Radar Quantitative Precipitation Estimation Based on the Gated Recurrent Unit Neural Network and Echo-Top Data

The Gated Recurrent Unit(GRU) neural network has great potential in estimating and predicting a variable. In addition to radar reflectivity(Z), radar echo-top height(ET) is also a good indicator of rainfall rate(R). In this study, we propose a new method, GRU_Z-ET, by introducing Z and ET as two independent variables into the GRU neural network to conduct the quantitative single-polarization radar precipitation estimation. The performance of GRU_Z-ET is compared with that of the other three methods in three heavy rainfall cases in China during 2018, namely, the traditional Z-R relationship(Z=300R1.4), the optimal Z-R relationship(Z=79R1.68) and the GRU neural network with only Z as the independent input variable(GRU_Z). The results indicate that the GRU_Z-ET performs the best, while the traditional Z-R relationship performs the worst. The performances of the rest two methods are similar.To further evaluate the performance of the GRU_Z-ET, 200 rainfall events with 21882 total samples during May–July of 2018 are used for statistical analysis. Results demonstrate that the spatial correlation coefficients, threat scores and probability of detection between the observed and estimated precipitation are the largest for the GRU_Z-ET and the smallest for the traditional Z-R relationship, and the root mean square error is just the opposite. In addition, these statistics of GRU_Z are similar to those of optimal Z-R relationship. Thus, it can be concluded that the performance of the GRU_ZET is the best in the four methods for the quantitative precipitation estimation.

A HybridManufacturing ProcessMonitoringMethod Using Stacked Gated Recurrent Unit and Random Forest

This study proposed a new real-time manufacturing process monitoring method to monitor and detect process shifts in manufacturing operations.Since real-time production process monitoring is critical in today’s smart manufacturing.The more robust the monitoring model,the more reliable a process is to be under control.In the past,many researchers have developed real-time monitoring methods to detect process shifts early.However,thesemethods have limitations in detecting process shifts as quickly as possible and handling various data volumes and varieties.In this paper,a robust monitoring model combining Gated Recurrent Unit(GRU)and Random Forest(RF)with Real-Time Contrast(RTC)called GRU-RF-RTC was proposed to detect process shifts rapidly.The effectiveness of the proposed GRU-RF-RTC model is first evaluated using multivariate normal and nonnormal distribution datasets.Then,to prove the applicability of the proposed model in a realmanufacturing setting,the model was evaluated using real-world normal and non-normal problems.The results demonstrate that the proposed GRU-RF-RTC outperforms other methods in detecting process shifts quickly with the lowest average out-of-control run length(ARL1)in all synthesis and real-world problems under normal and non-normal cases.The experiment results on real-world problems highlight the significance of the proposed GRU-RF-RTC model in modern manufacturing process monitoring applications.The result reveals that the proposed method improves the shift detection capability by 42.14%in normal and 43.64%in gamma distribution problems.

Impact of utilization of hepatitis C positive organs in liver transplant:Analysis of united network for organ sharing database

BACKGROUND The utility of hepatitis C virus(HCV)organs has increased after the Food and Drug Administration approval of direct acting anti-viral(DAA)medications for the HCV treatment.The efficacy of DAA in treating HCV is nearly 100%.AIM To analyze the United Network for Organ Sharing(UNOS)database to compare the survival rates between the hepatitis C positive donors and negative recipients and hepatitis C negative donors and recipients.METHODS We analyzed the adult patients in UNOS database who underwent deceased donor liver transplant from January 2014 to December 2017.The primary endpoint was to compare the survival rates among the four groups with different hepatitis C donor and recipient status:(Group 1)Both donor and recipient negative for HCV(Group 2)Negative donor and positive recipient for HCV(Group 3)Positive donor and negative recipient for HCV(Group 4)Both positive donor and recipient for HCV.SAS 9.4 software was used for the data analysis.Kaplan Meier log rank test was used to analyze the estimated survival rates among the four groups.RESULTS A total of 24512 patients were included:Group 1:16436,Group 2:6174,Group 3:253 and Group 4:1649.The 1-year(Group 1:91.8%,Group 2:92.12%,Group 3:87%,Group 4:92.8%),2-year(Group 1:88.4%,Group 2:88.1%,Group 3:84.3%,Group 4:87.5%),3-year(Group 1:84.9%,Group 2:84.3%,Group 3:75.9%,Group 4:83.2%)survival rates showed no statistical significance among the four groups.Kaplan Meier log rank test did not show any statistical significance difference in the estimated survival rates between Group 3 vs all the other groups.CONCLUSION The survival rates in hepatitis C positive donors and negative recipients are similar as compared to both hepatitis C negative donors and recipients.This could be due to the use of DAA therapy with cure rates of nearly 100%.This study supports the use of hepatitis C positive organs in the selected group of recipients with and without HCV infection.Further long-term studies are needed to further validate these findings.

