Road defect is one of the most important factors for traffic accident. Therefore, these defects should be corrected as soon as possible. It usually occurs cracks, rutting, and potholes in road surface. These errors are based on the fact that people have recognized and fixed these errors in our day. But if these errors are not corrected in a short time, the size of the error grows day by day. There are various methods used to detect road errors in the literature. One of these methods is the use of computer vision. There are various types of roads in real life. Since the studies in the literature have been carried out only by taking into account one type of road, the accuracy rates decrease when these studies are used in different types of roads. In the study carried out, different roads have been made adaptive by the operations performed in the detection of road errors from the received images. Images taken from the camera on a vehicle are used for the study. The study applied is ensured to have high accuracy rates in different types of roads via customization. In the second stage, the image blurred by using median filter and the unprocessed images are collected, and the darkest parts of the image are brought into the forefront. The image is converted into a binary image and improved by mathematical morphological operations. As a result of the operations performed, which of the five classes including un-cracked roads, superficial crack, crocodile crack, linear crack and transverse crack the roads belong to is determined. In the study carried out, the fact that it is fast and that its accuracy rates are good indicate that it can be used in real life.

The growing interest in photovoltaic systems has created a need for test devices required for these systems. PV panel emulators are needed to perform tests on photovoltaic systems and the devices used in them. Basically being DC power supplies, these emulators are controlled to have the same output characteristic as a PV panel and work in real time. The control systems of photovoltaic emulators contain a PV panel model whose accuracy affects the performance of the entire system. Therefore, in creating a PV panel model, mathematical modeling is preferred owing to its high accuracy. In this study, a five-parameter PV panel model has been used. Owing to the transcendental structure of this model, it cannot be analytically solved and requires numerical methods. The number of numerical iterations is rather important to the computational speed of the PV panel model and the numerical convergence time. Thus, real-time systems need to start with a well-suited initial value for iteration. This study proposed a new method for the initial value of numerical solution, and obtained rather favorable results compared to the other methods cited in the literature.

Reconfiguration process in photovoltaic (PV) arrays is very important to improve power-voltage characteristics of the system. In this paper, a new reconfiguration method based on neural network is proposed for PV arrays under partial shadow conditions. A new connection control algorithm based on artificial neural network is presented by the proposed method. This method includes fixed part and adaptive part and uses short circuit currents of PV panel group in every rows of adaptive and fixed part in array. A neural network used for reconfiguration strategy finds new configuration scheme of PV array. Then, adaptive parts are connected to rows of fixed part according to this configuration with switching matrix. Proposed approach has been verified with experimental results obtained using Beagle Board XM microprocessor board in real time for 3×4 array. As shown in results, many contributions such as an improvement in the output power of the PV array, an efficient reconfiguration strategy, real-time applicability, easy measurable parameters, and independence from panel types have been obtained with proposed method.