241 Hits in 2.9 sec

A New Learning and Fuzzy Strategy for Active Power Filtering

Hichem Laib, Abd Elaziz Chaghi, Patrice Wira
2016 International Journal on Electrical Engineering and Informatics  
Several methods have been proposed in [5] where ADALINE neural networks have been used to on-line learn the expressions of the signals, i.e., either instantaneous powers or currents.  ...  In the next section, we describe the ADALINE approach and more specifically the direct method and the design of the FLC applied to the APF system.  ... 
doi:10.15676/ijeei.2016.8.3.4 fatcat:lezktr23svd7pcbasjril64mk4

Diagnosis of mechanical pumping system using neural networks and system parameters analysis

Tai-Ming Tsai, Wei-Hui Wang
2009 Journal of Mechanical Science and Technology  
This paper addressed dealing with these signals to establish the database of input-output relation by using a number of neural network models through learning algorithms.  ...  By ignoring the neural network training time, it has been shown that if the mechanical diagnosis system is tackled off-line, the RBF method is suggested.  ...  Comparison of the three neural networks used in the mechanical pumping system, the BPN method has been determined to be the best in time-saving for learning followed by the ADALINE method and the RBF method  ... 
doi:10.1007/s12206-008-1003-7 fatcat:ka7iuttljjgchmjbxfsnzneysa


2007 International Conference on Aerospace Sciences and Aviation Technology  
In order to consider the uncertainty of communication delays and packet losses, intelligent computational approaches such as fuzzy logic, neural networks, and genetic algorithm can be used.  ...  Several simulation examples are applied using CAN network to clarify the efficiency of the proposed methods.  ...  An intelligent controller using fuzzy logic on top of a PI gain to adaptively compensate for the IP network-induced time delay in time-delay sensitive Networked Control System applications are proposed  ... 
doi:10.21608/asat.2007.23957 fatcat:5u55ramhqzffpl7zkajvhpqjv4

Adaline for Online Symmetrical Components and Phase-Angles Identification in Transmission Lines

Fatima Louisa Yousfi, Djaffar Ould Abdeslam, Tahar Bouthiba, Ngac-Ky Nguyen, Jean Merckle
2012 IEEE Transactions on Power Delivery  
The Adalines use a cosine and sine as inputs in order to learn the linear combination of the powers.  ...  The average and oscillating terms of powers in the αβ frame are separated by using four Adaline neural networks.  ...  As a result, an important number of fault protection based on these methods have been developed: Expert Systems [4] , [5] , Fuzzy Logic [6] - [8] , Wavelet Transform [9] , [10] , Artificial Neural  ... 
doi:10.1109/tpwrd.2012.2196526 fatcat:z7liky2f75f6hnvawiva5p6a6e

Fuzzy Clustering Data Arrays with Omitted Observations

Zhengbing Hu, Yevgeniy V. Bodyanskiy, Oleksii K. Tyshchenko, Vitalii M. Tkachov
2017 International Journal of Intelligent Systems and Applications  
The introduced neural system is characterized by both a high speed and a simple numerical implementation. It can process information in a real-time mode.  ...  An adaptive neural system which solves a problem of clustering data with missing values in an online mode with a permanent correction of restorable table elements and clusters' centroids is proposed in  ...  The adaline may be used both as an elementary neuron in a neural network and for solving pattern recognition problems, signal processing problems, and for implementation of logical functions.  ... 
doi:10.5815/ijisa.2017.06.03 fatcat:x26kjng2z5dadcjhve3ad53s74

Performance of Neural Network based PV Interfaced Hybrid Active Power FilterUnder Unbalanced Supply and Distorted Mains Condition

Anima Yadaw, Dr. S. P Dubey
2015 International Journal of Engineering Trends and Technoloy  
Neural network has been selected to improve the performance of filter because it having fast learning capability, simple calculation and high accuracy to mitigate harmonics from the system.  ...  To keep the capacitor voltage stable of the filter PV array is employed in the system.  ...  Fuzzy logic cannot provide accurate results at dynamic condition because the membership function and the parameter of single fuzzy logic controller are established based on experience and fixed during  ... 
doi:10.14445/22315381/ijett-v24p211 fatcat:734qnmy35vcyragv7hjavtdqni

Photovoltaic Integrated Shunt Active Power Filter with Simpler ADALINE Algorithm for Current Harmonic Extraction

Muhammad Mohd Zainuri, Mohd Mohd Radzi, Azura Che Soh, Norman Mariun, Nasrudin Abd Rahim, Jiashen Teh, Ching-Ming Lai
2018 Energies  
The updating algorithm of the Modified W-H ADALINE uses Weight (W) as its learning factor.  ...  Previously, this voltage error was controlled by such algorithms like proportional-integral (PI) and fuzzy logic techniques.  ...  Weight is used as the learning factor in the Widrow-Hoff (W-H) method. However, to reduce complexity of the normal ADALINE, the Modified W-H ADALINE has been proposed.  ... 
doi:10.3390/en11051152 fatcat:ocxyxgenfnfsbfkwhes52cwjcy

