Significant wave height forecasts integrating ensemble empirical mode decomposition with sequence-to-sequence model

As wave height is an important parameter in marine climate measurement,its accurate prediction is crucial in ocean engineering.It also plays an important role in marine disaster early warning and ship design,etc.However,challenges in the large demand for computing resources and the improvement of accuracy are currently encountered.To resolve the above mentioned problems,sequence-to-sequence deep learning model(Seq-to-Seq)is applied to intelligently explore the internal law between the continuous wave height data output by the model,so as to realize fast and accurate predictions on wave height data.Simultaneously,ensemble empirical mode decomposition(EEMD)is adopted to reduce the non-stationarity of wave height data and solve the problem of modal aliasing caused by empirical mode decomposition(EMD),and then improves the prediction accuracy.A significant wave height forecast method integrating EEMD with the Seq-to-Seq model(EEMD-Seq-to-Seq)is proposed in this paper,and the prediction models under different time spans are established.Compared with the long short-term memory model,the novel method demonstrates increased continuity for long-term prediction and reduces prediction errors.The experiments of wave height prediction on four buoys show that the EEMD-Seq-to-Seq algorithm effectively improves the prediction accuracy in short-term(3-h,6-h,12-h and 24-h forecast horizon)and long-term(48-h and 72-h forecast horizon)predictions.

Landslide displacement prediction based on optimized empirical mode decomposition and deep bidirectional long short-term memory network

There are two technical challenges in predicting slope deformation.The first one is the random displacement,which could not be decomposed and predicted by numerically resolving the observed accumulated displacement and time series of a landslide.The second one is the dynamic evolution of a landslide,which could not be feasibly simulated simply by traditional prediction models.In this paper,a dynamic model of displacement prediction is introduced for composite landslides based on a combination of empirical mode decomposition with soft screening stop criteria(SSSC-EMD)and deep bidirectional long short-term memory(DBi-LSTM)neural network.In the proposed model,the time series analysis and SSSC-EMD are used to decompose the observed accumulated displacements of a slope into three components,viz.trend displacement,periodic displacement,and random displacement.Then,by analyzing the evolution pattern of a landslide and its key factors triggering landslides,appropriate influencing factors are selected for each displacement component,and DBi-LSTM neural network to carry out multi-datadriven dynamic prediction for each displacement component.An accumulated displacement prediction has been obtained by a summation of each component.For accuracy verification and engineering practicability of the model,field observations from two known landslides in China,the Xintan landslide and the Bazimen landslide were collected for comparison and evaluation.The case study verified that the model proposed in this paper can better characterize the"stepwise"deformation characteristics of a slope.As compared with long short-term memory(LSTM)neural network,support vector machine(SVM),and autoregressive integrated moving average(ARIMA)model,DBi-LSTM neural network has higher accuracy in predicting the periodic displacement of slope deformation,with the mean absolute percentage error reduced by 3.063%,14.913%,and 13.960%respectively,and the root mean square error reduced by 1.951 mm,8.954 mm and 7.790 mm respectively.Conclusively,this model not only has high prediction accuracy but also is more stable,which can provide new insight for practical landslide prevention and control engineering.

Vehicle-Bridge Interaction Simulation and Damage Identification of a Bridge Using Responses Measured in a Passing Vehicle by Empirical Mode Decomposition Method

To prevent early bridge failures, effective Structural Health Monitoring (SHM) is vital. Vibration-based damage assessment is a powerful tool in this regard, as it relies on changes in a structure’s dynamic characteristics as it degrades. By measuring the vibration response of a bridge due to passing vehicles, this approach can identify potential structural damage. This dissertation introduces a novel technique grounded in Vehicle-Bridge Interaction (VBI) to evaluate bridge health. It aims to detect damage by analyzing the response of passing vehicles, taking into account VBI. The theoretical foundation of this method begins with representing the bridge’s superstructure using a Finite Element Model and employing a half-car dynamic model to simulate the vehicle with suspension. Two sets of motion equations, one for the bridge and one for the vehicle are generated using the Finite Element Method, mode superposition, and D’Alembert’s principle. The combined dynamics are solved using the Newmark-beta method, accounting for road surface roughness. A new approach for damage identification based on the response of passing vehicles is proposed. The response is theoretically composed of vehicle frequency, bridge natural frequency, and a pseudo-frequency component related to vehicle speed. The Empirical Mode Decomposition (EMD) method is applied to decompose the signal into its constituent parts, and damage detection relies on the Intrinsic Mode Functions (IMFs) corresponding to the vehicle speed component. This technique effectively identifies various damage scenarios considered in the study.

