Structured Multi-Head Attention Stock Index Prediction Method Based Adaptive Public Opinion Sentiment Vector

The present study examines the impact of short-term public opinion sentiment on the secondary market,with a focus on the potential for such sentiment to cause dramatic stock price fluctuations and increase investment risk.The quantification of investment sentiment indicators and the persistent analysis of their impact has been a complex and significant area of research.In this paper,a structured multi-head attention stock index prediction method based adaptive public opinion sentiment vector is proposed.The proposedmethod utilizes an innovative approach to transform numerous investor comments on social platforms over time into public opinion sentiment vectors expressing complex sentiments.It then analyzes the continuous impact of these vectors on the market through the use of aggregating techniques and public opinion data via a structured multi-head attention mechanism.The experimental results demonstrate that the public opinion sentiment vector can provide more comprehensive feedback on market sentiment than traditional sentiment polarity analysis.Furthermore,the multi-head attention mechanism is shown to improve prediction accuracy through attention convergence on each type of input information separately.Themean absolute percentage error(MAPE)of the proposedmethod is 0.463%,a reduction of 0.294% compared to the benchmark attention algorithm.Additionally,the market backtesting results indicate that the return was 24.560%,an improvement of 8.202% compared to the benchmark algorithm.These results suggest that themarket trading strategy based on thismethod has the potential to improve trading profits.

An Intelligent Framework for Resilience Recovery of FANETs with Spatio-Temporal Aggregation and Multi-Head Attention Mechanism

Due to the time-varying topology and possible disturbances in a conflict environment,it is still challenging to maintain the mission performance of flying Ad hoc networks(FANET),which limits the application of Unmanned Aerial Vehicle(UAV)swarms in harsh environments.This paper proposes an intelligent framework to quickly recover the cooperative coveragemission by aggregating the historical spatio-temporal network with the attention mechanism.The mission resilience metric is introduced in conjunction with connectivity and coverage status information to simplify the optimization model.A spatio-temporal node pooling method is proposed to ensure all node location features can be updated after destruction by capturing the temporal network structure.Combined with the corresponding Laplacian matrix as the hyperparameter,a recovery algorithm based on the multi-head attention graph network is designed to achieve rapid recovery.Simulation results showed that the proposed framework can facilitate rapid recovery of the connectivity and coverage more effectively compared to the existing studies.The results demonstrate that the average connectivity and coverage results is improved by 17.92%and 16.96%,respectively compared with the state-of-the-art model.Furthermore,by the ablation study,the contributions of each different improvement are compared.The proposed model can be used to support resilient network design for real-time mission execution.

Analysis of multiple-faults of high-voltage circuit breakers based on non-negative matrix decomposition

High-voltage circuit breakers are the core equipment in power networks,and to a certain extent,are related to the safe and reliable operation of power systems.However,their core components are prone to mechanical faults.This study proposes a component separation method to detect multiple mechanical faults in circuit breakers that can achieve online real-time monitoring.First,a model and strategy are presented for obtaining mechanical voiceprint signals from circuit breakers.Subsequently,the component separation method was used to decompose the voiceprint signals of multiple faults into individual component signals.Based on this,the recognition of the features of a single-fault voiceprint signal can be achieved.Finally,multiple faults in high-voltage circuit breakers were identified through an experimental simulation and verification of the circuit breaker voiceprint signals collected from the substation site.The research results indicate that the proposed method exhibits excellent performance for multiple mechanical faults,such as spring structures and loose internal components of circuit breakers.In addition,it provides a reference method for the real-time online monitoring of high-voltage circuit breakers.

