层特征向低层特征融合,增强低层特征表达能力.其次,使用高斯形式的非极大值抑制方法Soft-NMS得到更加精准的候选框,使用Smooth_L1作为损失函数,加速了模型收敛并且降低了训练中发生梯度爆炸的概率.最后,对于管线目标特殊的形状特征,设置合适的锚框长宽比和大小,提高锚框的生成质量.实验结果表明,本文方法解决了复杂特征的地下管线目标智能化检测,对地下管线目标检测的平均精度达到94.7%,比Cascade R-CNN方法提高了10.1%.

基于改进Cascade R-CNN的绝缘子故障检测方法研究

针对航拍图中存在的绝缘子故障位置在图像中占比小、背景环境复杂导致的故障检测准确率低的问题,提出一种基于改进Cascade R-CNN模型的绝缘子故障检测方法。在原有Cascade R-CNN模型的基础上,在骨干网络中引入可变形卷积学习几何变换能力,在检测器中引入平衡损失函数平衡难易样本。在模型训练阶段,使用Copy-Paste与Mosica丰富故障绝缘子样本,平衡正负样本。使用该模型对航拍绝缘子图片进行故障检测实验,改进损失函数的模型与传统Cascade R-CNN模型相比平均召回率提升0.38%,引入可变卷积后的Cascade R-CNN模型与Faster R-CNN模型,相比平均召回率,从原来的89.78%变成93.49%,结果表明该模型能够有效克服样本遮挡以及样本不平衡的干扰。

基于Cascade R-CNN的玉米幼苗检测

准确识别玉米幼苗是实现自动化精准除草、间苗、补种等苗期作业的重要前提。为此,针对自然环境下农业机器人对玉米幼苗的检测问题,结合深度残差网络强大的特征提取能力和级联网络连接多个检测器不断优化预测结果的特点,对Cascade R-CNN模型进行改进,使之适用于自然环境下玉米幼苗的检测。模型使用残差网络ResNet-50与特征金字塔网络FPN作为特征提取器提取玉米幼苗图像的特征图,利用区域建议网络生成目标候选框,通过感兴趣区域池化将不同大小的特征图转换为统一尺寸的输出;最后,分类回归模块根据特征图对目标进行分类,并使用边框回归修正候选框的位置和大小,从而完成玉米幼苗目标检测。同时,以3~5叶期玉米幼苗为研究对象,采集其田间图像并制作数据集,用所制作的数据集对Cascade R-CNN模型进行训练,选取AlexNet、VGG16、ResNet18、ResNet50与ResNet50+FPN分别作为特征提取网络进行对比试验,确定所提出的ResNet50+FPN为最优特征提取网络,平均精度均值(mAP)为91.76%,平均检测时间为6.5ms。选取双阶段目标检测模型Faster R-CNN、R-FCN、CoupleNet与以ResNet50+FPN为特征提取网络的Cascade R-CNN进行对比实验,结果表明:Cascade R-CNN模型检测效果最佳、速度最快,且能对自然环境下的玉米幼苗进行有效检测,可为玉米苗期自动化精准作业提供技术支持。

基于改进Cascade R-CNN模型的机器人抓取检测研究

为提高多物体抓取检测网络的抓取检测准确率,提出一种基于改进Cascade R-CNN模型的机械臂抓取检测算法.首先,引入ResNeXt结构能够在不加大网络设计难度的前提下提高了模型的准确率;引入带空洞卷积的空间金字塔池化模块以解决分辨率较低的问题;接着对抓取框回归分支和角度分类分支以分治方法进行优化.其次,针对多物体抓取数据集缺乏的问题,构建多目标抓取数据集(multi-object grasping dataset,MOGD),有效地扩充了多物体抓取检测数据集.最后,基于改进Cascade R-CNN模型设计抓取检测网络,实验结果表明,改进后的算法效率更高,PI-Cascade R-CNN实验准确率为93%,较Cascade R-CNN提升1.5个百分点.

