Fault Detection Based on Hierarchical Cluster Analysis in Wide Area Backup Protection System

In wide area backup protection of electric power systems, the prerequisite of protection device's accurate, fast and reliable performance is its corresponding fault type and fault location can be discriminated quickly and defined exactly. In our study, global information will be introduced into the backup protection system. By analyzing and computing real-time PMU measurements, basing on cluster analysis theory, we are using mainly hierarchical cluster analysis to search after the statistical laws of electrical quantities' marked changes. Then we carry out fast and exact detection of fault components and fault sections, and finally accomplish fault isolation. The facts show that the fault detection of fault component (fault section) can be performed successfully by hierarchical cluster analysis and calculation. The results of hierarchical cluster analysis are accurate and reliable, and the dendrograms of hierarchical cluster analysis are in intuition.

Islanding Protection and Islanding Detection in Low Voltage CIGRE Distribution Network with Distributed Generations

The Power Quality (PQ), security, reliability etc., are the prime objectives of the power system. The protection is developed in such a way that it should be selective, fast, reliable and the cost effective. The study about the islanding protection in Low Voltage (LV) CIGRE distribution and networks like this has been proposed in this paper. This is achieved by developing the protection against the short circuit faults which might appear at the Medium Voltage (MV) bus. The protection of the network with significant penetration of the Distributed Generations (DGs) is a complicated process. The DG units which are directly connected to the grid such as synchronous or induction generators contribute large short power, whereas the DG units which are connected to the grid via inverters carry small amount of the short circuit power. This creates the problems in the protection of the network. If the proper protection coordination measures have not been taken, it might cause the mal-function of the protection devices which put the portion of the power network into the security threats. The selection of the islanding protection devices in this paper is made to protect the network against bi-directional currents at the time of short circuit fault. The LV CIGRE distribution network will enter into islanding if a fault is cleared at the MV bus by the proposed islanding protection devices. It is therefore, essential to detect the islanding in the CIGRE power network. The detection of the island in this network is another major objective of this paper. The detection of the island is proposed by using the technique which is based on the voltage phase angle difference. The simulations are carried out by using DIgSILENT power factory software version 15.0.

Blackout Prevention by Power Swing Detection and Out-of-Step Protection

Power swing evoked by sudden changes like faults or switching operations will become more and more important for protective relaying, due to the growing load flow in electrical power networks. Unwanted trips of the distance protection function must be avoided to prevent cascading effects and blackouts in the network. Selective out-of-step-tripping is required to stop unstable power swing and to prevent damage to affected generators. Therefore a reliable method for detection of power swing is presented, which requires no settings for operation. Power swing can be detected from 0.1 Hz up to 10 Hz swing frequency, also during open pole condition and during asymmetrical operation. A blocking logic prevents unselective trips by the distance protection. However, faults that occur during a power swing must be detected and cleared with a high degree of selectivity and dependability. For unstable power swing a flexible out of step tripping function will be proposed. The coordination of power swing detection, distance protection and out of step protection provides a reliable system protection.

Fault Detection and Protection System of Electric Railway Substation

The industrial power systems are moving to digital networks,and unmanned systems are increasing recently with the technological development of information and communication technology.In particular,reliability of system operation is very important for stable power supply.Most industrial power distribution facilities use a 154 kV or 22.9 kV extra HV(high voltage)power system,and a special monitoring system is required because a large loss occurs when an error occurs in the power facility in the field.Although digital protection relay(IED;intelligent electronic device)and FR(fault recorder)are applied to the field to protect the power system,various improvement activities are still ongoing.In this paper,a 22.9 kV high-voltage panel and its test bed,which are widely used in railway stations,tunnels,substations and large plants,were tested as test subjects.The developed fault detection system automatically starts the AL(auto-lock)circuit or outputs an alarm signal to user by monitoring in real time problems such as CT(current transformer)-open and poor-contact that the existing digital protection relay cannot cover.In addition,it is intended to increase the safety and reliability of the power system by blocking various accidents in the system in advance and accurately analyzing the causes of faults with the developed fault detection system.

