Abnormal State Detection in Lithium-ion Battery Using Dynamic Frequency Memory and Correlation Attention LSTM Autoencoder

This paper addresses the challenge of identifying abnormal states in Lithium-ion Battery(LiB)time series data.As the energy sector increasingly focuses on integrating distributed energy resources,Virtual Power Plants(VPP)have become a vital new framework for energy management.LiBs are key in this context,owing to their high-efficiency energy storage capabilities essential for VPP operations.However,LiBs are prone to various abnormal states like overcharging,over-discharging,and internal short circuits,which impede power transmission efficiency.Traditional methods for detecting such abnormalities in LiB are too broad and lack precision for the dynamic and irregular nature of LiB data.In response,we introduce an innovative method:a Long Short-Term Memory(LSTM)autoencoder based on Dynamic Frequency Memory and Correlation Attention(DFMCA-LSTM-AE).This unsupervised,end-to-end approach is specifically designed for dynamically monitoring abnormal states in LiB data.The method starts with a Dynamic Frequency Fourier Transform module,which dynamically captures the frequency characteristics of time series data across three scales,incorporating a memory mechanism to reduce overgeneralization of abnormal frequencies.This is followed by integrating LSTM into both the encoder and decoder,enabling the model to effectively encode and decode the temporal relationships in the time series.Empirical tests on a real-world LiB dataset demonstrate that DFMCA-LSTM-AE outperforms existing models,achieving an average Area Under the Curve(AUC)of 90.73%and an F1 score of 83.83%.These results mark significant improvements over existing models,ranging from 2.4%–45.3%for AUC and 1.6%–28.9%for F1 score,showcasing the model’s enhanced accuracy and reliability in detecting abnormal states in LiB data.

E3GCAPS: Efficient EEG-Based Multi-Capsule Framework with Dynamic Attention for Cross-Subject Cognitive State Detection

Cognitive state detection using electroencephalogram(EEG)signals for various tasks has attracted significant research attention.However,it is difficult to further improve the performance of crosssubject cognitive state detection.Further,most of the existing deep learning models will degrade significantly when limited training samples are given,and the feature hierarchical relationships are ignored.To address the above challenges,we propose an efficient interpretation model based on multiple capsule networks for cross-subject EEG cognitive state detection,termed as Efficient EEG-based Multi-Capsule Framework(E3GCAPS).Specifically,we use a selfexpression module to capture the potential connections between samples,which is beneficial to alleviate the sensitivity of outliers that are caused by the individual differences of cross-subject EEG.In addition,considering the strong correlation between cognitive states and brain function connection mode,the dynamic subcapsule-based spatial attention mechanism is introduced to explore the spatial relationship of multi-channel 1D EEG data,in which multichannel 1D data greatly improving the training efficiency while preserving the model performance.The effectiveness of the E3GCAPS is validated on the Fatigue-Awake EEG Dataset(FAAD)and the SJTU Emotion EEG Dataset(SEED).Experimental results show E3GCAPS can achieve remarkable results on the EEG-based cross-subject cognitive state detection under different tasks.

Modified filter for mean elements estimation with state jumping

To investigate the real-time mean orbital elements(MOEs)estimation problem under the influence of state jumping caused by non-fatal spacecraft collision or protective orbit trans-fer,a modified augmented square-root unscented Kalman filter(MASUKF)is proposed.The MASUKF is composed of sigma points calculation,time update,modified state jumping detec-tion,and measurement update.Compared with the filters used in the existing literature on MOEs estimation,it has three main characteristics.Firstly,the state vector is augmented from six to nine by the added thrust acceleration terms,which makes the fil-ter additionally give the state-jumping-thrust-acceleration esti-mation.Secondly,the normalized innovation is used for state jumping detection to set detection threshold concisely and make the filter detect various state jumping with low latency.Thirdly,when sate jumping is detected,the covariance matrix inflation will be done,and then an extra time update process will be con-ducted at this time instance before measurement update.In this way,the relatively large estimation error at the detection moment can significantly decrease.Finally,typical simulations are per-formed to illustrated the effectiveness of the method.

Digital image correlation-based structural state detection through deep learning

This paper presents a new approach for automatical classification of structural state through deep learning.In this work,a Convolutional Neural Network(CNN)was designed to fuse both the feature extraction and classification blocks into an intelligent and compact learning system and detect the structural state of a steel frame;the input was a series of vibration signals,and the output was a structural state.The digital image correlation(DIC)technology was utilized to collect vibration information of an actual steel frame,and subsequently,the raw signals,without further pre-processing,were directly utilized as the CNN samples.The results show that CNN can achieve 99%classification accuracy for the research model.Besides,compared with the backpropagation neural network(BPNN),the CNN had an accuracy similar to that of the BPNN,but it only consumes 19%of the training time.The outputs of the convolution and pooling layers were visually displayed and discussed as well.It is demonstrated that:1)the CNN can extract the structural state information from the vibration signals and classify them;2)the detection and computational performance of the CNN for the incomplete data are better than that of the BPNN;3)the CNN has better anti-noise ability.

