Method of Multi-Mode Sensor Data Fusion with an Adaptive Deep Coupling Convolutional Auto-Encoder

To address the difficulties in fusing multi-mode sensor data for complex industrial machinery, an adaptive deep coupling convolutional auto-encoder (ADCCAE) fusion method was proposed. First, the multi-mode features extracted synchronously by the CCAE were stacked and fed to the multi-channel convolution layers for fusion. Then, the fused data was passed to all connection layers for compression and fed to the Softmax module for classification. Finally, the coupling loss function coefficients and the network parameters were optimized through an adaptive approach using the gray wolf optimization (GWO) algorithm. Experimental comparisons showed that the proposed ADCCAE fusion model was superior to existing models for multi-mode data fusion.

“人-车-桩-路-网”深度耦合下的配电网协同规划与运行优化

电动汽车(EV)作为连接交通电气化和电网清洁化的纽带和桥梁,可实现电力-交通-信息之间的深度耦合,形成电力-交通一体化的规划及运行架构。配电-交通融合系统(DTIS)中,EV充放电行为多时空动态交织、电能流-交通流-信息流深度融合、多利益主体动态博弈等大量不确定性因素使配电网的规划及运行优化的边界都将发生重大转变,但同时也给挖掘利用EV的移动储能特性和提升配电网灵活性带来了契机。为此,在分析“人-车-桩-路-网”深度耦合下配电网的形态演化特征基础上,剖析了新形态下配电网协同规划与运行优化所面临的新挑战,进而针对“人-车-桩-路-网”耦合下的EV灵活性建模、灵活域高效构建及预测、协同规划、运行优化4个方面关键技术展开讨论,并对相关技术问题的研究方向进行了展望。

一种可模态分离的高分辨率频率-波数法及其工程应用

高分辨率频率-波数法是通过计算F-K谱从能量角度获取主导表面波频散信息的一种常用方法。然而,由于高模态瑞利波的能量通常低于基阶波的能量,因此难以分离多模态频散信息。本文通过建立多模态瑞利波模型,并讨论其相速度、波数和能量特性,提出一种可模态分离的高分辨率频率-波数法。通过增强F-K谱上的高模态能量,提取其多模态能量的局部极值,进而得到相速度点,对所有相速度点进行概率分布并拟合,得到多模态频散曲线。工程应用表明,改进的高分辨率频率-波数法能够较好地还原多模态瑞利波信息,通过对提取的多模态频散曲线进行联合反演,可以得到与工程钻孔结果匹配较好的剪切波速度结构。

基于FBG和F-P的温度和折射率双参量传感器

提出了一种由单模布拉格光栅和多模Fabry-Perot腔级联而成的温度和折射率双参量传感器。对多模光纤的末端采用氢氟酸进行腐蚀,在腐蚀后形成的凹陷处填充紫外胶,从而形成Fabry-Perot腔。Fabry-Perot腔和单模光纤布拉格光栅级联后,构成最终的传感结构。Fabry-Perot腔对温度和折射率敏感,而光纤布拉格光栅对温度敏感而对折射率不敏感。利用上述特性,采用灵敏度矩阵法可实现对温度和折射率的同时测量。实验结果表明,传感器的温度和折射率灵敏度分别为-0.4832nm/℃和-508.64pm/RIU。该传感器具有制作工艺简单、结构紧凑、成本低、灵敏度高的优点,有很好的应用前景。

基于DTW K-medoids与VMD-多分支神经网络的多用户短期负荷预测

多用户电力负荷预测是指根据历史负荷数据对多个用户或区域的电力负荷进行预测,可使电网企业掌握不同用户或区域的电力需求,以便更好地开展规划和实施调度优化等。然而由于各用户呈现出复杂多样的用电行为,采用传统方法难以进行统一建模并实现快速准确预测。为此,构建了一种基于DTW Kmedoids与VMD-多分支神经网络的多用户短期负荷预测模型。首先,采用DTW K-medoids法进行用户负荷数据聚类,利用动态时间弯曲(dynamic time warping,DTW)计算数据间的距离,取代K-medoids算法中传统的欧氏距离度量方式,以改善多用户负荷聚类的效果;在此基础上,为充分表征负荷历史数据的长短期时序依赖特征,建立了一种基于变分模态分解(variational mode decomposition,VMD)-多分支神经网络模型的并行预测方法,用于多用户短期负荷预测;最后,使用某地区20个用户365天的负荷数据进行聚类、训练和测试实验,结果显示该模型结果的平均绝对误差和均方根误差等指标均较对比模型有较大幅度降低,表明该方法可有效表征多类用户的用电行为,提升多用户负荷预测效率和精度。

