Flux-measuring approach of high temperature metal liquid based on BP neural networks

A soft-measuring approach is presented to measure the flux of liquid zinc with high temperature andcausticity. By constructing mathematical model based on neural networks, weighing the mass of liquid zinc, the fluxof liquid zinc is acquired indirectly, the measuring on line and flux control are realized. Simulation results and indus-trial practice demonstrate that the relative error between the estimated flux value and practical measured flux value islower than 1.5%, meeting the need of industrial process.

Quantitative Interpretation for the Magnetic Flux Leakage Testing Data Based on Neural Network

In order to interpret the magnetic flux leakage (MFL) testing data quantitatively and size the defects accurately, some defect profiles inversion methods from the MFL signals are studied on the basis of the neural network.Because the wavelet ba- sis function neural network (WBFNN) has good accuracy in the forward calculation and the radial basis function neural network (RBFNN) has reliable precision in the inversion modeling respectively,a new neural network scheme combining WBFNN and RBFNN is presented to solve the nonlinear inversion problem for the MFL data and reconstruct the defect shapes.And such details as the choice of wavelet basis function,the initialization of the weight value and the input normalization are analyzed,the train- ing and testing algorithm for the network are also studied.The inversion results demonstrate that the proposed network scheme has good reliability to interpret the MFL data for some defects.

Predicting the composition of flux-cored wire claded metal by a neural network

In this paper, an artificial neural network method that can predict the chemical composition of deposited weld metal by CO 2 Shielded Flux Cored Wire Surfacing was studied. It is found that artificial neural network is a good approach on studying welding metallurgy processes that cannot be described by conventional mathematical methods. In the same time we explored a new way to study the no equilibrium welding metallurgy processes.

A thermal flux-diffusing model for complex networks and its applications in community structure detection

We introduce a thermal flux-diffusing model for complex networks. Based on this model, we propose a physical method to detect the communities in the complex networks. The method allows us to obtain the temperature distribution of nodes in time that scales linearly with the network size. Then, the local community enclosing a given node can be easily detected for the reason that the dense connections in the local communities lead to the temperatures of nodes in the same community being close to each other. The community structure of a network can be recursively detected by randomly choosing the nodes outside the detected local communities. In the experiments, we apply our method to a set of benchmarking networks with known pre-determined community structures. The experiment results show that our method has higher accuracy and precision than most existing globe methods and is better than the other existing local methods in the selection of the initial node. Finally. several real-world networks are investigated.

Study on limited-flux coefficient to achieve spare transportation of heat-supply network

Limited-heating is one of the heating statuses which can meet the reliability requirement of those uninterrupted heat-users under the accidental status of heat-supply network.It requires the network to be provided with both ability of spare-structure and spare-transportation,and the later one is depended on the limited-flux coefficient.This paper investigates the relationship between the limited-flux coefficient and limited-heating coefficient of indirect connection system.The optimal value of the limited-flux coefficient is presented as well.

YASA轴向磁通永磁电机定子槽漏感计算

定子槽漏感是定子无轭模块化(yokeless and segmented,YASA)轴向磁通永磁电机电感的主要分量,会降低电机的功率因数和最大输出转矩。该文提出定子槽内微小单元磁场能量法计算YASA电机的定子槽漏感,通过建立计及铁心饱和影响的二维等效磁网络模型准确计算槽内微小单元储存的磁场能量,进而计算定子槽漏感。基于所提出的方法,进一步研究定子结构参数以及极槽配合对YASA电机定子槽漏感的影响规律。有限元仿真和实验结果表明,该文所提出的YASA电机定子槽漏感计算方法的可行性和准确性。

Real-Time Traffic State and Boundary Flux Estimation with Distributed Speed Detecting Networks

The rapid development of 5G mobile communication and portable traffic detection technologies enhances highway transportation systems in detail and at a vehicle level. Besides the advantage of no disturbance to the regular traffic operation, these ubiquitous sensing technologies have the potential for unprecedented data collection at any temporal and spatial position. While as a typical distributed parameter system, the freeway traffic dynamics are determined by the current system states and the boundary traffic demand-supply. Using the three-step extended Kalman filtering, this paper simultaneously estimates the real-time traffic state and the boundary flux of freeway traffic with the distributed speed detector networks organized at any location of interest. In order to assess the effectiveness of the proposed approach, a freeway segment from Interstate 80 East (I-80E) in Alameda, Emeryville, and Northern California is selected. Experimental results show that the proposed method has the potential of using only speed detecting data to monitor the state of urban freeway transportation systems without access to the traditional measurement data, such as the boundary flows.