Fluid-chemical modeling of the near-cathode sheath formation process in a high current broken in DC air circuit breaker

When the contacts of a medium-voltage DC air circuit breaker(DCCB) are separated, the energy distribution of the arc is determined by the formation process of the near-electrode sheath. Therefore, the voltage drop through the near-electrode sheath is an important means to build up the arc voltage, which directly determines the current-limiting performance of the DCCB. A numerical model to describe the near-electrode sheath formation process can provide insight into the physical mechanism of the arc formation, and thus provide a method for arc energy regulation. In this work, we establish a two-dimensional axisymmetric time-varying model of a medium-voltage DCCB arc when interrupted by high current based on a fluid-chemical model involving 16 kinds of species and 46 collision reactions. The transient distributions of electron number density, positive and negative ion number density, net space charge density, axial electric field, axial potential between electrodes, and near-cathode sheath are obtained from the numerical model. The computational results show that the electron density in the arc column increases, then decreases, and then stabilizes during the near-cathode sheath formation process, and the arc column's diameter gradually becomes wider. The 11.14 V–12.33 V drops along the17 μm space charge layer away from the cathode(65.5 k V/m–72.5 k V/m) when the current varies from 20 k A–80 k A.The homogeneous external magnetic field has little effect on the distribution of particles in the near-cathode sheath core,but the electron number density at the near-cathode sheath periphery can increase as the magnetic field increases and the homogeneous external magnetic field will lead to arc diffusion. The validity of the numerical model can be proven by comparison with the experiment.

Fault DiagnosisMethod of Energy Storage Unit of Circuit Breakers Based on EWT-ISSA-BP

Aiming at the problem of energy storage unit failure in the spring operating mechanism of low voltage circuit breakers(LVCBs).A fault diagnosis algorithm based on an improved Sparrow Search Algorithm(ISSA)optimized Backpropagation Neural Network(BPNN)is proposed to improve the operational safety of LVCB.Taking the 1.5kV/4000A/75kA LVCB as an example.According to the current operating characteristics of the energy storage motor,fault characteristics are extracted based on Empirical Wavelet Transform(EWT).Traditional BPNN has problems such as difficulty adjusting network weights and thresholds,being sensitive to initial weights,and quickly falling into local optimal solutions.The Sparrow Search Algorithm(SSA)with self-adjusting weight factors combined with bidirectional mutations is added to optimize the selection of BPNN hyperparameters.The results show that the ISSA-BPNN can accurately and quickly distinguish six conditions of motor voltage reduction:motor voltage increase,motor voltage decrease,energy storage spring stuck,transmission gear stuck,regular state and energy storage spring not locked.It is suitable for fault diagnosis and detection of the energy storage part of LVCB.

Posture Detection of Heart Disease Using Multi-Head Attention Vision Hybrid(MHAVH)Model

Cardiovascular disease is the leading cause of death globally.This disease causes loss of heart muscles and is also responsible for the death of heart cells,sometimes damaging their functionality.A person’s life may depend on receiving timely assistance as soon as possible.Thus,minimizing the death ratio can be achieved by early detection of heart attack(HA)symptoms.In the United States alone,an estimated 610,000 people die fromheart attacks each year,accounting for one in every four fatalities.However,by identifying and reporting heart attack symptoms early on,it is possible to reduce damage and save many lives significantly.Our objective is to devise an algorithm aimed at helping individuals,particularly elderly individuals living independently,to safeguard their lives.To address these challenges,we employ deep learning techniques.We have utilized a vision transformer(ViT)to address this problem.However,it has a significant overhead cost due to its memory consumption and computational complexity because of scaling dot-product attention.Also,since transformer performance typically relies on large-scale or adequate data,adapting ViT for smaller datasets is more challenging.In response,we propose a three-in-one steam model,theMulti-Head Attention Vision Hybrid(MHAVH).Thismodel integrates a real-time posture recognition framework to identify chest pain postures indicative of heart attacks using transfer learning techniques,such as ResNet-50 and VGG-16,renowned for their robust feature extraction capabilities.By incorporatingmultiple heads into the vision transformer to generate additional metrics and enhance heart-detection capabilities,we leverage a 2019 posture-based dataset comprising RGB images,a novel creation by the author that marks the first dataset tailored for posture-based heart attack detection.Given the limited online data availability,we segmented this dataset into gender categories(male and female)and conducted testing on both segmented and original datasets.The training accuracy of our model reached an impressive 99.77%.Upon testing,the accuracy for male and female datasets was recorded at 92.87%and 75.47%,respectively.The combined dataset accuracy is 93.96%,showcasing a commendable performance overall.Our proposed approach demonstrates versatility in accommodating small and large datasets,offering promising prospects for real-world applications.