基于SI-SB系统安全模型的多层级边缘智能管控模式

为探索信息化、智能化技术赋能下的创新型安全生产管控模式,从安全信息学的角度分析安全管控过程中的信息流动特点,提出安全生产多层级边缘智能管控模式;基于安全信息-安全行为(SI-SB)系统安全模型分析安全管控过程中安全决策偏差和滞后的机制,提出安全管控系统性能改进的思路;结合安全生产组织管理体系特点和数字化技术优势,阐述数字化技术在信息感知传递、安全信息解释和安全行为引导等3个方面的赋能依据,以及数字化感知、智能化决策和多层级管控等3个方面的赋能途径,并提出具备智能决策、敏捷响应、弹性扩展和人机协同特点的安全生产多层级边缘智能管控模式;在紧急事件、短周期管控、长周期管控3类场景中,对应用智能管控模式前后的安全事件响应进行时效性计算和对比。结果表明:所提出的多层级边缘智能管控模式能够显著提高安全管控效能。

Signal classification method based on data mining formulti-mode radar

For the multi-mode radar working in the modern electronicbattlefield, different working states of one single radar areprone to being classified as multiple emitters when adoptingtraditional classification methods to process intercepted signals,which has a negative effect on signal classification. A classificationmethod based on spatial data mining is presented to address theabove challenge. Inspired by the idea of spatial data mining, theclassification method applies nuclear field to depicting the distributioninformation of pulse samples in feature space, and digs out thehidden cluster information by analyzing distribution characteristics.In addition, a membership-degree criterion to quantify the correlationamong all classes is established, which ensures classificationaccuracy of signal samples. Numerical experiments show that thepresented method can effectively prevent different working statesof multi-mode emitter from being classified as several emitters,and achieve higher classification accuracy.

基于CEEMDAN-SBiGRU-OMHA的短期电力负荷预测

为了提高短期电力负荷预测的精准度,充分挖掘电力负荷数据的复杂相关性,提出了一种优化多头注意力机制的CEEMDAN-SBiGRU组合预测模型,改进了特征提取和特征融合两个模块.首先,采用自适应噪声完全集成经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)将电力负荷数据分解成多个内在模态函数(IMF)和一个残差信号(RES);同时引入降噪自编码器DAE挖掘数据中受气象因素、工作日类型和温度变化的潜在特征.其次,将提取到的复杂特征输入至堆叠双向门控循环单元(stacked bidirectional gated recurrent unit,SBiGRU)模块中继续学习,以获取隐藏状态.最后,将获取的隐藏状态输入至加入残差机制和层归一化优化的多头注意力(optimized multi-head attention,OMHA)机制模块,可以准确地给重要特征分配更高的权重,解决噪声干扰问题.实验结果表明,CEEMDAN-SBiGRU-OMHA组合模型具有更高的精确性.

3D FEM simulation of responses of LWD multi-mode resistivity imaging sonde

A new multi-mode resistivity imaging sonde, with toroidal coils as source, can conduct three resistivity measurements: azimuthal resistivity, lateral resistivity, and bit resistivity measurements. Thus, the logging time and cost are greatly saved. The toroidal coils are simplified as an extended voltage dipole and the response equations are derived for a homogenous formation. Based on 3D FEM, the depth of investigation(DOI), vertical resolution, circumferential azimuthal capacity, borehole diameter, mud resistivity, thickness of target formation, and the resistivity of the surrounding formation and mud invasion are simulated. The results suggest that the three measurement modes of the new sonde are different in vertical resolutions and DOIs. The circumferential detection ability of the azimuth button depends on the contrast between the anomaly and formation resistivity and the open angle of the anomaly. Whether the borehole is truncated at the bit or not has a great influence on the simulation results. The borehole and mud invasion affect the apparent resistivity in all modes, but the effects of resistivity of surrounding formation and thickness of the target formation are only corrected for lateral resistivity measurement.

Multi-mode process monitoring based on a novel weighted local standardization strategy and support vector data description

There are multiple operating modes in the real industrial process, and the collected data follow the complex multimodal distribution, so most traditional process monitoring methods are no longer applicable because their presumptions are that sampled-data should obey the single Gaussian distribution or non-Gaussian distribution. In order to solve these problems, a novel weighted local standardization(WLS) strategy is proposed to standardize the multimodal data, which can eliminate the multi-mode characteristics of the collected data, and normalize them into unimodal data distribution. After detailed analysis of the raised data preprocessing strategy, a new algorithm using WLS strategy with support vector data description(SVDD) is put forward to apply for multi-mode monitoring process. Unlike the strategy of building multiple local models, the developed method only contains a model without the prior knowledge of multi-mode process. To demonstrate the proposed method's validity, it is applied to a numerical example and a Tennessee Eastman(TE) process. Finally, the simulation results show that the WLS strategy is very effective to standardize multimodal data, and the WLS-SVDD monitoring method has great advantages over the traditional SVDD and PCA combined with a local standardization strategy(LNS-PCA) in multi-mode process monitoring.