Determination of Instantaneous Frequencies of Low Plasma Waves in the Magnetosheath Using Empirical Mode Decomposition (EMD) and Hilbert Transform (HT)

The observations of in-situ spacecraft mission in the magnetosheath and a region of thermalized subsonic plasma behind the bow shock reveal a non-linear behaviour of plasma waves. The study of waves and optics in Physics has given the understanding of the effect of many waves coming together to form a wave field or wave packet. The common aspect of such study shows that two or more waves can superimpose constructively or destructively. The sudden high magnetic field data in the magnetosheath displays such possibility of superposition of waves. In this paper, we use the empirical mode decomposition (EMD) and Hilbert transform (HT) techniques to determine the instantaneous frequencies of low frequency plasma waves in the magnetosheath. Our analysis has shown that the turbulent behavior of magnetic field in the magnetosheath within the selected period is due to superposition of waves.

高速铁路日常客运量的EMD-Informer组合预测方法

铁路客流需求的科学预测是进行运输组织方案决策的重要依据。以高速铁路历史客票数据为基础,结合经验模态分解(empirical mode decomposition,EMD)与机器深度学习中的注意力机制,提出高速铁路日客流量的EMD-Informer组合预测方法。首先采用EMD方法分解高速铁路客流量序列,获得具有周期特征和线路客流内在特征的模态分量,再利用Informer模型分别训练和预测各模态分解分量,并通过多头注意力机制高效挖掘客流数据内在规律和捕捉数据序列中的关键特征,在此基础上重组各分量预测值,从而得到高速铁路日常客流的整体高精度预测值。同时,根据结合问题特征的大量实验,明确可供实际运用参考的超参数设置规则。基于京沪高速铁路全线的实例计算分析表明,相对对比预测方法,EMD-Informer组合预测方法在高速铁路客流的单步预测及超前预测上均具有明显更小的预测误差。

EEMD与LSTM在轴承剩余寿命预测中的应用

剩余使用寿命(RUL)预测是实现装备健康管理与预测性维护的最主要技术手段之一,为了准确预测轴承的剩余使用寿命,提出了一种基于集合经验模态分解(EEMD)和长短时记忆网络(LSTM)的轴承剩余寿命预测方法。首先,对采集到的振动信号做时域、频域及时频分析,同时记录相应特征;进而,筛选特征,通过EEMD对振动信号予以分解并重构;最后,通过LSTM结合经过处理的信号构建健康特征指标。通过实验证明了该方法能有效的预测出轴承的剩余寿命,且有较高的预测精度。

一种灰色关联分析优化ICEEMDAN的VP倾斜仪信号降噪模型

VP倾斜仪固体潮信号受仪器监测复杂环境限制,多含有大量环境噪声。为获得真实固体潮曲线,提出一种基于灰色关联分析优化改进的自适应噪声完备集合经验模态分解(ICEEMDAN)VP倾斜仪信号降噪模型(GRA-ICEEMDAN)。该方法首先将含噪信号进行ICCEMDAN处理,得到若干个固有模态函数(IMF),并依次排列与标记;然后基于这些IMF分别计算相关系数、互信息、R^(2)、Adj-R^(2)、MSE、SSE、RMSE、MAE、MAPE、样本熵等10个评价指标值,构建IMF可信度评价指标矩阵;最后借助灰色关联分析(GRA)计算各评价指标与不同IMF之间的关联系数和关联度,依据关联度大小对各个IMF进行排序,将排名靠前的IMF进行线性重构,即可完成信号降噪。仿真去噪实验和实测去噪实验均表明,GRA-ICEEMDAN模型优于卡尔曼滤波、70阶低通FIR滤波、Savitzky-Golay等经典降噪模型,能显著区分噪声成分和有效成分,原始信号分解后的重构误差与信号损失极小,可推广至其他仪器的复杂信号降噪中。

