Muhsin Tunay Gencoglu

An expert system based on S-transform and neural network for automatic classification of power quality disturbances

In this paper, an S-transform-based neural network structure is presented for automatic classification of power quality disturbances. The S-transform (ST) technique is integrated with neural network (NN) model with multi-layer perceptron to construct the classifier. Firstly, the performance of ST is shown for detecting and localizing the disturbances by visual inspection. Then, ST technique is used to extract the significant features of distorted signal. In addition, an optimum combination of the most useful features is identified for increasing the accuracy of classification. Features extracted by using the S-transform are applied as input to NN for automatic classification of the power quality (PQ) disturbances that solves a relatively complex problem. Six single disturbances and two complex disturbances as well pure sine (normal) selected as reference are considered for the classification. Sensitivity of proposed expert system under different noise conditions is investigated. The analysis and results show that the classifier can effectively classify different PQ disturbances.

Prediction of flashover voltage of insulators using least squares support vector machines

The importance of the research on insulator pollution has been increased considerably with the rise of the voltage of transmission lines. In order to determine the flashover behavior of polluted high voltage insulators and to identify to physical mechanisms that govern this phenomenon, the researchers have been brought to establish a modeling. In this paper, a dynamic model of AC flashover voltages of the polluted insulators is constructed using the least square support vector machine (LS-SVM) regression method. For this purpose, a training set is generated by using a numerical method based on Finite Element Method (FEM) for several of common insulators with different geometries. To improve the resulting models generalization ability, an efficient optimization algorithm known as the grid search are adopted to tune parameters in LS-SVM design. In addition, two different testing set, which are not introduced to the LS-SVM during the training procedures, is used to evaluate the effectiveness and feasibility of the proposed method. Then, optimum LS-SVM model is firstly obtained and the performance of the proposed system with other intelligence method based on ANN is compared. It can be concluded that the performance of LS-SVM model outperforms those of ANN, for the data set available, which indicates that the LS-SVM model has better generalization ability.

Investigation of pollution flashover on high voltage insulators using artificial neural network

High voltage insulators form an essential part of the high voltage electric power transmission systems. Any failure in the satisfactory performance of high voltage insulators will result in considerable loss of capital, as there are numerous industries that depend upon the availability of an uninterrupted power supply. The importance of the research on insulator pollution has been increased considerably with the rise of the voltage of transmission lines. In order to determine the flashover behavior of polluted high voltage insulators and to identify to physical mechanisms that govern this phenomenon, the researchers have been brought to establish a modeling. Artificial neural networks (ANN) have been used by various researches for modeling and predictions in the field of energy engineering systems. In this study, model of VC=f (H,D,L,?,n,d) based on ANN which compute flashover voltage of the insulators were performed. This model consider height (H), diameter (D), total leakage length (L), surface conductivity (?) and number of shed (d) of an insulator and number of chain (n) on the insulator.

Load frequency control for small hydro power plants using adaptive fuzzy controller

Electrical energy generation is very important due to the increasing energy need. To satisfy the need, small scale hydro power plants are constructed in addition to large scale hydro power plants. Hydro power plants have a significant role in the generation of electrical energy. Small hydro power is a kind of clean and renewable energy sources. Small hydro power has a big potential in most areas of the world. This article proposed a novel model design for small hydro power plant (SHPP) using linear and nonlinear turbine model without surge tank effects. The model was created using adaptive fuzzy logic controller. The aim of this article is to improve their implementations by developing a SHPP model without using conventional control methods. The conventional control methods require choosing individual P and I parameters for each load value whereas in the developed model this process carried out by means of a single equations by using adaptive fuzzy logic controller.

A New Experimental Approach Using Image Processing-Based Tracking for an Efficient Fault Diagnosis in Pantograph–Catenary Systems

The periodical maintenance of railway systems is very important in terms of maintaining safe and comfortable transportation. In particular, the monitoring and diagnosis of faults in the pantograph catenary system are required to provide a transmission from the catenary line to the electric energy locomotive. Surface wear that is caused by the interaction between the pantograph and catenary and nonuniform distribution on the surface of a pantograph of the contact points can cause serious accidents. In this paper, a novel approach is proposed for image processing-based monitoring and fault diagnosis in terms of the interaction and contact points between the pantograph and catenary in a moving train. For this purpose, the proposed method consists of two stages. In the first stage, the pantograph catenary interaction has been modeled; the simulation results were given a failure analysis with a variety of scenarios. In the second stage, the contact points between the pantograph and catenary were detected and implemented in real time with image processing algorithms using actual video images. The pantograph surface for a fault analysis was divided into three regions: safe, dangerous, and fault. The fault analysis of the system was presented using the number of contact points in each region. The experimental results demonstrate the effectiveness, applicability, and performance of the proposed approach.