Multi-Head Attention Spatial-Temporal Graph Neural Networks for Traffic Forecasting

Accurate traffic prediction is crucial for an intelligent traffic system (ITS). However, the excessive non-linearity and complexity of the spatial-temporal correlation in traffic flow severely limit the prediction accuracy of most existing models, which simply stack temporal and spatial modules and fail to capture spatial-temporal features effectively. To improve the prediction accuracy, a multi-head attention spatial-temporal graph neural network (MSTNet) is proposed in this paper. First, the traffic data is decomposed into unique time spans that conform to positive rules, and valuable traffic node attributes are mined through an adaptive graph structure. Second, time and spatial features are captured using a multi-head attention spatial-temporal module. Finally, a multi-step prediction module is used to achieve future traffic condition prediction. Numerical experiments were conducted on an open-source dataset, and the results demonstrate that MSTNet performs well in spatial-temporal feature extraction and achieves more positive forecasting results than the baseline methods.

Integrated Experimental and Simulation Investigation of Breakdown Voltage Characteristics Across Electrode Configurations in SF_(6) Circuit Breakers

This study investigates the breakdown voltage characteristics in sulfur hexafluoride(SF6)circuit breakers,employing a novel approach that integrates both experimental investigations and finite element simulations.Utilizing a sphere-sphere electrode configuration,we meticulously measured the relationship between breakdown voltage and electrode gap distances ranging from 1 cm to 4.5 cm.Subsequent simulations,conducted using COMSOL Multiphysics,mirrored the experimental setup to validate the model’s accuracy through a comparison of the breakdown voltage-electrode gap distance curves.The simulation results not only aligned closely with the experimental data but also allowed the extraction of detailed electric field strength,electric potential contours,and electric current flow curves at the breakdown voltage for gap distances extending from 1 to 4.5 cm.Extending the analysis,the study explored the electric field and potential distribution at a constant voltage of 72.5 kV for gap distances between 1 to 10 cm,identifying the maximum electric field strength.A comprehensive comparison of five different electrode configurations(sphere-sphere,sphere-rod,sphere-plane,rod-plane,rod-rod)at 72.5 kV and a gap distance of 1.84 cm underscored the significant influence of electrode geometry on the breakdown process.Moreover,the research contrasts the breakdown voltage in SF6 with that in air,emphasizing SF6’s superior insulating properties.This investigation not only elucidates the intricate dynamics of electrical breakdown in SF6 circuit breakers but also contributes valuable insights into the optimal electrode configurations and the potential for alternative insulating gases,steering future advancements in high-voltage circuit breaker technology.

Using Recurrent Neural Network Structure and Multi-Head Attention with Convolution for Fraudulent Phone Text Recognition

Fraud cases have been a risk in society and people’s property security has been greatly threatened.In recent studies,many promising algorithms have been developed for social media offensive text recognition as well as sentiment analysis.These algorithms are also suitable for fraudulent phone text recognition.Compared to these tasks,the semantics of fraudulent words are more complex and more difficult to distinguish.Recurrent Neural Networks(RNN),the variants ofRNN,ConvolutionalNeuralNetworks(CNN),and hybrid neural networks to extract text features are used by most text classification research.However,a single network or a simple network combination cannot obtain rich characteristic knowledge of fraudulent phone texts relatively.Therefore,a new model is proposed in this paper.In the fraudulent phone text,the knowledge that can be learned by the model includes the sequence structure of sentences,the correlation between words,the correlation of contextual semantics,the feature of keywords in sentences,etc.The new model combines a bidirectional Long-Short Term Memory Neural Network(BiLSTM)or a bidirectional Gate Recurrent United(BiGRU)and a Multi-Head attention mechanism module with convolution.A normalization layer is added after the output of the final hidden layer.BiLSTM or BiGRU is used to build the encoding and decoding layer.Multi-head attention mechanism module with convolution(MHAC)enhances the ability of the model to learn global interaction information and multi-granularity local interaction information in fraudulent sentences.A fraudulent phone text dataset is produced by us in this paper.The THUCNews data sets and fraudulent phone text data sets are used in experiments.Experiment results show that compared with the baseline model,the proposed model(LMHACL)has the best experiment results in terms of Accuracy,Precision,Recall,and F1 score on the two data sets.And the performance indexes on fraudulent phone text data sets are all above 0.94.

