The active suspension system is an important equipment that isolates the vibrations that may come from outside in a land vehicle. In heavy vehicles, the active suspension system can be used to dampen vibrations in the driver’s cabin. The electromagnetic actuator is used as an active element in suspension system. Traditionally, the use of active suspension systems is mainly on automobiles and the studies related to heavy vehicles like trucks lack enough interest. In this study, dynamic modeling of a three-axle heavy vehicle cabin is performed with a half-car approach and it is aimed to suppress the disruptive effects coming from the road with active electromagnetic actuators. Lyapunov based backstepping control design is expressed in vectorial form for the heavy vehicle system, which is a multi-input multi-output system. To demonstrate the performance of the designed controller, a comparison has been made for the active and passive states for the truck cabin suspension system. The main feature of the applied control method is that it does not require knowing the actuator parameters, the adaptive term can handle the estimate of the actuator parameter. The stability of the proposed system has been proven via Lyapunov based arguments and given simulation works. The results obtained are important to suppress vibration, consequently, decreases the vibration exposure for truck drivers in terms of occupational health and safety aspects.

In this work, the mechanical faults that occur in induction motors, which are widely used in industry due to their simple and rugged construction and cost effective pricing, are analyzed. The certain fault modes are generated synthetically in induction motors and motors are run by a voltage controlled frequency inverter with four different speed references and three different load conditions to gather the digitized stator current data in laboratory environment. By applying wavelet packet decomposition, wavelet packet coefficients are obtained from stator current and these coefficients are used to obtain feature vectors by using statistical properties of the data. Fault detection is performed by classifying these feature vectors with different types of classifiers. As a result, correct classification rates are compared not only with faulty and healthy motors, but also with different fault modes. The effects of the speed reference, stator current level, selected filter type in wavelet packet decomposition and type of the classifier in fault detection is also observed.

Demiryolu taşımacılığı, güvenilir, rekabetçi ve çevre dostu bir ulaşım ve yük taşıma alternatifi olduğu için günümüzde, demiryolu hatlarındaki trafiğin artması kaçınılmaz bir durumdur. Artan yolcu talebi sonucu sıklaşan seferler, tren hızlarının yükselmesi ve yüklerinin artması ile birleşince mevcut demiryolu üstyapısına önemli ek yükler getirmektedir. Bu ek yükler, raylarda olası problemlerin ortaya çıkma olasılığını arttırmaktadır. Buna bağlı olarak, raylarda görülen kusurlar daha önemli hale gelmiş; rayların kusurlara karşı kontrol edilmesi ve bakımının zamanında yapılması büyük önem kazanmıştır. Bu çalışmada ray görüntüleri Artık Ağ mimarisini kullanan evrişimli yapay sinir ağı ile eğitilmiş ve ray üzerindeki kusurlar ve ray kırıkları yüksek bir başarıyla sınıflandırılmıştır. Böylelikle birebirine karışma ihtimali fazla olan ve ayrıca ray kırığı probleminin öncülü olabilecek ciddi ray yüzey kusurlarının başlangıç aşamasında tespiti ile bakım onarım faaliyetlerine katkı sunabileceği düşünülmektedir.