面向微电网群的云储能经济-低碳-可靠多目标优化配置方法

微电网群技术通过多微电网间的协同互补,促进了分布式可再生能源在微电网间的协同消纳,被认为是未来新型电力系统中分布式电源接入电网的重要方式之一。考虑微电网群中多微电网协同互济的特性,提出了一种面向微电网群的“集中共享、分散复用”云储能运营架构。其中,集中式储能面向微电网群中的所有微电网进行共享,以合作共建、容量共享的方式为所有微电网提供服务,旨在降低各微电网的储能使用成本;分布式储能主要服务于微电网群中的各个微电网,以保障各微电网自身的可靠性为主要目标,同时兼顾协同互济的储能复用需求。在此基础上,构建了经济、低碳及可靠多目标驱动的云储能双层优化配置模型,并基于第二代非支配遗传算法实现模型求解。然后,建立了微电网群云储能系统商业模式,基于Shapley值法及系统运行模拟实现云储能系统投资、运营成本及效益的合理分摊,提出云储能初始投资成本的分配方法。最后,基于IEEE 33节点系统搭建微电网群系统并开展算例分析,结果显示所提方法可提出面向不同投资偏好的云储能配置方案解集,并验证了云储能模式提升系统投资运营效益的有效性。

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.

基于双模式分解多通道输入的VSC-STATCOM逆变器故障诊断模型

针对传统电压源型静止同步补偿器中逆变器故障诊断存在的信号特征提取不充分,深度学习网络识别能力不足以及高噪声情况下识别率较低等问题,提出了一种基于双模式分解、多通道输入(MCI)、并行卷积神经网络(PCNN)、双向长短时记忆(BiLSTM)网络和自注意力(SA)机制组合的逆变器故障诊断方法。首先利用变分模态分解和时变滤波经验模态分解对逆变器输出的三相电流进行分解,降低原始信号复杂程度,实现不同模态分量间的规律互补;其次,利用MCI-PCNN-BiLSTM-SA组合模型对特征矩阵进行深层特征提取、学习和识别;最后,通过仿真进行验证,结果表明所提方法特征提取能力较强,在无噪声情况下平均识别率高达99.48%,在高噪声情况下平均识别率达95.59%。

Current multifunctional albumin-based nanoplatforms for cancer multi-mode therapy

Albumin has been widely applied for rational design of drug delivery complexes as natural carriers in cancer therapy due to its distinct advantages of biocompatibility,abundance,low toxicity and versatile property.Hence,various types of multifunctional albumin-based nanoplatforms(MAlb-NPs)that adopt multiple imaging and therapeutic techniques have been developed for cancer diagnosis and treatment.Stimuli-responsive release,including reduction-sensitive,p H-responsive,concentration-dependent and photodynamic-triggered,is important to achieve low-toxicity cancer therapy.Several types of imaging techniques can synergistically improve the effectiveness of cancer therapy.Therefore,combinational theranostic is considered to be a prospective strategy to improve treatment efficiency,minimize side effects and reduce drug resistance,which has received tremendous attentions in recent years.In this review,we highlight several stimuli-responsive albumin nanoplatforms for combinational theranostic.

Vortex-Induced Vibration of a Tension Leg Platform Tendon:Multi-Mode Limit Cycle Oscillations

This paper studies the application of mathematical models to analyze the vortex-induced vibrations of the tendons of a given TLP along the Indian coastline, by using an analytical approach, using MATLAB. The tendon is subjected to a steady current load, which causes vortex-shedding downstream, leading to cross-flow vibrations. The magnitude of the excitation(lift and drag coefficients) depends on the vortex-shedding frequency. The resulting vibration is studied for possible resonant behavior. The excitation force is quantified empirically, the added mass by potential flow hydrodynamics, and the vibration by normal mode summation method. Non-linear viscous damping of the water is considered. The non-linear oscillations are studied by the phase-plane method, investigating the limit-cycle oscillations. The stable/unstable regions of the dynamic behavior are demarcated. The modal contribution to the total deflection is studied to establish the possibility of resonance of one of the wet modes with the vortex-shedding frequency.

