Effect Evaluation and Intelligent Prediction of Power Substation Project Considering New Energy

The evaluation of the implementation effect of the power substation project can find out the problems of the project more comprehensively,which has important practical significance for the further development of the power substation project.To ensure accuracy and real-time evaluation,this paper proposes a novel hybrid intelligent evaluation and prediction model based on improved TOPSIS and Long Short-Term Memory(LSTM)optimized by a Sperm Whale Algorithm(SWA).Firstly,under the background of considering the development of new energy,the influencing factors of power substation project implementation effect are analyzed from three aspects of technology,economy and society.Moreover,an evaluation model based on improved TOPSIS is constructed.Then,an intelligent prediction model based on SWA optimized LSTM is designed.Finally,the scientificity and accuracy of the proposed model are verified by empirical analysis,and the important factors affecting the implementation effect of power substation projects are pointed out.

The Research of Intelligent Substation Time Synchronization System and the Influence of Its Fault to Relay Protection

The intelligent substation realizes the digitization of information in the whole substation and thus time synchronization system becomes more and more important. This paper introduces time synchronization technology of intelligent substation and puts forward the principles for designing intelligent substation time synchronization system. According to some relay protection malfunction examples caused by time synchronization system fault, analyze the influence of time synchronization system fault to relay protection and correspondingly put forward some improving measures.

Application of Mobile Intelligent Inspection System in Substation Equipment Management

Intelligent inspection is more and more widely applied in all walks of life. This paper introduces the application of the intelligent inspection system in substation equipment management based on mobile phone terminal. It can make the power supply enterprise have more effective means to ensure the safe operation of equipment, improve equipment management level, and improve the economic benefits of power supply.

The Intelligent Terminal Design for Integrated Substation Auxiliary System

The integrated substation auxiliary system is a project composed by software and hardware to help operators of a substation carry daily maintain works. The intelligent terminal is the key part of the system and it provides important UI and communication functions for the user. Smart phones can achieve higher bandwidth data communication, and at the same time can carry Bluetooth communication, video call, multimedia display and other functions. Smart phone is a potential common platform, suitable for the deployment of substation integrated auxiliary system terminal. Based on the Android Smart phone platform, this paper develops intelligent client-side software for the integrated substation auxiliary system and it can realize the operation ticket control, the video call, the substation map display and other functions. This client-side software has been applied in practice, and has gained good effects.

Research on Communication Network Configuration and Simulation of Smart Substation Based on Ethernet

The characters of the intelligent substation communication network structure are analyzed in the paper. Combining existing integrated automation substation hardware circuit and VLAN (Virtual Local Area Network) research foundation to optimize the network configuration. In accordance with IEC61850 standard, the network is partitioned into several VLANs based on the Tag VLAN division method of ID address. Real-time communication packets between GOOSE networks, SV (sampling information) networks, and switches use 802.1Q protocol headers to distinguish these packets. Finally, OPNET simulation software was used to simulate and verify the simplified dual-star topology. The results demonstrate that the delay and traffic bandwidth meet the requirements of actual substation operation standards. Compared with ordinary single-star networks, the reliability is greatly improved and the effectiveness is improved.

Research on the Process Layer and Substation Layer Relay Protection in Smart Substation Relay Protection

The intelligent substation relay protection facility is a fundamental element in construction of modern power system,based on the principles of flexibility,security and accuracy,and it can be divided into process layer and substation layer according to specific equipment.The former is suitable for individual sampling of disposable equipment,can be separated from the base station synchronization sampling,with the help of synchronous digital system and ping-pong algorithm to achieve synchronization of the overall sampling,that is to take the distribution protection components,through the separate transmission medium to realize the information transmission;the latter is for variable power plant components centralized backup protection,taking online real-time tuning technique.

Automatic infrared image recognition method for substation equipment based on a deep self-attention network and multi-factor similarity calculation

Infrared image recognition plays an important role in the inspection of power equipment.Existing technologies dedicated to this purpose often require manually selected features,which are not transferable and interpretable,and have limited training data.To address these limitations,this paper proposes an automatic infrared image recognition framework,which includes an object recognition module based on a deep self-attention network and a temperature distribution identification module based on a multi-factor similarity calculation.First,the features of an input image are extracted and embedded using a multi-head attention encoding-decoding mechanism.Thereafter,the embedded features are used to predict the equipment component category and location.In the located area,preliminary segmentation is performed.Finally,similar areas are gradually merged,and the temperature distribution of the equipment is obtained to identify a fault.Our experiments indicate that the proposed method demonstrates significantly improved accuracy compared with other related methods and,hence,provides a good reference for the automation of power equipment inspection.