Investigation of odd-parity Rydberg states of Eu I with autoionization detection

Isolated-core-excitation （ICE） scheme and autoionization detection are employed to study the bound Rydberg states of europium atom. The high-lying states with odd parity have been measured using the autoionization detection method with three different excitation paths via 4f76s6p[8Ph/2], 4f76s6p[8P7/2] and 4f76s6p[SP9/2] intermediate states, respectively. In this paper the spectra of bound Rydberg states of Eu atom are reported, which cover the energy regions from 36000 cm-1 to 38250 cm-1 and from 38900 cm-1 to 39500 cm-1. The study provides the information about level energy, the possible J values and relative line intensity as well as the effective principal quantum number n＊ for these states. This work not only confirms the previous results of many states, but also discovers 11 new Rydberg states of Eu atom.

Fault detection based on H_∞ states observer for networked control systems

The influence of random short time-delay to networked control systems （NCS） is changed into an unknown bounded uncertain part. Without changing the structure of the system, an Hoo states observer is designed for NCS with short time-delay. Based on the designed states observer, a robust fault detection approach is proposed for NCS. In addition, an optimization method for the selection of the detection threshold is introduced for better tradeoff between the robustness and the sensitivity. Finally, some simulation results demonstrate that the presented states observer is robust and the fault detection for NCS is effective.

Super-resolution and super-sensitivity of entangled squeezed vacuum state using optimal detection strategy

Interference metrology is a method for achieving high precision detection by phase estimation. The phase sensitivity of a traditional interferometer is subject to the standard quantum limit, while its resolution is constrained by the Rayleigh diffraction limit. The resolution and sensitivity of phase measurement can be enhanced by using quantum metrology. We propose a quantum interference metrology scheme using the entangled squeezed vacuum state, which is obtained using the magic beam splitter, expressed as ｜ψ〉=（｜ξ〉｜0〉＋｜0〉｜ξ〉）/√2＋2/coshr, such as the N00 N state. We derive the phase sensitivity and the resolution of the system with Z detection, project detection, and parity detection. By simulation and analysis, we determine that parity detection is an optimal detection method, which can break through the Rayleigh diffraction limit and the standard quantum limit.

锂离子电池储能电站的热失控状态检测与安全防控技术研究进展

锂离子电池具有能量密度大、使用寿命长、工作温度范围宽、自放电小等优点,是中国电化学储能电站的主流电池技术。然而,在加热、过充等恶劣工况下,锂离子电池易发生热失控引发火灾甚至爆炸,因此其安全问题已逐渐成为锂离子电池储能电站建设及大规模应用的首要问题。该文系统分析了锂离子储能电池热失控的诱因、电池内部反应过程及外部特征参量的变化规律,重点总结了当前主要的电池热失控状态检测技术、智能诊断算法及储能电站安全防控技术,最后对储能电站热失控状态检测及安全防控技术进行了总结和展望。

Production and Detection of Ultracold Ground State 85Rb133Cs Molecules in the Lowest Vibrational Level by Short-Range Photoassociation

We investigate the production of ultracold ground state x^1∑7＋（u = 0） RbCs molecules in the lowest vibrational level via short-range photoassociation followed by spontaneous emission. The starting point is the laser cooled 85Rb and laa cs atoms in a dual species, forced dark magneto-optical trap. The special intermediate level （5）O＋ （u = 10） correlated to the （2）311 electric state is achieved by the photoassociation process. The formed ground state X1∑＋ （u = 0） molecule is resonantly excited to the 2111 intermediate state by a 651 nm pulse laser and is ionized by a 532nm pulse laser and then detected by the time-of-flight mass spectrum. Saturation of the photoionization spectroscopy at large ionization laser energy is observed and the ionization efficiency is obtained from the fitting. The production of ultracold ground state 85Rblaacs molecules is facilitative for the further research about the manipulation of ultracold molecules in the rovibrational ground state.

A long-distance quantum key distribution scheme based on pre-detection of optical pulse with auxiliary state

We construct a circuit based on PBS and CNOT gates, which can be used to determine whether the input pulse is empty or not according to the detection result of the auxiliary state, while the input state will not be changed. The circuit can be treated as a pre-detection device. Equipping the pre-detection device in the front of the receiver of the quantum key distribution （QKD） can reduce the influence of the dark count of the detector, hence increasing the secure communication distance significantly. Simulation results show that the secure communication distance can reach 516 km and 479 km for QKD with perfect single photon source and decoy-state QKD with weak coherent photon source, respectively.

