Device Anomaly Detection Algorithm Based on Enhanced Long Short-Term Memory Network

The problems in equipment fault detection include data dimension explosion,computational complexity,low detection accuracy,etc.To solve these problems,a device anomaly detection algorithm based on enhanced long short-term memory(LSTM)is proposed.The algorithm first reduces the dimensionality of the device sensor data by principal component analysis(PCA),extracts the strongly correlated variable data among the multidimensional sensor data with the lowest possible information loss,and then uses the enhanced stacked LSTM to predict the extracted temporal data,thus improving the accuracy of anomaly detection.To improve the efficiency of the anomaly detection,a genetic algorithm(GA)is used to adjust the magnitude of the enhancements made by the LSTM model.The validation of the actual data from the pumps shows that the algorithm has significantly improved the recall rate and the detection speed of device anomaly detection,with the recall rate of 97.07%,which indicates that the algorithm is effective and efficient for device anomaly detection in the actual production environment.

Trends of Temperature Extremes in China and their Relationship with Global Temperature Anomalies

Changes of temperature extremes over China were evaluated using daily maximum and minimum temperature data from 591 stations for the period 1961-2002. A set of indices of warm extremes, cold extremes and daily temperature range （DTR） extremes was studied with a focus on trends. The results showed that the frequency of warm extremes （F WE） increased obviously in most parts of China, and the intensity of warm extremes （I WE） increased significantly in northern China. The opposite distribution was found in the frequency and intensity of cold extremes. The frequency of high DTR extremes was relatively uniform with that of intensity： an obvious increasing trend was located over western China and the east coast, while significant decreases occurred in central, southeastern and northeastern China; the opposite distribution was found for low DTR extreme days. Seasonal trends illustrated that both F WE and I WE showed signifi- cant increasing trends, especially over northeastern China and along the Yangtze Valley basin in spring and winter. A correlation technique was used to link extreme temperature anomalies over China with global temperature anomalies. Three key regions were identified, as follows： northeastern China and its coastal areas, the high-latitude regions above 40~0N, and southwestern China and the equatorial eastern Pacific.

Short-term and imminent geomagnetic anomalies of the Wenchuan M_S8.0 earthquake and exploration on earthquake forecast

The diurnal variation of the geomagnetic vertical component is exhibited mainly by changes of phase and amplitude before strong earthquakes. Based on data recorded by the network of geomagnetic observatories in China for many years, the anomalous features of the appearance time of the minima of diurnal variations （i.e, low-point time） of the geo- magnetic vertical components and the variation of their spatial distribution （i.e, phenomena of low-point displacement） have been studied before the Wenchuan Ms8.0 earthquake. The strong aftershocks after two months＇ quiescence of M6 aftershocks of the Ms8.0 event were forecasted based on these studies. There are good correlativities between these geomagnetic anoma- lies and occurrences of earthquakes. It has been found that most earthquakes occur near the boundary line of sudden changes of the low-point time and generally within four days before or after the 27th or 41st day counting from the day of the appearance of the anomaly. In addition, the imminent anomalies in diurnal-variation amplitudes near the epicentral areas have also been studied before the Wenchuan earthquake.

POSSIBLE CONTRIBUTION OF A TROPICAL CYCLONE TO SHORT-TERM CLIMATE ANOMALIES IN EAST ASIA VIA SNOW COVER ON THE TIBETAN PLATEAU

Snow cover on the Tibetan Plateau(TP) has been shown to be essential for the East Asian summer monsoon.In this paper, we demonstrate that tropical cyclone(TC) 04B(1999) in the northern Indian Ocean, which made landfall during the autumn of 1999, may have contributed to climate anomalies over East Asia during the following spring and summer by increasing snow cover on the TP. Observations indicate that snow cover on the TP increased markedly after TC 04B(1999) made landfall in October of 1999. Sensitivity experiments, in which the TC was removed from a numerical model simulation of the initial field, verified that TC 04B(1999) affected the distribution as well as increased the amount of snow on the TP. In addition, the short-term numerical modeling of the climate over the region showed that the positive snow cover anomaly induced negative surface temperature, negative sensible heat flux, positive latent heat flux, and positive soil temperature anomalies over the central and southern TP during the following spring and summer. These climate anomalies over the TP were associated with positive(negative) summer precipitation anomalies over the Yangtze River valley(along the southeastern coast of China).

ON THE PREDICTION OF TROPICAL CYCLONE LANDFALL AND INFLUENCE ON SOUTHERN CHINA USING MONTHLY OLR ANOMALIES FOR PRIME SUMMER

With the OLR data, the landfall and activity of tropical cyclones (TC) in southern China over a 20-year period (1975～1994) are studied. The result shows that the variation of the monthly anomalous OLR is somewhat teleconnected with the TC activity in southern China. The former is used to predict short-term climate for the latter over months with frequent or no TC influence. To some extent, the relationship between the TC activity in southern China and the monthly mean OLR anomalies is dependent on the climatological location of the subtropical high in northwestern Pacific region.

