Cascading multi-segment rupture process of the 2023 Turkish earthquake doublet on a complex fault system revealed by teleseismic P wave back projection method

In this study,the vertical components of broadband teleseismic P wave data recorded by China Earthquake Network are used to image the rupture processes of the February 6th,2023 Turkish earthquake doublet via back projection analysis.Data in two frequency bands(0.5-2 Hz and 1-3 Hz)are used in the imaging processes.The results show that the rupture of the first event extends about 200 km to the northeast and about 150 km to the southwest,lasting~90 s in total.The southwestern rupture is triggered by the northeastern rupture,demonstrating a sequential bidirectional unilateral rupture pattern.The rupture of the second event extends approximately 80 km in both northeast and west directions,lasting~35 s in total and demonstrates a typical bilateral rupture feature.The cascading ruptures on both sides also reflect the occurrence of selective rupture behaviors on bifurcated faults.In addition,we observe super-shear ruptures on certain fault sections with relatively straight fault structures and sparse aftershocks.

Hierarchical multihead self-attention for time-series-based fault diagnosis

Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fault diagnosis methods have been developed in recent years.However,the existing methods have the problem of long-term dependency and are difficult to train due to the sequential way of training.To overcome these problems,a novel fault diagnosis method based on time-series and the hierarchical multihead self-attention(HMSAN)is proposed for chemical process.First,a sliding window strategy is adopted to construct the normalized time-series dataset.Second,the HMSAN is developed to extract the time-relevant features from the time-series process data.It improves the basic self-attention model in both width and depth.With the multihead structure,the HMSAN can pay attention to different aspects of the complicated chemical process and obtain the global dynamic features.However,the multiple heads in parallel lead to redundant information,which cannot improve the diagnosis performance.With the hierarchical structure,the redundant information is reduced and the deep local time-related features are further extracted.Besides,a novel many-to-one training strategy is introduced for HMSAN to simplify the training procedure and capture the long-term dependency.Finally,the effectiveness of the proposed method is demonstrated by two chemical cases.The experimental results show that the proposed method achieves a great performance on time-series industrial data and outperforms the state-of-the-art approaches.

SMSTracker:A Self-Calibration Multi-Head Self-Attention Transformer for Visual Object Tracking

Visual object tracking plays a crucial role in computer vision.In recent years,researchers have proposed various methods to achieve high-performance object tracking.Among these,methods based on Transformers have become a research hotspot due to their ability to globally model and contextualize information.However,current Transformer-based object tracking methods still face challenges such as low tracking accuracy and the presence of redundant feature information.In this paper,we introduce self-calibration multi-head self-attention Transformer(SMSTracker)as a solution to these challenges.It employs a hybrid tensor decomposition self-organizing multihead self-attention transformermechanism,which not only compresses and accelerates Transformer operations but also significantly reduces redundant data,thereby enhancing the accuracy and efficiency of tracking.Additionally,we introduce a self-calibration attention fusion block to resolve common issues of attention ambiguities and inconsistencies found in traditional trackingmethods,ensuring the stability and reliability of tracking performance across various scenarios.By integrating a hybrid tensor decomposition approach with a self-organizingmulti-head self-attentive transformer mechanism,SMSTracker enhances the efficiency and accuracy of the tracking process.Experimental results show that SMSTracker achieves competitive performance in visual object tracking,promising more robust and efficient tracking systems,demonstrating its potential to providemore robust and efficient tracking solutions in real-world applications.

A Self-Attention Based Dynamic Resource Management for Satellite-Terrestrial Networks

The satellite-terrestrial networks possess the ability to transcend geographical constraints inherent in traditional communication networks,enabling global coverage and offering users ubiquitous computing power support,which is an important development direction of future communications.In this paper,we take into account a multi-scenario network model under the coverage of low earth orbit(LEO)satellite,which can provide computing resources to users in faraway areas to improve task processing efficiency.However,LEO satellites experience limitations in computing and communication resources and the channels are time-varying and complex,which makes the extraction of state information a daunting task.Therefore,we explore the dynamic resource management issue pertaining to joint computing,communication resource allocation and power control for multi-access edge computing(MEC).In order to tackle this formidable issue,we undertake the task of transforming the issue into a Markov decision process(MDP)problem and propose the self-attention based dynamic resource management(SABDRM)algorithm,which effectively extracts state information features to enhance the training process.Simulation results show that the proposed algorithm is capable of effectively reducing the long-term average delay and energy consumption of the tasks.

