فهرست مطالب کامل صباحی

Today, the new coronavirus (Covid-19) has become a major global epidemic. Every day, a large proportion of the world's population is infected with the Covid-19 virus, and a significant proportion of those infected dies as a result of this virus. Because of the virus's infectious nature, prompt diagnosis, treatment, and quarantine are considered critical. In this paper, an automated method for detecting Covid-19 from chest X-ray images based on deep learning networks is presented. For the proposed deep learning network, a combination of convolutional neural networks with type-2 fuzzy activation function is used to deal with noise and uncertainty. In this study, Generative Adversarial Networks (GANs) were also used for data augmentation. Furthermore, the proposed network is resistant to Gaussian noise up to 10 dB. The final accuracy for the classification of the first scenario (healthy and Covid-19) and the second scenario (healthy, Pneumonia and Covid-19) is about 99% and 95%, respectively. In addition, the results of the proposed method in terms of accuracy, precision, sensitivity, and specificity in comparison with recent research are promising. For example, the proposed method for classifying the first scenario has 100% and 99% sensitivity and specificity, respectively. In the field of medical application, the proposed method can be used as a physician's assistant during patient treatment.

In this paper, the resilience of the Ardabil province power distribution network was investigated at the level of medium voltage feeders by studying the interruptions of the feeders caused by weather conditions. To do this, the weighted sum of the “number of failures due to weather condition (NFW)”, “failure time duration due to weather condition (FTW)”, and “energy not supplied due to weather condition (ENSW)” were used as an index to assess the resilience of the network. Considering the power interruptions of the last five years, for the interruptions caused by the weather conditions, the numerical value of the defined index for the electricity distribution network of Ardabil province resulted in about 20%, which indicates that the resilience of this network is about 20% less than its ideal value (it is about 80%). To reduce the defined index (increase the resilience), one of the preventive methods is to harden the equipment used in the distribution network for which the feeders that have the highest impact on the defined index were extracted as high-risk feeders to be hardened. Also, to increase the resilience of the Ardabil electricity distribution network, some suggestions have been made to harden high-risk feeders. For this purpose, a number of high-risk feeders were visited to determine possible design discrepancies (contrary to the standard design announced by Tavanir) or their incorrect implementation. By comparing the current status of the studied feeders with the design standards, solutions were provided to correct and increase the strength of these feeders (preventive action to increase resilience). The implementation of the proposed hardening methods is expected to reduce the number of interruptions (due to weather conditions), which will decrease the obtained index and increase the resilience of the network. Moreover, based on this study, it was found that wind, severe storms, rain, thunderstorms, and snow are the most common causes of outages at the level of medium voltage feeders, respectively.

In this paper, an adaptive T2FPID controller is designed for load frequency control (LFC) in a nonlinear, uncertain and time-delay power system. The time-varying delay at the input of the power system that is mainly due to the signal processing, filtering, calculations and breakdown in the communication channels in most cases may lead to system instability. The designed T2FPID controller is a nonlinear and adaptive controller and is able to handle the nonlinearities, uncertainties and time-varying delay at the input of the power system. An appropriate Lyapunov-Krasovskii functional has been used to examine the stability of the closed loop system and to obtain the adaptive rules for the T2FPID controller. Using this functional, it has been shown that the frequency deviations in the control areas have reached to zero and the adaptive parameters of the controller remain bounded. To demonstrate the efficiency of the proposed method, a two-area nonlinear input delayed power system (with four generation and distribution companies) is used for simulations and it is shown that the proposed control strategy outperforms other methods in terms of overshoot and settling time.

A micro grid (MG) system that benefits from distributed generation (DG) resources has a non-linear and time-varying nature which encounters the control problem with some difficulties. Also, due to the fact that in the most MG systems the frequency controllers are centralized in the control room and, the DGs are located at distances from the control room, the occurrence of delay is undeniable and it should be considered in the design of the controller. For this purpose, a self-tuning fuzzy PID controller has been designed for load frequency control in a MG system in the presence of delay. The designed fuzzy PID controller is a nonlinear controller and can handle the nonlinearities. To deal with the delay in the input of the system, the Ziegler-Nichols like criteria has been utilized to derive the adaptive mechanism which tunes the scaling factors according to the maximum amount of delay in the online manner. The proposed self-tuning fuzzy PID controller has been applied for load frequency control of a time-delay MG system and the simulation results have been compared with the results of fixed structure fuzzy PID controller. The simulation results indicate the efficiency of the proposed controllers in dealing with time-varying delay.