一种融合字词双通道的Domain-Flux僵尸网络检测方法

Domain-Flux是僵尸网络中常用的一种命令与控制信道隐蔽技术,其能有效躲避网络安全设备的检测。针对现有检测方法中对Domain-Flux域名信息提取不全面,无法有效捕获词典类域名关键分类特征的问题,提出了一种融合字词双通道的Domain-Flux僵尸网络检测方法。在字符向量和词根向量两个通道上分别采用卷积神经网络(CNN)和双向长短期记忆网络(BiLSTM)提取局部特征和全局特征,丰富输入域名的特征信息,提升分类性能。其中,字符向量通道针对随机字符域名提取局部空间特征,而词根向量通道基于TF-IDF算法,引入类内因子将词根重要性加权到词向量中,然后提取域名单词组合序列前后的时序特征。实验结果表明,与单一采用TextCNN或BiLSTM的模型相比,融合字词双通道的模型检测准确率分别提高7.12%和5.86%,针对词典类Domain-Flux的检测也具有更高的精确率。

基于BP神经网络的高通量铅铋反应堆中子通量最大化设计方法研究

优化设计高通量铅铋反应堆对于缓解快中子研究堆辐照资源稀缺难题、支撑先进核能系统的发展具有重要意义。本文以提升堆芯中子通量水平为目标,针对高通量铅铋反应堆复杂的多维非线性约束优化问题,依托反应堆蒙特卡罗程序RMC和子通道程序Subchanflow,构建了基于BP神经网络(Back Propagation Neural Network)算法的预测模型,并结合Sobol指数法开展堆芯设计参数的敏感性分析,提出了基于BP神经网络动态代理模型(Dynamic Surrogate Model,DSM)更新迭代的设计优化方法,开发了高通量铅铋反应堆设计优化平台。以多功能超高通量堆为例开展堆芯栅径比、燃料芯块直径、活性区高度、径向反射层厚度的多堆芯参数协同优化验证,结果表明:该优化方法对堆芯中子通量密度与有效增殖因数keff的预测精度误差在0.1%之内,在4组堆芯设计变量单独作用和共同作用下对于最大中子通量的影响程度都按照反射层厚度<栅径比<活性区高度<燃料芯块直径的递增顺序排列,优化后的中子通量密度相比原始设计方案提高了15.41%,表明开发的高通量铅铋反应堆设计优化平台有效可靠。

基于流量时空特征的fast-flux僵尸网络检测方法

僵尸网络已成为网络空间安全的主要威胁之一,虽然目前可通过逆向工程等技术来对其进行检测,但是使用了诸如fast-flux等隐蔽技术的僵尸网络可以绕过现有的安全检测并继续存活。现有的fast-flux僵尸网络检测方法主要分为主动和被动两种,前者会造成较大的网络负载,后者存在特征值提取繁琐的问题。因此为了有效检测fast-flux僵尸网络并解决传统检测方法中存在的问题,该文结合卷积神经网络和循环神经网络,提出了基于流量时空特征的fast-flux僵尸网络检测方法。结合CTU-13和ISOT公开数据集的实验结果表明,该文所提检测方法和其他方法相比,准确率提升至98.3%,召回率提升至96.7%,精确度提升至97.5%。