Numerical investigation of hydro-morphodynamic characteristics of a cascading failure of landslide dams

A cascading failure of landslide dams caused by strong earthquakes or torrential rains in mountainous river valleys can pose great threats to people’s lives,properties,and infrastructures.In this study,based on the three-dimensional Reynoldsaveraged Navier-Stokes equations(RANS),the renormalization group(RNG)k-εturbulence model,suspended and bed load transport equations,and the instability discriminant formula of dam breach side slope,and the explicit finite volume method(FVM),a detailed numerical simulation model for calculating the hydro-morphodynamic characteristics of cascading dam breach process has been developed.The developed numerical model can simulate the breach hydrograph and the dam breach morphology evolution during the cascading failure process of landslide dams.A model test of the breaches of two cascading landslide dams has been used as the validation case.The comparison of the calculated and measured results indicates that the breach hydrograph and the breach morphology evolution process of the upstream and downstream dams are generally consistent with each other,and the relative errors of the key breaching parameters,i.e.,the peak breach flow and the time to peak of each dam,are less than±5%.Further,the comparison of the breach hydrographs of the upstream and downstream dams shows that there is an amplification effect of the breach flood on the cascading landslide dam failures.Three key parameters,i.e.,the distance between the upstream and the downstream dams,the river channel slope,and the downstream dam height,have been used to study the flood amplification effect.The parameter sensitivity analyses show that the peak breach flow at the downstream dam decreases with increasing distance between the upstream and the downstream dams,and the downstream dam height.Further,the peak breach flow at the downstream dam first increases and then decreases with steepening of the river channel slope.When the flood caused by the upstream dam failure flows to the downstream dam,it can produce a surge wave that overtops and erodes the dam crest,resulting in a lowering of the dam crest elevation.This has an impact on the failure occurrence time and the peak breach flow of the downstream dam.The influence of the surge wave on the downstream dam failure process is related to the volume of water that overtops the dam crest and the erosion characteristics of dam material.Moreover,the cascading failure case of the Xiaogangjian and Lower Xiaogangjian landslide dams has also been used as the representative case for validating the model.In comparisons of the calculated and measured breach hydrographs and final breach morphologies,the relative errors of the key dam breaching parameters are all within±10%,which verify the rationality of the model is applicable to real-world cases.Overall,the numerical model developed in this study can provide important technical support for the risk assessment and emergency treatment of failures of cascading landslide dams.

An Aerial Target Recognition Algorithm Based on Self-Attention and LSTM

In the application of aerial target recognition,on the one hand,the recognition error produced by the single measurement of the sensor is relatively large due to the impact of noise.On the other hand,it is difficult to apply machine learning methods to improve the intelligence and recognition effect due to few or no actual measurement samples.Aiming at these problems,an aerial target recognition algorithm based on self-attention and Long Short-Term Memory Network(LSTM)is proposed.LSTM can effectively extract temporal dependencies.The attention mechanism calculates the weight of each input element and applies the weight to the hidden state of the LSTM,thereby adjusting the LSTM’s attention to the input.This combination retains the learning ability of LSTM and introduces the advantages of the attention mechanism,making the model have stronger feature extraction ability and adaptability when processing sequence data.In addition,based on the prior information of the multidimensional characteristics of the target,the three-point estimation method is adopted to simulate an aerial target recognition dataset to train the recognition model.The experimental results show that the proposed algorithm achieves more than 91%recognition accuracy,lower false alarm rate and higher robustness compared with the multi-attribute decision-making(MADM)based on fuzzy numbers.