A global analysis of multi-mode sea surface temperature pattern

The variability of the air-sea system in the low-frequency time domain can be decomposed into several systematic climate modes, namely, the decadal variability （DV） mode, the El Nino Southem Oscillation （ENSO） mode, the annual cycle （AC） mode, the semiannual cycle （ SC ） mode and the intraseasonal variability （ ISV ） mode. The combination of these primary modes in the air - sea system orchestrates a complex climate system. The multi-mode low-frequency variability in SST is investigated based on 22 a SST records from 1982 through 2003. The variation of SST in the past two decades undergoes a different combination of these dominant climate modes over different regions, which leads to an interesting new classification of the global ocean based on the relative importance of these modes. The new classification can provide ideal locations for better monitoring of these low-frequency modes in the scientific proof sense. Moreover, two no-annual variation and 14 no-semiannual variation oceanic points, termed annual and semiannual amphidromes, have been well defined in the AC and SC phase maps. The formation of these nodal points is attributed to the couplings of climate modes in EOF analysis results.

Memetic algorithm for multi-mode resource-constrained project scheduling problems

A memetic algorithm （MA） for a multi-mode resourceconstrained project scheduling problem （MRCPSP） is proposed. We use a new fitness function and two very effective local search procedures in the proposed MA. The fitness function makes use of a mechanism called ＂strategic oscillation＂ to make the search process have a higher probability to visit solutions around a ＂feasible boundary＂. One of the local search procedures aims at improving the lower bound of project makespan to be less than a known upper bound, and another aims at improving a solution of an MRCPSP instance accepting infeasible solutions based on the new fitness function in the search process. A detailed computational experiment is set up using instances from the problem instance library PSPLIB. Computational results show that the proposed MA is very competitive with the state-of-the-art algorithms. The MA obtains improved solutions for one instance of set J30.

基于VMD-WOA混合多尺度分解的区间组合预测模型

针对传统的点预测模型难以适用于随机性复杂系统和非线性非平稳时间序列预测的问题,提出基于VMD-WOA混合多尺度分解的区间组合预测模型。首先,引入基于鲸鱼优化(WOA)的变分模态分解(VMD)混合分解算法,得到最优区间模态子序列;其次,对各区间模态分序列使用指数平滑方法(Holt′s)、支持向量回归(SVR)和BP神经网络预测,得到3个单项预测结果,运用组合预测模型得到模态组合子序列;最后,对模态组合子序列重构,得到最终的区间组合预测序列。为了验证模型的有效性,选取AQI数据进行预测分析,实验表明所提出的基于VMD-WOA的区间组合预测方法具有较高的预测精度和良好的适应性。

基于EMD-DELM-LSTM组合模型的湖泊水位多时间尺度预测

针对水位时间序列具有线性与非线性混合、不确定性高等特点带来的预测困难问题,提出了一种基于经验模态分解(EMD)、长短时记忆网络(LSTM)和深度极限学习机(DELM)的EMD-DELM-LSTM组合模型,其中DELM和LSTM采用并联结构预测,并与EMD串联连接。首先使用EMD将原始信号分解为若干个具有单一特征的本征模态函数(IMFs),再将IMFs分类重组为高、中、低频信号后输入DELM-LSTM并联结构中进行预测并重构。以广州某大学重要湖泊为例验证模型的有效性,结果表明,与EMD-LSTM、EMD-DELM、LSTM、DELM和BiLSTM模型相比,本模型在不同时间尺度下的预测性能均有显著提升,其中40 min时间尺度下的预测性能提升效果最为明显,分别较对比模型提升43.08%、22.92%、45.79%、30.92%和47.31%。可见,本模型对于不同时间尺度的水位预测具有良好的可靠性和稳定性。

Segregation modes,characteristics,and mechanisms of multi-component lignite in a vibrated gas-fluidized bed

The segregation modes and characteristics of 1-6 mm multi-component lignite were studied in a microporous, vibrated, gas-fluidized bed of Φ110 mm ×400 mm. The effects of particle density and size, vibration frequency and amplitude, and gas velocity on these characteristics were considered. The average size, average density, size deviation coefficient, and density deviation coefficient were used to identify lignite size and density. The separation efficiency was adopted to evaluate the segregation performance,and the segregation mechanisms were explored. The results show that ε(size,max) of heterogeneous multisize-component lignite with K_(size) = 65% reaches 80% at f= 20 Hz, A = 5 mm, and N =(1,3). ε_(density,max) Of heterogeneous multi-density-component lignite with K_(density)= 25% reaches 50% at f = 15 Hz, A = 5 mm,and N =(1,1.5). The density segregations of 1-3 and 3-6 mm multi-component mixtures are remarkable,ε_(density,max)= 42% and 31% at f= 14 and 16 Hz, and A = 3 and 5 mm, respectively. The size segregation of 1-6 mm multi-component mixture is prominent and ε_(size,max)= 55% at f= 15 Hz, A = 5 mm. The mediumsized mixture with a narrow size distribution at low frequency is favorable for density segregation,and a mixture with a wider size distribution at high frequency is most favorable for size segregation.Precise control of gas flow and vibration as well as optimal design of the fluidized bed can improve the performance of segregation in the vibrated gas-fluidized bed.