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.

Stacking Ensemble Learning-Based Convolutional Gated Recurrent Neural Network for Diabetes Miletus

Diabetes mellitus is a metabolic disease in which blood glucose levels rise as a result of pancreatic insulin production failure.It causes hyperglycemia and chronic multiorgan dysfunction,including blindness,renal failure,and cardi-ovascular disease,if left untreated.One of the essential checks that are needed to be performed frequently in Type 1 Diabetes Mellitus is a blood test,this procedure involves extracting blood quite frequently,which leads to subject discomfort increasing the possibility of infection when the procedure is often recurring.Exist-ing methods used for diabetes classification have less classification accuracy and suffer from vanishing gradient problems,to overcome these issues,we proposed stacking ensemble learning-based convolutional gated recurrent neural network(CGRNN)Metamodel algorithm.Our proposed method initially performs outlier detection to remove outlier data,using the Gaussian distribution method,and the Box-cox method is used to correctly order the dataset.After the outliers’detec-tion,the missing values are replaced by the data’s mean rather than their elimina-tion.In the stacking ensemble base model,multiple machine learning algorithms like Naïve Bayes,Bagging with random forest,and Adaboost Decision tree have been employed.CGRNN Meta model uses two hidden layers Long-Short-Time Memory(LSTM)and Gated Recurrent Unit(GRU)to calculate the weight matrix for diabetes prediction.Finally,the calculated weight matrix is passed to the soft-max function in the output layer to produce the diabetes prediction results.By using LSTM-based CG-RNN,the mean square error(MSE)value is 0.016 and the obtained accuracy is 91.33%.

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.

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。

基于特征选择及ISSA-CNN-BiGRU的短期风功率预测

针对风电功率随机性大、平稳性低,以及直接输入预测模型往往难以取得较高精度等问题,提出了一种基于特征选择及改进麻雀搜索算法(ISSA)优化卷积神经网络-双向门控循环单元(CNN-BiGRU)的短期风电功率预测方法。首先,利用变分模态分解(VMD)将原始功率分解为一组包含不同信息的子分量,以降低原始功率序列的非平稳性,提升可预测性,同时通过观察中心频率方式确定模态分解数。其次,对每一分量采用随机森林(RF)特征重要度的方法进行特征选择,从风速、风向、温度、空气密度等气象特征因素中,选取对各个分量预测贡献度较高的影响因素组成输入特征向量。然后,建立各分量的CNN-BiGRU预测模型,针对神经网络算法参数难调、手动配置参数随机性大的问题,利用ISSA对模型超参数寻优,自适应搜寻最优参数组合。最后,叠加各分量的预测值,得到最终的预测结果。以中国内蒙古某风电场实际数据进行仿真实验,与多种单一及组合预测方法进行对比,结果表明,本文所提方法相比于其他方法具有更高的预测精度,其平均绝对百分比误差值达到2.644 0%;在其他4个数据集上进行的模型准确性及泛化性验证结果显示,模型平均绝对百分比误差值分别为4.385 3%、3.174 9%、1.576 1%和1.358 8%,均保持在5.000 0%以内,证明本文所提方法具有较好的预测精度及泛化能力。

基于CNN-BiGRU-Attention的短期电力负荷预测

针对目前电力负荷数据随机性强,影响因素复杂,传统单一预测模型精度低的问题,结合卷积神经网络(Convolutional neural network,CNN)、双向门控循环单元(Bi-directional gated recurrent unit,BiGRU)以及注意力机制(Attention)在短期电力负荷预测上的不同优点,提出一种基于CNN-BiGRU-Attention的混合预测模型。该方法首先通过CNN对历史负荷和气象数据进行初步特征提取,然后利用BiGRU进一步挖掘特征数据间时序关联,再引入注意力机制,对BiGRU输出状态给与不同权重,强化关键特征,最后完成负荷预测。试验结果表明,该模型的平均绝对百分比误差(Mean absolute percentage error,MAPE)、均方根误差(Root mean square error,RMSE)、判定系数(R-square,R~2)分别为0.167%、0.057%、0.993,三项指标明显优于其他模型,具有更高的预测精度和稳定性,验证了模型在短期负荷预测中的优势。

基于CNN-BiGRU-ResNet的网络入侵检测研究

网络入侵检测是网络安全中的一项重要工作,其主要是通过网络、系统等信息对入侵行为进行判断,它可以及时地发现网络中的攻击行为,传统的网络入侵检测方法存在准确率低并且误报率高的问题,针对上述问题,提出了一种融合双向门控循环单元(BiGRU)、卷积神经网络(CNN)以及残差网络(ResNet)的网络入侵检测方法,该方法通过双向门控循环单元对时间序列特征以及卷积神经网络和残差网络对局部空间特征的提取,利用softmax分类器获得最终的分类结果。实验表明,与基于GRU和ResNet等方法相比,该方法的网络入侵检测效果比较好,其准确率较高,误报率更低。

