The authors present an artificial neural network (ANN) approach to a diagnostic system for a gas insulated switchgear (GIS). Firstly they survey the status of operational experience of failures in GISs and its diagnostic techniques. Secondly, they present how to acquire signal samples from the GIS and how to process them so as to be provided for an input layer of ANN. Finally they propose a decision-tree like network referred to as module neural network (MNN), and compare it with the well-known three-layered network, the straight forward neural network (SFNN).<>
{"title":"Fault diagnosis system for GIS using an artificial neural network","authors":"H. Ogi, H. Tanaka, Y. Akimoto, Y. Izui","doi":"10.1109/ANN.1991.213507","DOIUrl":"https://doi.org/10.1109/ANN.1991.213507","url":null,"abstract":"The authors present an artificial neural network (ANN) approach to a diagnostic system for a gas insulated switchgear (GIS). Firstly they survey the status of operational experience of failures in GISs and its diagnostic techniques. Secondly, they present how to acquire signal samples from the GIS and how to process them so as to be provided for an input layer of ANN. Finally they propose a decision-tree like network referred to as module neural network (MNN), and compare it with the well-known three-layered network, the straight forward neural network (SFNN).<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134130611","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}
The advantage of fast computation capability of an artificial neural network (ANN) is used to introduce an iterative scheme for security assessment of power systems. Two related approaches are shown which demonstratedly work satisfactorily. The idea of feedback in a single-layer feedforward neural network is experimented yielding higher accuracy. The ANN is trained by using a set of data obtained from off-line analysis of the power network. After training, an approximate solution for a given condition may be found almost immediately. The approximate solution obtained is judged adequate for assessing the security of the power system. A case study is also presented for demonstrating the applicability of the approach.<>
{"title":"Security assessment using neural computing","authors":"B.H. Chowdhury, B. Wilamowski","doi":"10.1109/ANN.1991.213497","DOIUrl":"https://doi.org/10.1109/ANN.1991.213497","url":null,"abstract":"The advantage of fast computation capability of an artificial neural network (ANN) is used to introduce an iterative scheme for security assessment of power systems. Two related approaches are shown which demonstratedly work satisfactorily. The idea of feedback in a single-layer feedforward neural network is experimented yielding higher accuracy. The ANN is trained by using a set of data obtained from off-line analysis of the power network. After training, an approximate solution for a given condition may be found almost immediately. The approximate solution obtained is judged adequate for assessing the security of the power system. A case study is also presented for demonstrating the applicability of the approach.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130455454","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}
The authors describe what they believe to be the first application of artificial neural networks (ANN) for joint VAr control (JVC). While joint VAr controllers are not new, their implementation is important as a practical starting point for ANN control of power system equipment. As such, the knowledge and experience gained is more important than the actual accomplishment of implementing the system. Here, they attempt to share the practical knowledge that was gained through this paper.<>
{"title":"Joint VAr controller implemented in an artificial neural network environment","authors":"G. Neily, R. Barone, G. Josin, D. Charney","doi":"10.1109/ANN.1991.213464","DOIUrl":"https://doi.org/10.1109/ANN.1991.213464","url":null,"abstract":"The authors describe what they believe to be the first application of artificial neural networks (ANN) for joint VAr control (JVC). While joint VAr controllers are not new, their implementation is important as a practical starting point for ANN control of power system equipment. As such, the knowledge and experience gained is more important than the actual accomplishment of implementing the system. Here, they attempt to share the practical knowledge that was gained through this paper.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129071487","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}
The authors explore and demonstrate the feasibility of combined artificial intelligence/neural-net methodology for carrying out dynamic power system analysis in real-time. This methodology will be capable of characterizing the near term transient stability of the system, as well as perform mid-term and long term dynamic security analyses. In the transient stability analysis, the authors are principally concerned with a question whether the system can return to the steady state. In the mid-term and long-term-security analysis, they are also concerned with a manner in which the final steady state is reached, whether system performance constraints are violated on the way and whether further protective actions might be triggered unexpectedly with undesired actions.<>