Missing Value Imputation for Radar-Derived Time-Series Tracks of Aerial Targets Based on Improved Self-Attention-Based Network

The frequent missing values in radar-derived time-series tracks of aerial targets(RTT-AT)lead to significant challenges in subsequent data-driven tasks.However,the majority of imputation research focuses on random missing(RM)that differs significantly from common missing patterns of RTT-AT.The method for solving the RM may experience performance degradation or failure when applied to RTT-AT imputation.Conventional autoregressive deep learning methods are prone to error accumulation and long-term dependency loss.In this paper,a non-autoregressive imputation model that addresses the issue of missing value imputation for two common missing patterns in RTT-AT is proposed.Our model consists of two probabilistic sparse diagonal masking self-attention(PSDMSA)units and a weight fusion unit.It learns missing values by combining the representations outputted by the two units,aiming to minimize the difference between the missing values and their actual values.The PSDMSA units effectively capture temporal dependencies and attribute correlations between time steps,improving imputation quality.The weight fusion unit automatically updates the weights of the output representations from the two units to obtain a more accurate final representation.The experimental results indicate that,despite varying missing rates in the two missing patterns,our model consistently outperforms other methods in imputation performance and exhibits a low frequency of deviations in estimates for specific missing entries.Compared to the state-of-the-art autoregressive deep learning imputation model Bidirectional Recurrent Imputation for Time Series(BRITS),our proposed model reduces mean absolute error(MAE)by 31%~50%.Additionally,the model attains a training speed that is 4 to 8 times faster when compared to both BRITS and a standard Transformer model when trained on the same dataset.Finally,the findings from the ablation experiments demonstrate that the PSDMSA,the weight fusion unit,cascade network design,and imputation loss enhance imputation performance and confirm the efficacy of our design.

Self-Attention Spatio-Temporal Deep Collaborative Network for Robust FDIA Detection in Smart Grids

False data injection attack(FDIA)can affect the state estimation of the power grid by tampering with the measured value of the power grid data,and then destroying the stable operation of the smart grid.Existing work usually trains a detection model by fusing the data-driven features from diverse power data streams.Data-driven features,however,cannot effectively capture the differences between noisy data and attack samples.As a result,slight noise disturbances in the power grid may cause a large number of false detections for FDIA attacks.To address this problem,this paper designs a deep collaborative self-attention network to achieve robust FDIA detection,in which the spatio-temporal features of cascaded FDIA attacks are fully integrated.Firstly,a high-order Chebyshev polynomials-based graph convolution module is designed to effectively aggregate the spatio information between grid nodes,and the spatial self-attention mechanism is involved to dynamically assign attention weights to each node,which guides the network to pay more attention to the node information that is conducive to FDIA detection.Furthermore,the bi-directional Long Short-Term Memory(LSTM)network is introduced to conduct time series modeling and long-term dependence analysis for power grid data and utilizes the temporal selfattention mechanism to describe the time correlation of data and assign different weights to different time steps.Our designed deep collaborative network can effectively mine subtle perturbations from spatiotemporal feature information,efficiently distinguish power grid noise from FDIA attacks,and adapt to diverse attack intensities.Extensive experiments demonstrate that our method can obtain an efficient detection performance over actual load data from New York Independent System Operator(NYISO)in IEEE 14,IEEE 39,and IEEE 118 bus systems,and outperforms state-of-the-art FDIA detection schemes in terms of detection accuracy and robustness.

Prediction and scheduling of multi-energy microgrid based on BiGRU self-attention mechanism and LQPSO

To predict renewable energy sources such as solar power in microgrids more accurately,a hybrid power prediction method is presented in this paper.First,the self-attention mechanism is introduced based on a bidirectional gated recurrent neural network(BiGRU)to explore the time-series characteristics of solar power output and consider the influence of different time nodes on the prediction results.Subsequently,an improved quantum particle swarm optimization(QPSO)algorithm is proposed to optimize the hyperparameters of the combined prediction model.The final proposed LQPSO-BiGRU-self-attention hybrid model can predict solar power more effectively.In addition,considering the coordinated utilization of various energy sources such as electricity,hydrogen,and renewable energy,a multi-objective optimization model that considers both economic and environmental costs was constructed.A two-stage adaptive multi-objective quantum particle swarm optimization algorithm aided by a Lévy flight,named MO-LQPSO,was proposed for the comprehensive optimal scheduling of a multi-energy microgrid system.This algorithm effectively balances the global and local search capabilities and enhances the solution of complex nonlinear problems.The effectiveness and superiority of the proposed scheme are verified through comparative simulations.