Design and implementation of self-protection agent for network-based intrusion detection system

Static secure techniques, such as firewall, hierarchy filtering, distributed disposing,layer management, autonomy agent, secure communication, were introduced in distributed intrusion detection. The self-protection agents were designed, which have the distributed architecture,cooperate with the agents in intrusion detection in a loose-coupled manner, protect the security of intrusion detection system, and respond to the intrusion actively. A prototype self-protection agent was implemented by using the packet filter in operation system kernel. The results show that all the hosts with the part of network-based intrusion detection system and the whole intrusion detection system are invisible from the outside and network scanning, and cannot apperceive the existence of network-based intrusion detection system. The communication between every part is secure. In the low layer, the packet streams are controlled to avoid the buffer leaks exist ing in some system service process and back-door programs, so as to prevent users from misusing and vicious attack like Trojan Horse effectively.

Adaptive Protection Mechanisms in Power Systems

With the increasing complexity and dynamic nature of modern power grids,adaptive protection mechanisms have emerged as a promising solution to address the challenges faced by traditional protection systems.These systems dynamically adjust their settings based on real-time grid conditions,enabling faster fault detection,improved fault isolation,and enhanced system stability.The need for such adaptive protection systems has become more pronounced as power systems evolve with the integration of renewable energy sources,distributed generation,and microgrids.By leveraging advanced technologies such as machine learning,artificial intelligence,smart sensors,and wide-area measurement systems,adaptive protection mechanisms provide a more flexible and resilient approach to grid protection.This paper explores the definition,key features,enabling technologies,and applications of adaptive protection in power systems,with a focus on its role in distribution networks,transmission networks,and the integration of renewable energy sources.The integration of adaptive protection into modern power grids is essential for maintaining grid reliability,minimizing service interruptions,and optimizing the overall performance of power systems.

An Automated Detection Approach of Protective Equipment Donning for Medical Staff under COVID-19 Using Deep Learning

Personal protective equipment(PPE)donning detection for medical staff is a key link of medical operation safety guarantee and is of great significance to combat COVID-19.However,the lack of dedicated datasets makes the scarce research on intelligence monitoring of workers’PPE use in the field of healthcare.In this paper,we construct a dress codes dataset for medical staff under the epidemic.And based on this,we propose a PPE donning automatic detection approach using deep learning.With the participation of health care personnel,we organize 6 volunteers dressed in different combinations of PPE to simulate more dress situations in the preset structured environment,and an effective and robust dataset is constructed with a total of 5233 preprocessed images.Starting from the task’s dual requirements for speed and accuracy,we use the YOLOv4 convolutional neural network as our learning model to judge whether the donning of different PPE classes corresponds to the body parts of the medical staff meets the dress codes to ensure their self-protection safety.Experimental results show that compared with three typical deeplearning-based detection models,our method achieves a relatively optimal balance while ensuring high detection accuracy(84.14%),with faster processing time(42.02 ms)after the average analysis of 17 classes of PPE donning situation.Overall,this research focuses on the automatic detection of worker safety protection for the first time in healthcare,which will help to improve its technical level of risk management and the ability to respond to potentially hazardous events.

Research of Pure Electric Ferry System and Its Short-Circuit Protection and Calculation

System control and safety reliability are important links of the marine DC (Direct Current) power system. The simulationmodel is built by Matlab/Simulink, the battery and super-capacitor are supplied to the system through a three-phase interleaved DC/DCconverter, the fuse and disconnector switch combination are used as the protection device, and the short-circuit point is set betweeneach branch and the DC distribution board, performing short-circuit simulation. This paper also proposes a short-circuit calculationmethod for super-capacitors based on the simplified model of series RC (Resistors & Capacitors), and verifies its correctness throughsimulation data. The results show that the introduction of a three-phase interleaved DC/DC converter reduces the current ripple andmakes the system control more convenient;short-circuit calculation and simulation have determined the short-circuit withstandcapability of the DC distribution board, and verified the feasibility of the fuse selection method and the short-circuit calculation methodof the super-capacitor. This provides reliable verification for the application and calculation of the actual project.

