Journal of Intelligent Procedures in Electrical Technology
Year:2021 | Volume:11 | Issue:44|Papers Count:6

Diabetes is one of the most common diseases in the world, adversely affects different body organs. One of the most common causes of eye problems is diabetes. Analyzing retinal damage is one of the best ways to diagnose diabetes so one of the best ways to diagnose diabetes is to look at the damage to the retina. Hence, first, a highly applicable and effective method, which is a combination of the Wiener filter and the discrete wavelet transform (DWT), is used for the removal of noise from images. Afterward, the k-means clustering algorithm is used to remove the bad image sections including very light and very dark areas of the image. Next, the image color and shape features are extracted. We transfer the images to the lab space, which fits the eye more, to extract the image color features. To extract the image shape features, first the images are converted into grey images and then the shape features are extracted. After extracting the features, the number of features is reduced using the Principal Component Analysis (PCA) algorithm. Besides, the best and most effective features are also selected. Finally, the support vector machine classifier with different kernel is used to classify the features and images into two categories, namely the healthy participants and patients. The accuracy resulting from this algorithm using the test images is over 90%.

In this paper, a model predictive control approach is presented to regulate indoor temperature. In recent years, the highest energy consumption in buildings is related to heating, ventilation, and air conditioning systems. Therefore, the control of heating, ventilation, and air conditioning systems in buildings has been taken into consideration to reduce energy consumption. At first, a construction model is designed in the Energy-plus software, then all input and output data is collected from this software to identify the state-space model. Then the Model-based predictive control algorithm is applied to control the indoor building temperature. The contribution of this paper is two-fold. Firstly, the data used in the system identification section is based on the assumption that the rooms are not isolated. There is a temperature relationship between the rooms, which provides a more realistic model of the system. Secondly, the external ambient temperature is considered as a disturbance, and its effect on controller design has been investigated. The simulation results for 24 hours show the good performance of the model predictive control approach over the optimal control method along with reducing energy consumption while maintaining the optimal temperature conditions.

Risk level evaluation of power systems and reduction of its related destructive effects costs have been transformed to one of the basic challenges in power industry’ s operation and scheduling. In this paper a new method for mathematical modeling of failure correlation of parallel transformers using Poisson process and multi-Gaussian Copula function is presented. In this method, by using computation of selected reliability indices and related costs, a modeling method for estimation of expectation value of failure cost of parallel transformers with failure correlation and also cost of annual risk of power system has been proposed. According to the capability of production of stage-gate process of the system real mode and failure correlation and probability of parallel transformers, sequential Monte Carlo method for calculation of system’ s reliability indices and related costs estimation has been employed. Simulation results of the proposed method show that annual increase of failure correlation probability of parallel transformers in power stations, will lead to increase of expectation value of their failure, level and cost of power system’ s risk.

The increasing application of single-phase axial flux induction motors with a permanent capacitor and their low efficiency has led to the importance of optimization of this type of motors. In this paper, by introducing the classical algorithms of design of this type of motors, which consists of finding the dimensions of different parts of the motor and calculation of electrical parameters such as resistance and reactance, and capacitor, by introducing the proposed equivalent circuit in the permanent state to reduce the air gap of the motor, introduces the structure of optimization algorithms and then uses a genetic algorithm and improved particle swarm algorithm to optimize the design of the axial flux motor to increase efficiency, increase power factor and reduce core volume. For this purpose, a single-phase axial flux induction motor with a permanent capacitor that has considerable application in ventilation systems is investigated, and using design formulas and with the help of a circuit equivalent to the proposed permanent state, as well as using Intelligent methods such as genetic algorithm and improved particle swarm algorithm, engine optimization to increase maximum efficiency and the results are drawn in the form of torque-speed and efficiency-speed diagrams and compared with each other. Finally, the designed motor is simulated by the finite element method to verify the design algorithm, the steady-state model, the proposed optimization algorithm, and the test results.

Deep learning algorithms achieves some results at human level or even better in pattern recognition problems. Meanwhile they apply a different mechanism other than human brain. This paper describes a human-inspired segmentation and interpolation algorithm, which applies the retinal layer in the proposed model after the input layer. Following this retina, this layer encrypts the input image and transmits the input image to the second space, which try to change deep network structure inspired of the brain's visual path. Network feedback, recognition rate, and network energy level or the comprehensiveness of the trained network examined in subsets of the Caltech data set. In similar examples, deep learning algorithms require more data to learn other than human. In the difference between deep learning and human, there is a difference in the representation of information. In deep learning, weights improve in a way that optimizes the result in a particular experiment, but in millions of years of human evolution, the human brain has evolved optimally and effectively representation. Another point of contention is the deepening of deep learning layers. The number of these layers has multiplied compared to the brain that lead to more complexity and energy expenditure. However, in the brain it can make a diagnosis with less energy. The maximum recognition rate of the proposed model is 93% and the base model is close to 91%. Also, the proposed model is thinner and the rate of fire of neurons in the initial layers is lower and has a high stability to changes in light intensity. The Dissimilarity of the model layers has been higher and it has been able to show a better response in the face of noise images and record less recognition loss.

The proper and sustainable performance of any electrical system is mainly related to the designers' insight into the nature of that system. Therefore, the need to provide an accurate model based on the actual behavior of the system has considerable importance. In the case of inverter-based microgrid, due to the lack of sufficient synchronizing torque, the design process must be carried out with the utmost precision. In this paper, the stability of the inverter-based microgrid will be studied. First by presenting the equations of the microgrid components its state-space model is obtained and in the presence of the static load model the stability of the system will be investigated. Then, by placing the inventory of dynamic exponential recovery and static polynomial load models, the results of the static model-based design are investigated. In this study, the measure of system stability will be eigenvalue plots and system performance. In order to achieve system stability and performance improvement, the state variables participation factors extracted and the effective parameters will be studied.