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%。

CEEMD-FastICA-CWT联合瞬态响应阶次的电驱总成噪声源识别

以某增程式电驱动总成为研究对象,提出基于联合算法的噪声分离识别模型。首先,采用互补集合经验模态分解(complementary ensemble empirical mode decomposition,CEEMD)联合快速独立分量分析(fast independent component analysis,FastICA)方法提取纯电模式稳态工况下单一通道噪声信号特征,利用复Morlet小波变换及FFT对各分量信号时频特性进行识别。其次,采用阶次分析法和声能叠加法对稳态分量信号对应的各瞬态响应阶次能量进行对比分析,并结合皮尔逊积矩相关系数(Pearson product moment correlation coefficient,PPMCC)相似性识别确定不同噪声激励源贡献度。结果表明:减速齿副啮合噪声对该增程式电驱总成纯电模式运行噪声整体贡献度最大。

基于CEEMDAN-VSSLMS的滚动轴承故障诊断

针对传统机械轴承故障诊断模型易受系统噪声干扰、特征识别效率低等问题,提出一种基于信号固有模式深度建模分析的轴承故障诊断方法。首先,将采集到的轴承振动信号进行噪声自适应完全经验模态分解(CEEMDAN),获得不同时间尺度的局部特征信号,使用相关系数判别并去除虚假模态分量,再利用可变步长最小均方算法(VSSLMS)对剩余IMF分量降噪并进行重构;然后,将降噪后的振动信号进行离散小波变换(DWT)得到时频谱图,并利用形态学开运算进行特征增强;最后利用改进GoogLeNet网络模型对特征图进行训练,通过Softmax分类器完成特征归类,从而实现轴承故障诊断。将提出的故障诊断方法应用于不同工况下的轴承故障数据集,试验结果表明,所提方法在噪声干扰下具有较高的诊断精度。

CEEMDAN和盲源分离在轴承复合故障诊断中的应用

滚动轴承的复合故障信号中往往含有多个特征信息及背景噪声,为更高效实现故障信息的提取,提出一种基于具有自适应白噪声的完备集成经验模态分解(CEEMDAN)和盲源分离的滚动轴承复合故障特征提取方法。对实验所获取的故障数据进行CEEMDAN分解,得出一组固有模态函数(IMF),利用加权峭度因子选取其中有效IMF重构信号,再将重构的信号进行BSS分离。对分离出的信号做解调包络分析,从其解调谱中提取故障信号的特征频率。结果证明了此方法可以有效地分离轴承的内外圈故障,使故障特征更易被提取。

基于ICEEMDAN和分布熵的SS-Y伸缩仪信号随机噪声压制方法

结合改进的自适应噪声完备集合经验模态分解(ICEEMDAN)与分布熵(DistEn),提出一种无需自定义算法参数、去噪效果较好的伸缩仪信号随机噪声压制方法。首先将伸缩仪信号进行ICEEMDAN处理,得到若干个本征模态函数(IMF);然后计算各IMF分量的分布熵值,根据不同分布熵值的大小和表征的分量信号混乱程度,有针对性地对各IMF进行取舍;最后进行线性重构。设计仿真信号去噪实验和SS-Y伸缩仪信号去噪实验,结果表明,基于ICEEMDAN-DistEn去噪模型的伸缩仪信号重构还原度较好,去噪效果显著,明显优于CEEMDAN-DistEn、小波去噪和卡尔曼滤波等去噪模型。