数据驱动的脉冲风洞气动热试验数据分析方法探索

脉冲风洞的有效运行时间短,气动热测量信号易受干扰,通常采用人工判读的方式在大量的脉冲风洞测热试验数据中遴选有效数据,数据分析过程效率低、标准不统一。研究基于中国航天空气动力技术研究院1 m量级炮/激波双模式风洞气动热试验数据开展信号特征分析,确定了Fourier变换后的电压信号、总压-热流相关系数曲线、热流时间导数等参数对流动起止时间、运行模式分界时间、信号质量等关键信息的表征作用。在此基础上,基于卷积神经网络和密度基聚类算法,发展了传感器信号有效性判断模型、风洞有效运行时间段选取算法和传感器信号取值区间选取算法,实现了脉冲风洞气动热试验数据的智能处理。结果表明,智能算法对传感器信号有效性的判断准确度达到98%;针对3568条原始试验曲线进行处理,智能算法与人工方式得到的热流均值差异小于10%的数据约占91%,具有应用于风洞试验的价值。

互联网重点应用服务端算力分布及其对用户感知的影响

互联网应用在服务端的算力分布会对用户感知产生一定影响。选取互联网头部应用,以流量作为主要度量,通过采集和分析现网数据,研究其服务端的算力分布情况和流量远距离绕转情况。同时,结合用户感知数据,对流量绕转与实际感知进行关联分析。分析发现,互联网应用的服务端算力分布存在不平衡现象,服务调度中也存在非最优调度。互联网应用方应与运营商密切协作,减少流量绕转,协同改善用户感知和网络效率。

基于注意力特征融合的漏磁缺陷识别方法

针对漏磁缺陷识别率低、检测速度慢等问题,提出了一种基于注意力特征融合的漏磁缺陷识别方法。所提算法以CenterNet为基础进行修改,主干网络选取了一种轻量级网络PP-LCNet,相较于现在流行的主干特征提取网络既保证了低计算量又保证了高精度。采用注意力网络CBAM主动学习低层特征中的重要信息并与高层特征进行融合,使模型同时获得低层细粒度信息与高层语义信息,进而提升小缺陷识别的准确率。结果表明,当IOU大于0.5时,所提算法的准确率为94.3%,推理时间为9.6 ms。

固定式ADCP设备在嘉兴市平原河网通量监测中的应用研究

ADCP(Acoustic Doppler Current Profiler,声学多普勒流速剖面仪)测流技术是一种采用声学原理测量水流速度的技术,用于研究水深、水流速度、流向等水动力学特征。文章研究了固定式ADCP设备在嘉兴市平原河网通量监测中的应用效果及存在的问题和建议,结果表明:ADCP测流仪测量数据结果能较为准确地反映出海宁域内两条入海河流水平衡状态,基本厘清两条入海河流干流与各支流的流向、水动力状态等情况;ADCP测流技术应用中存在信号衰减大、抗干扰能力弱、操作难度高等问题;提高ADCP测流技术的抗干扰能力、改进操作方法有助于促进固定式ADCP设备的更好应用。

基于卫星遥感资料的近海海上通信环境研究

海气界面通量等要素会影响海上通信的可靠性和效率。相较于分布零星的海上现场观测数据,卫星遥感数据有覆盖范围广、时间跨度长的优势,基于星载合成孔径雷达风速数据和再分析数据以及浮标实测数据,结合神经网络方法,利用COARE V3.5算法计算海气界面的动量通量、感热通量和潜热通量。研究发现,经过神经网络校正后的SAR风速数据在计算海气通量时,与浮标实测风速的一致性得到了显著提升,摩擦风速的偏差从-0.03 m/s降低到0.01 m/s,风应力的偏差从-0.03 N/m^(2)降低到0.00 N/m^(2),拖曳系数的偏差从-0.29降低到-0.21,潜热通量的偏差从-8.32 W/m^(2)降低到5.41 W/m^(2),感热通量的偏差从0.67 W/m^(2)减小到0.06 W/m^(2)。研究结果表明,经过神经网络校正后的SAR风速资料能够提供更加可靠的海上通信环境数据。