电力信息物理系统中信息系统物理化的建模及分析方法

该文基于信息系统物理化的设想提出电力信息物理系统(cyber-physical power system,CPPS)中的信息流建模和计算分析方法。采用连续时间函数来刻画信息流的特征,并定义信息网络运行参数为流量累积函数、信息流速和时延。首先,基于遍历法搜索出信息流路径,建立信息流速矩阵的范式;然后利用改进的网络演算(network calculus,NC)特性赋值流速矩阵的元素;进一步采用流量累积函数表征信源数据发送规律,从而显式求解时延上界。最后将提出的信息流建模方法应用于智能变电站自动化系统的时延计算,通过与OPNET的仿真结果相比较,验证所提出模型的有效性,而且该方法可以提供定量分析指标以优化变电站组网方案设计中的信息流分布。

基于异步整形机制的智能变电站通信队列调度策略

时间敏感网络(TSN)因能为智能变电站关键通信业务提供确定性低延时传输服务而得到广泛关注。针对现有变电站工业以太网交换机通信队列调度策略难以从理论上保证关键通信业务的实时性和可靠性的问题,该文提出了基于TSN异步整形机制(ATS)的智能变电站通信队列调度策略。首先,基于智能变电站业务流服务质量需求及传输特点,提出了智能变电站业务流的优先级划分及整形队列分配方案;其次,建立了以业务流端到端时延最小化为目标的整形器参数最优化模型,并通过内点优化算法求解;最后,整形器采用基于令牌桶的流量整形方法对划分后的业务流进行整形,整形后的流量基于严格优先级算法调度传输。基于OMNet++进行了仿真实验,实验结果表明,该文所提方法能够保障关键通信业务的确定性低时延传输。

基于多目标优化的变电站消防资源配置算法

针对变电站消防资源分配与分布不均匀的问题,提出了一种基于多目标优化的变电站消防资源配置算法。该算法采用电力生产场所的道路网作为变电站消防责任区划分的依据,并结合各划分区域的消防需求构建消防资源配置模型。根据该模型的特点,在帕累托最优解的约束下提出了一种基于模拟退火的多目标优化算法,来求解该消防资源配置模型。仿真与实验结果表明,所提出的消防资源配置模型更符合实际变电站各场所分布的特点,且所提出的多目标优化算法得到的消防资源分配结果能在消防资源有限的条件下,实现最大的配置效益和快速的消防响应。

变电站电磁环境智能移动监测装置设计与实测

为提升变电站电磁环境信息采集的工作效率,提高数据测量精度,研究制作一台变电站电磁环境智能移动监测装置。所设计的工频电场探头可实现3个方向工频电场同步测量;带有复位电路的工频磁场采集电路可消除磁阻传感器处于过强磁场干扰时的异常问题;外置温湿度模块可保证测量准确度,采用憎水性复合材料支架,在湿度小于70%条件下测量误差在5%以内。第三方测试结果表明,电磁场测量结果误差在5%以内,采用此装置在实际110 kV变电站进行电磁环境实测,可准确按规定路径自主行走并进行测量。建立三维模型,进行空间电磁场分布的仿真模拟,所得实测数据与仿真数据有相同的变化趋势,进一步验证装置测量的准确性。

一种应用于智能变电站的系统配置描述文件配置方法

变电站配置描述(SCD)文件的正确性是智能变电站安全可靠运行的基础。针对SCD文件配置工作量大、人工参与度过高的问题,提出一种SCD文件配置方法,包含智能化二次设备站控层、过程层通信地址自动配置、过程层虚端子装置级配置及SCD文件远景配置三个方面,可减少SCD文件配置工作量,提高SCD文件配置的自动化水平,缩小变电站改扩建过程中SCD文件频繁修改对二次设备的影响范围,从而保证智能变电站的安全可靠运行。

多舱体系变电站模块化布局及其方案智能生成方法

为研究多舱体系变电站舱体布局方案的智能生成方法,本文考虑了设计原则对多舱体系变电站中舱体模块布局的约束,引入多舱体系变电站占地面积、线缆连接、模块搭接施工费用等成本作为目标函数,并通过将设计可行域离散为矩形单元建立了数学模型,提出一种基于遗传算法的求解方法。通过某多舱体系变电站的数值算例,阐释了所提出的多舱体系变电站模块化布局智能生成方法的应用过程和结果。结果表明:在满足所有约束的前提下,所提出方法生成的舱体呈聚集分布;设计可行域离散化模数的选择应平衡设计结果精度和计算代价;相比人工设计的方案,所提出方法生成的布局方案可以更好地协调各设计目标,并显著降低建站成本。本文将智能算法应用于模块化建筑的生成式设计,显著降低了多舱体系变电站的综合建站成本,为多舱体系变电站模块化布局智能设计提供了新的思路和方法,对同类型具有复杂设计原则和约束机制的模块化建筑的智能设计具有理论意义和实际应用价值。