Stroke Electroencephalogram Data Synthesizing through Progressive Efficient Self-Attention Generative Adversarial Network

Early and timely diagnosis of stroke is critical for effective treatment,and the electroencephalogram(EEG)offers a low-cost,non-invasive solution.However,the shortage of high-quality patient EEG data often hampers the accuracy of diagnostic classification methods based on deep learning.To address this issue,our study designed a deep data amplification model named Progressive Conditional Generative Adversarial Network with Efficient Approximating Self Attention(PCGAN-EASA),which incrementally improves the quality of generated EEG features.This network can yield full-scale,fine-grained EEG features from the low-scale,coarse ones.Specially,to overcome the limitations of traditional generative models that fail to generate features tailored to individual patient characteristics,we developed an encoder with an effective approximating self-attention mechanism.This encoder not only automatically extracts relevant features across different patients but also reduces the computational resource consumption.Furthermore,the adversarial loss and reconstruction loss functions were redesigned to better align with the training characteristics of the network and the spatial correlations among electrodes.Extensive experimental results demonstrate that PCGAN-EASA provides the highest generation quality and the lowest computational resource usage compared to several existing approaches.Additionally,it significantly improves the accuracy of subsequent stroke classification tasks.

Aerial target threat assessment based on gated recurrent unit and self-attention mechanism

Aerial threat assessment is a crucial link in modern air combat, whose result counts a great deal for commanders to make decisions. With the consideration that the existing threat assessment methods have difficulties in dealing with high dimensional time series target data, a threat assessment method based on self-attention mechanism and gated recurrent unit(SAGRU) is proposed. Firstly, a threat feature system including air combat situations and capability features is established. Moreover, a data augmentation process based on fractional Fourier transform(FRFT) is applied to extract more valuable information from time series situation features. Furthermore, aiming to capture key characteristics of battlefield evolution, a bidirectional GRU and SA mechanisms are designed for enhanced features.Subsequently, after the concatenation of the processed air combat situation and capability features, the target threat level will be predicted by fully connected neural layers and the softmax classifier. Finally, in order to validate this model, an air combat dataset generated by a combat simulation system is introduced for model training and testing. The comparison experiments show the proposed model has structural rationality and can perform threat assessment faster and more accurately than the other existing models based on deep learning.

Numerical and theoretical study of load transfer behavior during cascading pillar failure

To further study the load transfer mechanism of roofemulti-pillarefloor system during cascading pillar failure(CPF),numerical simulation and theoretical analysis were carried out to study the three CPF modes according to the previous experimental study on treble-pillar specimens,e.g.successive failure mode(SFM),domino failure mode(DFM)and compound failure mode(CFM).Based on the finite element code rock failure process analysis(RFPA^(2D)),numerical models of treble-pillar specimen with different mechanical properties were established to reproduce and verify the experimental results of the three CPF modes.Numerical results show that the elastic rebound of roofefloor system induced by pillar instability causes dynamic disturbance to adjacent pillars,resulting in sudden load increases and sudden jump displacement of adjacent pillars.The phenomena of load transfer in the roofemulti-pillarefloor system,as well as the induced accelerated damage behavior in adjacent pillars,were discovered and studied.In addition,based on the catastrophe theory and the proposed mechanical model of treble-pillar specimen edisc spring group system,a potential function that characterizes the evolution characteristics of roof emulti-pillarefloor system was established.The analytical expressions of sudden jump and energy release of treble-pillar specimenedisc spring group system of the three CPF modes were derived according to the potential function.The numerical and theoretical results show good agreement with the experimental results.This study further reveals the physical essence of load transfer during CPF of roof emulti-pillarefloor system,which provides references for mine design,construction and disaster prevention.