基于CNN-BiGRU的高压直流输电线路故障识别

针对高压直流(high voltage direct current,HVDC)输电线路故障暂态行波具有时序性和强非线性的特点,导致高过渡电阻情况下故障识别率低的问题,提出基于卷积神经网络(convolutional neural networks,CNN)和双向循环门单元(bidirectional gate recurrent unit,BiGRU)的HVDC输电线路故障识别方法。首先,采用故障后整流侧的双极暂态电流行波作为特征向量,利用CNN提取全局特征,并从中剔除噪声和不稳定成分,完成对数据的降维处理。然后,采用BiGRU来捕获CNN提取到特征的前后时间信息,进一步提取数据中的时序特征,以实现HVDC输电线路故障识别。仿真结果表明:该方法可在不同故障地点以及不同过渡电阻下对单极接地、双极短路、雷击故障、雷击干扰共四种故障实现准确识别,可靠性高,具有较强的耐受过渡电阻能力,同时具备一定的抗噪性能。

基于ResNet-TSM和BiGRU网络的移动视频感知质量评价模型

考虑到卡顿、质量切换、内容特征等因素对用户体验质量的影响都会直接体现在客户端的失真视频里,提出了一种客户端的移动视频感知质量评价模型。该模型无须对每种影响因素均进行表征和度量,而是基于深度特征提取+回归的思路,直接建立失真视频与平均意见分数之间的映射模型。首先,构建了ResNet-TSM网络结构,提取失真视频片段的深度时空特征;为了避免维度灾难,采用LargeVis算法对提取的深度特征进行降维,同时提升特征的表达与区分能力。然后,采用双向门控循环单元网络对视频的长时间依赖关系进行建模,得到各视频片段的打分,再利用时间平均池化方法将各片段分数进行聚合,得到整个视频的打分结果。在WaterlooSQoE-Ⅲ和LIVE-NFLX-Ⅱ数据集上的实验结果表明,提出的模型可以获得更高的预测精度。

Machine learning for pore-water pressure time-series prediction:Application of recurrent neural networks

Knowledge of pore-water pressure(PWP)variation is fundamental for slope stability.A precise prediction of PWP is difficult due to complex physical mechanisms and in situ natural variability.To explore the applicability and advantages of recurrent neural networks(RNNs)on PWP prediction,three variants of RNNs,i.e.,standard RNN,long short-term memory(LSTM)and gated recurrent unit(GRU)are adopted and compared with a traditional static artificial neural network(ANN),i.e.,multi-layer perceptron(MLP).Measurements of rainfall and PWP of representative piezometers from a fully instrumented natural slope in Hong Kong are used to establish the prediction models.The coefficient of determination(R^2)and root mean square error(RMSE)are used for model evaluations.The influence of input time series length on the model performance is investigated.The results reveal that MLP can provide acceptable performance but is not robust.The uncertainty bounds of RMSE of the MLP model range from 0.24 kPa to 1.12 k Pa for the selected two piezometers.The standard RNN can perform better but the robustness is slightly affected when there are significant time lags between PWP changes and rainfall.The GRU and LSTM models can provide more precise and robust predictions than the standard RNN.The effects of the hidden layer structure and the dropout technique are investigated.The single-layer GRU is accurate enough for PWP prediction,whereas a double-layer GRU brings extra time cost with little accuracy improvement.The dropout technique is essential to overfitting prevention and improvement of accuracy.

基于双注意力机制的MSCN-BiGRU的滚动轴承故障诊断方法

针对滚动轴承故障诊断模型在变工况和环境噪声干扰下诊断精度降低的问题,提出一种基于双注意力机制的多尺度卷积网络(dual attention and multi-scale convolutional networks,DAMSCN)与改进的双向门控循环单元(bidirectional gated recurrent unit,BiGRU)组成的故障诊断模型DAMSCN-BiGRU。首先,多尺度特征融合模块使用不同大小的卷积核,获得多种感受野,从而提取到轴承原始振动信号的多尺度特征信息,并根据重要性对其进行自适应融合,然后利用通道注意力和空间注意力组成的双注意力模块(dual attention module,DAM)对多尺度特征进行重新标定,分配注意力权重,削弱融合特征中的冗余特征;然后,增加注意力层和利用分段激活改进BiGRU进而挖掘信号的时域特征,以提高轴承故障诊断的性能;最后,通过Softmax层完成对不同故障的分类。试验结果表明,与其他智能诊断模型相比,DAMSCN-BiGRU在变工况环境下,平均诊断精度达到98.2%,在强噪声背景下仍然有着85.3%的准确率,且在不同程度的噪声强度下效果均优于其他常用模型,有利于促进滚动轴承的智能故障诊断研究和实际应用。

