2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)最新文献
Pub Date : 1900-01-01DOI: 10.1109/ROBOMECH.2019.8704795
Therasinamurthie P. Govender, I. Davidson
The artisan work force is the lifeblood of the engineering and technology sectors and is the key factor in driving the economic growth and development of any country. Presently South Africa is experiencing a shortage of skilled artisans who can maintain the various state-owned entities (SOE’s) and other processing and manufacturing plants in the industrial sectors. In the last 20 years different initiatives and interventions have being put in place by government in order to overcome the shortage of scare and critical skills [17]. The purpose of this paper is to present the artisan training and development model practiced at TEK-MATION Training Institute and to share the best practices and shortcomings of the model.
{"title":"Artisan Development and Training - An analysis of the Apprentice, Learnership and ARPL Trade Test Results of Candidates Tested at TEK-MATION Training Institute","authors":"Therasinamurthie P. Govender, I. Davidson","doi":"10.1109/ROBOMECH.2019.8704795","DOIUrl":"https://doi.org/10.1109/ROBOMECH.2019.8704795","url":null,"abstract":"The artisan work force is the lifeblood of the engineering and technology sectors and is the key factor in driving the economic growth and development of any country. Presently South Africa is experiencing a shortage of skilled artisans who can maintain the various state-owned entities (SOE’s) and other processing and manufacturing plants in the industrial sectors. In the last 20 years different initiatives and interventions have being put in place by government in order to overcome the shortage of scare and critical skills [17]. The purpose of this paper is to present the artisan training and development model practiced at TEK-MATION Training Institute and to share the best practices and shortcomings of the model.","PeriodicalId":344332,"journal":{"name":"2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123947079","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}
Pub Date : 1900-01-01DOI: 10.1109/ROBOMECH.2019.8704793
T. Ayodele, R. Olarewaju, J. Munda
In this paper, the capability of prediction models is compared for wind speed forecast at different time horizons (i.e. very-short term, short-term, medium term and long term horizons) with the aim of determining their prediction accuracy. The models include: Persistence, second order Markov chain, autoregressive moving average (ARMA) and Weibull models. The models have applications in the areas of electricity market clearing, regulation actions and maintenance scheduling to achieve optimal operating cost. The data used for the study consist of ten-minute average wind speeds for Alexander Bay region of South Africa. Statistical measure and error measures were employed for model validation. The key result reveals that the autoregressive model is best suited for very short and long term wind speed prediction while second order Markov chain is the most appropriate model for short and medium term prediction. Persistence model appears to be the least accurate of all the models for all time horizons.
{"title":"Comparison of Different Wind Speed Prediction Models for Wind Power Application","authors":"T. Ayodele, R. Olarewaju, J. Munda","doi":"10.1109/ROBOMECH.2019.8704793","DOIUrl":"https://doi.org/10.1109/ROBOMECH.2019.8704793","url":null,"abstract":"In this paper, the capability of prediction models is compared for wind speed forecast at different time horizons (i.e. very-short term, short-term, medium term and long term horizons) with the aim of determining their prediction accuracy. The models include: Persistence, second order Markov chain, autoregressive moving average (ARMA) and Weibull models. The models have applications in the areas of electricity market clearing, regulation actions and maintenance scheduling to achieve optimal operating cost. The data used for the study consist of ten-minute average wind speeds for Alexander Bay region of South Africa. Statistical measure and error measures were employed for model validation. The key result reveals that the autoregressive model is best suited for very short and long term wind speed prediction while second order Markov chain is the most appropriate model for short and medium term prediction. Persistence model appears to be the least accurate of all the models for all time horizons.","PeriodicalId":344332,"journal":{"name":"2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121337902","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}
Pub Date : 1900-01-01DOI: 10.1109/ROBOMECH.2019.8704810
Raymond O. Kene, S. Chowdhury, T. Olwal
To be able to dispatch electrical power effectively to consumers using solar photovoltaic (SPV) cells, there is a need to have information about the SPV power generation. This information is best derived from predicting the SPV power ahead of any supply. Artificial neural network intelligence technique is employed in this study with the aim of predicting SPV electrical power for a period of 7 days. The maximum power produced on a daily basis is been identified as well as the daily average power that is produced and predicted. With this information, the short-term availability of daily solar irradiation can be maximized. A statistical regression analysis has been used to establish the relationship between the produced and predicted power, using statistical functions like the mean bias error (MBE), the mean square error (MSE), root mean square error (RMSE), mean absolute deviation (MAD), mean absolute percentage error (MAPE), and the correlation coefficient (CC). The algorithm used in training the network is the backpropagation algorithm with feed-forward neural network. A total of 14,300 datasets have been used to establish this study with the application of artificial neural network (ANN) for prediction analysis. The result indicates that, the uncertainty in SPV power generation can be mitigated using ANN to predict its performance, thereby creating visibility as to what the SPV system can generate. This enables load balancing, efficient power dispatch and accurate scheduling.
