COMPUTATIONAL INTELLIGENCE IN ELECTRICAL ENGINEERING (INTELLIGENT SYSTEMS IN ELECTRICAL ENGINEERING)
Year:2012 | Volume:2 | Issue:4 (5)|Papers Count:7

Expansion planning of the electric power systems has significant importance considering increases in electricity load demand. Transmission network expansion planning (TNEP) is an important part of the electric power system development. In this paper, the TNEP is investigated as a new framework considering actual worth of network adequacy. To do so, a new economic based definition is introduced for network adequacy and statistical studies are developed to calculate the actual worth of network adequacy via proposed formulation. Next, the TNEP is investigated as an optimization problem, with two objectives, using Artificial Bee Colony algorithm. Moreover, new heuristic approaches are presented to enhance the optimization process. Detailed numerical studies and comparisons presented in the paper show that the proposed approach could improve the quality of problem solutions and can be used as a new framework for TNEP within actual networks.

Several scientific researchers have shown that synapses, far from what considered previously, are one of the most dynamic structures in the nervous system. It varies through and after the training stage. A novel feed forward chaotic neural network is designed in this project. The weights of a trained classic feed forward neural network are considered as basic weights. The outputs of chaotic logistic maps are added to the some of the basic weights and this produces a chaotic feed forward neural network. The chaotic weights are synchronized by a proposed algorithm to reduce the output error. Designed chaotic feed forward neural network can separate some data from test set which contain all the recognition errors of the classic feed forward neural network.

Due to simplicity and low cost, induction motors are more useful than direct current motors. Hence the control of these motors is important. The pervious methods are fitted normally for a limited speed range and could not be used for high, low and very low speeds. The voltage model is suitable for high speed because the voltage drop of stator resistance is not small in low speed. The current model is suitable for low speed because of the problems of flux saturation at high speed. This research presents a new method of PWM pulse generating in induction motors based on artificial neural networks in which, the switching pulses are generated by a multilayer feed-forward neural network that is trained by the voltage and current references. Also, for the estimation of required torque and flux information a multilayer perceptron is used. By application of this new method, there is no problem of stability at low and high speeds. The simulation results by matlab-simulink verify the proposed method in transient and steady-state operating modes.

With the widespread use of internet and the development in computer industry, copyright protection of digital multimedia has become a serious issue. Digital watermarking is an appropriate way to solve this problem. This paper proposes a novel adoptive image watermarking scheme in discrete cosine transform (DCT) domain. The host image is divided in to non-overlapping image blocks with size 8×8 and then the binary watermark bits are embedded into DCT domain of image blocks. The embedding locations are selected randomly to enhance the security of watermark. Selected embedding blocks are classified into six classes based on their characteristics like luminance, texture and nearness to the edges. In this research support vector machine (SVM) is used to simulate human visual system (HVS) in order to classify the blocks. Then optimal watermark strengths are determined to different classes by genetic algorithm for embedding adaptively. The experimental results show that the proposed method has good fidelity and robustness against different attacks.

This paper presents an efficient and reliable Evolutionary Algorithm based solution for Selective Harmonic Elimination (SHE) switching pattern. This method eliminates considerable amount of lower order line voltage harmonics in Voltage Source Inverter (VSI). Determination of pulse pattern for the elimination of some lower order harmonics of a PWM inverter necessitates solving a system of nonlinear transcendental equations. Imperialist Competitive Algorithm is used to solve nonlinear transcendental equations for PWM-SHE. Several methods are available to eliminate the higher order harmonics and it can be easily removed. But the greatest challenge is to eliminate the lower order harmonics and this is successfully achieved using Imperialist Competitive Algorithm without using transformer. Simulations using MATLAB are carried out to validate the solution and are compared with the Genetic Algorithm. The results show that the harmonics up to 13th were totally eliminated.

This paper presents a new method to design a robust power system stabilizer (PSS) by using the self-tuning fuzzy logic (SFL) technique in combination with Differential Evolution Algorithm (DEA). Depending on the process trend, the output Scaling Factor (SF) of the controller is modified on-line by an updating factor ( ). The DEA based method is used for off-line training of this controller. Simulation results are carried out on a multi-machine power system. Comparative results of the proposed controller (SFLPSS) with conventional fuzzy logic PSS (FLPSS) designed by DEA, lead-lag PSS designed by DEA (DELLPSS) and conventional PSS (CPSS) show the improvement in dynamic performance of the system.