New Principle for Grounding Fault Feeder Detection in MV Distributions with Neutral Ineffectively Earthed

A new principle for grounding fault feeder detection based on negative sequence current variation and energy dissipated in the fault point is presented. It has high precision in both isolated systems and resonance earthed systems, even in full compensated systems. And it can be installed at the local control unit of feeder in distribution automation systems, such as field terminal unit (FTU). This principle is verified by EMTP simulator and experimentation.

Real-Time Safety Helmet Detection Using Yolov5 at Construction Sites

The construction industry has always remained the economic and social backbone of any country in the world where occupational health and safety(OHS)is of prime importance.Like in other developing countries,this industry pays very little,rather negligible attention to OHS practices in Pakistan,resulting in the occurrence of a wide variety of accidents,mishaps,and near-misses every year.One of the major causes of such mishaps is the non-wearing of safety helmets(hard hats)at construction sites where falling objects from a height are unavoid-able.In most cases,this leads to serious brain injuries in people present at the site in general and the workers in particular.It is one of the leading causes of human fatalities at construction sites.In the United States,the Occupational Safety and Health Administration(OSHA)requires construction companies through safety laws to ensure the use of well-defined personal protective equipment(PPE).It has long been a problem to ensure the use of PPE because round-the-clock human monitoring is not possible.However,such monitoring through technological aids or automated tools is very much possible.The present study describes a systema-tic strategy based on deep learning(DL)models built on the You-Only-Look-Once(YOLOV5)architecture that could be used for monitoring workers’hard hats in real-time.It can indicate whether a worker is wearing a hat or not.The proposed system usesfive different models of the YOLOV5,namely YOLOV5n,YOLOv5s,YOLOv5 m,YOLOv5l,and YOLOv5x for object detection with the support of PyTorch,involving 7063 images.The results of the study show that among the DL models,the YOLOV5x has a high performance of 95.8%in terms of the mAP,while the YOLOV5n has the fastest detection speed of 70.4 frames per second(FPS).The proposed model can be successfully used in practice to recognize the hard hat worn by a worker.

A New Method of Early Short Circuit Detection

To reduce the pressure on contacts and circuit breaker and realize the zone selective interlocking (ZSI) function above the instantaneous protection threshold (e.g., >10In), the short circuit current needs to be early detected. The state-of–art of early short circuit detection (ESCD) method is reviewed. Based on the equivalent model of the short circuit, a new method based on the current and its integration is proposed. The prospective current value can be detected in the early stage of the short circuit. According to the evaluation result, the short circuit current can be early forecasted with the proposed method.

Video-based construction vehicles detection and its application in intelligent monitoring system

While vehicle detection on highways has been reported before, to the best of our knowledge, intelligent monitoring system that aims at detecting hydraulic excavators and dump trucks on state-owned land has not been explored thoroughly yet. In this paper, we present an automatic, video-based algorithm for detecting hydraulic excavators and dump trucks. Derived from lessons learned from video processing, we proposed methods for foreground detection based on an improved frame difference algorithm, and then detected hydraulic excavators and dump trucks in the respective region of interest. From our analysis, we proposed methods based on inverse valley feature of mechanical arm and spatial-temporal reasoning for hydraulic excavator detection. In addition, we explored dump truck detection strategies that combine structured component projection with the spatial relationship. Experiments on real-monitoring sites demonstrated the promising performance of our system.

An Intelligent Approach for Intrusion Detection in Industrial Control System

Supervisory control and data acquisition(SCADA)systems are computer systems that gather and analyze real-time data,distributed control systems are specially designed automated control system that consists of geographically distributed control elements,and other smaller control systems such as programmable logic controllers are industrial solid-state computers that monitor inputs and outputs and make logic-based decisions.In recent years,there has been a lot of focus on the security of industrial control systems.Due to the advancement in information technologies,the risk of cyberattacks on industrial control system has been drastically increased.Because they are so inextricably tied to human life,any damage to them might have devastating consequences.To provide an efficient solution to such problems,this paper proposes a new approach to intrusion detection.First,the important features in the dataset are determined by the difference between the distribution of unlabeled and positive data which is deployed for the learning process.Then,a prior estimation of the class is proposed based on a support vector machine.Simulation results show that the proposed approach has better anomaly detection performance than existing algorithms.

