COMPUTATIONAL INTELLIGENCE IN ELECTRICAL ENGINEERING (INTELLIGENT SYSTEMS IN ELECTRICAL ENGINEERING)
Year:2020 | Volume:11 | Issue:1 |Papers Count:10

In transmission and sub-transmission systems, distance and overcurrent relays have a vital role in protection of transmission lines. Power systems have different topological uncertainties such as planned or unplanned line outages. Such uncertainties affect network impedance matrix, and the distribution and amplitude of fault currents through the relays leads to changes in the coefficients of coordination constraints. Therefore, mal-operation of relays and non-selective operation of protection system may occur. In order to have a robust coordination, coordination constraints from different topologies must be taken into account in the coordination problem. In such conditions, in order to satisfy all constraints, operating time of relays increases. In this paper, the selection of appropriate characteristic among standard characteristics for overcurrent relays is proposed to reduce the operating time of relays despite the existence of robust coordination. The proposed approach is tested on an 8-bus and the IEEE 14-bus test systems. Simulation results show that, by applying the proposed method to the coordination problem of distance and overcurrent relays, the operating time of relays, while maintaining their correct operation of relays, is significantly reduced, despite the network restructuring.

The effectiveness of multi-objective optimization methods, especially the methods based on Swarm Intelligence, has led the researchers to utilize them significantly to solve complex engineering problems with multiple conflicting objectives. This paper aimed at evaluating the performance of new and powerful multi-objective heuristic methods based on Swarm Intelligence (including multi-objective versions of MOPSO, MOGWO, NSGSA, MOGOA, MOIPO, MOMIPO, and MOALO algorithms), and used them for optimal design of the Sense Amplifier-based Flip-Flop (SAFF) using 0. 18-μ m CMOS technology. In this paper, the channel's width values of the transistors as designing variables, and total average power and delay as the fitness values of the two objective functions were assessed and optimized in terms of multi-objective optimization problem using intelligent optimization algorithm based on Swarm Intelligence assumption in order to achieve the desired values of power-delay product (PDP). Comparing the results obtained for all of the above multi-objective optimization methods, the Multi-Objective Grasshopper Optimization Algorithm (MOGOA) performed better. This method was able to perform very well in the statistical indices of fitness and multi-objective optimization criteria in comparison with other methods. It creates an appropriate trade-off between conflicting objective functions with average power of 24 μ W, delay of 95. 4 ps and PDP of 2. 29 fJ.

The growing use of internet and the existence of vulnerable points in networks have made the use of intrusion detection systems as one of the most important security elements. Intrusion detection is essentially a classification problem and it is the identification of effective features such as important issues in the classification This paper presents a novel method for selecting effective features in network intrusion detection based on an estimation of distribution algorithm that uses a probabilistic dependency tree to identify important interactions between features. To evaluate the performance of the proposed method, the NSL-KDD dataset is used, in which the packets are divided into five normal types and intrusive types of DOS, U2R, R2L and Prob. The performance of the proposed algorithm has been compared alone and in combination with other feature selection algorithms such as forward selection, backward selection and genetic algorithm. Moreover, the effect of algorithm parameters like population size on intrusion detection accuracy is tested. Based on this analysis and also considering the intra-class accuracy of different feature selection methods studied in this paper, an effective subset of features for intrusion detection is identified.

Distance protection system as the main lines’ protection, has an essential role in networks’ reliability. Thus an optimized maintenance plan for distance protection can influence on network reliability and costs. Intrinsic hidden function of the protection systems cause some problem in the way of applying reliability-centered maintenance technique (RCM) as an effective planning method. In this study, the concept of systematic solution view in RCM is proposed instead of equipment-based solution view. The presented concept can well model the behavior of a hidden performance system. Also, Markov process and krill optimization algorithm is used for calculating the reliability and finding optimal time intervals between maintenance tasks. Increasing system reliability and decreasing costs are considered as optimization aims. The proposed method has been implemented and tested using real data of two distance protection systems. The output results show that the proposed method is capable of providing higher reliability and lower cost than other methods.