An Efficient Correlation-Aware Anomaly Detection Framework in Cellular Network

Nowadays,the fifth-generation(5G)mobile communication system has obtained prosperous development and deployment,reshaping our daily lives.However,anomalies of cell outages and congestion in 5G critically influence the quality of experience and significantly increase operational expenditures.Although several big data and artificial intelligencebased anomaly detection methods have been proposed for wireless cellular systems,they change distributions of the data and ignore the relevance among user activities,causing anomaly detection ineffective for some cells.In this paper,we propose a highly effective and accurate anomaly detection framework by utilizing generative adversarial networks(GAN)and long short-term memory(LSTM)neural networks.The framework expands the original dataset while simultaneously keeping the distribution of data unchanged,and explores the relevance among user activities to further improve the system performance.The results demonstrate that our framework can achieve 97.16%accuracy and 2.30%false positive rate by utilizing the correlation of user activities and data expansion.

The Anomaly Field of Subsurface Fluids and Its Formation and Evolution Mechanism Before Three Strong Earthquakes in the Northern North China Area

The data of pre-seismic subsurface fluid anomalies of such earthquakes as Datong-YanggaoM_s6.1 event on Oct.19,1989,western Baotou M_s6.4 event on May 3,1996 and Zhangbei-Shangyi M_s6.2 event on Jan.10,1998 are systematically collected and arranged.Then thefeatures of patterns,spatial distribution,time variation and time-spatial evolution of theseanomalies are compared and comprehensively analyzed.Then the formation and evolutionmechanism of medium-and short-term anomaly field of subsurface fluids in the northernNorth China area is proposed.The results show that the medium-term anomaly field is causedby regional tectonic activities,which further strengthen the local tectonic activities andpromote the formation and evolution of the seismic source body.The enhancement of loealtectonic activities causes the formation of anomaly field of short-term subsurface fluids,andthe evolution of source body engenders the source-precursor anomalies of subsurface fluids inthe epicenters at imminent stage.

Data-driven Anomaly Detection Method Based on Similarities of Multiple Wind Turbines

The operating conditions of wind turbines(WTs)in the same wind farm(WF)may share similarities due to their shared manufacturing process,control strategy,and operating environment.However,the similarities of WTs are seldom considered in WT anomaly detection,resulting in the disregard of useful information.This paper proposes a method to improve the reliability and accuracy of WT anomaly detection using the supervisory control and data acquisition(SCADA)data of multiple WTs in the same WF.First,a similarity assessment method based on a comparison of different observation time series is proposed,which objectively quantifies the similarities of WT operating conditions.Then,the SCADA data of the target WT and selected WTs that are similar are used to establish several estimation models through a long short-term memory(LSTM)algorithm.LSTM models that exhibit good estimation performance are used to construct a combined estimation model that estimates the variations in the monitored variables of the target WT.Finally,an anomaly detection method that jointly compares the effective value and information entropy of the residuals is proposed to identify anomalies.The effectiveness and accuracy of the proposed method are verified using the data of two actual WFs.

基于RST算法提取乌什M_(S)7.1地震地表温度异常

为探讨RST算法在新疆地区地震热红外异常提取中的适用性,以乌什M_(S)7.1地震为例,构建研究区MODIS地表温度数据集,并对数据集进行逐像元时间序列趋势去除后,利用RST算法提取乌什M_(S)7.1地震地表温度异常信息。结果表明:乌什M_(S)7.1地震地表温度异常的变化过程分为“出现—消失—再出现—扩大—达到最大—消失”6个阶段;乌什M_(S)7.1地震的地表温度异常区域大致沿构造带的走向分布;乌什M_(S)7.1地震发生在地表温度异常面积出现最大值后的第99天。利用MODIS数据结合RST算法提取地震热红外异常在新疆地区相关研究中具有一定的可行性。

船舶柴油机运行参数异常检测及分析

为保障船舶安全高效运行,提出4种船舶柴油机运行参数异常检测方法。该技术在空间向量统计的异常检测基础上,进一步提出新的方法监测运行参数时间序列的趋势异常。通过提取运行参数数据演化过程的趋势和规律,可以更早、更准确地识别异常趋势,为设备管理提供决策支持。实验结果表明,所提出的异常检测技术能够有效提高船舶柴油机异常检测的效率和准确性,及早发现安全隐患。

基于深度神经网络的异常检测算法在国网上海公司AIOps中的应用

AIOps是IT运维中一个极具革命性的概念,它以大数据和算法为基础,完善现在的运维体系。实现AIOps的体系构建最重要的是对监控采集的指标数据进行趋势预测以及异常检测。文章分别针对这两方面提出相应的算法,为实现AIOps更高级的功能奠定基础。

