A debris-flow forecasting method with infrasound-based variational mode decomposition and ARIMA

Infrasound,known for its strong penetration and low attenuation,is extensively used in monitoring and warning systems for debris flows.Here,a debris-flow forecasting method was proposed by combining infrasound-based variational mode decomposition and Autoregressive Integrated Moving Average(ARIMA)model.High-precision infrasound sensor was utilized in experiments to record signals under twelve varying conditions of debris flow volume and velocity.Variational mode decomposition was performed on the detected raw signals,and the optimal decomposition scale and penalty factor were obtained through the sparrow search algorithm.The Hilbert transform,rescaled range analysis,power spectrum analysis,and Pearson correlation coefficients judgment criteria were employed to separate and reconstruct the signals.Based on the reconstructed infrasound signals,an ARIMA model was constructed to forecast the trend of debris flow infrasound signal.Results reveal that the Hilbert transform effectively separated noise,and the predictive model’s results fell within a 95%confidence interval.The Mean Absolute Percentage Error(MAPE)across four experiments were 4.87%,5.23%,5.32%and 4.47%,respectively,showing a satisfactory accuracy and providing an alternative for predicting debris flow by infrasound signals.

Research on Modulation Signal Denoising Method Based on Improved Variational Mode Decomposition

In order to further analyze the micro-motion modulation signals generated by rotating components and extract micro-motion features,a modulation signal denoising algorithm based on improved variational mode decomposition(VMD)is proposed.To improve the time-frequency performance,this method decomposes the data into narrowband signals and analyzes the internal energy and frequency variations within the signal.Genetic algorithms are used to adaptively optimize the mode number and bandwidth control parameters in the process of VMD.This approach aims to obtain the optimal parameter combination and perform mode decomposition on the micro-motion modulation signal.The optimal mode number and quadratic penalty factor for VMD are determined.Based on the optimal values of the mode number and quadratic penalty factor,the original signal is decomposed using VMD,resulting in optimal mode number intrinsic mode function(IMF)components.The effective modes are then reconstructed with the denoised modes,achieving signal denoising.Through experimental data verification,the proposed algorithm demonstrates effective denoising of modulation signals.In simulation data validation,the algorithm achieves the highest signal-to-noise ratio(SNR)and exhibits the best performance.

Variational Mode Decomposition for Rotating Machinery Condition Monitoring Using Vibration Signals

The failure of rotating machinery applications has major time and cost effects on the industry.Condition monitoring helps to ensure safe operation and also avoids losses.The signal processing method is essential for ensuring both the efficiency and accuracy of the monitoring process.Variational mode decomposition(VMD)is a signal processing method which decomposes a non-stationary signal into sets of variational mode functions(VMFs)adaptively and non-recursively.The VMD method offers improved performance for the condition monitoring of rotating machinery applications.However,determining an accurate number of modes for the VMD method is still considered an open research problem.Therefore,a selection method for determining the number of modes for VMD is proposed by taking advantage of the similarities in concept between the original signal and VMF.Simulated signal and online gearbox vibration signals have been used to validate the performance of the proposed method.The statistical parameters of the signals are extracted from the original signals,VMFs and intrinsic mode functions(IMFs)and have been fed into machine learning algorithms to validate the performance of the VMD method.The results show that the features extracted from VMD are both superior and accurate for the monitoring of rotating machinery.Hence the proposed method offers a new approach for the condition monitoring of rotating machinery applications.

AMicroseismic Signal Denoising Algorithm Combining VMD and Wavelet Threshold Denoising Optimized by BWOA

The denoising of microseismic signals is a prerequisite for subsequent analysis and research.In this research,a new microseismic signal denoising algorithm called the Black Widow Optimization Algorithm(BWOA)optimized VariationalMode Decomposition(VMD)jointWavelet Threshold Denoising(WTD)algorithm(BVW)is proposed.The BVW algorithm integrates VMD and WTD,both of which are optimized by BWOA.Specifically,this algorithm utilizes VMD to decompose the microseismic signal to be denoised into several Band-Limited IntrinsicMode Functions(BLIMFs).Subsequently,these BLIMFs whose correlation coefficients with the microseismic signal to be denoised are higher than a threshold are selected as the effective mode functions,and the effective mode functions are denoised using WTD to filter out the residual low-and intermediate-frequency noise.Finally,the denoised microseismic signal is obtained through reconstruction.The ideal values of VMD parameters and WTD parameters are acquired by searching with BWOA to achieve the best VMD decomposition performance and solve the problem of relying on experience and requiring a large workload in the application of the WTD algorithm.The outcomes of simulated experiments indicate that this algorithm is capable of achieving good denoising performance under noise of different intensities,and the denoising performance is significantly better than the commonly used VMD and Empirical Mode Decomposition(EMD)algorithms.The BVW algorithm is more efficient in filtering noise,the waveform after denoising is smoother,the amplitude of the waveform is the closest to the original signal,and the signal-to-noise ratio(SNR)and the root mean square error after denoising are more satisfying.The case based on Fankou Lead-Zinc Mine shows that for microseismic signals with different intensities of noise monitored on-site,compared with VMD and EMD,the BVW algorithm ismore efficient in filtering noise,and the SNR after denoising is higher.

