Pub Date : 1995-11-21DOI: 10.1109/EMPD.1995.500729
W. Mielczarski, M. Khan, L. Sugianto
The paper presents an application of dynamic programming to optimal allocation of resources in spare items to increase reliability of supply. The System Average Interruption Duration Index (SAIDI) has been selected as the performance index. Distribution transformers have been selected to investigate the applicability of the proposed approach to distribution network equipment. The paper provides an analysis of relationships between the index assumed and parameters of distribution systems. Results of optimization for four levels of budget limitation show that resources can be allocated in the best way by dynamic programming but results depend on the assumed performance index and its parameters.
本文将动态规划方法应用于备件资源的优化配置，以提高供应的可靠性。性能指标选择SAIDI (System Average Interruption Duration Index)。以配电变压器为例，研究了该方法在配电网设备中的适用性。本文分析了配电系统的指标假设与参数之间的关系。在四种预算限制水平下的优化结果表明，动态规划可以实现资源的最佳配置，但其结果取决于所假设的性能指标及其参数。
{"title":"Management of inventory to reduce outages in supply feeder","authors":"W. Mielczarski, M. Khan, L. Sugianto","doi":"10.1109/EMPD.1995.500729","DOIUrl":"https://doi.org/10.1109/EMPD.1995.500729","url":null,"abstract":"The paper presents an application of dynamic programming to optimal allocation of resources in spare items to increase reliability of supply. The System Average Interruption Duration Index (SAIDI) has been selected as the performance index. Distribution transformers have been selected to investigate the applicability of the proposed approach to distribution network equipment. The paper provides an analysis of relationships between the index assumed and parameters of distribution systems. Results of optimization for four levels of budget limitation show that resources can be allocated in the best way by dynamic programming but results depend on the assumed performance index and its parameters.","PeriodicalId":447674,"journal":{"name":"Proceedings 1995 International Conference on Energy Management and Power Delivery EMPD '95","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123432205","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 : 1995-11-21DOI: 10.1109/EMPD.1995.500716
C. Chang, K. Lock, Fan Wang, A. Liew
Active and passive filters are used to reduce harmonic level in power systems. This paper presents techniques for designing these filters in the viewpoint of improving overall power system performance. Besides, a method for harmonic control optimisation for these filters is discussed and the conclusion is obtained through mathematical deduction.
{"title":"Harmonic level control schemes and evaluation methods in power system","authors":"C. Chang, K. Lock, Fan Wang, A. Liew","doi":"10.1109/EMPD.1995.500716","DOIUrl":"https://doi.org/10.1109/EMPD.1995.500716","url":null,"abstract":"Active and passive filters are used to reduce harmonic level in power systems. This paper presents techniques for designing these filters in the viewpoint of improving overall power system performance. Besides, a method for harmonic control optimisation for these filters is discussed and the conclusion is obtained through mathematical deduction.","PeriodicalId":447674,"journal":{"name":"Proceedings 1995 International Conference on Energy Management and Power Delivery EMPD '95","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121979312","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 : 1995-11-21DOI: 10.1109/EMPD.1995.500758
Hong-Tzer Yang, Yann-Chang Huang, C. Huang
In this paper, the capacitor placement problem in a radial distribution system is formulated and solved by a tabu search (TS) based solution algorithm. The capacitor placement problem considers practical operating constraints of capacitors, load growth, capacity of the feeder and the upper and lower bound constraints of voltage at different load levels to minimize the investment cost of capacitors and system energy loss. A sensitivity analysis method is used to select the candidate installation locations of the capacitors to reduce the search space of this problem a priori. Comparison results of the TS method with the simulated annealing (SA) show that the proposed TS method can offer the nearly optimal solution to the capacitor placement problem within reasonable computing time.