Robust fault detection in linear systemsbased on full-order state observers

A parametric approach to robust fault detection in linear systems with unknown disturbances is presented. The residual is generated using full-order state observers （FSO）. Based on an analytical solution to a type of Sylvester matrix equations, the parameterization of the observer gain matrix is given. In terms of the design degrees of freedom provided by the parametric observer design and a group of introduced parameter vectors, a sufficient and necessary condition for fullorder state observer design with disturbance decoupling is then established. By properly constraining the design parameters according to this proposed condition, the effect of the disturbance on the residual signal is also decoupled, and a simple algorithm is developed. The presented approach offers all the degrees of design freedom. Finally, a numerical example illustrates the effect of the proposed approach.

Weak wide-band signal detection method based on small-scale periodic state of Duffing oscillator

The conventional Duffing oscillator weak signal detection method, which is based on a strong reference signal, has inherent deficiencies. To address these issues, the characteristics of the Duffing oscillator＇s phase trajectory in a small- scale periodic state are analyzed by introducing the theory of stopping oscillation system. Based on this approach, a novel Duffing oscillator weak wide-band signal detection method is proposed. In this novel method, the reference signal is discarded, and the to-be-detected signal is directly used as a driving force. By calculating the cosine function of a phase space angle, a single Duffing oscillator can be used for weak wide-band signal detection instead of an array of uncoupled Duffing oscillators. Simulation results indicate that, compared with the conventional Duffing oscillator detection method, this approach performs better in frequency detection intervals, and reduces the signal-to-noise ratio detection threshold, while improving the real-time performance of the system.

基于改进YOLO v5的复杂环境下柑橘目标精准检测与定位方法

针对自然环境下柑橘果实机械化采收作业环境复杂和果实状态多样等情况,提出了一种多通道信息融合网络——YOLO v5-citrus,以解决柑橘果实识别精准度低、果实分类模糊和定位精准度低等难题。将不同的柑橘目标通过不同遮挡条件分为“可采摘”和“难采摘”两类,这种分类策略可指导机器人在真实果园中顺序摘取,提高采摘效率并减少机器人本体和末端执行器损坏率。YOLO v5-citrus中,在颈部网络插入多通道信息融合模块,对柑橘的深浅特征信息进行处理,提高柑橘采摘状态识别精度,同时修改颈部网络拼接方法,针对目标柑橘大小进行识别,训练后在识别部分嵌入聚类算法模块,将训练部分识别模糊的柑橘目标进行最后区分。识别后进行深度图像和彩色图像的像素对齐,并通过坐标系转换获取柑橘目标三维坐标。在使用多种增强技术处理的数据集中,YOLO v5-citrus比原始YOLO v5在平均精度均值和精确率上分别提高2.8个百分点与3.7个百分点,表现出更优异的泛化能力。与YOLO v7和YOLO v8等其他主流网络架构相比较,保持了更高的检测精度和更快的检测速度。通过真实果园的检测与定位试验,得到柑橘目标的三维坐标识别定位系统的定位误差为(1.97 mm,0.36 mm,9.63 mm),满足末端执行器的抓取条件。试验结果表明,该模型具有较强的鲁棒性,满足复杂环境下柑橘状态识别要求,可为柑橘园机械采收设备提供技术支持。

Unsupervised Time Series Segmentation: A Survey on Recent Advances

Time series segmentation has attracted more interests in recent years,which aims to segment time series into different segments,each reflects a state of the monitored objects.Although there have been many surveys on time series segmentation,most of them focus more on change point detection(CPD)methods and overlook the advances in boundary detection(BD)and state detection(SD)methods.In this paper,we categorize time series segmentation methods into CPD,BD,and SD methods,with a specific focus on recent advances in BD and SD methods.Within the scope of BD and SD,we subdivide the methods based on their underlying models/techniques and focus on the milestones that have shaped the development trajectory of each category.As a conclusion,we found that:(1)Existing methods failed to provide sufficient support for online working,with only a few methods supporting online deployment;(2)Most existing methods require the specification of parameters,which hinders their ability to work adaptively;(3)Existing SD methods do not attach importance to accurate detection of boundary points in evaluation,which may lead to limitations in boundary point detection.We highlight the ability to working online and adaptively as important attributes of segmentation methods,the boundary detection accuracy as a neglected metrics for SD methods.