Conundrum of combinatorial complexity

L.I. Perlovsky
1998 IEEE Transactions on Pattern Analysis and Machine Intelligence  
The potential role of the fuzzy logic in overcoming current difficulties is discussed. Current mathematical difficulties are related to philosophical debates of the past.  ...  Paradigms based on adaptive learning lead to the complexity of training procedures, while nonadaptive rule-based paradigms lead to complexity of rule systems.  ...  Fuzzy and probabilistic logics [49] may hold keys to the answer. Intermediate computational steps (before Forms meet matter) should employ fuzzy representations of concepts.  ... 
doi:10.1109/34.683784 fatcat:adsjbg3n7rd5vmz7b3dhefelqe

Robust diving motion control of an autonomous underwater vehicle using adaptive neuro-fuzzy sliding mode technique

Girish V. Lakhekar, Laxman M. Waghmare, Prakash G. Jadhav, Rupam Gupta Roy
2020 IEEE Access  
In the beginning, the fuzzy logic system is leading and drives the system towards the sliding surface.  ...  The proposed control scheme utilized the benefits of sliding mode, neural network, fuzzy logic, and adaptive PID techniques, while the shortcomings attributed to these methods are remedied by each other.From  ... 
doi:10.1109/access.2020.3001631 fatcat:zrikkqwsmrc6fpsga6olslk4mi

Solving Uncertain Problems using ANFIS

Dr G.S.V.P. Raju, V. Mary Sumalatha, K.V. Ramani, K.V. Lakshmi
2011 International Journal of Computer Applications  
The purpose of the paper is to solve an engineering problem, power failures in personal computers using neuro fuzzy modeling system ANFIS.  ...  for the solution of machine learning problems lead to high machine intelligence quotient.  ...  The learning algorithm L describes the mechanism for learning and adaptation to the new information. Fuzzy Inference System Fuzzy inference system maps the given input to output using fuzzy logic.  ... 
doi:10.5120/3690-5152 fatcat:ktdioeb2ozdebhswpybq443h2u

The design of a smart home controller based on ADALINE

Puji Catur Siswipraptini, Rosida Nur Aziza, Iriansyah Sangadji, Indrianto Indrianto
2020 TELKOMNIKA (Telecommunication Computing Electronics and Control)  
The construction of the proposed controller is carried out through several procedures, i.e. the implementation of the ADALINE (adaptive liniear) as the neural network method, the design of the smart home  ...  Unlike previous approaches, this design also utilizes the use of IoT (internet of thing) technology and neural network based-algorithm for developing the controller.  ...  ACKNOWLEDGEMENTS This work has been funded by The Ministry of Research, Technology, and Higher Education Republic of Indonesia.  ... 
doi:10.12928/telkomnika.v18i4.14893 fatcat:3yacld4spzaphd5nchxz7vjyei

Self-growing neural network architecture using crisp and fuzzy entropy

Krzysztof J. Cios, Dennis W. Ruck
1992 Science of Artificial Neural Networks  
The condition part of a decision rule consists of a number of feature tests linked by and/or logical operators.  ...  The sizes of the images obtained by the imaging system varied in proportion to the size of the actual defect.  ...  Two alternative ways of calculating the entropy, crisp and fuzzy, were used. The fuzzy entropy method showed better perfi)rmance in terms of convergent time.  ... 
doi:10.1117/12.140154 fatcat:vshoct52bva6xhgep32lovutsi

Neural Adaptive Kalman Filter for Sensorless Vector Control of Induction Motor

Ghlib Imane, Messlem Youcef, Gouichiche Abdelmadjid, Chedjara Zakaria
2017 International Journal of Power Electronics and Drive Systems  
Moreover, to improve the performance of the PI classical controller under different conditions, a novel adaptation scheme based on ADALINE (ADAptive LInear NEuron) neural network is used.  ...  The simulation results showed the robustness, efficiency, and superiority of the proposed scheme compared to the classical method even in low speed region.  ...  For this, many solutions are proposed such as advanced adaptation mechanisms, fuzzy logic controller [13] , [14] sliding mode adaption [15] , [16] , and ANN algorithms (BPN learning low [17] ).  ... 
doi:10.11591/ijpeds.v8.i4.pp1841-1851 fatcat:puh4ravpc5aufhtllcl7koa76q

A Review on Shunt Active Power Filter Control Strategies

Harnek Singh, Maneet Kour, Dip Vinod Thanki, Prakash Kumar
2018 International Journal of Engineering & Technology  
In this paper a technical review of various control strategies for operation of SAPF has been presented.  ...  The most commonly used structures of ANN are ADALINE and MADALINE.  ...  The most likely used approaches for triggering of VSI switches are hysteresis controller [19] , fuzzy logic controller [20] and Pulse width modulation [21] .  ... 
doi:10.14419/ijet.v7i4.5.20026 fatcat:dhwh46dxsjftzch2uvvisw5r4m

Artificial Intelligence for Inferential Control of Crude Oil Stripping Process

Mehdi Ebnali, Mehdi Shahbazian, Houshang Jazayerirad
2018 Iranian Journal of Oil & Gas Science and Technology  
In this paper, we have used a novel inferential control approach base on adaptive network fuzzy inference system (ANFIS) for stripping process.  ...  ANFIS with different learning algorithms is used for modeling the process and building a composition estimator to estimate the composition of the bottom product.  ...  Four intelligent controllers were designed based on fuzzy logic, adaptive linear network (Adaline), and hybrids of these two techniques.  ... 
doi:10.22050/ijogst.2017.54928.1337 doaj:aec606c9f35846b18ea2931239438319 fatcat:rwndf7hoyzdehjsg6ybbazrxqq
« Previous Showing results 1 — 15 out of 241 results