A new approach for wide-range optimal reactor temperature control using diagonal recurrent neural networks (DRNN) with an adaptive learning rate scheme is presented. The drawback of the usual feedforward neural network (FNN) is that it is a static mapping and requires a large number of neurons and takes a long training time. The usual fixed learning rate based on an empirical trial and error scheme is slow and does not guarantee convergence. The dynamic backpropagation algorithm coupled with an adaptive learning rate guarantees even faster convergence. A reference model which incorporates an optimal control law with improved reactor temperature response is used for training of the neurocontroller and neuroidentifier. Rapid convergence of this DRNN-based control system is demonstrated when applied to improve reactor temperature performance.<>
{"title":"Validation and verification of diagonal neural controller for nuclear power plant","authors":"C. Ku, K.Y. Lee, R. Edwards","doi":"10.1109/ANN.1993.264324","DOIUrl":"https://doi.org/10.1109/ANN.1993.264324","url":null,"abstract":"A new approach for wide-range optimal reactor temperature control using diagonal recurrent neural networks (DRNN) with an adaptive learning rate scheme is presented. The drawback of the usual feedforward neural network (FNN) is that it is a static mapping and requires a large number of neurons and takes a long training time. The usual fixed learning rate based on an empirical trial and error scheme is slow and does not guarantee convergence. The dynamic backpropagation algorithm coupled with an adaptive learning rate guarantees even faster convergence. A reference model which incorporates an optimal control law with improved reactor temperature response is used for training of the neurocontroller and neuroidentifier. Rapid convergence of this DRNN-based control system is demonstrated when applied to improve reactor temperature performance.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125916499","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}
M. A. Iskandar, M. Satoh, Y. Ohmori, S. Matoba, T. Okabe, Y. Mizutani
The paper presents an application of fuzzy control to determine the control signal of a static VAr compensator (SVC) for improving power system stability. The quantity of reactive power that should be supplied/absorbed by the SVC is calculated depending on the error and the change of error of the electrical power output at each sampling time. The control signal is calculated using fuzzy membership functions. The effectiveness of the proposed control method is demonstrated by a one machine infinite bus system.<>
{"title":"On fuzzy control based static VAr compensator for power system stability control","authors":"M. A. Iskandar, M. Satoh, Y. Ohmori, S. Matoba, T. Okabe, Y. Mizutani","doi":"10.1109/ANN.1993.264290","DOIUrl":"https://doi.org/10.1109/ANN.1993.264290","url":null,"abstract":"The paper presents an application of fuzzy control to determine the control signal of a static VAr compensator (SVC) for improving power system stability. The quantity of reactive power that should be supplied/absorbed by the SVC is calculated depending on the error and the change of error of the electrical power output at each sampling time. The control signal is calculated using fuzzy membership functions. The effectiveness of the proposed control method is demonstrated by a one machine infinite bus system.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129463269","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}
To cope with the growth of load demand, it is known that one of the power utilities in Hong Kong tried to implement an automatic scheme for capacitor switching. However, due to the frequent switching which occurred, resulting in hunting, and the difficulty in determining suitable ON/OFF settings, the scheme was unsuccessful. The authors propose a pragmatic design of a capacitor switching controller which has been successfully tested. Besides power factor, the control signal also incorporates MVAr and the advantages are highlighted. To improve the reliability and robustness of the system, fuzzy logic has been introduced. The performance is described based on both the conventional step control and the continuous TCR/TSC (thyristor controlled reactor/thyristor switched capacitor) control.<>
{"title":"Fuzzy logic based automatic capacitor switching for reactive power compensation","authors":"A. So, W. Chan, C. Tse","doi":"10.1109/ANN.1993.264352","DOIUrl":"https://doi.org/10.1109/ANN.1993.264352","url":null,"abstract":"To cope with the growth of load demand, it is known that one of the power utilities in Hong Kong tried to implement an automatic scheme for capacitor switching. However, due to the frequent switching which occurred, resulting in hunting, and the difficulty in determining suitable ON/OFF settings, the scheme was unsuccessful. The authors propose a pragmatic design of a capacitor switching controller which has been successfully tested. Besides power factor, the control signal also incorporates MVAr and the advantages are highlighted. To improve the reliability and robustness of the system, fuzzy logic has been introduced. The performance is described based on both the conventional step control and the continuous TCR/TSC (thyristor controlled reactor/thyristor switched capacitor) control.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128492949","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}
K. Ichiyanagi, Hideo Kobayashi, T. Matsumura, Y. Kito
