Orhan Yaman

Detection of pantograph geometric model based on fuzzy logic and image processing

In this study, a model based approach is proposed for the recognition of the pantograph type used in electric trains. The shape of the pantograph-catenary changes according to usage conditions of electric trains. A geometric model of the pantograph is constructed by using images taken from the pantograph-catenary system. The pantograph type is determined by using the constructed model. First, all straight lines are extracted from the image by applying the edge detection and Hough transform to the image. Some knowledge obtained from straight lines are given to fuzzy logic and type of pantograph is determined. The determination of pantograph type is useful to estimate the pantograph height and to analyze of contact point between pantograph and catenary. Therefore, contact point problems such as arcing and excessive contact force can be detected.

Particle swarm based arc detection on time series in pantograph-catenary system

Pantograph-catenary system is the most important component for transmitting the electric energy to the train. If the faults have not detected in an early stage, energy can disrupt the energy and this leads to more serious faults. The arcs occurred in the contact point is the first step of a fault. When they are detected in an early stage, catastrophic faults and accidents can be avoided. In this study, a new approach has been proposed to detect arcs in pantograph-catenary system. The proposed method applies a threshold value to each video frame and the rate of sudden glares are converted to time series. The phase space of the obtained time series is constructed and the arc event is found by using particle swarm optimization. The proposed method is analyzed by using real pantograph-videos and good result have been obtained.

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.

Real-time condition monitoring approach of pantograph-catenary system using FPGA

In recent years, the importance of railway transport increases with the development of fast trains. Maintenance of this train should be performed at an early stage for safety and reliability. Because pantograph-catenary system is used to transmit the energy to the train in most of the electric trains, the early detection of the problems occurred in these systems are very important. In this study, an FPGA (Field Programmable Gate Arrays) based new fault detection method is proposed by using normal and thermal images. The method takes the images of pantograph-catenary system by a camera attached to the FPGA Kit and saves them to SDRAM and RAM blocks. Thresholding method is applied to image matrix read from SDRAM and occurred arcs are detected. On the other hand, the pantograph overhead bar is detected by applying sobel edge detection to the image read from RAM block. Arcs occurred in contact point is detected in real time by combining two methods. The proposed method is verified in a real experimental setup.

Image processing based fault detection approach for rail surface

Railway transport is getting more and more preferred mode of transportation. Railway line should be established in a robust manner because of construction of used heavy vehicles. A small fault, which occurs in the railway line, can lead to serious accidents. Therefore, the railway line should be controlled at certain time intervals. Faults detected during the control process should be repaired and the required maintenance should be performed. In this study, an image processing based method has been proposed to detect the defects of rail surface. In the proposed method, the images were taken from two cameras, which of them were placed at different angles on the experimental setup. The preprocessing stage was made by applying OTSU method to obtained images. The rail surface is determined by using Canny edge detection and Hough transform. Faults occurred on the rail surface were detected by combining images taken from two camera. The accuracy of the proposed method was increased by using the images taken from two different cameras.

Image processing and model based arc detection in pantograph catenary systems

A pantograph-catenary system transmits the electric energy that an electrified train needs from electric power substation to train. Pantograph catenary system is extremely important in order to carry out continuous of the transmission. In this study, a model and image processing based arc detection system is proposed. Arcs occurred in a video frame are detected by using image processing techniques. Data obtained from a sequence of frames are used to model the arc. Arcs occurred in image sequences are modelled during modeling stage. As consequence of the modeling, current and voltage signals, which belong to healthy and arc occurred conditions, are obtained. These signals are analyzed to detect the condition of the pantograph-catenary system as healthy or faulty. S-transform is applied to these signals and occurred arcs are detected.

A New Approach for Condition Monitoring and Detection of Rail Components and Rail Track in Railway

Computer vision-based tracking and fault detection methods are increasingly growing method for use on railway systems. These methods make detection of components of the railways and fault detection and condition monitoring process can be performed using data obtained by means of computers. In this study, methods are proposed for fault detection on railway components and condition monitoring. With cameras placed on the bottom and the top of the experimental vehicle the images are taken. The camera at the top, overhead rails are positioned to see a way for war and the camera is fixed to the bottom mounted to see clearly railway components. Images from cameras placed on the bottom, Canny edge extraction and Hough transform methods are applied. The types of the components and faults are determined by using classification algorithm with decision trees using the obtained data. The condition monitoring has done by the camera is positioned on the upper part of the vehicle. By processing the taken images with processing methods, inclination angle of the rails and direction of railways are detected. Thus, during the course of the vehicle is obtained information of the direction of railway. Real images are used in the operation of railways belonging to the experimental environment. On these images, to identify the components of the proposed method using the railways and rail direction determination is made. The results obtained are given at the end of the study. The experimental results are analyzed, it is observed that the proposed method accurate and effective results.

A vision based diagnosis approach for multi rail surface faults using fuzzy classificiation in railways

The heavy construction of railway transportation vehicles is affecting the transportation route. The rail line, which is made with great care, can be damaged by the movements of freight trains. As a result of the use of rail lines, many faults occur. These failures are caused by the manufacturing error or use of the rails. There are many methods for early detection and repair of failures. One of these methods is the camera-based method. The rail components are inspected by taking images from the cameras fixed to the railway vehicle. Faults occurring in rail components are detected. In this study, a method for detecting and classifying faults on railway track surfaces is proposed. In the proposed method, the rail surface was detected using image processing techniques. Property extraction on the rail surface is performed. In addition, the type of fault is determined by using fuzzy logic.

Intrusion detection in computer networks via machine learning algorithms

With the internet of objects, the number of devices with internet connection is increasing day by day. This leads to a very high amount of data circulating on the internet. It is one of the most common problems that can be distinguished from normal and abnormal traffic by analyzing in high data amount. In this study, an analysis was carried out by using machine learning approaches to determine whether the data received on the internet is normal or abnormal data. In order to achieve this goal, the KDD Cup 99 data set which is frequently used in literature studies is classified by Naive Bayes (NB), bayes NET (bN), Random Forest (RF), Multilayer Perception (MLP) and Sequential Minimal Optimization (SMO) algorithms. Classifiers are also compared with false rate, precision, recall, and F measure metrics along with accuracy rate values. Classification times of classifiers are also given by comparison.

A real time interface for vision inspection of rail components and surface in railways

The importance given to the safety of railway transportation and the maintenance of railway components is also increasing as railway transportation is widespread all over the world. The most basic measure is to take to reduce railway accidents is to check the railway components at regular intervals. The identification of railways with advanced technology, unlike traditional methods, has made a great demand in recent years. Regular inspection of rail, railway component, traverse, turnout crossing and level crossing at regular intervals will prevent possible accidents. In this study, it has ensured that railway components have been diagnosed using contact image processing based techniques. The proposed approach consists of preprocessing, morphological feature extraction, fault and deficiency detection steps. The railway component which is missing after the fixing of the connecting element and the rail line is determined. The lack of railway components can jeopardize the safety of railway transportation. After the rail track has been detected, the existing faults on the rail surface have been determined. The operations applied in rail surface diagnosis include image padding, average filter, difference of images, feature extraction and defects labeling. The proposed method is performed through the interface created with Emgu CV library in Visual Studio and high accuracy results are obtained.