An extraction method for pressure beat vibration characteristics of hydraulic drive system based on variational mode decomposition

In the pump-controlled motor hydraulic transmission system,when the pressure pulsation frequencies seperately generated by the pump and the motor are close to each other,the hydraulic system will generate a strong pressure beat vibration phenomenon,which will seriously affect the smooth running of the hydraulic system.However,the modulated pressure signal also carries information related to the operating state of the hydraulic system,and a accurate extraction of pressure vibration characteristics is the key to obtain the operating state information of the hydraulic system.In order to extract the pressure beat vibration signal component effectively from the multi-component time-varying aliasing pressure signal and reconstruct the time domain characteristics,an extraction method of the pressure beat vibration characteristics of the hydraulic transmission system based on variational mode decomposition(VMD)is proposed.The experimental results show that the VMD method can accurately extract the pressure beat vibration characteristics from the high-pressure oil pressure signal of the hydraulic system,and the extraction effect is preferable to that of the traditional signal processing methods such as empirical mode decomposition(EMD).

基于DBO-VMD滤波的煤岩爆破电磁信号时-频特征

井工开采爆破作业的常规振动监测易受周围环境或监测系统影响,使煤岩破裂信号提取困难,本文提出一种基于电磁信号的爆破监测方法,并研究了爆破电磁信号时频特征.首先,提出了基于蜣螂优化算法(DBO)寻优变分模态分解(VMD)参数的降噪模型,得到了此类信号的最佳适应度函数为包络熵,该函数可迅速锁定最优参数组合,避免模态混叠现象,且基于DBO-VMD的降噪模型性能优于基于经验模态分解(EMD)的降噪模型;其次,提出了基于经验法的中心频率准则降噪方法,并证实了该方法降噪性能在信噪比表现上约是EMD的2倍;最后,发现煤岩破裂期的偏度大于0、峭度介于0.9~4.6,脉冲指标介于3.7~6.1,频段在20 kHz以下,主破裂事件发生时信号能量最大,主频段在5 kHz以下,并随着频率上升信号分量幅值迅速下降,非破裂期的低能脉冲则集中于0~3 kHz频段.本文的研究结果明确了爆破电磁辐射信号的时-频特征,为井工开采过程中爆破的电磁辐射监测奠定了理论基础.

Removal of Ocular Artifacts from Electroencephalo-Graph by Improving Variational Mode Decomposition

Ocular artifacts in Electroencephalography(EEG)recordings lead to inaccurate results in signal analysis and process.Variational Mode Decomposition(VMD)is an adaptive and completely nonrecursive signal processing method.There are two parameters in VMD that have a great influence on the result of signal decomposition.Thus,this paper studies a signal decomposition by improving VMD based on squirrel search algorithm(SSA).It’s improved with abilities of global optimal guidance and opposition based learning.The original seasonal monitoring condition in SSA is modified.The feedback of whether the optimal solution is successfully updated is used to establish new seasonal monitoring conditions.Opposition-based learning is introduced to reposition the position of the population in this stage.It is applied to optimize the important parameters of VMD.GOSSA-VMD model is established to remove ocular artifacts from EEG recording.We have verified the effectiveness of our proposal in a public dataset compared with other methods.The proposed method improves the SNR of the dataset from-2.03 to 2.30.