基于DL-BiGRU多特征融合的注塑件尺寸预测方法

为了充分挖掘注塑成型过程中模腔内的高频时序特征和注塑成型机状态特征,提出基于双层双向门控循环单元网络(DL-BiGRU)的多特征融合注塑件尺寸预测方法.分析膜腔内传感器高频时序特征与注塑件尺寸间的关联性,采用DL-BiGRU网络从高频数据中自动提取时序特征,表征注塑件成型过程状态变化特性.通过采样模腔内高频时序数据进行展成平铺,表征注塑成型的瞬时特征.融合时序特征、瞬时特征和成型机状态特征,构建端到端的深度学习多特征融合框架.将上述3种特征融合并联合训练,提升注塑件尺寸预测精度.在注塑成型数据集上进行模型验证,预测尺寸平均均方误差为4.7×10^(-4) mm^(2),最小误差波动为10^(-5) mm^(2)量级,模型具有较高的预测精度和稳定性.

Lightweight and highly robust memristor-based hybrid neural networks for electroencephalogram signal processing

Memristor-based neuromorphic computing shows great potential for high-speed and high-throughput signal processing applications,such as electroencephalogram(EEG)signal processing.Nonetheless,the size of one-transistor one-resistor(1T1R)memristor arrays is limited by the non-ideality of the devices,which prevents the hardware implementation of large and complex networks.In this work,we propose the depthwise separable convolution and bidirectional gate recurrent unit(DSC-BiGRU)network,a lightweight and highly robust hybrid neural network based on 1T1R arrays that enables efficient processing of EEG signals in the temporal,frequency and spatial domains by hybridizing DSC and BiGRU blocks.The network size is reduced and the network robustness is improved while ensuring the network classification accuracy.In the simulation,the measured non-idealities of the 1T1R array are brought into the network through statistical analysis.Compared with traditional convolutional networks,the network parameters are reduced by 95%and the network classification accuracy is improved by 21%at a 95%array yield rate and 5%tolerable error.This work demonstrates that lightweight and highly robust networks based on memristor arrays hold great promise for applications that rely on low consumption and high efficiency.

基于注意力机制的CNN-BIGRU短期电价预测

针对短期电价预测的复杂性和精确度较差的问题,本文提出一种基于注意力机制的卷积神经网络和双向门控循环单元网络的短期电价预测模型。该模型将历史电价数据经过数据预处理后作为输入,首先利用卷积神经网络提取历史电价序列中的特征;其次,将提取的特征向量构造成时间序列输入到双向门控循环单元网络,充分挖掘特征内部的变化规律进行训练;然后,引入注意力机制来突出重要信息的影响并赋予权重,利用注意力机制对双向门控循环单元网络每个时间步的输出进行加权求和;最后,在全连接层通过激活函数计算输出最终预测值。通过实例验证了本文所提模型的准确性。

Neural Network-Based State of Charge Estimation Method for Lithium-ion Batteries Based on Temperature

Lithium-ion batteries are commonly used in electric vehicles,mobile phones,and laptops.These batteries demonstrate several advantages,such as environmental friendliness,high energy density,and long life.However,battery overcharging and overdischarging may occur if the batteries are not monitored continuously.Overcharging causesfire and explosion casualties,and overdischar-ging causes a reduction in the battery capacity and life.In addition,the internal resistance of such batteries varies depending on their external temperature,elec-trolyte,cathode material,and other factors;the capacity of the batteries decreases with temperature.In this study,we develop a method for estimating the state of charge(SOC)using a neural network model that is best suited to the external tem-perature of such batteries based on their characteristics.During our simulation,we acquired data at temperatures of 25°C,30°C,35°C,and 40°C.Based on the tem-perature parameters,the voltage,current,and time parameters were obtained,and six cycles of the parameters based on the temperature were used for the experi-ment.Experimental data to verify the proposed method were obtained through a discharge experiment conducted using a vehicle driving simulator.The experi-mental data were provided as inputs to three types of neural network models:mul-tilayer neural network(MNN),long short-term memory(LSTM),and gated recurrent unit(GRU).The neural network models were trained and optimized for the specific temperatures measured during the experiment,and the SOC was estimated by selecting the most suitable model for each temperature.The experimental results revealed that the mean absolute errors of the MNN,LSTM,and GRU using the proposed method were 2.17%,2.19%,and 2.15%,respec-tively,which are better than those of the conventional method(4.47%,4.60%,and 4.40%).Finally,SOC estimation based on GRU using the proposed method was found to be 2.15%,which was the most accurate.