Comprehensive evaluation of chemical breakers for multistage network ultra-high strength gel

Polymer gels have been accepted as a useful tool to address many sealing operations such as drilling and completion,well stimulation,wellbore integrity,water and gas shutoff,etc.Previously,we developed an ultra-high strength gel(USGel)for medium to ultra-low temperature reservoirs.However,the removal of USGel is a difficult problem for most temporary plugging operations.This paper first provides new insights into the mechanism of USGel,where multistage network structure and physical entanglement are the main reasons for USGel possessing ultra-high strength.Then the effects of acid breakers,encapsulated breakers,and oxidation breakers(including H_(2)O_(2),Na_(2)S_(2)O_(8),Ca(ClO)_(2),H_(2)O_(2)+NaOH,Na_(2)S_(2)O_(8)+NaOH,and Ca(ClO)_(2)+NaOH)were evaluated.The effects of component concentration and temperature on the breaking solution were studied,and the corrosion performance,physical simulation and formation damage tests of the breaking solution were carried out.The final formulation of 2%-4%NaOH+4.5%-6%H_(2)O_(2) breaking solution was determined,which can make USGel completely turn into water at 35e105C.The combinations of“acid t breaking solution”,“acid+encapsulated breaker”and“encapsulated breaker+breaking solution”were evaluated for breaking effect.The acid gradually reduced the volume of USGel,which increased the contact area between breaking solution and USGel,and the effect of“4%acid+breaking solution”was 23 times higher than that of breaking solution alone at 35C.However,the acid significantly reduced the strength of USGel.This paper provides new insights into the breaking of high-strength gels with complex network structures.

Magneto-hydrodynamic simulation study of direct current multi-contact circuit breaker for equalizing breaking arc

This work is based on a direct current(DC)natural current commutation topology,which uses load-carrying branch contacts carrying rated current and multiple sets of series arcing branch contacts in parallel to achieve circuit breaking.The proposed topology can meet the new requirements of higher voltage DC switches in aviation,aerospace,energy and other fields.First,a magneto-hydrodynamic arc model is built using COMSOL Multiphysics,and the different arc breaking characteristics of the arcing branch contacts in different gas environments are simulated.Then,a voltage uniformity coefficient is used to measure the voltage sharing effect in the process of dynamic interruption.In order to solve the dispersion of arcing contact action,a structural control method is adopted to improve the voltage uniformity coefficient.The uniform voltage distribution can improve the breaking capacity and electrical life of the series connection structure.

Discharge Summaries Based Sentiment Detection Using Multi-Head Attention and CNN-BiGRU

Automatic extraction of the patient’s health information from the unstructured data concerning the discharge summary remains challenging.Discharge summary related documents contain various aspects of the patient health condition to examine the quality of treatment and thereby help improve decision-making in the medical field.Using a sentiment dictionary and feature engineering,the researchers primarily mine semantic text features.However,choosing and designing features requires a lot of manpower.The proposed approach is an unsupervised deep learning model that learns a set of clusters embedded in the latent space.A composite model including Active Learning(AL),Convolutional Neural Network(CNN),BiGRU,and Multi-Attention,called ACBMA in this research,is designed to measure the quality of treatment based on discharge summaries text sentiment detection.CNN is utilized for extracting the set of local features of text vectors.Then BiGRU network was utilized to extract the text’s global features to solve the issues that a single CNN cannot obtain global semantic information and the traditional Recurrent Neural Network(RNN)gradient disappearance.Experiments prove that the ACBMA method can demonstrate the effectiveness of the suggested method,achieve comparable results to state-of-arts methods in sentiment detection,and outperform them with accurate benchmarks.Finally,several algorithm studies ultimately determined that the ACBMA method is more precise for discharge summaries sentiment analysis.