基于威胁情报语义规则抽取的智能变电站告警分析方法

威胁情报作为一种弥补攻防信息不对称的安全技术,能够帮助安防人员发现威胁行为,并采取相应的预防措施。近年来,威胁情报研究受到业界广泛关注,然而现有的研究对威胁情报的利用率较低,为此,提出了一种基于威胁情报语义规则抽取的智能变电站告警分析方法。首先,通过构建语义规则模型生成语义规则图,对攻击技术手段进行描述;其次,面向ATT&CK攻击技术文本构建语义规则抽取框架,对攻击技术文本进行知识抽取,从中得到语义规则。该方法在解决智能变电站告警信息冗余繁杂问题的同时,提升了威胁情报的利用率,实现了对高层级威胁情报的自动化分析与处理。

基于哈希和编辑距离算法的SCD双层向量化与变更校验技术

针对智能变电站配置描述(substation configuration description,SCD)文件变更、智能变电站二次设备配置不清晰导致运维工作量剧增的问题,提出基于哈希和编辑距离算法的SCD双层向量化与变更校验技术。首先,考虑文件变更的启动与校验,应用节点元素、校验码与元素属性构建面向SCD文件解析的双层向量模型;其次,利用哈希算法将构建的文本向量模型转化为哈希字符串向量模型;然后,引入编辑距离算法分别计算原始文件与变更文件的双层向量模型相似度,基于第一层相似度比较构成第二层校验启动判据,基于第二层相似度结合回溯路径方法实现变更校验;最后,通过算例分析验证了所提算法的有效性。

数字化变电站配电系统设计

为了提高变电站配电系统的监控能力和管理水平,设计了数字化变电站配电系统。通过对变电站系统的数字化改造,对配电系统的各个部分进行监控和保护。结果表明,改造后系统不但能够对用电事故准确判断,减少故障时间,提高系统可靠性,还可以及时反映设备的用电状况和用电量,准确地进行成本核算。所设计系统提高了企业的管理水平,促进了企业的数字化、智能化和信息化的发展。

智能变电站二次系统安全隔离策略研究

针对传统隔离策略难以适用于智能变电站虚拟化配置的问题,提出了一种智能变电站的二次系统安全隔离策略。通过对SCD文件结构与各种隔离手段的分析,设计了一种可靠性评估方式。同时基于图信息技术生成安全隔离链路矩阵,采用边集数组存储虚回路信息,利用邻接矩阵实现对安全措施的分析与判断,从而获得可靠性较高的安全隔离措施。以ADPSS数字化系统为基础,对所提策略进行的实验论证结果表明,该策略的可靠性约为99.65%,且能将二次回路可视化,具有一定的工程意义。

智能变电站就地化继电保护的配置及校验

针对现阶段智能变电站保护动作时间过长导致部分设备受干扰而易出现故障的情况,研究设计了110 kV变电站就地化继电保护配置框架。具体分析了线路保护、变压器保护、母线保护以及智能管理单元等装置的技术要点,在某变电站使用设计的框架对提出的就地化保护配置系统进行了校验,分析了不同装置的定制校验和整定原则。对比了线路保护、变压器保护和母线保护的选择性和灵敏性,并给出了具体评价结果。

变电站远程智能巡检系统研究与应用

针对目前变电站运行过程中存在的巡检不及时、漏巡检、故障判断不准、现场环境对人身安全存在隐患等问题,将监测技术、通信技术和信息处理技术相结合,构建变电站远程智能巡检系统。该系统能够实时感知、远程监测、智能巡检各种类型的变电设备,其架构分为应用端、通信端和服务端3个层次。将该系统应用于变电站的远程巡检工作中,可实现对变电站的远程图像采集和联动,进而实现变电站的智能巡检,对出现问题的设备进行实时报警,以进行高效的处理。

基于改进BA-PNN的智能变电站二次设备故障定位方法

针对概率神经网络(PNN)在二次设备故障定位中训练规模较大、容易受到平滑因子干扰的问题,提出了一种基于改进蝙蝠算法优化概率神经网络(BA-PNN)的智能变电站二次设备故障定位方法。首先,在PNN的求和层中采用拉普拉斯分布代替高斯分布,并用BA算法来获得最优平滑因子,进而提出一种改进蝙蝠算法优化概率神经网络方法;其次,基于智能变电站中二次设备的特征分析,选择故障特征量并对其映射,建立了基于BAPNN的智能变电站二次设备故障定位模型;最后,以某智能变电站故障定位为例,对BA-PNN神经网络进行样本训练,实现对故障元件的精确定位。仿真表明,该方法缩小了神经网络的训练规模,提升了神经网络的计算性能,增强了故障定位的准确性。