{"title":"Solution to capacitor placement problem in a radial distribution system using tabu search method","authors":"Hong-Tzer Yang, Yann-Chang Huang, C. Huang","doi":"10.1109/EMPD.1995.500758","DOIUrl":"https://doi.org/10.1109/EMPD.1995.500758","url":null,"abstract":"In this paper, the capacitor placement problem in a radial distribution system is formulated and solved by a tabu search (TS) based solution algorithm. The capacitor placement problem considers practical operating constraints of capacitors, load growth, capacity of the feeder and the upper and lower bound constraints of voltage at different load levels to minimize the investment cost of capacitors and system energy loss. A sensitivity analysis method is used to select the candidate installation locations of the capacitors to reduce the search space of this problem a priori. Comparison results of the TS method with the simulated annealing (SA) show that the proposed TS method can offer the nearly optimal solution to the capacitor placement problem within reasonable computing time.","PeriodicalId":447674,"journal":{"name":"Proceedings 1995 International Conference on Energy Management and Power Delivery EMPD '95","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126133398","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 : 1995-11-21DOI: 10.1109/EMPD.1995.500711
Cheng-Tsung Liu, Tzeng-Shong Yeh
For providing detailed power system transient characteristic analysis, more rigorous system representations are generally required. Consequently, the computational burden will become heavier. To speedup the solution time while maintaining the required accuracy, an attractive way is to implement the parallel computation techniques on multiprocessor architecture. This paper investigates the applications of two parallel predictor-corrector algorithms, namely the multistep predictor-corrector algorithm (MPG) and the block predictor-corrector algorithm (BPC), on a generalized power system transient simulation program running on both the 2-CPU Alliant FX/80 and the 4-CPU Convex C3840 systems. The IEEE Second Benchmark Model System 2 is selected for detailed numerical verifications, and the cross comparisons and discussions are also provided. From these illustrations, valuable guidance can be obtained for the associated multiprocessor parallel processing schemes applied to power system transient characteristic analyses.
为了提供详细的电力系统暂态特性分析，通常需要更严格的系统表示。因此，计算负担将变得更重。为了在保证精度的前提下加快求解速度，在多处理器架构下实现并行计算技术是一种很有吸引力的方法。本文研究了多步预测校正算法(MPG)和块预测校正算法(BPC)两种并行预测校正算法在2 cpu Alliant FX/80和4 cpu Convex C3840系统上的广义电力系统暂态仿真程序中的应用。选择IEEE第二基准模型系统2进行了详细的数值验证，并进行了交叉比较和讨论。这些实例可为相关的多处理机并行处理方案应用于电力系统暂态特性分析提供有价值的指导。
{"title":"Parallel implementation of predictor-corrector methods for power system transient characteristic studies","authors":"Cheng-Tsung Liu, Tzeng-Shong Yeh","doi":"10.1109/EMPD.1995.500711","DOIUrl":"https://doi.org/10.1109/EMPD.1995.500711","url":null,"abstract":"For providing detailed power system transient characteristic analysis, more rigorous system representations are generally required. Consequently, the computational burden will become heavier. To speedup the solution time while maintaining the required accuracy, an attractive way is to implement the parallel computation techniques on multiprocessor architecture. This paper investigates the applications of two parallel predictor-corrector algorithms, namely the multistep predictor-corrector algorithm (MPG) and the block predictor-corrector algorithm (BPC), on a generalized power system transient simulation program running on both the 2-CPU Alliant FX/80 and the 4-CPU Convex C3840 systems. The IEEE Second Benchmark Model System 2 is selected for detailed numerical verifications, and the cross comparisons and discussions are also provided. From these illustrations, valuable guidance can be obtained for the associated multiprocessor parallel processing schemes applied to power system transient characteristic analyses.","PeriodicalId":447674,"journal":{"name":"Proceedings 1995 International Conference on Energy Management and Power Delivery EMPD '95","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128537668","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 : 1995-11-21DOI: 10.1109/EMPD.1995.500788
T.N. Nagabhushana, H.S. Chandrasekharaiah
Most of the proposed neural networks for fault diagnosis of systems are multilayer perceptrons (MLP) employing the popular backpropagation (BP) learning rule. It has been shown that the backpropagation algorithm usually takes a long time for convergence and sometimes gets trapped into local minimum. The algorithm requires the architecture to be fixed initially (i.e. the number of hidden units) before learning begins. Final network size is obtained by repeated trials. When the size of the training set is large, especially in the case of fault diagnosis, such a repeated training consumes a large amount of time and sometimes it can be frustrating. Thus there is a need of a good neural network architecture that decides its size automatically while learning the input/output relationships and must posses reasonably good generalization. Neural networks based on radial basis functions (RBF) have emerged as potential alternatives to MLPs. RBFs have a simple architecture and they can learn the input/output relations fast compared to MLPs. In this paper we present a constructive neural network based on radial basis functions (RBF) due to Fritzke for classification of fault patterns in a model power system. The performance of this neural network with traditional BP network and nonconstructive RBF network in terms of size, learning speed and generalization are presented.