Risk-Balanced Routing Strategy for Service Function Chains of Cyber-Physical Power System Considering Cross-Space Cascading Failure

Cyber-physical power system(CPPS)has significantly improved the operational efficiency of power systems.However,cross-space cascading failures may occur due to the coupling characteristics,which poses a great threat to the safety and reliability of CPPS,and there is an acute need to reduce the probability of these failures.Towards this end,this paper first proposes a cascading failure index to identify and quantify the importance of different information in the same class of communication services.On this basis,a joint improved risk-balanced service function chain routing strategy(SFC-RS)is proposed,which is modeled as a robust optimization problem and solved by column-and-constraint generation(C-CG)algorithm.Compared with the traditional shortest-path routing algorithm,the superiority of SFC-RS is verified in the IEEE 30-bus system.The results demonstrate that SFC-RS effectively mitigates the risk associated with information transmission in the network,enhances information transmission accessibility,and effectively limits communication disruption from becoming the cause of cross-space cascading failures.

Simulation and Analysis of Cascading Faults in Integrated Heat and Electricity Systems Considering Degradation Characteristics

Cascading faults have been identified as the primary cause of multiple power outages in recent years.With the emergence of integrated energy systems(IES),the conventional approach to analyzing power grid cascading faults is no longer appropriate.A cascading fault analysis method considering multi-energy coupling characteristics is of vital importance.In this study,an innovative analysis method for cascading faults in integrated heat and electricity systems(IHES)is proposed.It considers the degradation characteristics of transmission and energy supply com-ponents in the system to address the impact of component aging on cascading faults.Firstly,degradation models for the current carrying capacity of transmission lines,the water carrying capacity and insulation performance of thermal pipelines,as well as the performance of energy supply equipment during aging,are developed.Secondly,a simulation process for cascading faults in the IHES is proposed.It utilizes an overload-dominated development model to predict the propagation path of cascading faults while also considering network islanding,electric-heating rescheduling,and load shedding.The propagation of cascading faults is reflected in the form of fault chains.Finally,the results of cascading faults under different aging levels are analyzed through numerical examples,thereby verifying the effectiveness and rationality of the proposed model and method.

A Cascading Fault Path Prediction Method for Integrated Energy Distribution Networks Based on the Improved OPA Model under Typhoon Disasters

In recent times,the impact of typhoon disasters on integrated energy active distribution networks(IEADNs)has received increasing attention,particularly,in terms of effective cascading fault path prediction and enhanced fault recovery performance.In this study,we propose a modified ORNL-PSerc-Alaska(OPA)model based on optimal power flow(OPF)calculation to forecast IEADN cascading fault paths.We first established the topology and operational model of the IEADNs,and the typical fault scenario was chosen according to the component fault probability and information entropy.The modified OPA model consisted of two layers:An upper-layer model to determine the cascading fault location and a lower-layer model to calculate the OPF by using Yalmip and CPLEX and provide the data to update the upper-layer model.The approach was validated via the modified IEEE 33-node distribution system and two real IEADNs.Simulation results showed that the fault trend forecasted by the novel OPA model corresponded well with the development and movement of the typhoon above the IEADN.The proposed model also increased the load recovery rate by>24%compared to the traditional OPA model.

基于改进Cascade R-CNN的安全帽检测算法

针对安全帽检测中,目标形状、尺度变化大,易出现漏检、误检等问题,提出了一种基于改进级联基于区域的卷积神经网络(Cascade R-CNN)的安全帽检测算法。首先,对ResNet50进行改进形成D-ResNet50,利用可变形卷积仅增加少量参数就可增大感受野的特性,对特征提取网络的C2~C5卷积层进行重塑,提高网络对目标几何变换的适应能力和特征提取能力。其次,将D-ResNet50作为主干网络引入Cascade R-CNN,形成级联目标检测器,在每个阶段对正负样本重采样,抑制误检问题。再次,对递归特征金字塔进行改进,更高效地进行多尺度特征融合,并且基于反馈信息对特征进行二次处理,增强特征表达,提高网络的分类和定位能力。最后,使用Soft-非极大值抑制(Soft-NMS)进行后处理,进一步解决漏检问题。提出的方法在Hard hat workers数据集上的AP值相比检测基线提高了3.5%,与Sparse R-CNN、TridentNet、VFnet等先进算法相比分别提升了4.7%、5.9%、2.3%等。

CFSA-Net:Efficient Large-Scale Point Cloud Semantic Segmentation Based on Cross-Fusion Self-Attention