基于参数优化VMD和改进GoogLeNet的滚动轴承故障诊断

【目的】深度学习方法在滚动轴承故障诊断领域的应用十分有效,但传统神经网络由于采用单一尺度的卷积核而无法多尺度提取特征,且并未考虑到不同特征在故障诊断中的重要程度,滚动轴承信号在噪声干扰下的故障特征提取较为困难。为此,提出了一种基于参数优化变分模态分解(Variational Mode Decomposition,VMD)降噪,并用以注意力机制改进的GoogLeNet网络进行诊断的滚动轴承故障诊断方法。【方法】以局部极小包络熵为适应度函数,采用麻雀搜索算法(Sparrow Search Algorithm,SSA)对VMD参数组合[K,α]进行寻优;利用优化后的VMD算法分解轴承振动信号,得到若干模态分量,根据包络熵和峭度筛选故障特征丰富的模态分量,进行信号重构;以重构信号构建特征矩阵并输入经改进的GoogLeNet网络中完成诊断。【结果】试验结果表明,在不同噪声背景下,该方法诊断准确率为95.5%~99.8%,比其他方法噪声鲁棒性更好。

Ultrasonic echo denoising in liquid density measurement based on improved variational mode decomposition

The ultrasonic echo in liquid density measurement often suffers noise,which makes it difficult to obtain the useful echo waveform,resulting in low accuracy of density measurement.A denoising method based on improved variational mode decomposition(VMD)for noise echo signals is proposed.The number of decomposition layers of the traditional VMD is hard to determine,therefore,the center frequency similarity factor is firstly constructed and used as the judgment criterion to select the number of VMD decomposition layers adaptively;Secondly,VMD algorithm is used to decompose the echo signal into several modal components with a single modal component,and the useful echo components are extracted based on the features of the ultrasonic emission signal;Finally,the liquid density is calculated by extracting the amplitude and time of the echo from the modal components.The simulation results show that using the improved VMD to decompose the echo signal not only can improve the signal-to-noise ratio of the echo signal to 20.64 dB,but also can accurately obtain the echo information such as time and amplitude.Compared with the ensemble empirical mode decomposition(EEMD),this method effectively suppresses the modal aliasing,keeps the details of the signal to the maximum extent while suppressing noise,and improves the accuracy of the liquid density measurement.The density measurement accuracy can reach 0.21%of full scale.

基于WOA-VMD与PSO-SVM的滚动轴承故障诊断

滚动轴承工作环境恶劣且振动信号容易受到噪声干扰,使得轴承故障不易被识别。针对此问题,提出了鲸鱼优化算法变分模态分解(whale optimization algorithm variational mode decomposition,WOA-VMD)和粒子群算法优化支持向量机(particle swarm optimization support vector machine,PSO-SVM)的滚动轴承故障诊断方法,首先,采用WOA-VMD寻找分解层数和惩罚因子最优参数组合;其次,将轴承正常信号以及故障信号作为输入进行变分模态分解(variational mode decomposition,VMD),得到若干个本征模态函数(intrinsic mode function,IMF),计算各模态分量的样本熵值作为特征向量;再次,将特征向量分成训练集和测试集;最后,将分组的特征向量分别输入到支持向量机(support vector machine,SVM)模型与PSO-SVM模型中进行训练与故障诊断。结果表明,SVM模型故障诊断率分别为89.1667%和86.2500%,PSO-SVM模型故障诊断率分别为100%和99.5833%,轴承故障得到了有效识别。

基于POA-VMD-WT的MEMS去噪方法

针对MEMS传感器所测得的加速度和角速度输出信号噪声较大问题,提出一种基于鹈鹕优化算法(pelican optimization algorithm,POA)的变分模态分解(variational mode decomposition,VMD)结合小波阈值(wavelet threshold,WT)的去噪方法。首先利用POA对VMD的参数组合进行优化选择,然后应用POA-VMD将含噪信号自适应、非递归地分解为一系列本征模态函数(intrinsic mode function,IMF)。再通过计算每个IMF的余弦相似度对IMFs进行分类,根据计算结果将IMFs分为噪声主导分量与信号主导分量,对分类后的噪声主导分量进行改进小波阈值去噪处理,最后对处理后的噪声分量与信号主导分量进行重构,获得降噪后的MEMS传感器信号。静态和动态实验结果表明,该方法去噪处理后信号的信噪比分别提高12和10 dB,均方误差分别降低75.5%和46.6%,去噪效果显著,能够提高MEMS传感器的精度。