基于DCNN网络及Self-Attention-BiGRU机制的轴承剩余寿命预测

深度神经网络在剩余寿命预测(RUL)领域得到了广泛的应用。传统的滚动轴承寿命预测模型存在预测精确度较低、鲁棒性较弱的问题。为了进一步提升预测模型的精确度以及鲁棒性,提出了一种融合深度卷积神经网络(DCNN)、双向门控循环单元(BiGRU)以及自注意力机制(Self-Attention)三种模块的滚动轴承剩余使用寿命预测模型。首先,利用DCNN网络对原始振动信号的时域特征、频域特征进行了提取;然后,使用不确定量化的方法对提取到的特征进行了评价和筛选,利用筛选过后的特征构建了新的替代特征集;最后,利用Self-Attention-BiGRU网络对轴承的剩余使用寿命进行了预测,并在IEEE PHM2012数据集上进行了验证。实验结果表明:相较于BiGRU、GRU和BiLSTM三种模型的预测结果,基于DCNN及Self-Attention-BiGRU方法的预测结果最优,两项误差值:平均绝对误差(MAE)、均方根误差(RMSE)最低,其中工况一的一号轴承RUL预测的MAE值相较于BiGRU、GRU以及BiLSTM网络分别下降了7.0%、7.4%和6.5%,RMSE值相较于其他三种模型分别下降了7.6%、8.4%和6.9%,预测的Score值最高,分值为0.985。通过不同数据集的划分,证明了该方法在轴承RUL预测时的强鲁棒性。实验结果验证了基于DCNN网络及Self-Attention-BiGRU模型在轴承剩余使用寿命预测中的有效性。

基于ERNIE-BiGRU-Attention-CRF的电子病历命名实体识别方法

目的/意义改善中文电子病历命名实体识别模型的性能,更好地开展医疗信息的组织和挖掘。方法/过程构建ERNIE-BiGRU-Attention-CRF中文电子病历命名实体识别模型,首先采用ERNIE1.0预训练模型生成具有语义特征的词向量,然后利用BiGRU捕获全局语义特征与语法结构特征,通过Attention机制进一步增强语义特征的捕获,最后连接CRF解码层输出全局概率最大的标签序列。结果/结论在公开的医疗文本数据集CCKS2017开展对比实验、消融实验,利用生成的模型进行实例分析,取得较好的识别效果。

基于DA-TCN-BiGRU的坡面泥石流预测研究

为解决当前坡面泥石流预测中存在的多因素数建模问题,并提高预测的精确度,提出一种融合双注意力机制、时间卷积神经网络和双向门控循环单元(DA-TCN-BiGRU)的坡面泥石流风险预测方法。通过模拟平台进行坡面泥石流模拟实验,采集多类传感器数据得到风险度大小,并以此表征所处的风险阶段。实验结果表明,所提模型短期预测的均方根误差、平均百分比误差和平均绝对百分比误差分别为0.013 59、0.010 407和1.182 64,中期预测的均方根误差、平均百分比误差和平均绝对百分比误差分别为0.019 01、0.015 17和1.729 46,优于其他比较模型。

Practical Options for Adopting Recurrent Neural Network and Its Variants on Remaining Useful Life Prediction

The remaining useful life(RUL)of a system is generally predicted by utilising the data collected from the sensors that continuously monitor different indicators.Recently,different deep learning(DL)techniques have been used for RUL prediction and achieved great success.Because the data is often time-sequential,recurrent neural network(RNN)has attracted significant interests due to its efficiency in dealing with such data.This paper systematically reviews RNN and its variants for RUL prediction,with a specific focus on understanding how different components(e.g.,types of optimisers and activation functions)or parameters(e.g.,sequence length,neuron quantities)affect their performance.After that,a case study using the well-studied NASA’s C-MAPSS dataset is presented to quantitatively evaluate the influence of various state-of-the-art RNN structures on the RUL prediction performance.The result suggests that the variant methods usually perform better than the original RNN,and among which,Bi-directional Long Short-Term Memory generally has the best performance in terms of stability,precision and accuracy.Certain model structures may fail to produce valid RUL prediction result due to the gradient vanishing or gradient exploring problem if the parameters are not chosen appropriately.It is concluded that parameter tuning is a crucial step to achieve optimal prediction performance.