{"title":"A perspective on use of neural-net computing in training simulator design","authors":"Y. Pao, D. Sobajic","doi":"10.1109/ANN.1991.213476","DOIUrl":"https://doi.org/10.1109/ANN.1991.213476","url":null,"abstract":"The authors explore and demonstrate the feasibility of combined artificial intelligence/neural-net methodology for carrying out dynamic power system analysis in real-time. This methodology will be capable of characterizing the near term transient stability of the system, as well as perform mid-term and long term dynamic security analyses. In the transient stability analysis, the authors are principally concerned with a question whether the system can return to the steady state. In the mid-term and long-term-security analysis, they are also concerned with a manner in which the final steady state is reached, whether system performance constraints are violated on the way and whether further protective actions might be triggered unexpectedly with undesired actions.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124767724","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}
The authors present a hierarchical architecture which couples an expert system (ES) with multiple neural networks (NNs) for classifying power system contingencies. The ES performs the 'coarse' screening to decide if a contingency is potentially harmful and then determines its type of security limit violations. It uses a set of heuristic rules and a set of performance indicators to filter out the secure contingencies and direct the potentially harmful ones for further analysis in the appropriate NN. The NN's take the coarse classification outcome from the ES and perform a 'finer' screening by classifying the contingencies according to the severity of limit violations.<>
{"title":"Hybrid expert system neural network hierarchical architecture for classifying power system contingencies","authors":"H. Yan, J. Chow, M. Kam, R. Fischl, C.R. Sepich","doi":"10.1109/ANN.1991.213501","DOIUrl":"https://doi.org/10.1109/ANN.1991.213501","url":null,"abstract":"The authors present a hierarchical architecture which couples an expert system (ES) with multiple neural networks (NNs) for classifying power system contingencies. The ES performs the 'coarse' screening to decide if a contingency is potentially harmful and then determines its type of security limit violations. It uses a set of heuristic rules and a set of performance indicators to filter out the secure contingencies and direct the potentially harmful ones for further analysis in the appropriate NN. The NN's take the coarse classification outcome from the ES and perform a 'finer' screening by classifying the contingencies according to the severity of limit violations.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114571959","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}
G. Lambert-Torres, C.O. Traore, F. Mandolesi, D. Mukhedkar
The authors describe a knowledge engineering tool for short-term load forecasting to be used as an aid in operation and planning of distribution systems. This engineering tool is composed by two parts. Firstly, an artificial neural network is trained to produce the first evaluation of forecasted load. Following, a fuzzy expert system manipulate actual and forecasted values of real power and weather conditions to find the final forecasted load. Illustrative examples are presented using Hydro-Quebec Power System data.<>
{"title":"Short-term load forecasting using a fuzzy engineering tool","authors":"G. Lambert-Torres, C.O. Traore, F. Mandolesi, D. Mukhedkar","doi":"10.1109/ANN.1991.213494","DOIUrl":"https://doi.org/10.1109/ANN.1991.213494","url":null,"abstract":"The authors describe a knowledge engineering tool for short-term load forecasting to be used as an aid in operation and planning of distribution systems. This engineering tool is composed by two parts. Firstly, an artificial neural network is trained to produce the first evaluation of forecasted load. Following, a fuzzy expert system manipulate actual and forecasted values of real power and weather conditions to find the final forecasted load. Illustrative examples are presented using Hydro-Quebec Power System data.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116033564","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}
A neural network (NN) for static security assessment (SSA) of a large scale power system is proposed. A group of multi-layer perceptron type NN's are trained to classify the security status of the power system for specific contingencies based on the pre-contingency system variables. Curse of dimensionality of the input data is reduced by partitioning the problem into smaller sub-problems. Better class separation and further dimensionality reduction is obtained by a feature selection scheme based on Karhunen-Loe've expansion. When each trained NN is queried on-line, it can provide the power system operator with the security status of the current operating point for a specified contingency. The parallel network architecture and the adaptive capability of the NN's are combined to achieve high speeds of execution and good classification accuracy. With the expected emergence of affordable NN hardware, this technique has the potential to become a viable alternative to existing computationally intensive schemes for SSA.<>