Most speech enhancement algorithms focus on obtaining an estimator relying on stochastic models. In this paper, a minimum mean-square error (MMSE) estimator under a stochastic– deterministic model is proposed where a heavy-tail distribution called t-Location-Scale (tls) is used for modeling Discrete Fourier Transform coefficients of clean speech signals and exponential and sinusoidal models are employed as deterministic models. In the exponential model, the frequency and damping coefficient are estimated by using the Matrix Pencil method. Also, in previous studies, the number of exponential components in the deterministic model for stochastic-deterministic speech enhancement algorithm has been considered to be one. In this paper, the corresponding exponential model is developed to have an arbitrary number of exponential components. The speech enhancement experiments are performed in three modes, exponential-Gaussian (the first proposed method), exponential-tls (the second proposed method), and sinusoidal-Gaussian. Comparisons are made with the exponential-Gaussian method (with only one exponential component), as well as with the Weiner and tls stochastic estimators. The implementation results in the presence of six noise types from Noisex-92 dataset show that the two proposed methods improve the segSNR values and have quite similar PESQ values comparing with the stochastic based speech enhancement methods.

Alzheimer's is a type of brain dementia that gradually reduces mental abilities of the patient. The lack of memory, decision-making disorder, and mistakes in choosing the correct vocabulary are the early symptoms of Alzheimer's disease. Therefore, extensive studies have been conducted on the diagnosis of Alzheimer's disease using the noninvasive speech signal recognition method. Identifying of Alzheimer's disease is dependent on culture and language, speech content, gender, age, accent, and many other factors. Therefore, Alzheimer's speech signal has been studied in various languages. The purpose of this paper is to recognize Alzheimer's patients from healthy people by the use of their speech signal processing in Persian using the combination of time, frequency, and frequency-temporal features. In this paper, after pre-processing, the speech features extracted using the wavelet packet as a frequency-temporal feature next to Mel frequency Cepstral coefficients, zero crossing rate, spectral roll off, band width, root mean square and spectral centroid frequency. Finally, the extracted features have been classified by the support vector machine which achieves recognition precision of 96% on Persian healthy and Alzheimer's speaker experiments. The acceptable results demonstrate the applicability of the proposed non-invasive and low-cost algorithm for the diagnosis of Persianspeaking Alzheimer's patients.

Directional overcurrent relays utilize the voltage phasor as a reference for determining the direction of the fault. This requires measuring both current and voltage and makes the directional overcurrent relays more costly than the non-directional type. In this paper, a new method for detection the fault occurrence and fault direction is proposed, that is based on Teager energy operator. Teager energy operator is a simple algorithm that is used to signal processing and extraction of instantaneous changes in amplitude and frequency of a signal. To this end, the proposed algorithm uses only three consecutive samples of measured current signal for detection of fault and its direction. This method does not require phasor estimation and complex calculations. In addition, the method is very fast. This Algorithm is implemented and verified for different types of fault and several conditions using Matlab/Simulink. The simulation results show that the proposed method is fast and has acceptable accuracy.

With the increasing development of human science and societies as well as increased air pollution and global temperature, the need for renewable energy and electric vehicles has increased more than ever. Wind farms, as well as solar cells have a special place because of their greater production capacity, more general acceptability and cost-effectiveness. The main challenge in RESs development is uncertainty in their generation due to lack of continuous availability of adequate wind speed and solar radiation during 24 hours of day. In this paper, a mixed integer linear programming (MILP) model is proposed for power system probabilistic scheduling considering electric vehicles and RESs. In the proposed model, autoregressive moving average (ARMA) approach is employed to generate scenarios for wind speed and solar radiation. Besides, a technique based on Kantorovich distance matrix is employed to reduce the generated scenarios. Conditional value at risk (CVaR) method is used for management and analysis of risks due to the system uncertainties. Moreover, the efficiency of electric vehicles batteries to cover the uncertainties of RESs is evaluated. Furthermore, the optimal placement of Vehicle to grid (V2g) stations and RESs (wind and solar farms) are determined. Modified IEEE 24-bus test system including two wind farms, three solar farms and three V2g stations is studied to verify the effectiveness of the proposed model. Results of simulation in Gams software environment demonstrate that the power stored in V2g stations play an effective role in covering the uncertainties of wind and solar farms power generation.