CEEMDAN-WPE-CLSA超短期风电功率预测方法研究

提出了一种结合自适应噪声完全集合经验模态分解、加权排列熵、卷积神经网络、长短期记忆网络和自注意力机制的超短期风电功率预测方法。首先,利用自适应噪声完全集合经验模态分解将原始风电功率时间序列自适应分解为一系列的模态分量,降低原始序列的非线性和波动性;其次,根据加权排列熵计算各模态分量间的相似性并对相似的分量进行重组,以修正自适应噪声完全集合经验模态分解的过度分解问题,使得修正后的模态分量更具规律性;最后,将重组后的分量输入卷积长短期记忆网络进行时序建模,并利用自注意力机制对卷积长短期记忆网络的神经元权重进行重新分配,提高了卷积长短期记忆网络对输入特征不确定性的适应能力。在此基础上,明确了自注意力机制和自适应噪声完全集合经验模态分解、加权排列熵在风电功率预测中的作用机制,以及风电功率信号包含的重要物理信息,证明了自适应噪声完全集合经验模态分解、加权排列熵以及自注意力机制在风电功率信号模态分解和长短期记忆网络隐层输出权重分配中的有效性。

基于MEEMD算法的二冲程柴油发动机机体振动分析

二冲程低速柴油机具有复杂的振动特性,传统的经验模态分解(Empirical Mode Decomposition,EMD)算法对其振动信号处理效果不理想。为此,采用修正多元集合经验模态分解(Modified Ensemble Empirical Mode Decomposition,MEEMD)算法对低速柴油机机体振动信号进行分解。首先,采用三轴加速度计测量发动机机体振动。然后利用均方根(Root Mean Square,RMS)对三轴振动强度进行分析。最后,对x轴上的信号进行MEEMD分析。结果表明:砌块在x轴方向的振动强度最大;与EMD算法相比,MEEMD算法可以抑制模态混合,有助于更好地识别块振动激励。

基于EMD-BiLSTM-ANFIS的负荷区间预测

考虑到新型电力负荷随机性增强,传统的准确预测方法已无法满足要求,提出一种EMD-BiLSTM-ANFIS(Empirical Mode Decomposition-Bi-directional Long Short-Term Memory-Adaptive Network-based Fuzzy Inference System)分位数预测负荷概率密度的方法,使用负荷预测区间取代点预测的准确数值,能为电力系统分析与决策提供更多数据,增强预测的可靠性。首先将原始负荷序列通过EMD(Empirical Mode Decomposition)分解成若干分量,并通过计算样本熵分为3类分量。然后将重构后的3类分量与由相关性筛选的外界因素特征采用BiLSTM、ANFIS模型进行训练和分位数回归(QR:Quantile Regression),并将分量的预测区间结果累加得到最终负荷的预测区间。最后利用核密度估计输出任意时刻用户负荷概率密度预测结果。通过与CNN-BiLSTM(Convolutional Neural Network-Bidirectional Long Short-Term Memory)、LSTM(Long Short-Term Memory)模型对比点预测及区间预测结果,证明了该方法的有效性。

基于EMD-PSO-Bi LSTM组合模型的短期风电功率预测

风电功率预测对风电并网的稳定运行具有重要意义。为了解决风电功率预测中的精度和模型稳定性问题,引入了EMD-PSO-BiLSTM模型。通过经验模态分解技术将原始风电功率序列分解为一系列固有模态函数,以有效捕捉数据中的多尺度特征,并为每个模态序列建立了各自的预测模型。鉴于双向长短时记忆神经网络良好的泛化能力,建立了基于BiLSTM的各模态预测模型。进一步采用粒子群算法优化了BiLSTM参数,解决了模型非线性、高维、多模态等问题,获得了各模态分量的最优模型,并通过汇总各模态分量的结果得到了风电功率预测值。最后,以湖南省某风电场的实际运行数据为例,验证了EMD-PSO-BiLSTM模型可以有效提高风电功率短期预测精度。

Missing interpolation model for wind power data based on the improved CEEMDAN method and generative adversarial interpolation network

