2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)最新文献_第2页

Optimal Distribution Automation Devices Placement for Reliability Improvement of a Real Distribution Network with Sub-Feeders Considering Customer Interruption Cost 考虑用户中断成本的带子馈线实际配电网可靠性优化配电自动化装置配置

2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA) Pub Date : 2019-01-01 DOI: 10.1109/ROBOMECH.2019.8704786

Jabulani Masimula, K. Awodele

{"title":"Optimal Distribution Automation Devices Placement for Reliability Improvement of a Real Distribution Network with Sub-Feeders Considering Customer Interruption Cost","authors":"Jabulani Masimula, K. Awodele","doi":"10.1109/ROBOMECH.2019.8704786","DOIUrl":"https://doi.org/10.1109/ROBOMECH.2019.8704786","url":null,"abstract":"This paper presents predictive analytical and simulation approaches to reliability worth/cost assessments conducted on a test system and a typical Cape Town real system. Feeder 3 of bus 6 of the RBTS was utilized to illustrate various cases of switch configurations and for each arrangement the reliability indices were evaluated analytically as well as in Monte Carlo Simulation and results found to be similar. In this paper three scenarios were investigated in the Waterkloof Farmers-1 11 kV network (real system); Reliability assessment was firstly performed without automation devices (Scenario 1), secondly with automation devices in the current or existing positions (Scenario 2) and lastly, with optimal placement of the automation devices on the feeder using analytical and evolutionary algorithms methodologies (Scenario 3). The objective function behind placement can either be based on SAIDI or the ECOST and the best switch position for SAIDI might be worst position for the ECOST.","PeriodicalId":344332,"journal":{"name":"2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"25 11-12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127182531","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

DepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesis DepthwiseGANs:用于逼真图像合成的快速训练生成对抗网络

2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA) Pub Date : 2019-01-01 DOI: 10.1109/ROBOMECH.2019.8704766

Mkhuseli Ngxande, J. Tapamo, Michael Burke

{"title":"DepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesis","authors":"Mkhuseli Ngxande, J. Tapamo, Michael Burke","doi":"10.1109/ROBOMECH.2019.8704766","DOIUrl":"https://doi.org/10.1109/ROBOMECH.2019.8704766","url":null,"abstract":"Recent work has shown significant progress in the direction of synthetic data generation using Generative Adversarial Networks (GANs). GANs have been applied in many fields of computer vision including text-to-image conversion, domain transfer, super-resolution, and image-to-video applications. In computer vision, traditional GANs are based on deep convolutional neural networks. However, deep convolutional neural networks can require extensive computational resources because they are based on multiple operations performed by convolutional layers, which can consist of millions of trainable parameters. Training a GAN model can be difficult and it takes a significant amount of time to reach an equilibrium point In this paper, we investigate the use of depthwise separable convolutions to reduce training time while maintaining data generation performance. Our results show that a DepthwiseGAN architecture can generate realistic images in shorter training periods when compared to a StarGan architecture, but that model capacity still plays a significant role in generative modelling. In addition, we show that depthwise separable convolutions perform best when only applied to the generator. For quality evaluation of generated images, we use the Fréchet Inception Distance (FID), which compares the similarity between the generated image distribution and that of the training dataset.","PeriodicalId":344332,"journal":{"name":"2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123712777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

Battery Monitoring and Energy Forecasting for an Off-Grid Solar Photovoltaic Installation 离网太阳能光伏装置的电池监测与能量预测

2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA) Pub Date : 2019-01-01 DOI: 10.1109/ROBOMECH.2019.8704728

Sailen Nair, William Becerra Gonzalez, J. Braid

引用次数: 2

Three-Phase Five-Limb Transformer Harmonic Analysis under DC-bias 直流偏置下三相五肢变压器谐波分析

2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA) Pub Date : 2019-01-01 DOI: 10.1109/ROBOMECH.2019.8704818

T. T. Murwira, S. Mkhonta, D. Oyedokun, K. Folly, C. T. Gaunt

引用次数: 0

Improving Reliability on Distribution Systems Using BPSO for Device Placement 用BPSO提高配电系统的可靠性

2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA) Pub Date : 2019-01-01 DOI: 10.1109/ROBOMECH.2019.8704777

R. Bhugwandeen, A. Saha

引用次数: 0

Application of Reliability-Centred Maintenance for DC Traction Motors - A Review 以可靠性为中心的维修在直流牵引电动机中的应用综述

2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA) Pub Date : 2019-01-01 DOI: 10.1109/ROBOMECH.2019.8704755

M. Mayisela, D. Dorrell

引用次数: 2

Image processing towards the automated identification of nanoparticles in SEM images 面向扫描电镜图像中纳米颗粒自动识别的图像处理

2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA) Pub Date : 2019-01-01 DOI: 10.1109/ROBOMECH.2019.8704799

Nicolene Botha, G. Wessels, N. Botha, Beatrice van Eden

引用次数: 2

A Comparison of Skin Detection Algorithms for Hand Gesture Recognition 手势识别中皮肤检测算法的比较

2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA) Pub Date : 2019-01-01 DOI: 10.1109/ROBOMECH.2019.8704839

Timothy James McBride, Nabeel Vandayar, K. Nixon

引用次数: 14

Recloser placement on medium voltage distribution networks 中压配电网上的重合闸安置

2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA) Pub Date : 2019-01-01 DOI: 10.1109/ROBOMECH.2019.8704784

Renaldo Strydom, P. Hertzog

{"title":"Recloser placement on medium voltage distribution networks","authors":"Renaldo Strydom, P. Hertzog","doi":"10.1109/ROBOMECH.2019.8704784","DOIUrl":"https://doi.org/10.1109/ROBOMECH.2019.8704784","url":null,"abstract":"Re-evaluating methods in any business is essential, as it reinforces knowledge, improves methodologies and proves concepts can possibly be used in other applications. Eskom’s standard for placing reclosers does not focus on the financial costs and benefits thereof it only focusses to reach their performance targets. The purpose of this paper is to present a method to optimise the placement of reclosers on the distribution networks. Eskom could by focusing at the financial benefits of recloser placement improve their performance targets as well as save more money in fault conditions. The recloser placements will be done using a design to cost methodology. Formulas and matrix tables will be used to determine the maximum number of reclosers to be installed and used for placements on networks. The findings prove that placing reclosers on the network using this method will payback itself within one year. The work to be done in this paper will give another dynamic when focusing on recloser placements that include finances and technical parameters combined to place reclosers. Future studies can be done by combining recloser placements with other protection sensing equipment Fault Path Indicators or Current Voltage Monitors to isolate and find faults on the network. using abbreviations in the abstract.","PeriodicalId":344332,"journal":{"name":"2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124639854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Bringing Back the Synchronous Compensator for the South Africa Power Network—Simulation and Compensator Technology 南非电网同步补偿器的回归仿真与补偿技术

2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA) Pub Date : 2019-01-01 DOI: 10.1109/ROBOMECH.2019.8704841

Christopher Africa, U. B. Akuru, M. Kamper

引用次数: 2