{"title":"Fault diagnosis of electrical power systems using incremental radial basis function nets","authors":"T.N. Nagabhushana, H.S. Chandrasekharaiah","doi":"10.1109/EMPD.1995.500788","DOIUrl":"https://doi.org/10.1109/EMPD.1995.500788","url":null,"abstract":"Most of the proposed neural networks for fault diagnosis of systems are multilayer perceptrons (MLP) employing the popular backpropagation (BP) learning rule. It has been shown that the backpropagation algorithm usually takes a long time for convergence and sometimes gets trapped into local minimum. The algorithm requires the architecture to be fixed initially (i.e. the number of hidden units) before learning begins. Final network size is obtained by repeated trials. When the size of the training set is large, especially in the case of fault diagnosis, such a repeated training consumes a large amount of time and sometimes it can be frustrating. Thus there is a need of a good neural network architecture that decides its size automatically while learning the input/output relationships and must posses reasonably good generalization. Neural networks based on radial basis functions (RBF) have emerged as potential alternatives to MLPs. RBFs have a simple architecture and they can learn the input/output relations fast compared to MLPs. In this paper we present a constructive neural network based on radial basis functions (RBF) due to Fritzke for classification of fault patterns in a model power system. The performance of this neural network with traditional BP network and nonconstructive RBF network in terms of size, learning speed and generalization are presented.","PeriodicalId":447674,"journal":{"name":"Proceedings 1995 International Conference on Energy Management and Power Delivery EMPD '95","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129938785","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 : 1995-11-21DOI: 10.1109/EMPD.1995.500812
T. Chan, K. M. Chua, K. T. Lim
This paper highlights some techniques employed to model dynamic operational characteristics of distance relays using EMTP. Simulation results of a selfand a cross-polarised Mho relay are presented.
{"title":"Modeling relay operational characteristics using electromagnetic transients program","authors":"T. Chan, K. M. Chua, K. T. Lim","doi":"10.1109/EMPD.1995.500812","DOIUrl":"https://doi.org/10.1109/EMPD.1995.500812","url":null,"abstract":"This paper highlights some techniques employed to model dynamic operational characteristics of distance relays using EMTP. Simulation results of a selfand a cross-polarised Mho relay are presented.","PeriodicalId":447674,"journal":{"name":"Proceedings 1995 International Conference on Energy Management and Power Delivery EMPD '95","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125555514","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 : 1995-11-21DOI: 10.1109/EMPD.1995.500740
J. Kim, D. Lee, K. Shin, Kwang-ho Yang, Hee Sung Ahan, J. Koo
This paper describes corona and electric field effects studies of a 765 kV double circuit test line. In Korea there are many mountains and it is very difficult to get the right of way because the population density is very high and the territory is small. So Korea Electric Power Corporation (KEPCO) decided to build one double-circuit 765 kV line of vertical arrangement configuration instead of two single-circuit 765 kV lines of horizontal configuration. Corona performance on several candidate conductor bundles has been investigated with a corona cage since 1984 by KEPRI. We have known that a bundle of 6-Rail (29.61 mm) conductors per phase is the optimum and its audible noise (AN) level L/sub 60/ in the corona cage was measured as 45.0 dB(A) in GE method. To investigate the electrical environmental impact of the future commercial line with this conductor bundle, KEPRI built a full scale 765 kV test line in 1993 as the second step study. Long-term measurements have been made in this double-circuit test line. We have found that the AN data were very close to that predicted by BPA Corona and Field Effects computer program, however, the RI data in fair weather was higher than the predicted by the BPA program by 2.4 dB (/spl mu/V/m). AN L/sub 60/ in foul weather is below 50 dB(A). We think the 6-Rail conductor bundle is the optimum size in the 765 kV double-circuit transmission line from the environmental view-point.