Wide-band underwater acoustic absorption based on locally resonant unit and interpenetrating network structure

The interpenetrating network structure provides an interesting avenue to novel materials. Locally resonant phononic crystal （LRPC） exhibits excellent sound attenuation performance based on the periodical arrangement of sound wave scatters. Combining the LRPC concept and interpenetrating network glassy structure, this paper has developed a new material which can achieve a wide band underwater strong acoustic absorption. Underwater absorption coefficients of different samples were measured by the pulse tube. Measurement results show that the new material possesses excellent underwater acoustic effects in a wide frequency range.Moreover, in order to investigate impacts of locally resonant units,some defects are introduced into the sample. The experimental result and the theoretical calculation both show that locally resonant units being connected to a network structure play an important role in achieving a wide band strong acoustic absorption.

Real-time analysis and prediction of shield cutterhead torque using optimized gated recurrent unit neural network

An accurate prediction of earth pressure balance(EPB)shield moving performance is important to ensure the safety tunnel excavation.A hybrid model is developed based on the particle swarm optimization(PSO)and gated recurrent unit(GRU)neural network.PSO is utilized to assign the optimal hyperparameters of GRU neural network.There are mainly four steps:data collection and processing,hybrid model establishment,model performance evaluation and correlation analysis.The developed model provides an alternative to tackle with time-series data of tunnel project.Apart from that,a novel framework about model application is performed to provide guidelines in practice.A tunnel project is utilized to evaluate the performance of proposed hybrid model.Results indicate that geological and construction variables are significant to the model performance.Correlation analysis shows that construction variables(main thrust and foam liquid volume)display the highest correlation with the cutterhead torque(CHT).This work provides a feasible and applicable alternative way to estimate the performance of shield tunneling.

Security System in United Storage Network and Its Implementation

With development of networked storage and its applications, united storage network (USN) combined with network attached storage (NAS) and storage area network (SAN) has emerged. It has such advantages as high performance, low cost, good connectivity, etc. However the security issue has been complicated because USN responds to block I/O and file I/O requests simultaneously. In this paper, a security system module is developed to prevent many types of attacks against USN based on NAS head. The module not only uses effective authentication to prevent unauthorized access to the system data, but also checks the data integrity. Experimental results show that the security module can not only resist remote attacks and attacks from those who has physical access to the USN, but can also be seamlessly integrated into underlying file systems, with little influence on their performance.

Research on the Security of the United Storage Network Based on NAS

A multi-user view file system (MUVFS) and a security scheme are developed to improve the security of the united storage network (USN) that integrates a network attached storage (NAS) and a storage area network (SAN). The MUVFS offers a storage volume view for each authorized user who can access only the data in his own storage volume, the security scheme enables all users to encrypt and decrypt the data of their own storage view at client-side, and the USN server needs only to check the users’ identities and the data’s integrity. Experiments were performed to compare the sequential read, write and read/write rates of NFS+MUVFS+secure_module with those of NFS. The results indicate that the security of the USN is improved greatly with little influence on the system performance when the MUVFS and the security scheme are integrated into it.