基于Spearman相关性阈值寻优和VMD-LSTM的用户级综合能源系统超短期负荷预测

由于用户级综合能源系统(integrated energy system,IES)的多元负荷序列之间复杂的耦合关系及易受外部因素影响等原因,综合能源系统多元负荷的精准预测面临很大困难。为此,提出一种基于Spearman相关性分析阈值寻优(threshold optimization,TO)和变分模态分解结合长短期记忆网络(variational mode decomposition based long short-term memory network,VMD-LSTM)的多元负荷预测方法。首先,使用斯皮尔曼等级(Spearman rank,SR)相关系数定量计算多元负荷间以及负荷与其他气候因素间的相关关系并通过循环寻优确定最优相关阈值,然后采用VMD算法将以最优阈值筛选出的负荷特征序列分解成更简单、平稳、有规律性的本征模态函数(intrinsic mode function,IMF)后与最优气象特征一起输入LSTM模型进行负荷预测。通过某用户级IES的实际数据对所提方法的有效性进行了验证,结果表明,所提方法能有效提高IES的多元负荷预测精度。

基于VMD-ISSA-GRU组合模型的短期风电功率预测

为解决风速不确定性和波动性造成风电功率预测精度不高的问题,提出一种基于变分模态分解(VMD)、改进麻雀搜索算法(ISSA)和门控循环神经网络(GRU)的VMD-ISSA-GRU组合模型。首先,利用中心频率法确定采用VMD分解后的模态分量个数,这样有效避免了过分解或者分解不充分。其次引入混沌映射、非线性递减权重以及一个突变策略来改进麻雀搜索算法,用于优化门控循环神经网络,然后对分解得到的各个子序列建立ISSA-GRU预测模型,最后叠加每个子序列的预测值得到最终的预测值。将该模型用于实际风电功率预测,实验结果表明:VMD-ISSA-GRU组合模型的平均绝对误差、平均绝对百分比误差、均方根误差分别为1.2118MW、1.8900及1.5916MW;相较于传统的GRU、长短时记忆(LSTM)神经网络、BiLSTM(Bi-directional LSTM)神经网络模型以及其他组合模型在预测精度上都有明显的提升,能很好地解决风电功率预测精度不高的问题.

基于VMD-GA-BiLSTM的月降水量预测方法

利用辽宁省气象局提供的地面观测降水资料,构建了具有多元时间特征的降水数据,采用变分模态分解方法(variational mode decomposition,VMD)组合遗传算法(genetic algorithm,GA)对双向长短时记忆神经网络(bidirectional long short-term memory,BiLSTM)进行优化,建立基于VMD-GA-BiLSTM的月降水量预测模型,并与BiLSTM、VMD-BiLSTM和GA-BiLSTM进行实验对比,应用均方根误差(root mean square error,RMSE)、平均绝对误差(mean absolute error,MAE)和R 2决定系数作为模型评价指标。实验结果表明:VMD-GA-BiLSTM模型的R 2决定系数达到0.98,RMSE和MAE表现更低,验证了VMD-GA-BiLSTM模型在时间序列预测方面的优势。

基于新型相似日选取和VMD-NGO-BiGRU的短期光伏功率预测

光伏功率预测在现代电力系统调度和运行中起着重要作用.针对光伏发电功率的多变性和复杂性,提出了一种基于新型相似日选取和北方苍鹰算法(Northern Goshawk Optimization,NGO)优化双向门控循环单元(Bidirectional Gated Recurrent Unit,BiGRU)的短期光伏功率预测方法.首先,利用斯皮尔曼相关系数选取主要气象因子,通过变分模态分解(Variational Mode Decomposition,VMD)将原始光伏功率和最大气象因子分解重构为一系列子信号.其次,通过构建新的评价指标筛选出相似日数据集,利用一组BiGRU建立以相似日子信号为网络输入的深度学习模型,并利用NGO对每个BiGRU网络的超参数进行有效优化.最后,对各子信号的预测结果进行综合,得到最终的光伏功率预测值.仿真结果表明,所提混合深度学习方法在预测精度和计算效率方面均优于其他方法.

基于NGO-VMD和改进GoogLeNet的齿轮箱故障诊断方法

目前的齿轮箱故障诊断方法,在多转速工况及噪声干扰下,存在过拟合及诊断效果不佳的问题。针对此问题,提出一种北方苍鹰(NGO)算法优化变分模态分解(VMD)结合改进GoogLeNet的齿轮箱故障诊断方法。使用NGO对VMD进行参数寻优,利用优化后的VMD去除故障信号中的噪声;对原始GoogLeNet的结构进行合理删减,并利用延迟丢弃法、可训练的ReLU函数(TReLU)对其改进;最后,将去噪后的故障信号转换为二维图作为改进GoogLeNet的输入数据进行网络的训练及分类,得到故障诊断结果。实验结果表明:与其他降噪方法相比,NGO-VMD方法的降噪效果明显,能显著提高故障诊断的准确率;与常见的卷积神经网络相比,提出的改进GoogLeNet能进一步提高故障诊断的准确率,达到了97.2%。