Traditional models for semantic segmentation in point clouds primarily focus on smaller scales.However,in real-world applications,point clouds often exhibit larger scales,leading to heavy computational and memory requirements.The key to handling large-scale point clouds lies in leveraging random sampling,which offers higher computational efficiency and lower memory consumption compared to other sampling methods.Nevertheless,the use of random sampling can potentially result in the loss of crucial points during the encoding stage.To address these issues,this paper proposes cross-fusion self-attention network(CFSA-Net),a lightweight and efficient network architecture specifically designed for directly processing large-scale point clouds.At the core of this network is the incorporation of random sampling alongside a local feature extraction module based on cross-fusion self-attention(CFSA).This module effectively integrates long-range contextual dependencies between points by employing hierarchical position encoding(HPC).Furthermore,it enhances the interaction between each point’s coordinates and feature information through cross-fusion self-attention pooling,enabling the acquisition of more comprehensive geometric information.Finally,a residual optimization(RO)structure is introduced to extend the receptive field of individual points by stacking hierarchical position encoding and cross-fusion self-attention pooling,thereby reducing the impact of information loss caused by random sampling.Experimental results on the Stanford Large-Scale 3D Indoor Spaces(S3DIS),Semantic3D,and SemanticKITTI datasets demonstrate the superiority of this algorithm over advanced approaches such as RandLA-Net and KPConv.These findings underscore the excellent performance of CFSA-Net in large-scale 3D semantic segmentation.

Pluggable multitask diffractive neural networks based on cascaded metasurfaces

Optical neural networks have significant advantages in terms of power consumption,parallelism,and high computing speed,which has intrigued extensive attention in both academic and engineering communities.It has been considered as one of the powerful tools in promoting the fields of imaging processing and object recognition.However,the existing optical system architecture cannot be reconstructed to the realization of multi-functional artificial intelligence systems simultaneously.To push the development of this issue,we propose the pluggable diffractive neural networks(P-DNN),a general paradigm resorting to the cascaded metasurfaces,which can be applied to recognize various tasks by switching internal plug-ins.As the proof-of-principle,the recognition functions of six types of handwritten digits and six types of fashions are numerical simulated and experimental demonstrated at near-infrared regimes.Encouragingly,the proposed paradigm not only improves the flexibility of the optical neural networks but paves the new route for achieving high-speed,low-power and versatile artificial intelligence systems.

基于改进Cascade R-CNN算法的船舶目标检测方法

为了解决实际场景下船舶目标检测精度低的问题,本文在Cascade R-CNN算法的基础上,提出一种船舶目标检测方法 Boat R-CNN。Boat R-CNN使用带自注意力机制的Swin-Transformer Tiny网络提取图像特征,使用Soft-NMS非极大值抑制方法提升候选框过滤精度,使用Smooth_L1损失函数加速模型收敛并减少梯度爆炸情况,使用CIOU边界框回归损失提高候选框回归质量,并针对船舶目标的形状特征优化锚框的长宽比,提高锚框的生成质量。实验结果表明,Boat R-CNN算法的精度相比原版Cascade R-CNN算法提高了21.8%,相比主流Faster R-CNN算法提高了30.3%,有效提升了实际场景下的船舶目标检测精度。

Multi-dimensional multiplexing optical secret sharing framework with cascaded liquid crystal holograms

Secret sharing is a promising technology for information encryption by splitting the secret information into different shares.However,the traditional scheme suffers from information leakage in decryption process since the amount of available information channels is limited.Herein,we propose and demonstrate an optical secret sharing framework based on the multi-dimensional multiplexing liquid crystal(LC)holograms.The LC holograms are used as spatially separated shares to carry secret images.The polarization of the incident light and the distance between different shares are served as secret keys,which can significantly improve the information security and capacity.Besides,the decryption condition is also restricted by the applied external voltage due to the variant diffraction efficiency,which further increases the information security.In implementation,an artificial neural network(ANN)model is developed to carefully design the phase distribution of each LC hologram.With the advantage of high security,high capacity and simple configuration,our optical secret sharing framework has great potentials in optical encryption and dynamic holographic display.