Inferior outcomes of liver transplantation for hepatocellular carcinoma during early-COVID-19 pandemic in the United States

BACKGROUND Early in the coronavirus disease 2019(COVID-19)pandemic,there was a significant impact on routine medical care in the United States,including in fields of transplantation and oncology.AIM To analyze the impact and outcomes of early COVID-19 pandemic on liver transplantation(LT)for hepatocellular carcinoma(HCC)in the United States.METHODS WHO declared COVID-19 as a pandemic on March 11,2020.We retrospectively analyzed data from the United Network for Organ Sharing(UNOS)database regarding adult LT with confirmed HCC on explant in 2019 and 2020.We defined pre-COVID period from March 11 to September 11,2019,and early-COVID period as from March 11 to September 11,2020.RESULTS Overall,23.5%fewer LT for HCC were performed during the COVID period(518 vs 675,P<0.05).This decrease was most pronounced in the months of March-April 2020 with a rebound in numbers seen from May-July 2020.Among LT recipients for HCC,concurrent diagnosis of non-alcoholic steatohepatitis significantly increased(23 vs 16%)and alcoholic liver disease(ALD)significantly decreased(18 vs 22%)during the COVID period.Recipient age,gender,BMI,and MELD score were statistically similar between two groups,while waiting list time decreased during the COVID period(279 days vs 300 days,P=0.041).Among pathological characteristics of HCC,vascular invasion was more prominent during COVID period(P<0.01),while other features were the same.While the donor age and other characteristics remained same,the distance between donor and recipient hospitals was significantly increased(P<0.01)and donor risk index was significantly higher(1.68 vs 1.59,P<0.01)during COVID period.Among outcomes,90-day overall and graft survival were the same,but 180-day overall and graft were significantly inferior during COVID period(94.7 vs 97.0%,P=0.048).On multivariable Coxhazard regression analysis,COVID period emerged as a significant risk factor of post-transplant mortality(Hazard ratio 1.85;95%CI:1.28-2.68,P=0.001).CONCLUSION During COVID period,there was a significant decrease in LTs performed for HCC.While early postoperative outcomes of LT for HCC were same,the overall and graft survival of LTs for HCC after 180 days were significantly inferior.

Speech Separation Algorithm Using Gated Recurrent Network Based on Microphone Array

Speech separation is an active research topic that plays an important role in numerous applications,such as speaker recognition,hearing pros-thesis,and autonomous robots.Many algorithms have been put forward to improve separation performance.However,speech separation in reverberant noisy environment is still a challenging task.To address this,a novel speech separation algorithm using gate recurrent unit(GRU)network based on microphone array has been proposed in this paper.The main aim of the proposed algorithm is to improve the separation performance and reduce the computational cost.The proposed algorithm extracts the sub-band steered response power-phase transform(SRP-PHAT)weighted by gammatone filter as the speech separation feature due to its discriminative and robust spatial position in formation.Since the GRU net work has the advantage of processing time series data with faster training speed and fewer training parameters,the GRU model is adopted to process the separation featuresof several sequential frames in the same sub-band to estimate the ideal Ratio Masking(IRM).The proposed algorithm decomposes the mixture signals into time-frequency(TF)units using gammatone filter bank in the frequency domain,and the target speech is reconstructed in the frequency domain by masking the mixture signal according to the estimated IRM.The operations of decomposing the mixture signal and reconstructing the target signal are completed in the frequency domain which can reduce the total computational cost.Experimental results demonstrate that the proposed algorithm realizes omnidirectional speech sep-aration in noisy and reverberant environments,provides good performance in terms of speech quality and intelligibility,and has the generalization capacity to reverberate.

Research on Network-based Integrated Condition Monitoring Unit for Rotating Machinery

In this paper, a network-based monitoring unit for condition monitoring andfault diagnosis of rotating machinery is designed and implemented. With the technology of DSP(Digital signal processing) , TCP/IP, and simultaneous acquisition, a mechanism of multi-process andinter-process communication, the integrating problem of signal acquisition, the data dynamicmanagement and network-based configuration in the embedded condition monitoring system is solved. Itoffers the input function of monitoring information for network-based condition monitoring and afault diagnosis system.

