基于改进麻雀搜索算法优化BN的变压器故障诊断研究

针对变压器故障诊断准确率低和稳定性差的问题,文中提出了一种改进麻雀搜索算法优化贝叶斯网络的变压器故障诊断方法。首先,通过计算互信息建立最大支撑树并进行定向处理得到贝叶斯网络初始结构即初始种群。然后,在算法中引入一种新的合作机制和正弦余弦算法,提高算法收敛速度和全局搜索能力,并利用油中溶解气体分析,创建基于改进麻雀搜索算法优化贝叶斯网络的变压器故障诊断模型。最后,为了证明所提方法的优越性,将所提的方法与现有变压器故障诊断方法进行对比。结果表明,文中所提出的方法故障诊断率最高,可以更精准地对变压器进行故障诊断。     

A matching game framework for users clustering and resource allocation with wireless power transfer in a CR-NOMA network

This paper investigates the resource allocation in a massively deployed user cognitive radio enabled non-orthogonal multiple access (CR-NOMA) network considering the downlink scenario. The system performance deteriorates with the number of users who are experiencing similar channel characteristics from the base station (BS) in NOMA. To address this challenge, we propose a framework for maximizing the system throughput that is based on one-to-one matching game theory integrated with the machine learning technique. The proposed approach is decomposed to solve users clustering and power allocation subproblems. The selection of optimal cluster heads (CHs) and their associated cluster members is based on Gale-Shapley matching game theoretical model with the application of Hungarian method. The CHs can harvest energy from the BS and transfer their surplus power to the primary user (PU) through wireless power transfer. In return, they are allowed to access the licensed band for secondary transmission. The power allocation to the users intended for power conservation at CHs is formulated as a probabilistic constraint, which is then solved by employing the support vector machine (SVM) algorithm. The simulation results demonstrate the efficacy of our proposed schemes that enable the CHs to transfer the residual power while ensuring maximum system throughput. The effects of different parameters on the performance are also studied.     

BP神经网络结合变量选择方法在牛奶蛋白质含量检测中的应用北大核心CSCD

牛奶中的蛋白质含量会影响牛奶的品质,利用高光谱图像的光谱特征信息研究对牛奶蛋白质含量预测的可行性。本文提出一种基于竞争性自适应重加权算法(competitive adaptive reweighted sampling, CARS)和连续投影算法(successive projections algorithm, SPA)结合多层前馈神经网络(back propagation, BP)的预测建模方法,实验以含有不同浓度蛋白质的牛奶为对象,利用可见光/近红外高光谱成像系统共采集到5种牛奶共计250组高光谱数据,通过实验对比选择采用标准化方法对获取到的吸收光谱预处理,然后采用CARS结合SPA筛选特征波长,得到18个特征波长,建立CARS-SPA-BP模型,经过试验,CARS-SPA-BP模型的训练集决定系数和测试集决定系数R;和R;分别达到0.971和0.968,训练集均方根误差(root mean square error of calibration,RMSEC)和测试集均方根误差(root mean square error of prediction,RMSEP)达到了0.033和0.034。研究发现,采用CARS结合SPA筛选的牛奶特征波长建立的多层前馈神经网络模型,其模型预测结果与全波长建模相比并没有明显降低,因此将CARS结合SPA用于波长筛选并且结合BP神经网络基本可以完成对牛奶蛋白质含量的预测。为验证CARS-SPA-BP模型的预测能力,在相同数据环境下,使用较为传统的偏最小二乘回归(partial least squares regression, PLSR)进行建模,实验结果表明,CARS-SPA-BP相较于PLSR,R;和RMSEP均有明显提升。研究表明,CARS-SPA-BP可充分利用牛奶光谱特征信息实现较高精度的牛奶蛋白质含量检测。     

一种实时多尺度目标检测识别算法

无人机目标检测与识别任务中,目标随着飞行高度的改变尺寸发生显著变化。常规目标检测模型中,获取的小目标细节信息有限,检测精度较低;而适用于小目标的实时检测模型往往容易丢失大目标的背景信息,降低大目标的检测精度。针对以上多尺度目标检测识别任务难点,提出一种基于改进特征金字塔网络(Feature Pyramid Network, FPN)结构的实时多尺度目标检测识别模型。该模型通过增加特征金字塔层级覆盖更广的目标尺度,获取更为丰富的目标信息;同时,利用跨连接增加不同尺度特征融合的多样性,降低特征传导距离,保留更加完整的尺度特征来提高模型检测识别多尺度目标的性能。通过实验发现,相比于原始网络结构和相同特征层级的四层特征金字塔结构,加入改进特征金字塔结构的多尺度目标检测模型识别性能得到了提升。     

太赫兹网络中基于中继协作转发的高效双信道MAC协议

针对现有多输入多输出(Multiple-Input Multiple-Output, MIMO)太赫兹通信网络双信道MAC协议存在波束重叠干扰和冗余控制开销等问题,提出了一种太赫兹网络中基于中继协作转发的双信道MAC协议(High Efficiency Dual channel MAC Protocol Based on Relay Cooperative Forwarding in Terahertz Networks, HE-RCFMAC)。HE-RCFMAC协议包含动态帧聚合、基于位置信息自适应协作转发和精简RTS(Request To Send)/CTS(Clear To Send)帧三种机制。经三种机制处理后,可有效提升信道利用率,同时减小控制开销,提高数据传输成功率和整体网络吞吐量。仿真结果表明,所提协议与现有的MIMO太赫兹双信道MAC协议相比,MAC层吞吐量、数据传输成功率和信道利用率分别提升了12.82%、12.28%和8.73%,证明了所提协议的有效性。     