Development and Application of Lightning Protection Technologies in Power Grids of China

In recent years,along with the rapid expansion of power grids,the increasing complication of grid structures,and the development of smart grids and energy technologies,the lightning protection of power grids becomes increasingly prominent.Power grids of China have acquired significant achievements on lightning protection technologies,which are reviewed in this paper.A technical route of lightning protection is introduced in detail; it allows us to find problems through detection and measurement of lightning,to analyze problems through evaluation and simulation of lightning,to solve problems through lightning protection measures,and to prevent problems through hazard risk warning of lightning.Following the route,the technical breakthroughs of these four aspects in China are presented,including the chinese lightning detection network(CLDN),natural lightning observations,lightning faults detection at transmission lines,lightning current measurements,progresses in lightning distribution maps,lightning fault replays,lightning hazard risk evaluations,and lightning simulated experiments,as well as novel lightning protection measures.The practical devices and systems corresponding to the technologies mentioned above are also introduced and discussed.Due to the progress of lightning protection technologies in recent years,despite the rapidly growing length of transmission lines in China,the lightning accident rate is controlled at a certain level.

Theoretical and experimental assessment of a novel method to establish the complete measurement range of the calorimeter and its limit of detection and quantification

For determining the accuracy of a calorimeter over the instrument’s entire measuring range,a novel method has been established.For this new approach,(a)benzoic acid(C_(6)H_(5)CO_(2)H) as a certified reference material(CRM),(b)SiO_(2) and(c)a mixture of CRM benzoic acid and SiO_(2) have been used.To illustrate the essential difference between 1)the novel analytical method for control of the entire measurement range and 2)the calorimeter calibration,both applications of benzoic acid(BA)have been demonstrated.An experimental result showed that BA was successfully used to check the whole calorimeter measurement range.The results also showed that the same new method was successfully applied to determine the limit of detection and quantification.A new instrument testing process and a new measurement technique have thus been established.In this way,the cost of using CRM to control the accuracy of measuring the entire measuring range of the calorimeter,as shown in this paper,is minimized.The requirements of the ISO/IEC 17025:2017 standard are satisfied.ISO/IEC 17025:2017,together with ISO 9001:2015(quality management systems),ISO 14001:2015(relate to environmental protection)and ISO45001:2018(occupational safety),constitute an integrated quality system by which a testing laboratory may also accredit.

Fast and Accurate Detection of Masked Faces Using CNNs and LBPs

Face mask detection has several applications,including real-time surveillance,biometrics,etc.Identifying face masks is also helpful for crowd control and ensuring people wear them publicly.With monitoring personnel,it is impossible to ensure that people wear face masks;automated systems are a much superior option for face mask detection and monitoring.This paper introduces a simple and efficient approach for masked face detection.The architecture of the proposed approach is very straightforward;it combines deep learning and local binary patterns to extract features and classify themasmasked or unmasked.The proposed systemrequires hardware withminimal power consumption compared to state-of-the-art deep learning algorithms.Our proposed system maintains two steps.At first,this work extracted the local features of an image by using a local binary pattern descriptor,and then we used deep learning to extract global features.The proposed approach has achieved excellent accuracy and high performance.The performance of the proposed method was tested on three benchmark datasets:the realworld masked faces dataset(RMFD),the simulated masked faces dataset(SMFD),and labeled faces in the wild(LFW).Performancemetrics for the proposed technique weremeasured in terms of accuracy,precision,recall,and F1-score.Results indicated the efficiency of the proposed technique,providing accuracies of 99.86%,99.98%,and 100%for RMFD,SMFD,and LFW,respectively.Moreover,the proposed method outperformed state-of-the-art deep learning methods in the recent bibliography for the same problem under study and on the same evaluation datasets.

