Browsing by Author "Karacor, M"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Comparison of Artificial Neural Network and Fuzzy Logic Approaches for the Prediction of In-Cylinder Pressure in a Spark Ignition Engine
    Solmaz, Ö; Gürbüz, H; Karacor, M
    In first stage, a machine learning (ML) was performed to predict in-cylinder pressure using both fuzzy logic (FL) and artificial neural networks (ANN) depending on the results of experimental studies in a spark ignition (SI) engine. In the ML phase, the experimental in-cylinder pressure data of SI engine was used. SI engine was operated at stoichiometric air-fuel mixture (phi = 1.0) at 1200, 1400, and 1600 rpm engine speeds. Six different ignition timings, ranging from 15 to 45 degrees CA, were used for each engine speed. Correlations (R-2) between data from in-cylinder pressure obtained via FL and ANN models and data form experimental in-cylinder pressure were determined. R(2)values over 0.995 were obtained at an ML stage of ANN model for all test conditions of the engine. However, R(2)values were remained between range of 0.820-0.949 with the FL model for different engine speeds and ignition timings. In the second stage, in-cylinder pressure prediction was performed by using an ANN model for engine operating conditions where no experimental results were obtained. Furthermore, indicated mean effective pressure (IMEP) values were calculated by predicting in-cylinder pressure data for different engine operation conditions, and then compared with experimental IMEP values. The results show that the in-cylinder pressure and IMEP results estimated with the trained ANN model are fairly close to the experimental results. Moreover, it was found that using the trained ANN model, the ignition timing corresponding to the maximum brake torque (MBT) used in the engine management systems and engine studies could be determined with high accuracy.
  • No Thumbnail Available
    Item
    Principle, design and analysis of a novel axial flux switched reluctance machine with fully pitched winding structure
    Sahin, C; Karacor, M
    In this study, the fully pitched axial flux switched reluctance machine (FP-AFSRM), which is a new configuration in the literature, was designed and 3D magnetostatic analyses were performed. The focus of the study is to produce higher torque density by simply changing the winding structure. Conventional SRMs are also known as short pitched SRM (SPSRM) since they have a short pitched winding structure. Fully pitched SRMs (FPSRMs) produce higher torque compared to SPSRMs with the mutual coupling effect between phases due to their fully pitched winding structure. In parallel with that, especially for electric vehicles, axial designs have increased gradually instead of radial design of electrical machines. For this purpose, the FP-AFSRM structure was proposed by combining axial design and fully pitched winding structure. The proposed FP-AFSRM model achieved up to 15.07% higher torque density than the basic SP-AFSRM model at different currents and equal copper losses. The proposed FP-AFSRM can be considered as an important alternative machine, especially for electric vehicle technologies and different technological fields, with the advantages of the high torque density and axial geometric structure.