{"title":"Application of Artificial Intelligence Technique in Predicting 7-Days Solar Photovoltaic Electrical Power","authors":"Raymond O. Kene, S. Chowdhury, T. Olwal","doi":"10.1109/ROBOMECH.2019.8704810","DOIUrl":"https://doi.org/10.1109/ROBOMECH.2019.8704810","url":null,"abstract":"To be able to dispatch electrical power effectively to consumers using solar photovoltaic (SPV) cells, there is a need to have information about the SPV power generation. This information is best derived from predicting the SPV power ahead of any supply. Artificial neural network intelligence technique is employed in this study with the aim of predicting SPV electrical power for a period of 7 days. The maximum power produced on a daily basis is been identified as well as the daily average power that is produced and predicted. With this information, the short-term availability of daily solar irradiation can be maximized. A statistical regression analysis has been used to establish the relationship between the produced and predicted power, using statistical functions like the mean bias error (MBE), the mean square error (MSE), root mean square error (RMSE), mean absolute deviation (MAD), mean absolute percentage error (MAPE), and the correlation coefficient (CC). The algorithm used in training the network is the backpropagation algorithm with feed-forward neural network. A total of 14,300 datasets have been used to establish this study with the application of artificial neural network (ANN) for prediction analysis. The result indicates that, the uncertainty in SPV power generation can be mitigated using ANN to predict its performance, thereby creating visibility as to what the SPV system can generate. This enables load balancing, efficient power dispatch and accurate scheduling.","PeriodicalId":344332,"journal":{"name":"2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"16 s3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113956965","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}
Pub Date : 1900-01-01DOI: 10.1109/ROBOMECH.2019.8704768
K. Moloi, A. Yusuff
In this paper, a method for detection and classification of faults in an electrical power distribution system is presented. Digsilent Power Factory software was used to model a section of a 66 kV power system. Fault incidents were instantiated on the model. The signal obtained from fault incidences were subsequently fed as input to discrete wavlet transform in order to obtained fault features and subsequently the features were then used as inputs for a support vector machine (SVM) and artificial neural network (ANN) for fault classification and detection. In addition, a Gaussian Process Regression (GPR) technique was employed for estimation of fault locations along the distribution line. Fault detection, classification and location estimation scheme were developed in MATLAB. The method showed that most faults on electric power distribution network can be classified with a good accuracy and minimum fault estimation error. The method is further validated on a real world power system. A hybrid method is thus proposed for detection, classification and estimation of fault location in a distribution network.
本文提出了一种配电系统故障检测与分类的方法。使用Digsilent Power Factory软件对66千伏电力系统的一个部分进行建模。故障事件在模型上实例化。将故障事件信号作为离散小波变换的输入，得到故障特征，然后将这些特征作为支持向量机(SVM)和人工神经网络(ANN)的输入，进行故障分类和检测。此外，采用高斯过程回归(GPR)技术对配电线路沿线的故障位置进行估计。在MATLAB中开发了故障检测、分类和定位估计方案。结果表明，该方法能以较好的准确率和最小的故障估计误差对配电网中的大多数故障进行分类。该方法在实际电力系统中得到了进一步验证。提出了一种用于配电网故障定位检测、分类和估计的混合方法。
{"title":"A Support Vector Machine Based Fault Diagnostic Technique In Power Distribution Networks","authors":"K. Moloi, A. Yusuff","doi":"10.1109/ROBOMECH.2019.8704768","DOIUrl":"https://doi.org/10.1109/ROBOMECH.2019.8704768","url":null,"abstract":"In this paper, a method for detection and classification of faults in an electrical power distribution system is presented. Digsilent Power Factory software was used to model a section of a 66 kV power system. Fault incidents were instantiated on the model. The signal obtained from fault incidences were subsequently fed as input to discrete wavlet transform in order to obtained fault features and subsequently the features were then used as inputs for a support vector machine (SVM) and artificial neural network (ANN) for fault classification and detection. In addition, a Gaussian Process Regression (GPR) technique was employed for estimation of fault locations along the distribution line. Fault detection, classification and location estimation scheme were developed in MATLAB. The method showed that most faults on electric power distribution network can be classified with a good accuracy and minimum fault estimation error. The method is further validated on a real world power system. A hybrid method is thus proposed for detection, classification and estimation of fault location in a distribution network.","PeriodicalId":344332,"journal":{"name":"2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132558676","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}
Pub Date : 1900-01-01DOI: 10.1109/ROBOMECH.2019.8704732
Dumusani Kunene, Vusi Skosana
The lack of suitable robust appearance models hinders the performance of most image descriptors. Descriptors often rely on pieces of information in images called image features to discriminate the contents of images. Most successful descriptors use gradient images for determining the overall shapes of objects. Consequently, the inferred features are often susceptible to the noise caused by shadows, reflections and inner textures within the object. Significant efforts have been made towards improving the performance of image classifiers, yet generic object detection remains an open problem. In this paper, a method aimed at improving existing appearance models is proposed. The focus is on enhancing the acquired information at fundamental stages to improve the robustness of common statistical learning classifiers, as seen with the work of Holger Winnemoller et al. with human subjects.The selective Gaussian blur filter was applied to several human classification datasets to reduce the amount of ambiguous low-frequency noise. Experiments were then conducted to determine whether the unification of similar colours in local image regions could improve the acquired image features. The classification results that were obtained with the processed images were competitive to the results obtained with the original images, however inconclusive for demonstrating the benefits of image smoothing.
