Cemal Yilmaz

Network induced delay of asynchronous motor connected to Profibus-DP networks using fuzzy logic control algorithm

In this study the remote control of an asynchronous motor (ASM) was performed by fuzzy logic. The study is substantially in the form of Profibus-DP network structure, ASM and fuzzy logic control (FLC). The aim of the study is to reduce the network-induced delay by the help of fuzzy logic algorithm and high speed data transfer feature of the Profibus-DP network structure. Also, the designed system was controlled by Proportional-Integral-Derivative (PID). Findings related to PID were compared with FLC. By the builded structure, the network-induced delay, the reaction time of the motor during remote control and the effect of the fuzzy logic algorithm in the application has been examined. The experimental analyses have been graphically presented. In these graphs, the network-induced delays have been presented by the structures in which only Profibus-DP network with PID was used firstly then the structure with FLC respectively.

Application of Symbiotic Organisms Search Algorithm to solve various economic load dispatch problems

This paper proposes the application of Symbiotic Organisms Search (SOS) Algorithm to solve the various Economic Load Dispatch (ELD) problems. Both classical ELD problem which has smooth fuel cost function and nonconvex ELD problem which has nonconvex and discontinuous fuel cost function due to considering of some practical constraints like valve point effects, ramp rate limits and prohibited generating zones have been solved in the study. Three different test cases have been used to show the efficiency and reliability of the proposed algorithm. 38-unit test system has been used for classical ELD and 3-unit and 15-unit test systems have been used for nonconvex ELD problem. Results have been compared to various heuristic methods reported before in the literature and they show that proposed algorithm converges to the global optimum in early iterations and can produce superior results than others in the solution of ELD problems which have both smooth and nonconvex and discontinuous fuel cost function.

A comperative study on novel machine learning algorithms for estimation of energy performance of residential buildings

This study aims to improve the energy performance of residential buildings. heating load (HL) and cooling load (CL) are considered as a measure of heating ventilation and air conditioning (HVAC) system in this process. In order to achive an effective estimation, hybrid machine learning algorithms including, artificial bee colony-based k-nearest neighbor (abc-knn), genetic algorithm-based knn (ga-knn), adaptive artificial neural network with genetic algorithm (ga-ann) and adaptive ann with artificial bee colony (abc-ann) are used. Results are compared classical knn and ann methods. Thence, relations between input and target parameters are defined and performance of well-known classical knn and ann is improved substantialy.

Asenkron Motorlarda Rotor Oluğunun Farklı Optimizasyon Yöntemleri ile Optimizasyonunun Gerçekleştirilmesi ve Performansa Etkilerinin İncelenmesi

Bu calismada asenkron motorlarda optimal rotor oluk olculerinin, Sequential Nonlineer Programming (SNP), Genetik Algoritma (GA) ve Sequential Mixed Integer NonLinear Programming (SMINP) yontemleri ile bulunmasi gerceklestirilmis ve karsilastirmali olarak motor performansina olan etkisi incelenmistir. Gerceklestirilen optimizasyon calismasindaki amac maksimum motor veriminin saglandigi oluk geometrisini elde etmektir. Simulasyon calismalari, Ansys Maxwell paket programi kullanilarak gerceklestirilmistir. Gerceklestirilen optimizasyon calismasi sonrasinda elde edilen rotor oluk geometrisine gore Ansys Maxwell 2D programinda motor modeli olusturulmus ve gerekli analizler gerceklestirilmistir. Elde edilen sonuclara gore, en verimli motor geometrisi GA algoritmasi kullanildiginda elde edilmektedir.

Developing of decision support system for land mine classification by meta-heuristic classifier

In this study, a decision support system has been developed for land mine detection and classification. Data obtained from detector based magnetic anomaly have been used to classify the land mines. With this classification, it is decided that whether obtained data belongs to a land mine or not, and the type of mine. The meta-heuristic k-NN classifier (HKC) has been used in developed decision support system. Consequently, it is seen that decision support system detects the presence of mines and decides the type of mine with 100% success for measurements in a certain range, and the proposed classifying method shows much higher performance than traditional instance-based classification method.