基于改进Cascade R-CNN的布匹瑕疵检测算法

布匹瑕疵的自动化检测是目前纺织行业面临的一个难点问题。针对当前布匹瑕疵检测算法对尺度和长宽比变化大、小目标众多的样本检测效果并不理想的问题,提出了基于改进Cascade R-CNN网络的布匹瑕疵检测算法。首先,在特征提取网络ResNet-50中融入可变形卷积,自适应地提取更多的瑕疵形状与尺度特征;其次,在特征金字塔网络上采样前引入平衡特征金字塔,缩小特征融合前各特征层之间的语义差距,得到更具表达力的多尺度特征;然后,根据瑕疵尺度与长宽比特点重新设计更适合的初始锚框;最后,采用具有尺度不变性的GIoU Loss作为级联检测器的回归损失,以获取更加精确的瑕疵预测边界框。实验结果表明,相比基于Cascade R-CNN的算法,改进后的Cascade R-CNN算法对布匹瑕疵检测的平均精确率获得了明显提升。

基于Cascade R⁃CNN改进的PCB瑕疵检测方法

由于印刷电路板(PCB)的集成度、线路复杂性以及其产量的日益增加,针对PCB的瑕疵检测已成为关键的检测任务。传统检测方法存在误检率较大、检测速度较慢、能够检测出的瑕疵类型较少等问题,而常用的基于深度学习的目标检测模型计算量庞大,难以应用到工业场景中算力较弱的边缘设备。为了减少算法参数量和计算量,在Cascade R⁃CNN基础上改进网络结构,提出将ResNeSt作为主干网络,颈部网络采用路径聚合特征金字塔网络(PAFPN),增加对小目标PCB瑕疵的定位精度。将使用多尺度训练方法训练出的高性能改进Cascade R⁃CNN模型作为教师模型,再通过使用重点与全局知识蒸馏算法,将教师模型知识蒸馏在主干轻量化的MobileNetV3学生模型中,在提升模型精度的同时,缓解模型参数量和计算量过大的问题。在PCB Defect数据集上,改进模型相较原Cascade R⁃CNN模型,在IoU=0.5时,mAP提高了17.0%,推理速度提高3.5 FPS,参数量缩小了28.2%,计算量减少了27.3%。

基于Open CASCADE的弯管参数提取与建模系统研发

为解决自动化弯管CAD/CAM系统中弯管数字化模型到加工坐标参数之间的转换问题,提出了基于Open CASCADE的弯管参数提取与参数化建模的方法。通过开源三维几何引擎Open CASCADE读取弯管数字化模型并提取弯管的几何参数信息,然后通过弯管几何参数信息到加工坐标参数的转换方法获得弯管加工坐标参数。根据弯管加工原理通过弯管加工坐标参数使用Open CASCADE来建立弯管数字化模型。根据以上参数提取和参数化建模方法,开发了弯管参数提取与参数化建模软件系统,实现了弯管数字化模型与加工坐标参数的相互转换。该系统能应用于弯管的设计与制造过程,为实现自动化弯管CAD/CAM系统奠定了基础。

基于Cascade RCNN的热轧带钢表面缺陷检测

在工业生产过程中,带钢表面产生的缺陷影响其质量和使用性能,需要对表面缺陷进行检测,为此提出了基于深度学习的缺陷检测模型Cascade RCNN。首先,对骨干网络进行改进,将标准卷积替换为可切换空洞卷积,在不增加参数量的情况下,增大输出单元的感受野。其次,改变特征金字塔FPN,结构不变的情况下添加了自上而下的连接方式,同时使用特征上采样算子CARAFE替换最邻近上采样,提高了上采样精度和定位精度。最后,将损失函数换为Focal Loss,解决目标检测过程中正负样本不平衡问题。结果显示:通过以上方法的改进,检测精度有大幅提升,平均均值精度提高了7.61%,达到77.82%,各类缺陷的检测精度都得到了提高;与其他检测模型对比,模型的检测能力得到了提高,采用的改进方法有一定的应用价值。