本文介绍了765kv双回试验线路的电晕效应和电场效应研究。韩国有很多山，很难找到正确的道路，因为人口密度很高，国土面积很小。因此，韩国电力公社决定，将原来的2条单线765kv水平线路改为1条双线765kv垂直布置线路。1984年以来，KEPRI用电晕笼研究了几种候选导体束的电晕性能。我们已经知道，每相一束6轨(29.61 mm)导体是最佳的，其在电晕笼中的可听噪声(AN)电平L/sub 60/在GE方法中测量为45.0 dB(a)。为了研究使用这种导体束的未来商业线路对电气环境的影响，KEPRI在1993年建造了一条全尺寸的765千伏测试线路作为第二步研究。在该双回路测试线上进行了长期测量。结果表明，AN数据与BPA电晕和场效应计算机程序预测的结果非常接近，而晴天的RI数据比BPA程序预测的结果高出2.4 dB (/spl mu/V/m)。恶劣天气下的声压/声压/声压小于50db (A)。从环境的角度出发，认为765kv双回输电线路中6轨导体束是最优尺寸。
{"title":"KEPCO 765 kV transmission system development: corona and electric field effects studies","authors":"J. Kim, D. Lee, K. Shin, Kwang-ho Yang, Hee Sung Ahan, J. Koo","doi":"10.1109/EMPD.1995.500740","DOIUrl":"https://doi.org/10.1109/EMPD.1995.500740","url":null,"abstract":"This paper describes corona and electric field effects studies of a 765 kV double circuit test line. In Korea there are many mountains and it is very difficult to get the right of way because the population density is very high and the territory is small. So Korea Electric Power Corporation (KEPCO) decided to build one double-circuit 765 kV line of vertical arrangement configuration instead of two single-circuit 765 kV lines of horizontal configuration. Corona performance on several candidate conductor bundles has been investigated with a corona cage since 1984 by KEPRI. We have known that a bundle of 6-Rail (29.61 mm) conductors per phase is the optimum and its audible noise (AN) level L/sub 60/ in the corona cage was measured as 45.0 dB(A) in GE method. To investigate the electrical environmental impact of the future commercial line with this conductor bundle, KEPRI built a full scale 765 kV test line in 1993 as the second step study. Long-term measurements have been made in this double-circuit test line. We have found that the AN data were very close to that predicted by BPA Corona and Field Effects computer program, however, the RI data in fair weather was higher than the predicted by the BPA program by 2.4 dB (/spl mu/V/m). AN L/sub 60/ in foul weather is below 50 dB(A). We think the 6-Rail conductor bundle is the optimum size in the 765 kV double-circuit transmission line from the environmental view-point.","PeriodicalId":447674,"journal":{"name":"Proceedings 1995 International Conference on Energy Management and Power Delivery EMPD '95","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125107274","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 : 1995-11-21DOI: 10.1109/EMPD.1995.500694
S.P. Zhu
Wheeling is the conveying of electric power from a seller to a buyer through a third party owned transmission network. World wide, there are plans to privatize state-owned utility assets. In many countries, it is hypothesized that competition could improve the economic efficiency achieved by the existing rules of the game. This paper presents the basic concept which uses the share of wheeling gains as a pricing mechanism.