Randomness and fluctuations in wind power output may cause changes in important parameters(e.g.,grid frequency and voltage),which in turn affect the stable operation of a power system.However,owing to external factors(such as weather),there are often various anomalies in wind power data,such as missing numerical values and unreasonable data.This significantly affects the accuracy of wind power generation predictions and operational decisions.Therefore,developing and applying reliable wind power interpolation methods is important for promoting the sustainable development of the wind power industry.In this study,the causes of abnormal data in wind power generation were first analyzed from a practical perspective.Second,an improved complete ensemble empirical mode decomposition with adaptive noise(ICEEMDAN)method with a generative adversarial interpolation network(GAIN)network was proposed to preprocess wind power generation and interpolate missing wind power generation sub-components.Finally,a complete wind power generation time series was reconstructed.Compared to traditional methods,the proposed ICEEMDAN-GAIN combination interpolation model has a higher interpolation accuracy and can effectively reduce the error impact caused by wind power generation sequence fluctuations.

水田平地机GNSS高程数据EMD与S-G联合降噪研究

【目的】减小基于全球卫星导航系统(Global navigation satellite system,GNSS)的水田平地机在测量地势高程信息时存在的多路径效应和机器振动影响,提高水田平地前基准面建立的准确度,进而提升平地质量。【方法】结合经验模态分解(Empirical mode decomposition,EMD)和Savitzky-Golay(S-G)滤波各自的优势,提出了一种EMD与S-G联合降噪的方法。该方法首先采用EMD将原始高程信号分解成若干本征模态函数(Intrinsic mode functions,IMFs),利用归一化自相关函数和相关系数将其细分为噪声IMFs、混合IMFs和有效IMFs,然后利用S-G算法对混合IMFs进行滤波,最后将S-G滤波后的IMFs与有效IMFs进行重构,得到最终降噪后的数据。【结果】静态验证试验结果表明,联合滤波后的均方根误差比滤波前降低了36.9%,信噪比比滤波前提高了6.3%。田间测量试验结果表明,滤波后的数据波动范围减少了11.9%。【结论】EMD与S-G联合降噪算法有效削减了多路径效应误差和振动误差,改善了数据的平滑度,对于提高水田平地作业质量具有现实意义。

基于CEEMDAN和改进的混合时间序列模型工作面涌水量预测研究

为提高采煤工作面涌水量预测准确度,收集大量工作面涌水量观测数据进行整理、统计、分析,将涌水量稳定性、周期性和季节性特征考虑在内,提出1种基于数据驱动的完全自适应模态分解算法(CEEMDAN)和改进的混合时间序列模型工作面涌水量预测方法。该方法利用CEEMDAN处理涌水量数据,构建麻雀搜索算法(SSA)优化的长短期记忆网络(LSTM)和自回归移动平均模型(ARIMA)并行级联而成的混合时间序列模型对工作面涌水量进行预测。研究结果表明:该模型预测结果与真实数据相差更小,平均绝对误差为6.36 m 3/h,均方根误差为10.6 m 3/h,模型拟合系数为0.95,更适用于工作面涌水量预测。研究结果可为矿井工作面涌水量预测及防控提供参考。

A New Method of Wind Turbine Bearing Fault Diagnosis Based on Multi-Masking Empirical Mode Decomposition and Fuzzy C-Means Clustering

Based on Multi-Masking Empirical Mode Decomposition (MMEMD) and fuzzy c-means (FCM) clustering, a new method of wind turbine bearing fault diagnosis FCM-MMEMD is proposed, which can determine the fault accurately and timely. First, FCM clustering is employed to classify the data into different clusters, which helps to estimate whether there is a fault and how many fault types there are. If fault signals exist, the fault vibration signals are then demodulated and decomposed into different frequency bands by MMEMD in order to be analyzed further. In order to overcome the mode mixing defect of empirical mode decomposition (EMD), a novel method called MMEMD is proposed. It is an improvement to masking empirical mode decomposition (MEMD). By adding multi-masking signals to the signals to be decomposed in different levels, it can restrain low-frequency components from mixing in highfrequency components effectively in the sifting process and then suppress the mode mixing. It has the advantages of easy implementation and strong ability of suppressing modal mixing. The fault type is determined by Hilbert envelope finally. The results of simulation signal decomposition showed the high performance of MMEMD. Experiments of bearing fault diagnosis in wind turbine bearing fault diagnosis proved the validity and high accuracy of the new method.