COMPUTATIONAL INTELLIGENCE IN ELECTRICAL ENGINEERING (INTELLIGENT SYSTEMS IN ELECTRICAL ENGINEERING)
Year:2013 | Volume:4 | Issue:2|Papers Count:7

This paper presents a novel method based on machine learning strategies for fault locating in high voltage direct current (HVDC) transmission lines. In the proposed fault-location method, only post-fault voltage signals measured at one terminal are used for feature extraction. In this paper, due to high dimension of input feature vectors, two different estimators including the generalized regression neural network (GRNN) and the random forest (RF) algorithm are examined to find the relation between the features and the fault location. The results of evaluation using training and test patterns obtained by simulating various fault types in a long overhead transmission line with different fault locations, fault resistance and pre-fault current values have indicated the efficiency and the acceptable accuracy of the proposed approach.

The human movement analysis is an attractive topic in biometric research. Recent studies indicate that people have considerable ability to recognize others by their natural walking. Therefore, gait recognition has obtained great interest in biometric systems. The common biometrics is usually time-consuming, limited and collaborative. These drawbacks pose major challenges to the recognition process. Gait analysis is inconspicuous, needs no contact, is difficult to hide and can be evaluated at distance. This paper presents a bag of word method for gait recognition based on dynamic textures. Dynamic textures combine appearance and motion information. Since human walking has statistical variations in both spatial and temporal space, it can be described with dynamic texture features. To obtain these features, we extract spatiotemporal interest points and describe them by a dynamic texture descriptor. Afterwards, the hierarchical K-means as a clustering algorithm is applied to obtain the visual dictionary of video-words. As a result, human walking is represented as a histogram of video-words occurrences. The performance of our method is evaluated on two dataset: the KTH and IXMAS multiview datasets.

This paper presents a Brain Emotional Learning Based Intelligent Controller (BELBIC) scheme for speed control of an interior permanent magnet synchronous motor (IPMSM) drive over a wide speed range. The speed control of IPMSM becomes a complex issue due to the nonlinear nature as well as coupling among its winding currents and the rotor speed particularly at high speeds. Therefore, in this paper a BELBIC is designed for simplicity and insensitivity to disturbances and ability to control the IPMSM in the whole speed range. The proposed BELBIC is designed based on maximum torques per ampere operation below the rated speed and the field weakening operation above the rated speed, respectively. The effectiveness of the proposed BELBIC is investigated for a 40kW IPMSM and simulated using MatLab/Simulink. The simulation results are compared to those obtained from the conventional PI controller based drive at various conditions such as: step change of command speed and load torque, the disconnection of one phase and parameter variations. Simulation results demonstrate the appropriate dynamic response, robustness again changes, capability in removing load disturbances, without overshoot and undershoot, minimum settling time and lowest steady-state error of the proposed controller over a wide speed range.

This paper presents a new approach for power transformer differential protection. The Wavelet Transform is applied to discriminate between inrush currents and internal fault currents in power transformers. Discrete wavelet transform decomposes the current signal into sub-bands that give more information about the properties of the signals in different frequency bands. Also, this transform is used to investigate the energy distribution of the signal on the different time and frequency scales. Recognition method is based on the correlation factors between energy percentage vectors of the Wavelet coefficients. Discrete Wavelet transform is used for decomposing the current signals to different frequency coefficients. After that, by constituting the energy percentage vectors of wavelet transform coefficients and calculating the correlation factors between these vectors, it is possible to form a recognition criterion to distinguish between inrush and internal fault current in the proposed method. The proposed algorithm is tested for several conditions by simulated inrush and internal fault currents. Simulation of current signals is performed using electromagnetic transient program PSCAD/EMTDC software that is a powerful program for the investigation of transient signals. Simulation results show that the proposed scheme accurately identifies inrush and fault currents in the distance of the power transformer protection in less than quarter of power frequency cycle. Also, beside the sensitivity and high reliability, the proposed method has low computation content and unlike the common methods does not require to determine the threshold for each new power system.

In spite of high reliability, high torque to weight ratio and the efficiency of brushless permanent magnet motors, cogging torque and torque ripple are the main obstacles in development and application of these motors. In this paper, the Taguchi experiment design method is used for reduction of cogging torque. Case study upon two types of permanent magnet motor is applied for validation of this method. First type is surface brushless permanent magnet motor with 4 poles and 6 slots and second type is Interior Permanent Magnet (IPM) motor with 8 poles and 48 slots. Results from simulations indicate a considerable reduction of the peak to peak value of cogging torque.

In this paper, a SEPIC (Single-Ended Primary Inductance Converter) with high efficiency has been proposed for photovoltaic applications. In the proposed converter, an auxiliary circuit without any additional switches has been used. The switch works under ZCS and ZVS conditions. No auxiliary switch was added to the circuit, thus any additional drive circuit is not needed. The proposed control system based on fuzzy logic method has shown the smart accurate and faster tracking of the maximum power point, in different environmental conditions (radiation and temperature). Also, this controller delivers the maximum power to the load with adjusting the duty cycle of a converter. Finally, the simulation results were compared with experimental results to verify the theoretical calculation.