A hybrid disturbance observer for delivery drone’s oscillation suppression

This paper proposes a new hybrid disturbance observer (DOB) to help suppress disturbance to the control systems. The proposed hybrid DOB consists of three main parts: (1) an actual system, (2) a simulated system, and (3) a learning filter that connects the actual and simulated systems. The simulated system aims to replicate the actual system response, where it leverages a neural network model to predict the input disturbance and generate the predicted system response. Such system response is used to generate a learning signal through a learning filter; this learning signal is then added to the feedforward loop of the estimation framework to enhance the disturbance estimate and its suppression performance for the actual system. The proposed hybrid DOB is designed to advance the standard DOB structure with a learning-based feedforward compensation. While the proposed method does not modify the baseline controller, it is well suited to systems whose baseline controllers are difficult or impossible to be changed. Considering the delivery drones are subject to oscillations when dropping payloads, experimental tests with multiple payload dropping scenarios have been conducted using both the hybrid and standard DOB, where the compared results validate the effectiveness and advantages of the proposed hybrid DOB.     

基于深度学习和灰度纹理特征的铁路接触网绝缘子状态检测

铁路接触网绝缘子状态检测对铁路行车安全有着 重大的意义,为解决目前人工对绝缘 子图像检测结果的不确定性,提出一种深度学习结合灰度纹理特征的检测方法。首先使用 Faster R-CNN (faster region-based convolutional neural network)目标检测算法对图像中绝缘子精确识别,再通过灰度共生矩阵对绝缘子纹理 特征进行分析提取,之后结合支持向量机将绝缘子分为正常绝缘子和异常绝缘子,实验数 据结果证明使用能量、熵、相关度3种纹理特征进行绝缘子状态分类时对实验数据中的正 常状态绝缘子的分类精度可达100%,异常状态绝缘子的分类精度达97.5%,最后依据绝缘 子图像灰度分布的周期性特点,利用灰度积分投影将异常绝缘子分为破损绝缘子和夹杂异 物绝缘子。实验结果表明所提方法可以有效对绝缘子状态进行检测分类。     

基于多尺度特征选择性融合的遥感图像检测算法北大核心CSCD

遥感图像的检测在监察自然环境、军事、国土安全等方面具有极其广阔的应用前景,而遥感图像具有背景复杂、目标面积小、特征提取困难等缺点,进行检测时容易产生小目标漏检问题。本文提出一种基于多尺度特征选择性融合的遥感图像检测算法。所提算法采用改进的Resnet50作为主干网络,将Resnet50第一个卷积替换成动态卷积,并将其ConvBlock模块中的卷积替换成金字塔卷积,提高特征提取能力。同时,为了避免遗漏底层信息,在动态卷积层后加入所提有效空间通道注意力机制模块。最后,选取基于上下文信息的不同尺度特征进行融合,提高了模型对目标物体的定位能力。实验结果表明,本文算法在保证速度的同时提高了对遥感图像的检测精度,在遥感图像公开数据集RSOD和NWPUVHR-10上平均精度均值(mean average precision,mAP)分别达到91.88%和90.23%,检测速度达到33 FPS。     

基于拓扑链路识别的光网络流量数据合成算法

基于深度学习的光网络流量诊断与预测等场景中,由于保密等原因,光链路的流量数据采集和存储工作受限。针对数据量少而无法支撑深度学习的问题,文章提出了一种基于拓扑链路识别的光网络流量数据合成算法,其核心思想是在生成对抗网络框架下,联合基于光网络拓扑的条件生成模型和基于光网络流量的数据合成模型,以自监督的方式合成指定光链路的流量数据。仿真结果表明,所提算法合成的光网络流量数据在自相关系数指标上与真实数据接近且使得基于全连接神经网络的流量预测模型准确率达到95%以上。     

Multi-scale fusion residual encoder-decoder approach for low illumination image enhancement

The sensing light source of the line scan camera cannot be fully exposed in a low light environment due to the extremely small number of photons and high noise, which leads to a reduction in image quality. A multi-scale fusion residual encoder-decoder (FRED) was proposed to solve the problem. By directly learning the end-to-end mapping between light and dark images, FRED can enhance the image's brightness with the details and colors of the original image fully restored. A residual block (RB) was added to the network structure to increase feature diversity and speed up network training. Moreover, the addition of a dense context feature aggregation module (DCFAM) made up for the deficiency of spatial information in the deep network by aggregating the context's global multi-scale features. The experimental results show that the FRED is superior to most other algorithms in visual effect and quantitative evaluation of peak signa-to-noise ratio (PSNR) and structural similarity index measure (SSIM). For the factor that FRED can restore the brightness of images while representing the edge and color of the image effectively, a satisfactory visual quality is obtained under the enhancement of low-light.