{"title":"Enhancing edge-based image descriptor models through colour unification","authors":"Dumusani Kunene, Vusi Skosana","doi":"10.1109/ROBOMECH.2019.8704732","DOIUrl":"https://doi.org/10.1109/ROBOMECH.2019.8704732","url":null,"abstract":"The lack of suitable robust appearance models hinders the performance of most image descriptors. Descriptors often rely on pieces of information in images called image features to discriminate the contents of images. Most successful descriptors use gradient images for determining the overall shapes of objects. Consequently, the inferred features are often susceptible to the noise caused by shadows, reflections and inner textures within the object. Significant efforts have been made towards improving the performance of image classifiers, yet generic object detection remains an open problem. In this paper, a method aimed at improving existing appearance models is proposed. The focus is on enhancing the acquired information at fundamental stages to improve the robustness of common statistical learning classifiers, as seen with the work of Holger Winnemoller et al. with human subjects.The selective Gaussian blur filter was applied to several human classification datasets to reduce the amount of ambiguous low-frequency noise. Experiments were then conducted to determine whether the unification of similar colours in local image regions could improve the acquired image features. The classification results that were obtained with the processed images were competitive to the results obtained with the original images, however inconclusive for demonstrating the benefits of image smoothing.","PeriodicalId":344332,"journal":{"name":"2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128841859","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}
Pub Date : 1900-01-01DOI: 10.1109/ROBOMECH.2019.8704754
E. Buraimoh, I. Davidson
The Distributed Generators (DGs) based on Renewable Energy System (RES) lack the inertia (rotating mass) and damping features of conventional power system, where fossil fuel based synchronous generators are dominant. The consequence of insignificant inertia and damping on grid stability and dynamic performance is further compounded with growing intermittent RES introduction into the grid. The use of RES based converters with appropriate Virtual Synchronous Generator (VSG) control strategy offers the necessary inertia support which culminates exceptional grid stability enhancement. However, the existing VSG studies focused on inverters in steady-state and under balanced grid voltage without emphasis on VSG dynamic performance during fault and other transients. Conversely, under fault conditions, it’s imperative to investigate the dynamic performance of the VSG control strategies while ensuring the protection of inverters owing to their low overvoltage and overcurrent tolerance capacities. Consequently, this study investigated the two methods of Virtual Synchronous Machine (VISMA) and carried out a comparative analysis to observe how the two methods ensure the VSG-inverter’s sustained grid connection under grid fault. Fault-Ride-Through (FRT) is the ability of electrical generating units to remain grid connected in the brief periods of fault and after fault clearance. Conclusions are drawn as to which VISMA strategies provide a better performance in terms of fault ride-through capability, current-limiting and recovery from faults.