Simulation of Low TDS and Biological Units of Fajr Industrial Wastewater Treatment Plant Using Artificial Neural Network and Principal Component Analysis Hybrid Method

Being familiar with characteristics of industrial town effluents from various wastewater treatment units, which have high qualitative and quantitative variations and more uncertainties compared to urban wastewaters, plays very effective role in governing them. With regard to environmental issues, proper operation of wastewater treatment plants is of par- ticular importance that in the case of inappropriate utilization, they will cause serious problems. Processes that exist in environmental systems mostly have two major characteristics: they are dependent on many variables;and there are complex relationships between its components which make them very difficult to analyze. In order to achieve a better and efficient control over the operation of an industrial wastewater treatment plant (WWTP), powerful mathematical tool can be used that is based on recorded data from some basic parameters of wastewater during a period of treatment plant operation. In this study, the treatment plant was divided into two main subsystems including: Low TDS (Total Dissolved Solids) treatment unit and Biological unit (extended aeration). The multilayer perceptron feed forward neural network with a hidden layer and stop training method was used to predict quality parameters of the industrial effluent. Data of this study are related to the Fajr Industrial Wastewater Treatment Plant, located in Mahshahr—Iran that qualita- tive and quantitative characteristics of its units were used for training, calibration and validation of the neural model. Also, Principal Component Analysis (PCA) technique was applied to improve performance of generated models of neural networks. The results of L-TDS unit showed good accuracy of the models in estimating qualitative profile of wastewater but results of biological unit did not have sufficient accuracy to being used. This model facilitates evaluating the performance of each treatment plant units through comparing the results of prediction model with the standard amount of outputs.

融合CNN-BiGRU和注意力机制的网络入侵检测模型

为提高网络入侵检测模型特征提取能力和分类准确率,提出了一种融合双向门控循环单元(CNN-BiGRU)和注意力机制的网络入侵检测模型.使用CNN有效提取流量数据集中的非线性特征;双向门控循环单元(BiGRU)提取数据集中的时序特征,最后融合注意力机制对不同类型流量数据通过加权的方式进行重要程度的区分,从而整体提高该模型特征提取与分类的性能.实验结果表明:其整体精确率比双向长短期记忆网络(BiLSTM)模型提升了2.25%.K折交叉验证结果表明:该模型泛化性能良好,避免了过拟合现象的发生,印证了该模型的有效性与合理性.

基于KPCA-CNN-DBiGRU模型的短期负荷预测方法

本文针对已有神经网络模型在短期负荷预测中输入维度过高、预测误差较大等问题,提出了一种结合核主成分分析、卷积神经网络和深度双向门控循环单元的短期负荷预测方法。先运用核主成分分析法对原始高维输入变量进行降维,再通过卷积深度双向门控循环单元网络模型进行负荷预测。以第九届全国电工数学建模竞赛试题A题中的负荷数据作为实际算例,结果表明所提方法较降维之前预测误差大大降低,与已有预测方法相比也有大幅的误差降低。

基于动态工况实测数据图像和深度学习的锂电池容量估计方法

针对实际应用中基于动态工况下电池状态参数的片段数据进行电池健康状态(state of health,SOH)实时估计的问题,提出基于动态工况下锂离子电池状态参数(电压、电流、温度)实测数据二维特征图像和深度学习的锂离子电池容量估计算法。首先,将动态工况下电池状态参数监测量(电压、电流和温度)的片段数据转化为二维特征图像。其次,提出基于残差卷积神经网络(residual convolutional neural network,Res-CNN)和门控循环单元(gate recurrent unit,GRU)网络结合的多通道深度学习模型Res-CNN-GRU,以构建动态工况下电池状态参数特征图像和SOH之间的复杂非线性关系,其中电压、电流和温度的二维特征图像以三通道的方式输入到Res-CNN-GRU模型中,模型输出为对应电池的相邻参考充放电循环实验所获得容量的差值。研究结果表明:此方法在锂电池随机充放电工况下对电池健康状态估计效果更佳,且Res-CNN-GRU模型的泛化性和全局特征提取能力较强。论文研究为现实工况下电池健康状态估计的进一步深入研究提供了参考。