This paper describes an attempt to apply a neural network method to forecast river flow rate following a fall of rain. The authors use a perceptron-type network comprised of three layers. The input data to the neural network are rainfall amounts and subsequent river flow rates. Further the predicted total volume and duration of the spell of rainfall in question are taken as additional input data. The output from the neural network is forecasted river flow rate. It is found from these investigations that the forecasting accuracy of the neural network is improved by utilization of the linear input-output relations of neurons.<>
{"title":"Application of artificial neural network to forecasting methods of time variation of the flow rate into a dam for a hydro-power plant","authors":"K. Ichiyanagi, Hideo Kobayashi, T. Matsumura, Y. Kito","doi":"10.1109/ANN.1993.264323","DOIUrl":"https://doi.org/10.1109/ANN.1993.264323","url":null,"abstract":"This paper describes an attempt to apply a neural network method to forecast river flow rate following a fall of rain. The authors use a perceptron-type network comprised of three layers. The input data to the neural network are rainfall amounts and subsequent river flow rates. Further the predicted total volume and duration of the spell of rainfall in question are taken as additional input data. The output from the neural network is forecasted river flow rate. It is found from these investigations that the forecasting accuracy of the neural network is improved by utilization of the linear input-output relations of neurons.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126807356","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}
Distribution feeder reconfiguration is an optimization problem for loss minimization, and, in this paper, the authors investigate the use of a Hopfield neural network for distribution feeder reconfiguration. A network model is developed and presented, and then the method applied to a distribution system used by Wagner et al. (1991) consisting of three feeders, thirteen normally closed sectionalizing switches, three normally open tie switches and thirteen load points. Simulation results using this distribution system modelled as a neural network are presented.<>
{"title":"Applications of Hopfield neural networks to distribution feeder reconfiguration","authors":"D. Bouchard, A. Chikhani, V. I. John, M. Salama","doi":"10.1109/ANN.1993.264329","DOIUrl":"https://doi.org/10.1109/ANN.1993.264329","url":null,"abstract":"Distribution feeder reconfiguration is an optimization problem for loss minimization, and, in this paper, the authors investigate the use of a Hopfield neural network for distribution feeder reconfiguration. A network model is developed and presented, and then the method applied to a distribution system used by Wagner et al. (1991) consisting of three feeders, thirteen normally closed sectionalizing switches, three normally open tie switches and thirteen load points. Simulation results using this distribution system modelled as a neural network are presented.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126924859","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}
Faults are going to occur in most power distribution systems. It is sometimes critical to know the cause of the faults as soon they occur so that appropriate action can be taken, fast and efficiently, in order to reduce the cost of distribution system preparation and to increase the security of the power system. Recently, artificial neural networks have been successfully used to recognize the causes of sustained faults in power distribution systems, by using the fault current information collected for each outage. Here, the authors describe a neural-fuzzy hybrid system to identify the causes of temporary faults as well as sustained faults. The generalization ability of the hybrid fault identification system with respect to different system configurations is analyzed and discussed in the paper.<>
{"title":"Neural-fuzzy hybrid system for distribution fault causes identification","authors":"M. Chow, J. P. Thrower, L. Taylor","doi":"10.1109/ANN.1993.264310","DOIUrl":"https://doi.org/10.1109/ANN.1993.264310","url":null,"abstract":"Faults are going to occur in most power distribution systems. It is sometimes critical to know the cause of the faults as soon they occur so that appropriate action can be taken, fast and efficiently, in order to reduce the cost of distribution system preparation and to increase the security of the power system. Recently, artificial neural networks have been successfully used to recognize the causes of sustained faults in power distribution systems, by using the fault current information collected for each outage. Here, the authors describe a neural-fuzzy hybrid system to identify the causes of temporary faults as well as sustained faults. The generalization ability of the hybrid fault identification system with respect to different system configurations is analyzed and discussed in the paper.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126789991","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 hybrid neural network-fuzzy expert system is developed to forecast one hour to forty-eight hour ahead electric load accurately. The fuzzy membership values of load and other weather variables are the inputs to the neural network and the output comprises the membership value of the predicted load. An adaptive fuzzy correction scheme is used to forecast the final load by using a fuzzy rule base and fuzzy inference mechanism. The paper also presents a fuzzy pattern classification approach for identifying the day-type from the historical load database to be used for training the neural network. Extensive studies have been performed for all seasons, although the results for a typical winter day are given in the paper to demonstrate the powerfulness of this technique.<>