{"title":"Comparative Analysis of the Fault Ride-Through Capabilities of the VSG Methods of Microgrid Inverter Control under Faults","authors":"E. Buraimoh, I. Davidson","doi":"10.1109/ROBOMECH.2019.8704754","DOIUrl":"https://doi.org/10.1109/ROBOMECH.2019.8704754","url":null,"abstract":"The Distributed Generators (DGs) based on Renewable Energy System (RES) lack the inertia (rotating mass) and damping features of conventional power system, where fossil fuel based synchronous generators are dominant. The consequence of insignificant inertia and damping on grid stability and dynamic performance is further compounded with growing intermittent RES introduction into the grid. The use of RES based converters with appropriate Virtual Synchronous Generator (VSG) control strategy offers the necessary inertia support which culminates exceptional grid stability enhancement. However, the existing VSG studies focused on inverters in steady-state and under balanced grid voltage without emphasis on VSG dynamic performance during fault and other transients. Conversely, under fault conditions, it’s imperative to investigate the dynamic performance of the VSG control strategies while ensuring the protection of inverters owing to their low overvoltage and overcurrent tolerance capacities. Consequently, this study investigated the two methods of Virtual Synchronous Machine (VISMA) and carried out a comparative analysis to observe how the two methods ensure the VSG-inverter’s sustained grid connection under grid fault. Fault-Ride-Through (FRT) is the ability of electrical generating units to remain grid connected in the brief periods of fault and after fault clearance. Conclusions are drawn as to which VISMA strategies provide a better performance in terms of fault ride-through capability, current-limiting and recovery from faults.","PeriodicalId":344332,"journal":{"name":"2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124652707","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}
Pub Date : 1900-01-01DOI: 10.1109/ROBOMECH.2019.8704770
C. Landman, A. Rix
This article focusses on the modelling of an electric vehicle (EV) as well as the development of an algorithm that suggests optimal driving speeds to the user, knowing the power available from the batteries. This is done to ensure that the destination is reached in the shortest possible time and to help ease the range anxiety of the driver. The platform for the modelling and algorithm development is Python. Factors such as road angle, distance and speed will serve as parameters for the modelled EV. The model is able to return the power, torque and energy requirements to complete a specific route within a specific time. Knowing the energy requirements, the algorithm that suggests optimal driving speeds was developed. Investigations was done to determine the influence of different factors, such as tyre pressure and air temperature, on the power and energy requirements. A 2016 Nissan Leaf was modelled in this article.
{"title":"Performance Prediction for an Electric Vehicle","authors":"C. Landman, A. Rix","doi":"10.1109/ROBOMECH.2019.8704770","DOIUrl":"https://doi.org/10.1109/ROBOMECH.2019.8704770","url":null,"abstract":"This article focusses on the modelling of an electric vehicle (EV) as well as the development of an algorithm that suggests optimal driving speeds to the user, knowing the power available from the batteries. This is done to ensure that the destination is reached in the shortest possible time and to help ease the range anxiety of the driver. The platform for the modelling and algorithm development is Python. Factors such as road angle, distance and speed will serve as parameters for the modelled EV. The model is able to return the power, torque and energy requirements to complete a specific route within a specific time. Knowing the energy requirements, the algorithm that suggests optimal driving speeds was developed. Investigations was done to determine the influence of different factors, such as tyre pressure and air temperature, on the power and energy requirements. A 2016 Nissan Leaf was modelled in this article.","PeriodicalId":344332,"journal":{"name":"2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130607050","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}
Pub Date : 1900-01-01DOI: 10.1109/ROBOMECH.2019.8704765
K. Moloi, J. Jordaan, Y. Hamam
High impedance faults (HIFs) have over the years brought a complex challenge for protection engineers. This complexity is founded of the fact tha a HIF poses characteristics which appear to be difficult for conventional protection schemes to detect their presence in a power system. In this work, we propose a method which makes an attempt to diagnose HIFs effectively. The method uses a feature extraction, classification and regression schemes by applying packet wavelet transform (PWT), support vector machine (SVM) and support vector regression (SVR) respectively. The effectiveness of the proposed method was tested using MATLAB. Furthermore, a practical setup was conducted to test the viability of the proposed method. The results showed good classification accuracy and minimum error of estimation.
{"title":"A hybrid method for high impedance fault classification and detection","authors":"K. Moloi, J. Jordaan, Y. Hamam","doi":"10.1109/ROBOMECH.2019.8704765","DOIUrl":"https://doi.org/10.1109/ROBOMECH.2019.8704765","url":null,"abstract":"High impedance faults (HIFs) have over the years brought a complex challenge for protection engineers. This complexity is founded of the fact tha a HIF poses characteristics which appear to be difficult for conventional protection schemes to detect their presence in a power system. In this work, we propose a method which makes an attempt to diagnose HIFs effectively. The method uses a feature extraction, classification and regression schemes by applying packet wavelet transform (PWT), support vector machine (SVM) and support vector regression (SVR) respectively. The effectiveness of the proposed method was tested using MATLAB. Furthermore, a practical setup was conducted to test the viability of the proposed method. The results showed good classification accuracy and minimum error of estimation.","PeriodicalId":344332,"journal":{"name":"2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130959350","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}
Pub Date : 1900-01-01DOI: 10.1109/ROBOMECH.2019.8704702
S. Gerber, R. Wangi
The simple three-phase inverter topology that is most widely used in electrical machine drive systems produces a large, high-frequency common-mode voltage. Through capacitive coupling, a fraction of this common-mode voltage typically appears on the machine’s shaft relative to ground. The shaft voltage can discharge through the bearings of the machine, causing damage and eventually resulting in premature bearing failure compared with equivalent line-fed machines. As a first step in the investigation of mitigation techniques for this problem, this paper evaluates the use of simple aluminium foil shielding applied to a standard 4-pole induction machine with a rated power of 11 kW for mitigation of bearing currents.