Development and Evaluation of an Optical Sensing System for Detection of Herbicide Spray Droplets

Real time monitoring of herbicide spray droplet drift is important for crop production management and environmental protection. Existing spray droplet drift detection methods, such as water-sensitive paper and tracers of fluorescence and Rubidium chloride, are time-consuming and laborious, and the accuracies are not high in general. Also, the tracer methods indirectly quantify the spray deposition from the concentration of the tracer and may change the drift characteristics of the sprayed herbicides. In this study, a new optical sensor system was developed to directly detect the spray droplets without the need to add any tracer in the spray liquid. The system was prototyped using a single broadband programmable LED light source and a near infrared sensor containing 6 broadband spectral detectors at 610, 680, 730, 760, 810, and 860 nm to build a detection system for monitoring and analysis of herbicide spray droplet drift. A rotatory structure driven by a stepper motor in the system was created to shift the droplet capture line going under the optical sensor to measure and collect the spectral signals that reflect spray drift droplets along the line. The system prototype was tested for detection of small (Very Fine and Fine), medium (Medium), and large (Coarse) droplets within the droplet classifications of the American Society of Agricultural and Biological Engineers. Laboratory testing results indicated that the system could detect the droplets of different sizes and determine the droplet positions on the droplet capture line with 100% accuracy at the wavelength of 610 nm selected from the 6 bands to detect the droplets.

基于同源录波数据比对的继电保护采样回路异常检测方法

处于改建阶段的智能变电站采样模式复杂,继电保护装置难以发现采样回路轻微异常,导致回路隐患暴露时间严重滞后。针对上述问题,分析改建时期智能变电站的采样模式和二次设备配置情况,提出基于同源录波数据比对的继电保护采样回路异常检测方法。首先,利用双向编码器表征(bidirectional encoder representations from transformers,BERT)语言模型与余弦相似度算法,实现同源录波数据的通道匹配。然后,利用重采样技术和曼哈顿距离完成波形的采样频率统一与时域对齐。最后,基于动态时间规整(dynamic time warping,DTW)算法提出改进算法,并结合采样点偏移量共同设置采样回路的异常判据。算例分析表明,该方法可以完成录波数据的同源通道匹配,实现波形的一致性对齐,并且相比于传统DTW算法,改进DTW算法对异常状态识别的灵敏性和准确性更高。根据异常判据能够有效检测继电保护采样回路的异常状态,确保了智能变电站的安全可靠运行。

基于联邦学习的智慧采购供应链网络入侵检测系统

为了保护智慧采购供应链网络中各参与企业的数据隐私安全,提出了一种基于联邦学习的入侵检测系统。首先,针对传统基于联邦学习的入侵检测模型训练低效的问题,提出了联合节点选择和带宽分配的模型训练方法,为高数据质量节点分配合适带宽;然后,为了客观衡量企业节点的入侵检测模型的迁移性能,构建基于数据分布和模型质量量化的迁移性能评估体系,进而提出入侵检测模型迁移效率最优函数,将复杂的节点选择和带宽分配问题转化为易于求解的迁移效率最大化问题;最后,提出了基于深度确定性策略梯度的迁移效率优化算法,求解最佳节点选择与带宽分配策略。实验结果表明,所提方法在确保高检测性能的同时,可以减少模型训练时间,提高训练效率,为智慧采购供应链网络提供更为可靠和高效的安全防护。

基于谐波检测的调相机失磁保护研究

首先对现有的调相机失磁保护进行分析,结果表明在系统低电压工况下调相机发生部分失磁故障,现有的失磁保护不能可靠动作,保护存在死区。通过研究调相机失磁后的励磁电流变化规律,得出调相机发生失磁故障后气隙合成磁势中含有高次谐波分量,将在定子绕组中产生对应的谐波电流。在此基础上,提出了一种基于谐波检测的调相机失磁保护方法。利用定子绕组中偶次谐波电流含量构建新的失磁保护策略,解决了系统低电压工况下失磁保护不能识别部分失磁故障的问题。最后,通过PSCAD/EMTDC建立了带有调相机的扎鲁特-青州±800 kV特高压直流输电模型,仿真结果验证了该方案的可行性。