一种参数自适应VMD应用于轴承故障特征提取

针对传统的变分模态分解(VMD)需要预先设置模态个数和惩罚参数,提出了一种基于麻雀搜索算法(SSA)的参数自适应VMD方法。首先,引入一种新的测量指标-相关脉冲,该指标能反映出原始信号与分解模态之间的相关性,并且能有效突出包含丰富信息的模态。其次,基于相关脉冲指标,采用麻雀搜索算法选择最优VMD分解参数。最后,通过最大相关脉冲指标对模态分量进行分析,利用希尔伯特包络谱进行频谱分析。此外,将故障轴承放在轴承寿命试验台上进行仿真验证,实验结果表明该方法在轴承故障特征提取上具有可行性。

基于双层优化VMD-LSTM的农村超短期电力负荷预测

稳定的供电是农村发展建设的有力保障,而电力负荷水平是建设效果的重要衡量标准,因此建立精确的负荷预测模型可以更准确直观显现电力负荷情况,为供电公司制定决策提供有力支撑。由于LSTM负荷预测模型在数据预测方面存在收敛性差、预测精度不高等问题,为提高模型的预测精度,提出一种基于双层优化VMD-LSTM的超短期电力负荷预测方法。首先提出麻雀算法优化变分模态分解(sparrow variational mode decomposition,SVMD),通过SVMD将原始数据转化为模态分量(intrinsic mode functions,IMF);其次采用改进樽海鞘群算法(association salp swarm algorithm,ASSSA)优化LSTM模型。通过引入4种策略增强标准樽海鞘算法优化能力;最后将各模态分量分别代入到新模型并进行叠加预测。选取辽宁省某市某乡村10kV变压器真实历史负荷数据,以均方根误差(RMSE)、平均绝对误差(MAE)、平均绝对百分比误差(MAPE)、拟合度(R^(2))作为评价指标,并与其他基础预测模型进行对比,结果表明,改进后的算法在计算精度、稳定性方面均优于其他基础预测模型。

基于WOA-VMD-XGBoost的混凝土坝变形预测

建立混凝土坝高精准变形预测模型是掌握坝体结构服役性态的关键,而其变形监测数据具有复杂的非线性和非平稳特征,会影响预测模型的精度及泛化能力。针对上述问题,引入鲸鱼优化算法(WOA)和包络熵理论自适应寻优变分模态分解(VMD)参数,根据最佳参数组合多尺度分解变形数据,得到多个不同特征尺度的本征模态函数(IMF)。通过重构分量为新分量,将新分量分别输入极端梯度提升(XGBoost)模型中进行预测,叠加各预测结果得到最终预测值。基于山口岩碾压混凝土拱坝变形监测数据,开展支持向量回归机(SVR)、随机森林(RF)、XGBoost、WOA-VMD-XGBoost等4种模型的精度、泛化能力对比研究。结果表明:相比于单一预测模型,组合模型有效挖掘了变形信号多尺度特征,降低了非线性、非平稳性对模型性能的影响,在精度、泛化能力中表现出更高性能。该组合模型为大坝变形监测提供了理论依据和应用参考。

基于VMD-SSA-LSTM考虑刀具磨损的数控铣床切削功率预测模型研究

传统的切削过程功率获取需要基于复杂的切削功率模型且很少考虑刀具磨损的影响,针对此设计了一种基于变分模态分解(VMD)、麻雀搜索算法(SSA)、长短时记忆(LSTM)神经网络的考虑刀具磨损的数控铣床切削功率预测模型,该模型无需解构数控铣床运行过程的能耗机理,基于一次性的历史实验数据即可实现数控铣床切削过程功率的高精度预测。首先,采用人工智能机器视觉技术对刀具磨损图片进行分析处理,获取刀具磨损图像的数字化特征,从而得到刀具最大磨损量;然后,建立基于VMD-SSA-LSTM考虑刀具磨损的数控铣床切削功率预测模型,利用VMD对数控铣床运行数据进行分解,采用SSA算法对LSTM神经网络超参数进行寻优,并将分解出的铣床运行数据分量输入到LSTM神经网络中,接着将每个分量的预测值相加,得到切削功率预测值;最后以面铣加工为例,将所提出的预测模型与BP神经网络、LSTM神经网络和传统模型进行对比分析,验证了所提模型的有效性和优越性。