AI-based Automation Control in Substations

The rapid development of Artificial Intelligence(AI)technologies has led to transformative applications in substation automation,addressing the growing complexities and demands of modern power grids.Substations,as crucial nodes in power distribution systems,play a vital role in maintaining grid stability,reliability,and security.However,traditional substation control systems face significant challenges in coping with system instability,aging infrastructure,and the integration of renewable energy sources.AI offers advanced solutions such as machine learning,deep learning,fuzzy logic,expert systems,and natural language processing to enhance fault detection,predictive maintenance,energy management,and grid security.This paper explores the AI technologies applied in substation automation,the challenges encountered in their integration,and the potential for future improvements.With the ability to analyze vast datasets,identify patterns,and make real-time decisions,AI is set to revolutionize substation operations,improving operational efficiency,reducing downtime,and enhancing system resilience.

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.

Analysis on the fault characteristics of three-phase short-circuit for half-wavelength AC transmission lines

Half-wavelength AC transmission(HWACT) is an ultra-long distance AC transmission technology, whose electrical distance is close to half-wavelength at the system power frequency. It is very important for the construction and operation of HWACT to analyze its fault features and corresponding protection technology. In this paper, the steady-state voltage and current characteristics of the bus bar and fault point and the steady-state overvoltage distribution along the line will be analyzed when a three-phase symmetrical short-circuit fault occurs on an HWACT line. On this basis, the threephase fault characteristics for longer transmission lines are also studied.

Research on Inter-turn Short-circuit Fault Diagnosis Method Based on High Frequency Voltage Residual for PMSM

Inter-turn fault is a serious stator winding short-circuit fault of permanent magnet synchronous machine(PMSM). Once it occurs, it produces a huge short-circuit current that poses a great risk to the safe operation of PMSM. Thus, an inter-turn short-circuit fault(ITSCF) diagnosis method based on high frequency(HF) voltage residual is proposed in this paper with proper HF signal injection. First, the analytical models of PMSM after the ITSCF are deduced. Based on the model, the voltage residual at low frequency(LF) and HF can be obtained. It is revealed that the HF voltage residual has a stronger ITSCF detection capability compared to the LF voltage residual. To obtain optimal fault signature, a 3-phase symmetrical HF voltage is injected into the machine drive system, and the HF voltage residuals are extracted. The fault indicator is defined as the standard deviation of the 3-phase HF voltage residuals. The effectiveness of the proposed ITSCF diagnosis method is verified by experiments on a triple 3-phase PMSM. It is worth noting that no extra hardware equipment is required to implement the proposed method.

Research on the Seismic-Geological Conditions for a Large Transformer Substation-A Case Study in the Shimian Region,Sichuan Province

A seismic-geological disaster can obviously affect an engineering site in three aspects:the first is ground faulting caused by the earthquake;the second is strong ground motion;the third is geological disasters such as landslides,mud-rock flows and liquefaction.Through the case study of selection of the huge transformer substation in the Shimian region of Sichuan Province,this paper proposes that the activity pattern and spatial distribution of faults near the site are crucial factors for evaluating the seismic-geological conditions for the location of huge transformer substations.

Short-circuit fault analysis and isolation strategy for matrix converters

The behavior of matrix converter(MC) drive systems under the condition of MC short-circuit faults is comprehensively investigated. Two isolation strategies using semiconductors and high speed fuses(HSFs) for MC short-circuit faults are examined and their performances are compared. The behavior of MC drive systems during the fuse action time under different operating conditions is explored. The feasibility of fault-tolerant operation during the fuse action time is also studied. The basic selection laws for the HSFs and the requirements for the passive components of the MC drive system from the point view of short-circuit faults are also discussed. Simulation results are used to demonstrate the feasibility of the proposed isolation strategies.

Remedial Phase-Angle Control of a Five-Phase Fault-Tolerant Permanent- Magnet Vernier Machine With Short-Circuit Fault

A fault-tolerant permanent-magnet vernier(FT-PMV)machine incorporates the merits of high fault-tolerant capability and high torque density.In this paper,a remedial phase-angle control(RPAC)strategy is proposed for a five-phase FT-PMV machine with short-circuit fault.Firstly,the proposed strategy can reduce the amount of unknown quantities by structuring the phase-angles of the normal phases.It can simplify the calculation of the remedial currents.Then,in order to obtain the desired torque,only the amplitudes of the remedial currents need to be calculated.Based on the principle of instantaneous electrical input power and mechanical output power balance condition,the real components are used to maintain the torque capability,while the reactive components are limited zero to minimize the torque ripple.Both simulations and experiments are presented to verify the proposed RPAC strategy.