{"title":"Some considerations on transmission services concerning optimizing wheeling parties' benefits","authors":"S.P. Zhu","doi":"10.1109/EMPD.1995.500694","DOIUrl":"https://doi.org/10.1109/EMPD.1995.500694","url":null,"abstract":"Wheeling is the conveying of electric power from a seller to a buyer through a third party owned transmission network. World wide, there are plans to privatize state-owned utility assets. In many countries, it is hypothesized that competition could improve the economic efficiency achieved by the existing rules of the game. This paper presents the basic concept which uses the share of wheeling gains as a pricing mechanism.","PeriodicalId":447674,"journal":{"name":"Proceedings 1995 International Conference on Energy Management and Power Delivery EMPD '95","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131407307","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 : 1995-11-21DOI: 10.1109/EMPD.1995.500705
L. Ruomei, Chen Yunping, Guo Jianbo
An artificial neural network (ANN) based optimization method in scheduling pumped-storage is proposed in the paper. Short-term scheduling as well as real-time dispatch of a pumped-storage station is a constrained optimization problem. It becomes more complicated when coordinated with other generation resources. The computation time is often long and the operation conditions may change unpredictably. A fast and practical way is expected. The ANN is used as a signal processing device, which represents mapping functions from input space to output space. Through a training process, multi-layered feedforward and neural networks can be used to approximate the continuous functions with a given accuracy and real-time solution can be achieved. In this paper three layer feedforward ANN and improved BP algorithm are adopted to solve the problem of pumped-storage scheduling. A set of ANN training data are obtained by running an optimization software. The paper describes how to select and organize the input data and how to train the ANN. A work example is presented and a comparison with traditional method is made. It shows that a fast and accurate solution for pumped-storage scheduling can be achieved with ANN.
{"title":"An application of ANN in scheduling pumped-storage","authors":"L. Ruomei, Chen Yunping, Guo Jianbo","doi":"10.1109/EMPD.1995.500705","DOIUrl":"https://doi.org/10.1109/EMPD.1995.500705","url":null,"abstract":"An artificial neural network (ANN) based optimization method in scheduling pumped-storage is proposed in the paper. Short-term scheduling as well as real-time dispatch of a pumped-storage station is a constrained optimization problem. It becomes more complicated when coordinated with other generation resources. The computation time is often long and the operation conditions may change unpredictably. A fast and practical way is expected. The ANN is used as a signal processing device, which represents mapping functions from input space to output space. Through a training process, multi-layered feedforward and neural networks can be used to approximate the continuous functions with a given accuracy and real-time solution can be achieved. In this paper three layer feedforward ANN and improved BP algorithm are adopted to solve the problem of pumped-storage scheduling. A set of ANN training data are obtained by running an optimization software. The paper describes how to select and organize the input data and how to train the ANN. A work example is presented and a comparison with traditional method is made. It shows that a fast and accurate solution for pumped-storage scheduling can be achieved with ANN.","PeriodicalId":447674,"journal":{"name":"Proceedings 1995 International Conference on Energy Management and Power Delivery EMPD '95","volume":"145 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115311546","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 : 1995-11-21DOI: 10.1109/EMPD.1995.500790
Chul-Hwan Kim, Y. Lim, Woo-Gon Chung, Tae-Won Kwon, Jong-young Hwang, I. Kim
This paper presents a fault identification system based on neural networks for underground cable transmission systems (UCTS). EMTP was used for necessary transient data in training for fault type identification purposes. Data for various fault types in the underground cable system were generated and were used in training backpropagation neural networks. For the operation of the system a new data is tested for fair assessment of the designed system. Normalization of input data is adopted for reliable learning in neural networks. A proper size of the neural network was found via trial and error method, a brute-force method. This system was tested with various fault distances and fault incidence angles and proved its reliability.
{"title":"A study on the fault indentification of underground cable using neural networks","authors":"Chul-Hwan Kim, Y. Lim, Woo-Gon Chung, Tae-Won Kwon, Jong-young Hwang, I. Kim","doi":"10.1109/EMPD.1995.500790","DOIUrl":"https://doi.org/10.1109/EMPD.1995.500790","url":null,"abstract":"This paper presents a fault identification system based on neural networks for underground cable transmission systems (UCTS). EMTP was used for necessary transient data in training for fault type identification purposes. Data for various fault types in the underground cable system were generated and were used in training backpropagation neural networks. For the operation of the system a new data is tested for fair assessment of the designed system. Normalization of input data is adopted for reliable learning in neural networks. A proper size of the neural network was found via trial and error method, a brute-force method. This system was tested with various fault distances and fault incidence angles and proved its reliability.","PeriodicalId":447674,"journal":{"name":"Proceedings 1995 International Conference on Energy Management and Power Delivery EMPD '95","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114102779","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}
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：