Multi-Headed Deep Learning Models to Detect Abnormality of Alzheimer’s Patients

Worldwide,many elders are suffering from Alzheimer’s disease(AD).The elders with AD exhibit various abnormalities in their activities,such as sleep disturbances,wandering aimlessly,forgetting activities,etc.,which are the strong signs and symptoms of AD progression.Recognizing these symptoms in advance could assist to a quicker diagnosis and treatment and to prevent the progression of Disease to the next stage.The proposed method aims to detect the behavioral abnormalities found in Daily activities of AD patients(ADP)using wearables.In the proposed work,a publicly available dataset collected using wearables is applied.Currently,no real-world data is available to illustrate the daily activities of ADP.Hence,the proposed method has synthesized the wearables data according to the abnormal activities of ADP.In the proposed work,multi-headed(MH)architectures such as MH Convolutional Neural Network-Long Short-Term Mem-ory Network(CNN-LSTM),MH one-dimensional Convolutional Neural Network(1D-CNN)and MH two dimensional Convolutional Neural Network(2D-CNN)as well as conventional methods,namely CNN-LSTM,1D-CNN,2D-CNN have been implemented to model activity pattern.A multi-label prediction technique is applied to detect abnormal activities.The results obtained show that the proposed MH architectures achieve improved performance than the conventional methods.Moreover,the MH models for activity recognition perform better than the abnormality detection.

高压断路器触头烧蚀及电寿命评估研究综述

随着高压断路器接近设计寿命年限其触头烧蚀情况越来越严重,评估高压断路器电寿命可提高利用效率同时保证其运行可靠性。根据近些年有关开关电器电寿命相关文献,首先从触头烧蚀数学模型出发剖析了断路器电寿命终结物理过程;然后对比了目前常用的断路器电寿命评估方法优缺点,指出数据模型是驱动设备寿命准确评估的关键,并借鉴其他类型开关电器电寿命相关研究为高压断路器靠性评估开拓了思路。最后指出高压断路器电寿命预测所面临挑战以及研究方向。

中高压直流断路器的研究与应用

多端直流系统及直流电网是未来柔性直流输配电系统的发展方向,其安全可靠稳定运行需要有直流断路器作为保障。虽然国内外研究人员提出了各种直流断路器技术方案,但目前市场上能够满足实际工程应用的直流断路器产品仍十分缺乏。该文对直流断路器的研究工作进行了梳理。首先,分析了不同技术方案采取的换流方式及性能,并介绍了直流断路器中的核心组件及其驱动保护。其次,对各类型的直流断路器拓扑结构进行了总结,并归纳出改进优化的方向。最后,对直流断路器研制的关键技术与未来的发展趋势进行了讨论和总结,为中高压直流断路器研制与应用提供参考。

溯源弹簧形变过程的断路器振动信号递归量化分析辨识方法

从锁止机构脱扣引起储能弹簧释能,经部件带动动触头运动再到静止的每个动作具有严格阶段特征,伴随断路器动作的机械振动展现了能量传递及设备健康状态。该文提出一种溯源弹簧形变过程的断路器振动信号递归量化分析方法,首先由高速相机捕捉断路器操动时储能弹簧的动作图像,通过计算机视觉跟踪动态提取反映弹簧形变特征帧,再依据特征帧时序划分操动过程;然后将不同阶段振动信号映射至高维相空间,经递归分析得到体现动力系统变化特征的递归图,并递归量化分析其纹理结构特征;最后利用支持向量机模型对正常及故障状态下的断路器振动特征样本进行分析辨识,对比结果证明,由弹簧释能时序细化振动信号特征分析有效提高了分类识别准确率。该文方法在断路器操动机构状态辨识中具有广阔的应用前景。

