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.

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.

基于磁网络法的正弦调磁环磁齿轮研究

提出的一种适合高速运行的磁齿轮,其调磁环具有正弦轮廓。为了研究这类磁齿轮性能,引入磁网络法,该方法将计算区域离散化,便于描述不规则边界条件,并建立等效磁网络模型。对比研究了矩形调磁块磁齿轮和正弦调磁环磁齿轮的气隙磁密、峰值转矩、稳态转矩和涡流损耗。结果表明,磁网络法和有限元结果整体吻合,局部存在偏差,正弦调磁环内、外转子峰值转矩的相对误差为12.95%和14.9%,相较于传统结构,正弦调磁环磁齿轮的峰值转矩减小了15%,涡流损耗降低了29%,验证了所提出结构在高速下的潜在应用前景。

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%。

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.

A novel hyper-cube shrink algorithm to predict metabolic fluxes based on enzyme activity only

OBJECTIVE One of the long-expected goals of genome-scale metabolic modeling is to evaluate the influence of the perturbed enzymes to the yield of an expected end product.METHDOS Metabolic control analysis(MCA)performs such role to calculate the sensitivity of flux change upon that of enzymes under the framework of ordinary differential equation(ODE)models,which are restricted in small-scale networks and require explicit kinetic parameters.The constraint-based models,like flux balance analysis(FBA),lack of the room of performing MCA because they are parameters-free.In this study,we developed a hyper-cube shrink algorithm(HCSA)to incorporate the enzymatic properties to the FBA model by introducing a pair of parameters for each reaction.Our algorithm was able to handle not only prediction of knockout strains but also strains with an adjustment of expression level of certain enzymes.RESULTS We first showed the concept by applying HCSA to a simplest three-nodes network.Then we show the HCSA possesses Michaelis-Menten like behaviors characterized by steady state of ODE.We obtained good prediction of a synthetic network in Saccharomyces cerevisiae producing voilacein and analogues.Finally we showed its capability of predicting the flux distribution in genome-scale networks by applying it to sporulation in yeast.CONCLUSION We have developed an algorithm the impact on fluxes when certain enzymes were inhibited or activated.It provides us a powerful tool to evaluate the consequences of enzyme inhibitor or activator.

Effects of node buffer and capacity on network traffic

In this paper, we study the optimization of network traffic by considering the effects of node buffer ability and capacity. Two node buffer settings are considered. The node capacity is considered to be proportional to its buffer ability. The node effects on network traffic systems are studied with the shortest path protocol and an extension of the optimal routing [Phys. Rev. E 74 046106 （2006）]. In the diagrams of flux-density relationships, it is shown that a nodes buffer ability and capacity have profound effects on the network traffic.

Application of artificial neural networks in analysis of CHF experimental data in round tubes

Artificial neural networks (ANNs) are applied successfully to analyze the critical heat flux (CHF) experimental data from some round tubes in this paper. A set of software adopting artificial neural network method for predicting CHF in round tube and a set of CHF database are gotten. Comparing with common CHF correlations and CHF look-up table, ANN method has stronger ability of allow-wrong and nice robustness. The CHF predicting software adopting artificial neural network technology can improve the predicting accuracy in a wider parameter range,and is easier to update and to use. The artificial neural nefwork method used in this paper can be applied to some similar physical problems.

Wet Deposition Fluxes and Related Atmospheric Chemistry at Three Sites in Mexico

Wet deposition was collected in Mexico City (MC), Metropolitan Area of Monterrey (MAM) and El Chico National Park (ECNP), during 2009 and 2010. pH, conductivity, Cl-, , Na+, K+, Ca2+ and Mg2+ were determined. In MC, sulphate levels were greater than nitrate levels, and NH4 had mixed sources (vehicular emissions and agriculture activities). MAM had markedly alkaline atmospheric deposition, Na+ and Cl-levels were unexpectedly high, especially during hurricane “Alex”. Low pH values were found in ECNP and nitrate concentrations were high, suggesting the influence of a local source (forest fires). Deposition fluxes (Kg.ha-1yr-1) for N-NO3, N-NH4 and S-SO4 were 1.36, 2.74 and 4.84 for MAM;7.27, 0.57 and 4.32 for ECNP;and 5.97, 4.96 and 6.78 for MC, respectively. Nitrogen deposition fluxes in ECNP were high considering that this site is a natural reserve.