基于CEEMD-SE的CNN&LSTM-GRU短期风电功率预测

为进一步提升短期风电功率的预测精度,提出了一种基于互补集合经验模态分解-样本熵(complementary ensemble empirical mode decomposition-sample entropy,CEEMD-SE)的卷积神经网络(convolutional neural network,CNN)和长短期记忆-门控循环单元(longshorttermmemory-gatedrecurrentunit,LSTM-GRU)的短期风电功率预测模型。首先,利用互补集合经验模态分解将原始风电功率序列分解为若干本征模态函数(intrinsic mode function,IMF)分量和一个残差(residual,RES)分量,利用样本熵算法将相近的分量进行重构;其次,搭建卷积神经网络和长短期记忆网络的并行网络结构,提取数据的局部特征和时序特征,并将特征融合后输入门控循环单元网络中进行学习预测;最后,通过算例进行验证,结果表明采用该模型后预测精度得到了有效提升,其均方根误差降低了15.06%、平均绝对误差降低了15.22%、决定系数提高了1.91%。

基于深度学习的盾构机土舱压力场预测方法

土舱压力是盾构机受力状态和掌子面稳定等核心问题中的关键因素。土舱压力具有显著的空间变异性,其形成演化机制源于装备与岩土之间的复杂耦合作用,与地质特征、掘进参数等多源参数相关。然而,现有土舱压力预测方法一般未考虑空间分布特征或地质参数影响。针对该问题,提出了一种基于空间分布物理特征函数导引深度学习的盾构机土舱压力场预测方法。该方法构建物理特征函数用于解耦土舱压力空间分布特征,采用卷积神经网络和门控循环单元分别提取多源参数历史信息的空间特征和特征系数的时序特征,结合多源参数实时信息对特征系数进行预测,从而实现土舱压力场的预测。以长沙地铁四号线某区段为案例,利用该方法准确预测了土舱压力空间分布实测数据,准确率高达0.98,验证了所提方法的有效性。敏感性分析表明,不同地层中土舱压力空间分布特征系数的主要敏感参数基本一致,但其敏感度随地层地质条件的变化规律差异显著,可为复杂地层盾构机土舱压力精细化调控提供参考。

基于门控循环单元网络的钻井井漏智能监测方法

井漏是钻井过程中常见的钻井风险,若对该风险发现、处理不及时,极易导致井塌事故,轻则延长施工周期,重则危害现场人员人身安全。为了提高油气井钻井过程中井漏风险识别的准确性,降低风险识别对人为经验的依赖,结合钻井参数的非线性以及长时依赖特征,提出了一种基于门控循环单元(Gated Recurrent Unit,GRU)网络的井漏风险智能识别方法。该模型以池体积、出口流量和立管压力作为监测参数构建GRU网络,能够提取监测参数的时间序列特征,以实现对井漏风险的准确识别。利用现场实测钻井数据对模型进行了实验测试,结果表明,该方法对井漏风险的识别准确率达到了90.1%,优于长短期记忆网络的识别结果。

基于时序生成对抗网络的居民用户非侵入式负荷分解

现有的非侵入式负荷分解算法往往需要大量电器设备级的负荷数据才能保证分解精度,但由于用户对隐私性的考虑以及安装成本过高等问题,很难获取这些数据。因此,构建一种能深度挖掘电力负荷数据时序特性和电器相关性的时序生成对抗网络。利用降维网络对所有电器有功功率序列组成的高维向量进行降维以降低计算的复杂度,通过复原网络将结果还原为高维向量。基于电器运行状态和深度学习的非侵入式分解方法,运用卷积神经网络-双向门控循环单元构建状态复杂电器的负荷分解回归模型,对状态简单电器利用深度神经网络构建负荷识别分类模型。通过对比其他数据生成方法,以及改变典型公开数据集中生成数据比例所得的负荷分解结果验证了所提方法的有效性。

新型电力系统数据跨域流通泛安全边界防护技术

新型电力系统建设涉及多业务系统、多部门、多方主体间进行海量、异构数据的交互和共享,电力数据的内外部网络环境与安全形势日趋复杂化,数据流通的脆弱性风险加剧。首先,分析新型电力系统下数据流的类型与特性,概括电力数据流通安全防护面临的新形势;其次,基于专用数据处理器(DPU)的高性能流量编排和多功能安全网关能力,构建面向电力数据跨域流通安全增强的泛安全边界,凭借数据面可编程技术沟通网络安全与数据安全双维度安全能力,提出基于DPU的数据跨域流通协同防护技术应用方案;最后,阐释DPU在不同电力通信网络层次的部署方式、价值与关键技术,分析现阶段DPU在电力领域应用存在的挑战。