智能牵引变电所配电网故障定位及识别研究

针对配电网结构的复杂性、设备的多样性和运行环境的不确定性及保护方法优化的需求,提出了一种智能牵引变电所配电网故障定位及识别方法,通过深入研究智能牵引变电所配电网故障定位及识别方法,并进行对比试验。结果表明,基于多维尺度分析和局部异常因子检测相结合的配电网故障定位算法,以及采用小波变换与支持向量机融合技术进行配电网故障类型识别的方法,能精确定位配电网故障区域并准确识别故障类型,从而提高供电的可靠性。

基于GWO-LSTM算法的智能变电站二次设备故障定位研究

目前,根据运行信息人工甄别并定位智能变电站的二次设备故障已无法满足新型电力系统对高可靠性的要求。提出一种基于GWO-LSTM算法的智能变电站二次设备故障定位的方法,首先分析智能变电站二次设备的建模关键信息,其次利用Apriori算法建立故障现象和故障位置的映射关系,得到智能变电站二次设备故障定位模型,再次利用长短期记忆神经网络和改进的灰狼算法训练模型,实现对故障位置的精准定位,最后通过仿真验证所提方法的有效性。结果表明,所提方法可以有效提升智能变电站二次设备故障定位的准确性。

基于物联网的变电站设备监控与故障预防

针对变电站设备监控中实时性不足和故障预防效果不佳的问题,本文提出了一种基于物联网的智能监控与故障预防系统。该系统通过传感器网络实时监测设备运行状态,利用高速无线通信技术实现数据的快速传输,并结合机器学习算法进行智能分析与故障预测。系统设计包括数据采集模块、数据传输模块、以及数据分析与故障预防模块。实验结果表明,该系统有效提升了变电站设备的监控实时性和故障预防能力,为设备的智能化管理提供了新的解决方案。

Design and Optimization of Dual-Winding Fault-Tolerant Permanent Magnet Motor

To improve the performance of the traditional fault-tolerant permanent magnet(PM)motor,the design and optimal schemes of dual-winding fault-tolerant permanent magnet motor(DWFT-PMM)are proposed and investigated.In order to obtain small cogging torque ripple and inhibiting the short-circuit current,the air gap surface shape of the PM and the anti short-circuits reactance parameters are designed and optimized.According to the actual design requirements of an aircraft electrical actuation system,the parameters,finite element analysis and experimental verification of the DWFT-PMM after optimal design are presented.The research results show that the optimized DWFT-PMM owns the merits of strong magnetic isolation,physics isolation,inhibiting the short circuit current,small cogging torque ripple and high fault tolerance.

Placement optimization of Multi-Type fault current limiters based on genetic algorithm

The fault current limiter(FCL)is an effective measure for improving system stability and suppressing short-circuit fault current.Because of space and economic costs,the optimum placement of FCLs is vital in industrial applications.In this study,two objectives with the same dimensional measurement unit,namely,the total capital investment cost of FCLs and circuit breaker loss related to short-circuit currents,are considered.The circuit breaker loss model is developed based on the attenuation rule of the circuit breaker service life.The circuit breaker loss is used to quantify the current-limiting effect to avoid the problem of weight selection in a multi-objective problem.The IEEE 10-generator 39-bus system in New England is used to evaluate the performance of the proposed genetic algorithm(GA)method.Comparative and sensitivity analyses are performed.The results of the optimized plan are validated through simulations,indicating the significant potential of the GA for such optimization.

Single-phase earth fault current distribution between optical fiber composite overhead ground wire and ordinary ground wire in transmission system

It is important for the safety of transmission system to accurately calculate single-phase earth fault current distribution.Features of double sided elimination method were illustrated.Quantitative calculation of single-phase earth fault current distribution and case verification were accomplished by using the loop method.Influences of some factors,such as single-phase earth fault location and ground resistance of poles,on short-circuit current distribution were discussed.Results show that:1) results of the loop method conform to those of double sided elimination method;2) the fault location hardly influences macro-distribution of short-circuit current.However,current near fault location is evidently influenced;and 3) the short-circuit current distribution is not so sensitive to the ground resistance of poles.