An investigation of pantograph parameter effects for pantograph-catenary systems

The pantograph and the catenary perform the current collection process in electrical railway systems. In such systems, the main purpose is to improve the quality of current collection. Many factors and parameters can affect the interaction between the pantograph and the catenary. Internal or external factors affect the dynamic behavior of the system and lead to parameter variations. In practical applications, the system parameters can be changed very quickly. Therefore, the sensitivity of the system corresponding to the parameter variations is very important. In this study, the effects of parameter variations of pantograph on the system were investigated for the pantograph-catenary system. The system response caused by the parameter variations was examined for a constant reference contact force. Simulation studies were performed in Matlab-Simulink. The new transfer function was obtained by keeping the other parameters fixed in each parameter variation. The simulation result obtained by the new transfer function was compared with the simulation result of reference value. A parameter variation impact on the system response was also interpreted by comparing it with other parameter variations. After analyzing the effects of parameters on the system response, modeling can be accomplished by determining the appropriate control techniques. However, instead of setting the controller parameters for each parameter variation, the use of active control techniques would be more appropriate.

An Analysis Approach for Condition Monitoring and Fault Diagnosis in Pantograph-Catenary System

High-speed trains have a great importance for long distances. The electrical energy for trains must be continuous and uninterrupted. So, the interaction and the mechanical contact between the pantograph and the catenary must be complete. Periodic condition monitoring, fault detection and pre-estimation are extremely important in the electrical railway systems. Therefore, in this study, a condition monitoring and fault diagnosis approach for pantograph-catenary system is proposed with improved model, control and analysis methods. There are two main aims of the study. The first is a regular monitoring of the system to determine whether any failure is occur. The second is to reveal the status of fault occurrence in the future. For this purpose, the contact point analysis between the pantograph strip and the catenary is performed. The most wearied points of the pantograph strip are defined by the method of condition monitoring.

A new arc detection method based on fuzzy logic using S-transform for pantograph–catenary systems

Abstractpantograph–catenary system is one of the critical components used in electrical trains. It ensures the transmission of the electrical energy to the train taken from the substation that is required for electrical trains. The condition monitoring and early diagnosis for pantograph–catenary systems are very important in terms of rail transport disruption. In this study, a new method is proposed for arc detection in the pantograph–catenary system based signal processing and S-transform. Arc detection and condition monitoring were achieved by using current signals received from a real pantograph–catenary system. Firstly, model based current data for pantograph–catenary system is obtained from Mayr arc model. The method with S-transform is developed by using this current data. Noises on the current signal are eliminated by applying a low pass filter to the current signal. The peak values of the noiseless signals are determined by taking absolute values of these signals in a certain frequency range. After the data of the peak points has been normalized, a new signal will be obtained by combining these points via a linear interpolation method. The frequency-time analysis was realized by applying S-transform on the signal obtained from peak values. Feature extraction that obtained by S-matrix was used in the fuzzy system. The current signal is detected the contdition as healthy or faulty by using the outputs of the fuzzy system. Furthermore the real-time processing of the proposed method is examined by applying to the current signal received from a locomotive.

Prediction of power production from a single axis photovoltaic system by Artificial Neural Networks

The power production from a photovoltaic module depends on environmental factors such as radiation, air temperature, wind speed and direction and relative humidity. This study aimed to predict some atmospheric indicators which may affect upon the power production from a single axis (East-West) tracking PV module by using Artificial Neural Network architecture. The novelty side of this research is to use a single axis tracking PV system as first in the literature to predict effective factors of the power production. Besides, unlike previous study, many atmospheric indicators were used to estimate the power production. In this study, the performance of Artificial Neural Network is measured with Mean Square Error, Root Mean Square Error, Mean Absolute Error, Relative Absolute Error, Root Relative Square Error and correlation coefficient. In the established Artificial Neural Network model for sunny and cloudy days, the correlation coefficients are computed as 0.995 and 0.990, respectively. The models of the study will project for future estimation of power production from a single axis photovoltaic module.

Simulation and experimental study of a hybrid system for different loads

In recent years, renewable energy sources such as solar, hydrogen, wind and so on are becoming more popular with the global warming and depletion of fossil fuels. Especially, hydrogen and solar energy have been used in hybrid system to meet these needs. Solar cells generate electricity depending on weather conditions. Therefore, the fuel cells which convert chemical energy of a reaction directly into the electrical energy used in conjunction with solar cells. In this way, energy demand can be supplied using clean energy sources without interruption. In this study, simulation and experimental studies of the solar cell and fuel cell hybrid system have been performed. 100 W fuel cell and 160 W solar cell have been employed in the experimental study. The energy demand is provided from solar cell when the sun is sufficient. During overnight and sunlight is insufficient, interrupted power is provided by the fuel cell. 40 W incandescent lamp and fan (inductive load) were used as the load. The output voltage of the fuel cell and buck converter are given for the experimental results. The curves of load current and voltage were obtained using LabVIEW interface. To compare the experimental and simulation results, same curves were obtained from the simulation.