基于卷积神经网络的疲劳检测改进算法

为了解决当前的疲劳检测算法准确率低或实时性差的缺点,提出一种改进的卷积神经网络疲劳检测算法。使用HOG检测算法结合KCF跟踪算法对采集的人脸进行检测和跟踪;随后调用Dlib库进行脸部关键点的提取;通过引入可变形卷积神经网络对提取的眼部和嘴部进行状态识别;通过CEW和YAWDD数据集进行测试,疲劳检测准确率达到94.36%。实验表明,与当前的疲劳检测算法相比,提出的方法能够实时地检测驾驶员疲劳,并且具有较高的准确率。

非接触式生理心理检测在长期模拟失重效应分析中的应用研究

目的在模拟失重生理效应场景下,构建基于面部视频的非接触式生理心理检测模型,探索长期模拟失重生理效应分析的非接触式心率和负性心境状态检测新方法。方法搭建可见光和热红外视频融合分析的非接触式生理心理数据采集系统,采集“地星二号”90 d头低位卧床实验中受试者生理心理相关数据,构建基于图卷积网络面部多区域特征融合的非接触式心率检测模型和考虑数据可靠性的非接触式负性心境状态检测模型,并以指夹式心率和POMS-SF量表为标签,验证模型的有效性。结果研究结果显示,非接触式心率检测模型的Bland-Altman图差值平均数为-1.26 bpm,且96.3%的误差值检测数据处于95%一致性区间内,模型检测的心率与指夹式心率有较高的一致性;非接触式负性心境状态检测模型对于紧张、压抑、愤怒、疲劳的检测准确率均超过0.85,且心率、AU06、眼部视线、头部姿态对心境状态检测的影响显著。结论非接触式生理心理检测方法不仅能够用于长期模拟失重的生理效应分析,还可为未来长期空间飞行的航天员在轨健康保障提供新途径。

钻井平台关键设备异常检测预警技术研究

海洋钻井平台为国家油气资源开发做出重要贡献,保证平台关键设备安全运维是进行油气资源开发的基本要求。针对传统设备异常检测预警方法中单参数表征设备状态不准确、阈值确定困难等问题,从多参数关联关系角度出发,研究了基于随机森林的特征提取方法,构建了基于相似度聚类理念的多维健康记忆矩阵,利用概率图的原理,实现了设备多级报警阈值的确定方法,最后利用泥浆泵仿真数据对所提方法进行测试,验证了该方法的及时性、准确性、漏报率均优于常规预警方法,可有效进行异常参数的辨识。

Real-Time Traffic State and Boundary Flux Estimation with Distributed Speed Detecting Networks

The rapid development of 5G mobile communication and portable traffic detection technologies enhances highway transportation systems in detail and at a vehicle level. Besides the advantage of no disturbance to the regular traffic operation, these ubiquitous sensing technologies have the potential for unprecedented data collection at any temporal and spatial position. While as a typical distributed parameter system, the freeway traffic dynamics are determined by the current system states and the boundary traffic demand-supply. Using the three-step extended Kalman filtering, this paper simultaneously estimates the real-time traffic state and the boundary flux of freeway traffic with the distributed speed detector networks organized at any location of interest. In order to assess the effectiveness of the proposed approach, a freeway segment from Interstate 80 East (I-80E) in Alameda, Emeryville, and Northern California is selected. Experimental results show that the proposed method has the potential of using only speed detecting data to monitor the state of urban freeway transportation systems without access to the traditional measurement data, such as the boundary flows.

含LCC/MMC交直流混联系统的状态估计及不良数据检测

基于调度系统导出的通用信息模型(common information model,CIM)中的XML和E文档,从数据生成的角度出发,首先将导出文档转化为状态估计原始输入数据,考虑交流系统与电网换相换流器(line commutated converter,LCC)、模块化多电平换流器(modular multilevel converter,MMC)以及LCC与MMC间的相互影响,采用统一迭代法对500kV子网络进行交直流状态估计建模;其次,在原始量测数据的基础上施加高斯噪声,借助最大化残差检验方法以进行不良数据的检测与辨识;最后,通过仿真数据验证了交直流状态估计模型及不良数据检测与辨识的有效性。

GIS绝缘子表面金属异物附着缺陷局部放电UHF信号间歇性与有效检出率分析

局部放电特高频(UHF)方法检测局部放电(PD)是当前评估气体绝缘开关设备(GIS)状态和绝缘性能的重要手段之一。本文为解决局部放电UHF检测出现大量漏报和误报的问题,通过开展GIS绝缘子表面金属异物附着缺陷长期恒压实验,结合现有UHF检测策略对放电信号的成功捕捉概率进行分析,从检测时长和检出阈值两方面对现有UHF信号的检测策略提出了优化方案。结果表明:绝缘子表面金属异物附着缺陷局部放电具有间歇性特点,现有UHF带电检测及在线监测策略对放电的检出概率均不高。针对带电检测策略进行优化,延长检测时长至2247s,有效放电的捕捉概率可达85%;针对在线监测策略进行优化,延长形成一个局部放电事件(PDEvent)的测量时间和降低其检出阈值皆可增大PDEvent的检出概率,工程应用中可选择合适的测量时间和检出阈值相组合的方式来进行间歇性放电的检测。