Long Term Temperature Trends at Major, Medium, Small Cities and Hill Stations in India during the Period 1901-2013

Industrialization and urbanization are the most dominant causal factors for long-term changes in surface air temperatures. To examine this fact, the long term changes in the surface-air temperatures have been evaluated by the linear trend for the different periods, i.e. 1901-2013, 1901-1970 and recent period 1971-2013 as rapid industrialization was observed during the recent four decades. In the present study, seasonal and annual mean, maximum and minimum temperature data of 36 stations for the period 1901-2013 have been used. These stations are classified into 4 groups, namely major, medium, small cities and hill stations. During the period 1901-1970, less than 50% stations from each group showed a significant increasing trend in annual mean temperature, whereas in the recent period 1971-2013, more than 80% stations from all the groups except small city group showed a significant increasing trend. The minimum temperature increased faster than that of the maximum temperature over major and medium cities, while maximum temperature increased faster than the minimum temperature over the small cities and hill stations. The annual mean temperature of all the coastal stations showed a significant increasing trend and positive correlation with Precipitable Water Vapour (PWV). The effect of PWV is more pronounced on minimum temperature than that of the maximum.

Multidecadal Trends in Large-Scale Annual Mean SATa Based on CMIP5 Historical Simulations and Future Projections

基于观测和第五次耦合模式比较计划(CMIP5)模式的模拟结果,本文对全球、半球、半球陆地及海洋尺度的年平均地面气温异常在过去一百多年及两个代表性浓度路径(RCPs)情景下的多年代际变化及趋势进行了评估分析。根据模式对全球平均地面气温异常的时间变率、长期趋势、多年代际变化及趋势的模拟能力,筛选出15个模式进行分析。观测结果表明,北半球陆地、北半球海洋和南半球海洋平均地面气温异常与全球平均地面气温异常具有相似的多年代际变化特征:在1900—1944年及1971—2000年呈现增暖趋势,并在1945—1970年和2001—2013年呈现增暖停滞甚至变冷趋势。模式能够基本再现以上观测特征。然而,与以上变化不同的是,南半球陆地的平均地面气温在1945—1970年呈现增暖趋势,并且模式不能很好模拟该特征。对于近期的增暖停滞阶段(2001—2013年),BCC-CSM1-1-m模式、CMCC-CM模式、GFDL-ESM2M模式及NorESM1-ME模式在RCP4.5和RCP8.5情景下预估的全球及半球尺度的地面气温异常趋势值最接近观测值,表明它们具有较好的预估能力。由于这四个模式在地面气温异常的多年代际趋势上具有较好的模拟及预估性能,故选择它们来预估2006—2099年的地面气温异常在全球及半球尺度上的变化特征。结果显示在RCP4.5(RCP8.5)情景下,所选四个模式集合平均的全球、北半球及南半球年平均地面气温异常趋势值分别为0.17(0.29)、0.22(0.36)及0.11(0.23)℃·decade^(–1),其趋势值明显小于未经过模式筛选的CMIP5模式集合的结果。

图表示学习在网络安全领域的应用研究综述

近年来,图表示学习由于其能够更全面地捕捉网络数据的特征,在与各种网络异常检测方法结合后能获得更好的检测结果等特点,逐渐引起网络安全领域的关注.为进一步理清使用图表示学习进行网络安全检测相关工作的研究脉络,本文首先研究了图表示学习的定义,并从基于降维、随机游走和深度学习三类分别介绍目前被广泛使用的图表示学习算法;其次,对公开可用的网络安全数据集按照日志和网络流量、可执行文件、社交和交易网络分类,给出其具体的数据内容;再次,总结了近年来将图表示学习方法应用到网络安全领域的研究成果,给出了模型的基本流程和优缺点分析;最后探讨了目前研究的局限性和未来研究的方向.

Data-driven unsupervised anomaly detection and recovery of unmanned aerial vehicle flight data based on spatiotemporal correlation

Anomaly detection is crucial to the flight safety and maintenance of unmanned aerial vehicles(UAVs)and has attracted extensive attention from scholars.Knowledge-based approaches rely on prior knowledge,while model-based approaches are challenging for constructing accurate and complex physical models of unmanned aerial systems(UASs).Although data-driven methods do not require extensive prior knowledge and accurate physical UAS models,they often lack parameter selection and are limited by the cost of labeling anomalous data.Furthermore,flight data with random noise pose a significant challenge for anomaly detection.This work proposes a spatiotemporal correlation based on long short-term memory and autoencoder(STCLSTM-AE)neural network data-driven method for unsupervised anomaly detection and recovery of UAV flight data.First,UAV flight data are preprocessed by combining the Savitzky-Golay filter data processing technique to mitigate the effect of noise in the original historical flight data on the model.Correlation-based feature subset selection is subsequently performed to reduce the reliance on expert knowledge.Then,the extracted features are used as the input of the designed LSTM-AE model to achieve the anomaly detection and recovery of UAV flight data in an unsupervised manner.Finally,the method's effectiveness is validated on real UAV flight data.