{"title":"Use of Karhunen-Loe've expansion in training neural networks for static security assessment","authors":"S. Weerasooriya, M. El-Sharkawi","doi":"10.1109/ANN.1991.213498","DOIUrl":"https://doi.org/10.1109/ANN.1991.213498","url":null,"abstract":"A neural network (NN) for static security assessment (SSA) of a large scale power system is proposed. A group of multi-layer perceptron type NN's are trained to classify the security status of the power system for specific contingencies based on the pre-contingency system variables. Curse of dimensionality of the input data is reduced by partitioning the problem into smaller sub-problems. Better class separation and further dimensionality reduction is obtained by a feature selection scheme based on Karhunen-Loe've expansion. When each trained NN is queried on-line, it can provide the power system operator with the security status of the current operating point for a specified contingency. The parallel network architecture and the adaptive capability of the NN's are combined to achieve high speeds of execution and good classification accuracy. With the expected emergence of affordable NN hardware, this technique has the potential to become a viable alternative to existing computationally intensive schemes for SSA.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"30 8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121335938","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}
Reactive power dispatch problem is still an active problem in the area of power system operation. Finding an optimum solution that provides a balance between system performance and the cost associated with the reactive power placement (in terms of improved voltage profile and voltage stability) is essential. The objective of the research is to explore the applicability of a new emerging global optimization technique, called a genetic algorithm to the reactive power dispatch problem. The algorithm is based on the mechanics of natural selection and has been tested in other fields with promising results.<>
{"title":"Application of genetic based algorithms to optimal capacitor placement","authors":"V. Ajjarapu, Zaid Albanna","doi":"10.1109/ANN.1991.213468","DOIUrl":"https://doi.org/10.1109/ANN.1991.213468","url":null,"abstract":"Reactive power dispatch problem is still an active problem in the area of power system operation. Finding an optimum solution that provides a balance between system performance and the cost associated with the reactive power placement (in terms of improved voltage profile and voltage stability) is essential. The objective of the research is to explore the applicability of a new emerging global optimization technique, called a genetic algorithm to the reactive power dispatch problem. The algorithm is based on the mechanics of natural selection and has been tested in other fields with promising results.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117133152","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}
The authors present a method of short term load forecasting using a neural network. A three layered feedforward adaptive neural network, trained by back-propagation, is used. This method is applied to real data from a power system and comparative results with other methods are given.<>
{"title":"An adaptive neural network approach in load forecasting in a power system","authors":"T. Dillon, S. Sestito, S. Leung","doi":"10.1109/ANN.1991.213490","DOIUrl":"https://doi.org/10.1109/ANN.1991.213490","url":null,"abstract":"The authors present a method of short term load forecasting using a neural network. A three layered feedforward adaptive neural network, trained by back-propagation, is used. This method is applied to real data from a power system and comparative results with other methods are given.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"11 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133925131","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}
The authors consider the problem of finding minimal neural networks (in terms of number of neurons and synapses) subject to desired learning and generalization capabilities. An algorithm which automatically determines the number of neurons and the location of synaptic connections is proposed. A new neural network model is introduced to facilitate solving the optimal architecture problem. The synaptic connections are pruned based on testing hypotheses that the corresponding weights be smaller than cutting thresholds. Simulation results are demonstrated for designing neural networks for: (1) a 7-segment electronic display; and (2) a power system load modeling problem. Optimal architecture (in the sense of achieving the lower bound on the number of neurons) are obtained for (1), and a 50%-60% save-up of synapses with the desired learning/generalization capabilities is obtained for (2).<>
{"title":"Towards constructing optimal feedforward neural networks with learning and generalization capabilities","authors":"Jen-Lun Yuan, H. Chiang, Chia-Jen Lin, Tai-Hsiung Li, Yung-Tien Chen, Chiew-Yann Chiou","doi":"10.1109/ANN.1991.213473","DOIUrl":"https://doi.org/10.1109/ANN.1991.213473","url":null,"abstract":"The authors consider the problem of finding minimal neural networks (in terms of number of neurons and synapses) subject to desired learning and generalization capabilities. An algorithm which automatically determines the number of neurons and the location of synaptic connections is proposed. A new neural network model is introduced to facilitate solving the optimal architecture problem. The synaptic connections are pruned based on testing hypotheses that the corresponding weights be smaller than cutting thresholds. Simulation results are demonstrated for designing neural networks for: (1) a 7-segment electronic display; and (2) a power system load modeling problem. Optimal architecture (in the sense of achieving the lower bound on the number of neurons) are obtained for (1), and a 50%-60% save-up of synapses with the desired learning/generalization capabilities is obtained for (2).<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122371920","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：