{"title":"A fuzzy adaptive correction scheme for short term load forecasting using fuzzy layered neural network","authors":"P. Dash, S. Dash, S. Rahman","doi":"10.1109/ANN.1993.264309","DOIUrl":"https://doi.org/10.1109/ANN.1993.264309","url":null,"abstract":"A hybrid neural network-fuzzy expert system is developed to forecast one hour to forty-eight hour ahead electric load accurately. The fuzzy membership values of load and other weather variables are the inputs to the neural network and the output comprises the membership value of the predicted load. An adaptive fuzzy correction scheme is used to forecast the final load by using a fuzzy rule base and fuzzy inference mechanism. The paper also presents a fuzzy pattern classification approach for identifying the day-type from the historical load database to be used for training the neural network. Extensive studies have been performed for all seasons, although the results for a typical winter day are given in the paper to demonstrate the powerfulness of this technique.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115942519","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 propose the cooperative fuzzy controller of AVR and GOV to improve the transient stability of power systems. The fuzzy rules to stabilize the power systems are selected from general ideas based on the sliding mode controller. Both the AVR and GOV input are determined to satisfy the system's stability and reduce the chattering effect in the essential problem of sliding mode. Therefore, this fuzzy controller acts to improve the transient stability of power systems. By introducing the ideas of sliding mode control, the fuzzy rules can easily be constructed systematically.<>
{"title":"Cooperative control of AVR and GOV for improving transient stability of power systems using fuzzy controller","authors":"T. Senjyu, N. Gibo, K. Uezato","doi":"10.1109/ANN.1993.264353","DOIUrl":"https://doi.org/10.1109/ANN.1993.264353","url":null,"abstract":"The authors propose the cooperative fuzzy controller of AVR and GOV to improve the transient stability of power systems. The fuzzy rules to stabilize the power systems are selected from general ideas based on the sliding mode controller. Both the AVR and GOV input are determined to satisfy the system's stability and reduce the chattering effect in the essential problem of sliding mode. Therefore, this fuzzy controller acts to improve the transient stability of power systems. By introducing the ideas of sliding mode control, the fuzzy rules can easily be constructed systematically.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122103573","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 fault section estimation problem can be formulated as a nonlinear integer optimization problem. The Boltzmann machine is applied to solve the problem. Since the objective function for the problem has the form of high order polynomial expression, an approximation is made so that the Boltzmann machine can be easily used for the problem. Another problem is to find out all solutions that have equal probability. The objective function is modified for solving the problem. As a result, for single and double fault cases, the Boltzmann machine with modified objective function works very well.<>
{"title":"Fault section estimation in power system using Boltzmann machine","authors":"T. Oyama","doi":"10.1109/ANN.1993.264358","DOIUrl":"https://doi.org/10.1109/ANN.1993.264358","url":null,"abstract":"The fault section estimation problem can be formulated as a nonlinear integer optimization problem. The Boltzmann machine is applied to solve the problem. Since the objective function for the problem has the form of high order polynomial expression, an approximation is made so that the Boltzmann machine can be easily used for the problem. Another problem is to find out all solutions that have equal probability. The objective function is modified for solving the problem. As a result, for single and double fault cases, the Boltzmann machine with modified objective function works very well.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117141413","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 propose a new method based on neural network technology to optimize the operation of generating units. The iterative use of a neural network permits less accuracy of learning and makes the method applicable to larger power systems. Simulations of transmission loss reduction and steady-state stability improvement have demonstrated the effectiveness of the proposed method.<>
{"title":"application of neural network to operation of power generating units","authors":"K. Nishimura, H. Iida, H. Hayashi, T. Asano","doi":"10.1109/ANN.1993.264341","DOIUrl":"https://doi.org/10.1109/ANN.1993.264341","url":null,"abstract":"The authors propose a new method based on neural network technology to optimize the operation of generating units. The iterative use of a neural network permits less accuracy of learning and makes the method applicable to larger power systems. Simulations of transmission loss reduction and steady-state stability improvement have demonstrated the effectiveness of the proposed method.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121097049","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：