A discrete model for prediction of radon flux from fractured rocks

Prediction of radon flux from the fractured zone of a propagating cave mine is basically associated with uncertainty and complexity. For instance, there is restricted access to these zones for field measure- ments, and it is quite difficult to replicate the complex nature of both natural and induced fractures in these zones in laboratory studies. Hence, a technique for predicting radon flux from a fractured rock using a discrete fracture network （DFN） model is developed to address these difficulties. This model quantifies the contribution of fractures to the total radon flux, and estimates the fracture density from a measured radon flux considering the effects of advection, diffusion, as well as radon generation and decay. Radon generation and decay are classified as reaction processes. Therefore, the equation solved is termed as the advection-diffusion-reaction equation （ADRE）. Peclet number （Pe）, a conventional dimensionless parameter that indicates the ratio of mass transport by advection to diffusion, is used to classify the transport regimes. The results show that the proposed model effectively predicts radon flux from a fractured rock. An increase in fracture density for a rock sample with uniformly distributed radon generation rate can elevate radon flux significantly compared with another rock sample with an equivalent increase in radon generation rate. In addition to Pe, two other independent dimensionless parameters （derived for radon transport through fractures） significantly affect radon dimensionless flux. Findings provide insight into radon transport through fractured rocks and can be used to improve radon control measures for proactive mitigation.

A self-organizing shortest path finding strategy on complex networks

The shortcomings of traditional methods to find the shortest path are revealed, and a strategy of finding the self- organizing shortest path based on thermal flux diffusion on complex networks is presented. In our method, the shortest paths between the source node and the other nodes are found to be self-organized by comparing node temperatures. The computation complexity of the method scales linearly with the number of edges on underlying networks. The effects of the method on several networks, including a regular network proposed by Ravasz and Barabasi which is called the RB network, a real network, a random network proposed by Ravasz and Barabasi which is called the ER network and a scale-free network, are also demonstrated. Analytic and simulation results show that the method has a higher accuracy and lower computational complexity than the conventional methods.

Constrain-based analysis of gene deletion on the metabolic flux redistribution of Saccharomyces Cerevisiae

Based on the gene-protein-reaction (GPR) model of S. cerevisiae_iND750 and the method of constraint-based analysis, we first calculated the metabolic flux distribution of S. cere-visiae_iND750. Then we calculated the deletion impact of 438 calculable genes, one by one, on the metabolic flux redistribution of S. cere-visiae_iND750. Next we analyzed the correlation between v (describing deletion impact of one gene) and d (connection degree of one gene) and the correlation between v and Vgene (flux sum controlled by one gene), and found that both of them were not of linear relation. Furthermore, we sought out 38 important genes that most greatly affected the metabolic flux distribution, and determined their functional subsystems. We also found that many of these key genes were related to many but not several subsystems. Because the in silico model of S. cere-visiae_iND750 has been tested by many ex-periments, thus is credible, we can conclude that the result we obtained has biological sig-nificance.

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。

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。

全球陆地生态系统净生态系统生产力估算

陆地生态系统作为全球最重要的碳库之一,对缓解全球气候变暖起着重要作用。对陆地生态系统碳通量的估算是评价陆地生态系统碳汇变化的重要环节。该研究基于通量站点观测数据,利用卷积神经网络(CNN),综合气象数据、遥感数据和土壤数据,估算全球陆地生态系统的净生态系统生产力(NEP)。结果表明:CNN能够有效模拟全球NEP的空间分布和总量大小,全球陆地生态系统NEP总量为(22±2)pgC/a,空间上约有三分之二的区域属于碳汇区,整体以碳汇为主导。其中,中国的NEP总量约为1.17 pgC/a,约占全球的5.3%。2000—2018年,全球陆地生态系统NEP平均值的变化趋势不明显,碳汇的变化整体处于动态平衡中。

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。