基于Dialux结合深度学习技术的办公室智能照明设计

针对传统的照明设计方案不能有效节能的问题,研究提出一种基于人工神经网络算法的室内光环境优化以及预测方法,既可以减少能耗,又可以提高员工在室内办公的舒适性.结果表明,采用人工神经网络算法进行光控制后,其平均绝对误差、均方误差以及均方根误差依次为0.49445、0.49984和0.48726,经过217次的训练,该方法能够满足预先设定的10~(-2)错误率,从而达到预期的目的,在对办公室室内抽取4个采光点进行预测时,通过模拟得出的最大照度误差为21 lx,低于人类肉眼可感知的50 lx.综上所述,说明该办公室室内光环境优化实用效果很好且稳定性很强.

漏磁检测在管道损伤探测中的应用

漏磁检测技术是油气管道损伤检测中最常用的方法之一。其是一种利用磁敏传感器检测漏磁信号进而探测管道缺陷的无损检测技术。首先介绍了漏磁检测的原理和操作流程,而后综述了近年来漏磁检测技术在信号预处理、异常识别以及缺陷量化3方面取得的重要成果。其中,重点介绍了基于深度学习的异常识别和缺陷量化方法,并分析了这些方法存在的不足。最后,对管道漏磁检测的未来发展进行了展望。

计及电动汽车充电需求的城市配电网多场景低碳优化调度研究

【目的】随着光伏、储能、电动汽车负荷在配电网中占比不断增加,高比例新能源的波动性与不确定性给配电网低碳运行带来了巨大挑战。为了有效地减少配电网的碳排放量,【方法】提出了一种考虑电动汽车负荷充电需求的配电网低碳经济优化调度方法。首先给出了基于动态碳排放因子的配电网负荷侧碳排放量计算方法,并针对居民用户、商业用户场景,构建城市配电网多场景下的电动汽车负荷充电模型,并将电动汽车负荷充电状态作为决策变量,以调度成本和碳排放量最小为目标,对配电网进行优化调度。通过在改进IEEE-33节点配电网中进行算例分析【结果】以夏季典型日为例,在可协调SOC调度模式下,居民负荷调度成本和碳排放量相比于无序SOC调度模式分别降低了8.06%、13.92%,商业负荷调度成本和碳排放量相比于无序SOC调度模式分别降低了4.31%、4.87%。【结论】结果表明,针对不同的用户场景,对电动汽车充电负荷采用可协调SOC的充电调度方法,可以有效减小配电网的调度成本,降低配电网的碳排放量。

小管径管道弯头缺陷漏磁信号量化方法

漏磁内检测器通过小管径弯头部位时提离值发生改变,检测的缺陷漏磁信号与直管有较大差异性,传统量化方法的适用性有待研究。通过建立弯头及直管的三维漏磁仿真模型,获取三轴缺陷漏磁信号,并提取其中的多模态特征参数以构建样本库,再将特征样本作为输入融合粒子群优化的动态神经网络,分别构建弯头和直管量化模型,以建立漏磁信号与缺陷尺寸的三维映射关系。研究结果表明:本量化方法对弯头缺陷长度、深度和宽度的量化准确率分别达到94.2%、94.4%和95.0%,结果优于BP神经网络,可为小管径弯头缺陷量化提供一定依据。

Noise effect in metabolic networks

Constraint-based models such as flux balance analysis （FBA） are a powerful tool to study biological metabolic networks. Under the hypothesis that cells operate at an optimal growth rate as the result of evolution and natural selection, this model successfully predicts most cellular behaviours in growth rate. However, the model ignores the fact that cells can change their cellular metabolic states during evolution, leaving optimal metabolic states unstable. Here, we consider all the cellular processes that change metabolic states into a single term‘noise＇, and assume that cells change metabolic states by randomly walking in feasible solution space. By simulating a state of a cell randomly walking in the constrained solution space of metabolic networks, we found that in a noisy environment cells in optimal states tend to travel away from these points. On considering the competition between the noise effect and the growth effect in cell evolution, we found that there exists a trade-off between these two effects. As a result, the population of the cells contains different cellular metabolic states, and the population growth rate is at suboptimal states.