{"title":"Reduction of Inverter-Induced Shaft Voltages Using Electrostatic Shielding","authors":"S. Gerber, R. Wangi","doi":"10.1109/ROBOMECH.2019.8704702","DOIUrl":"https://doi.org/10.1109/ROBOMECH.2019.8704702","url":null,"abstract":"The simple three-phase inverter topology that is most widely used in electrical machine drive systems produces a large, high-frequency common-mode voltage. Through capacitive coupling, a fraction of this common-mode voltage typically appears on the machine’s shaft relative to ground. The shaft voltage can discharge through the bearings of the machine, causing damage and eventually resulting in premature bearing failure compared with equivalent line-fed machines. As a first step in the investigation of mitigation techniques for this problem, this paper evaluates the use of simple aluminium foil shielding applied to a standard 4-pole induction machine with a rated power of 11 kW for mitigation of bearing currents.","PeriodicalId":344332,"journal":{"name":"2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125441405","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}
Pub Date : 1900-01-01DOI: 10.1109/ROBOMECH.2019.8704727
A. O. Joshua, F. Nelwamondo, G. Mabuza-Hocquet
Glaucoma has been attributed to be the leading cause of blindness in the world second only to diabetic retinopathy. About 66.8 million people in the world have glaucoma and about 6.7 million are suffering from blindness as a result of glaucoma. A cause of glaucoma is the enlargement of the optic cup such that it occupies the optic disc area. Hence, the estimation of optic Cup to Disc ratio (CDR) is a valuable tool in diagnosing glaucoma. The CDR can be obtained by segmenting the optic cup and optic disc from the fundus image. In this work, an improved U-net Convolutional Neural Network (CNN) architecture was used to segment the optic disc and the optic cup from the fundus image. The dataset used was obtained from the DRISHTI-GS database and the RIM-ONE v.3. The proposed pipeline and architecture outperforms existing techniques on Optic Disc (OD) and Optic Cup (OC) segmentation on the Dice-score metric and prediction time.
青光眼被认为是世界上仅次于糖尿病视网膜病变的主要致盲原因。全世界约有6680万人患有青光眼，约670万人因青光眼而失明。青光眼的一个原因是视杯扩大，以致它占据视盘区域。因此，估计视杯盘比(CDR)是诊断青光眼的一个有价值的工具。通过从眼底图像中分割视杯和视盘得到CDR。在这项工作中，使用改进的U-net卷积神经网络(CNN)架构从眼底图像中分割视盘和视杯。使用的数据集来自DRISHTI-GS数据库和RIM-ONE v.3。所提出的管道和架构在Dice-score指标和预测时间上优于现有的Optic Disc (OD)和Optic Cup (OC)分割技术。
{"title":"Segmentation of Optic Cup and Disc for Diagnosis of Glaucoma on Retinal Fundus Images","authors":"A. O. Joshua, F. Nelwamondo, G. Mabuza-Hocquet","doi":"10.1109/ROBOMECH.2019.8704727","DOIUrl":"https://doi.org/10.1109/ROBOMECH.2019.8704727","url":null,"abstract":"Glaucoma has been attributed to be the leading cause of blindness in the world second only to diabetic retinopathy. About 66.8 million people in the world have glaucoma and about 6.7 million are suffering from blindness as a result of glaucoma. A cause of glaucoma is the enlargement of the optic cup such that it occupies the optic disc area. Hence, the estimation of optic Cup to Disc ratio (CDR) is a valuable tool in diagnosing glaucoma. The CDR can be obtained by segmenting the optic cup and optic disc from the fundus image. In this work, an improved U-net Convolutional Neural Network (CNN) architecture was used to segment the optic disc and the optic cup from the fundus image. The dataset used was obtained from the DRISHTI-GS database and the RIM-ONE v.3. The proposed pipeline and architecture outperforms existing techniques on Optic Disc (OD) and Optic Cup (OC) segmentation on the Dice-score metric and prediction time.","PeriodicalId":344332,"journal":{"name":"2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114213322","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}
2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：