基于数理统计方法的煤矿瓦斯异常预警模型研究

基于收集的西南地区40多对矿井瓦斯监测数据,分析矿井瓦斯浓度数理变化特征,建立了数据驱动的矿井瓦斯异常涌出识别方法与模型。该模型从当前瓦斯浓度、瓦斯突变指数、偏离均值指数、长期不变指数、波动幅度指数、中期上升趋势指数等方面对监测点瓦斯风险进行量化评价;使用单一预警指标对趋势偏离、瓦斯突变等异常进行识别;采用各监测点调和平均数,以采掘工作面为单位,量化区域瓦斯灾害风险趋势。研发了煤矿瓦斯灾害大数据风险分析平台,并应用于现场监管监察,应用结果表明该模型能及时准确判识各矿井瓦斯灾害风险,有效提高监管能效。

基于趋势分析技术的设备运行态势自动感知建模研究

态势感知系统在电力设备运行的安全监测和异常控制中起着主要作用。以往增强态势感知系统的方法主要集中在状态估计、安全分析和视觉感知上。作为自动识别持续变化过程的趋势特征的有效工具,趋势分析系统技术可用于增强电力设备运行异常的态势感知。通过定性的趋势分析提出了一个增强的态势感知框架。增强框架包括3个层次:信息的感知、对当前状态的安全评估以及对未来系统状态和趋势的预测。在感知信息的基础上,引入N-1稳态安全距离模型来评估当前电力设备状态的安全水平。实际应用结果表明:稳态安全距离趋势提取与电力设备原始数据拟合度较好,误差大于97%,且基于趋势的方法可以有效监测电力设备及线路异常,帮助电力设备操作人员监测设备运行异常问题。

Real-time anomaly detection for very short-term load forecasting

Although the recent load information is critical to very short-term load forecasting(VSTLF), power companies often have difficulties in collecting the most recent load values accurately and timely for VSTLF applications.This paper tackles the problem of real-time anomaly detection in most recent load information used by VSTLF.This paper proposes a model-based anomaly detection method that consists of two components, a dynamic regression model and an adaptive anomaly threshold. The case study is developed using the data from ISO New England. This paper demonstrates that the proposed method significantly outperforms three other anomaly detection methods including two methods commonly used in the field and one state-of-the-art method used by a winning team of the Global Energy Forecasting Competition 2014. Finally, a general anomaly detection framework is proposed for the future research.

An Improved Method for Defining Short-Term Climate Anomalies

A conventional method to define short-term climate anomalies for atmospheric and oceanic variables,recommended by the World Meteorological Organization(WMO),is the departure from a 30-yr climatological mean in the preceding three decades.Such a method,however,introduces spurious errors such as sudden jumps and artificial trends.A new method,named a trend correctional method,is introduced to eliminate the errors.To demonstrate the capability of this new method,we examine a set of idealized cases first by superposing a"true"interannual or interdecadal signal onto a linear or a nonlinear trend.Comparing to the conventional method,the trend correctional method is able to retain,to a large extent,the"true"anomaly signals.Next,we examined real-time indices.The anomaly time series derived based on the trend correctional method show a better agreement with the observed anomaly series.The rootmean-square error is greatly improved,comparing to that calculated based on the conventional method.Therefore,the results from both the idealized and real cases demonstrate that the new method has a clear advantage to the conventional method in deriving true climate anomalies,in particular under the ongoing global warming circumstance.

青岛地震台2020年5月-2021年5月体应变趋势异常分析

2020年5月至2021年5月,青岛地震台体应变观测数据年漂移量明显小于往年同期变化,基于周边监测环境、同场地其他观测手段、气象因素、其他台站测项数据、青岛GPS观测站数据、潮汐因子和超限率等进行分析,结果发现:①台站附近小学建设地下车库进行基坑开挖,有可能对体应变观测造成影响;②体应变异常为地下应变的真实反映;③体应变年漂移量减小非气象因素所致,且非区域性变化;④经小波分析,表明钻孔体应变数据变化趋势正常。采用midas GTS软件,基于有限元模型,模拟计算基坑开挖对体应变的影响量,结果显示,体应变仪探头处体应变变化量约为-1.7×10^(-5),而实际漂移量差值约为-0.53×10^(-5),二者量级一致,仅数值稍有差别。综合判定认为,青岛地震台体应变年漂移量变小与台站附近地下车库的基坑开挖有关。