Pantograf katener sistemlerde görüntü işleme ve model tabanlı ark tespiti

Abstract

Pantograf katener sistemi, elektrikli trenin ihtiyaç duyduğu elektrik enerjisini trafo merkezinden trene iletilmesini sağlamaktadır. Bu işlemin kesintisiz bir şekilde gerçekleştirilmesi için pantograf katener sistemler oldukça önemlidir. Bu çalışmada, pantograf katener sistemi için görüntü işleme ve model tabanlı yeni bir ark tespit yöntemi önerilmektedir. Görüntü işleme yöntemleri kullanılarak videodan alınan bir görüntü çerçevesinde oluşan arklar tespit edilmektedir. Bir dizi görüntüden elde edilen veriler ark modellemesinde kullanılmıştır. Bu modelleme sonucunda pantograf katener sistemin, normal ve ark oluşmuş durumlarına ait akım ve gerilim sinyalleri elde edilmektedir. Elde edilen akım gerilim sinyallerinde normal ve ark oluşmuş durumlar incelenmiştir. Akım, gerilim sinyalleri kullanılarak S dönüşümü yapılmıştır. S dönüşümü ile sinyallerin frekans zaman analizi yapılmaktadır.

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. Stransform is applied to these signals and occurred arcs are detected.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. Stransform is applied to these signals and occurred arcs are detected.