高海拔环境下大容量直流空气断路器灭弧性能研究

高原轨道交通和电工产业转型对起关键保护作用的大容量直流空气断路器(LC-DCCB)提出了更高要求,但现有产品在高海拔地区的开断仍存在一定问题。该文以轨道交通用LC-DCCB为研究对象,首先基于磁流体动力学(MHD)理论,考虑湍流效应的影响,对其在高海拔环境下开断18 kA短路电流进行仿真;然后对电弧形态及灭弧室内温度场、电磁场、气流场进行分析,得出高海拔地区空气电弧开断困难的主要原因;最后根据仿真与理论分析,考虑采用合理数量和布局的间插式U型栅片改善电弧开断特性。结果表明:随着海拔的升高,电弧前期运动速度加快,但断路器的灭弧性能降低;在高海拔环境下电弧存在严重的弧根粘滞和弧根拖尾现象,弧根拖尾畸变空间电场,不利于熄弧;同时,在不同海拔环境下,电弧会产生不同程度的反向运动现象,易导致弧后重燃。该研究深入揭示了高海拔环境下LC-DCCB电弧演变过程及复杂开断现象背后的物理本质,可为该类产品研发提供理论指导。

混合式直流断路器状态感知技术与智慧框架体系探讨

直流断路器是柔性直流输电工程中故障清除和隔离的关键设备,当前的热点集中在新型拓扑结构、直流开断特性和新型电力电子器件等功能方面的研究,对其全状态的智能感知和状态评估方面研究较少。该文以混合式直流断路器为研究对象,全面梳理了需要重点监测的状态量,归纳了混合式直流断路器中快速机械开关、压接式绝缘栅双极性晶体管(insulated gate bipolar transistor,IGBT)、避雷器、快速机构动作电容和隔离供能单元等关键组件状态量的感知方法。基于现有研究,提出了智慧型直流断路器的框架体系。分析了所提框架体系中智能感知层、信息通信层、数据融合层和智能应用层的实现思路,为实现直流断路器的智能化和模块化提供一定参考依据。

动作时序优化振动信号混沌吸引子特征的断路器操动状态辨识方法

高压断路器分合闸操作过程包括掣子脱扣、弹簧释能、动静触头碰撞等动作,机械振动信号作为能量传递的表现,蕴含着丰富的运行状态信息。该文基于断路器关键动作节点的时序,提出一种动作时序优化振动信号混沌吸引子特征的断路器操动状态辨识方法。首先,由高速相机捕捉断路器操动过程主轴拐臂运动图像,利用目标跟踪算法获取动触头关键运动节点时序指标;然后,依据时序指标划分操动过程,通过对不同阶段的振动信号相空间重构,提取相空间吸引子几何和属性特征;最后,利用智能分类算法进行故障辨识,实验结果验证该方法在大幅节省时间开销的同时,有效提高了分类辨识的准确率达96.9%。该文方法在断路器状态监测和带电测试中具有广阔应用前景。

基于电容自然充电换相的混合式直流断路器设计与仿真

以晶闸管作为主断器件是降低混合式直流断路器造价和技术难度的手段之一,电容电压是此类直流断路器能够顺利开断直流故障的关键影响因素。现有结构中电容大多为预充电型,但预充电方式和电容电压的维持较为复杂。因此,该文提出一种基于电容自然充电换相的混合式直流断路器,利用母线电压与预充电电容的电压差值实现电容的预充电和电容电压的自动维持,从而保证断路器的开断能力。此外该断路器还具备二次开断能力,可以满足极短时间内重复开断的需求。针对所提断路器的工作过程和元器件参数进行了详细的理论推导,基于PSCAD/EMTDC建立单端等效和四端柔性直流电网模型验证了所提结构的适用性。最后与其他方案进行比较,结果表明,所提方案在开断速度、电容预充电方式和二次开断方面具备一定优势。