Series compensation consists of capacitors in series is used in the transmission lines as a tool to improve the performance after disturbed by a fault. Transmission line needs a protection scheme to protect the lines from faults due to natural disturbances, short circuit and open circuit faults. The fault can happen in any location of transmission line and it is important to know which location has been affected. So that, the fault can be eliminated and can maintain the optimum performance. Therefore, in this paper Artificial Neural Network (ANN) is used to detect and classified the fault happen in single line to ground fault and three phase to ground fault. Two different tests of each types of fault have been tested in order to prove the effectiveness of ANN to detect the fault location by using different length and fault resistance. The simulation has been accomplished in MATLAB with ANN fitting tool which build and train the network before evaluated its performance using regression analysis. The analysis shows that the ANN can accurately detect the different types of faults and classified it into the respective category even the random vectors are put on the system are used.
This paper outlines an alternative approach using fuzzy production rules to handle approximate reasoning in expert systems without using the Generalised Modus Ponens (GMP) model by Zadeh. The proposed approach provides a method whereby a collection of rules is used to specify the properties of the inference as required by the expert. An example on the medical diagnosis of Acute Rheumatic Fever is used for illustration.
In this article, we propose and study a self-switching network concept known as an ingenious multiple communicator mechanism which can be applied to energy provider's smart metering device. We outline reasons why such multiple connections networks are required through real case study scenarios and key components that drive towards such concept. We have gathered actual measurement values for a particular network and identified in what situation this is most suitable and applicable. We have come out with the basic system model for this multiple communicator. We also observed that a less fluctuating and similar pattern of network performance helps to design better network predictive analytics function. Finally numerical examples and analysis of the results are presented.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.