New “Intellectual Networks” (Smart Grid) for Detecting Electrical Equipment Faults, Defects and Weaknesses

The most important elements of “intellectual networks” (Smart Grid) are the systems of monitoring the parameters of electrical equipment. Information-measuring systems (IMS), which described in this paper, were proposed to use together with rapid digital protection against short-circuit regimes in transformer windings. This paper presents an application’s experience of LVI-testing, some results of the use of Frequency Response Analysis (FRA) to check the condition of transformer windings and infra-red control results of electrical equipment. The LVI method and short-circuit inductive reactance measurements are sensitive for detecting such faults as radial, axial winding deformations, a twisting of low-voltage or regulating winding, a losing of winding’s pressing and others.

Intelligent System Design for Stator Windings Faults Diagnosis:Suitable for Maintenance Work

The short circuit is a severe fault that occurs in the stator windings. Therefore, it is very important to diagnose this type of failure in its beginning before it causes unscheduled stop and the machine loss. In this context, the Support Vector Machine (SVM) is a tool of considerable importance for standard classification. From some training data, it can diagnose whether or not there is a short circuit beginning, and which is important for predictive maintenance. This work proposes a technique for early detection of a short circuit between the turns aiming at its implementation in a real plant. The paper shows simulation and experimental results, and validates the proposed technique.

Validation of Full-Converter Wind Power Plant Generic Model Based on Actual Fault Ride-Through Measurements

Modeling and validation of full power converter wind turbine models with field measurement data are rarely reported in papers. In this paper an aggregated generic dynamic model of the wind farm consisting of full power converter wind turbines is composed and the model validation based on actual field measurements is performed. The paper is based on the measurements obtained from the real short circuit test applied to connection point of observed wind farm. The presented approach for validating the composed model and fault ride-through （FRT） capability for the whole wind park is unique in overall practice and its significance and importance is described and analyzed.

基于深度卷积神经网络的变电一次设备故障检测方法研究

该文介绍了一种变电一次设备故障检测方法:通过不同光照环境收集一次设备的图像,创建设备数据集并进行预处理,通过深度卷积神经网络提取设备特征并加以检测。经检测,此方法能够明显降低变电一次设备故障的漏报和误报率。

基于连接状态定位的智能变电站二次系统故障定位方法

变电站二次回路及系统运行状态因设备自身及物理连接等原因具有一定的不确定性,二次系统故障定位难度较大。提出一种基于连接状态定位的智能变电站二次系统故障定位方法。首先将二次系统设备拓扑连接关系抽象为矩阵描述,二次系统设备节点状态量作为相应矩阵元素;然后通过矩阵算法对二次系统连接状态进行定位,确定与故障有关的矩阵元素;在连接状态定位后利用模糊径向基神经网络将故障相关矩阵元素与故障集中各故障情况对应,进行故障搜索定位。故障算例结果表明,所提出的二次系统故障定位方法具有较高的准确率。

变电设备健康状态监测系统设计

在电力系统中,某一环节的变电设备一旦出现故障且未及时检修,就会对整个电力系统运行造成严重影响。由于人工巡检难以做到实时监测,设备状态频发事件时有发生,亟须一种手段能够对这类变电设备的运行进行实时监测,同时根据变电设备的实时状态变化对变电设备可能出现的故障进行分类预警。通过实验证明了可听声局部放电模型的可行性。以该模型为基础,设计和开发了软硬一体的变电设备健康状态监测系统。该系统能够实时监测变电设备的运行状态,并通过设备的状态变化及时作出相应的故障判断与预警。该系统的成功研制对提升电力系统的设备监测效率、降低人力成本与运维成本、提高经济效益具有一定的参考价值。

高速铁路10 kV变配电所馈线保护方式优化研究

铁路10 kV变配电所地方进线电源一般为中性点不接地系统。高速铁路变配电所内的馈线、贯通线多为全电缆线路,发生单相接地故障后,馈线电缆零序保护不跳闸只报警,允许故障馈线带故障运行。然而,电力电缆的绝缘裕度比架空线路的绝缘裕度小得多,承受过电压的能力低,一旦发生单相接地故障,易引起永久性的绝缘击穿,进而发展成为相间故障,使故障范围扩大。本文提出高速铁路变配电所故障馈线小电流选线方法,可准确判断出发生电缆单相接地故障的馈线,避免故障扩大。对于高阻接地故障,提出了采用基于暂态量的综合选线方法,除比对故障和非故障线路的零序电流幅值和相位,还利用暂态无功功率方向进行准确选线。