Yazar "Yildirim, Sahin" seçeneğine göre listele

Listeleniyor 1 - 7 / 7
  • Küçük Resim Yok
    Öğe
    DESIGN OF A PROPOSED NEURAL NETWORK FOR SOUND QUALITY ANALYSIS OF DIFFERENT TYPES FOR CAR SYSTEMS
    (Cefin Publishing House, 2024) Yildirim, Sahin; Bingol, Mehmet Safa
    Nowadays, in spite of advanced technology, there are still some sound problems on modern cars because of mechanical parts, oil lubrications, and electric motors. Due to these unwanted problems, it is necessary to design intelligent predictors such as artificial neural networks. In this investigation, a procedure of testing and evaluation on the sound quality of two types of cars are proposed and sound quality is analyzed through the cars road running test on the providing ground, which is carried out with varying running speed. To improve and predict the results of experimental approach analysis, a proposed neural network predictor is also designed to model of the system for possible experimental applications. The proposed neural network is a feedforward type network, which consists of multi hidden layers. Three different training algorithms are used for training the network. As basic factors for sound quality, only objective factors a considered such as loudness, sharpness, speech intelligibility, sound pressure level. The correlation between sound pressure level and other factors are discussed from a point of view of running speed dependency. Results of both computer simulations and experiments show that the neural predictor algorithm gives good results at accommodating different cases and provides superior prediction on two cars’s sound analysis. © 2024, Cefin Publishing House. All rights reserved.
  • Küçük Resim Yok
    Öğe
    Design of artificial neural networks for rotor dynamics analysis of rotating machine systems (Retraction of vol 15, pg 573, 2005)
    (PERGAMON-ELSEVIER SCIENCE LTD, 2013) Kalkat, Menderes; Yildirim, Sahin; Uzmay, Ibrahim
    [Abstract Not Available]
  • Küçük Resim Yok
    Öğe
    DESIGN OF INTELLIGENT CRUISE CONTROLLER OF MOTOR VEHICLES
    (Cefin Publishing House, 2023) Yildirim, Sahin; Bingol, Mehmet Safa; Savas, Sertac
    Nowadays, due to traffic jam and many cars on traffic, it is very necessary to control the distance between cars and obstacle. Many car producers have been designed and manufacture Cruise Control Systems for cars. Reinforcement learning, one of the popular artificial intelligence techniques, is a method used to train autonomous systems in many different fields. In this simulation study, the adaptive cruise control (ACC) of a ring bus serving in the campus area is controlled with Deep Deterministic Policy Gradient, which is one of the reinforcement learning methods. This simulation study is carried out considering the speed limit in the campus area and the acceleration values required for a comfortable journey of the passengers. Acceleration, velocity and distance values are given with graphs. Consequently; the proposal neural predictor has superior performance to adapt and predict the distance, velocity and acceleration of ego vehicle (bus). © 2023, Cefin Publishing House. All rights reserved.
  • Küçük Resim Yok
    Öğe
    Force analysis of bearings on a modified mechanism using proposed recurrent hybrid neural networks
    (KOREAN SOC MECHANICAL ENGINEERS, 2008) Yildirim, Sahin; Eski, Ikbal; Kalkat, Menderes
    Due to different load conditions on four-bar mechanisms, it is necessary to analyze force distribution on the bearing systems of mechanisms. A proposed neural network was developed and designed to analyze force distribution on the bearings of a four bar mechanism. The proposed neural network has three layers: input layer, output layer and hidden layer. The hidden layer consists of a recurrent structure to keep dynamic memory for later use. The mechanism is an extended version of a four-bar mechanism. Two elements, spring and viscous, are employed to overcome big force problem on the bearings of the mechanism. The results of the proposed neural network give superior performance for analyzing the forces on the bearings of the four-bar mechanism undergoing big forces and high repetitive motion tracking. This continuation of simulation analysis of bearings should be a benefit to bearing designers and researchers of such mechanisms.
  • Küçük Resim Yok
    Öğe
    NEURAL PREDICTOR DESIGN FOR COVID-19 CASES IN DIFFERENT REGIONS
    (Cefin Publishing House, 2023) Yildirim, Sahin; Durmusoglu, Aslı; Sevim, Caglar; Bingol, Mehmet Safa; Kalkat, Menderes
    COVID-19, which emerged in the past years, has affected human life in many different ways. The COVID-19 virus has spread very quickly around the world and has become a pandemic. In many applications, artificial neural networks are used to estimate system parameters in real-time or simulation-based methods. In this study, the daily and total number of cases in Turkey, Italy and India are predicted. Three alternative areas, with or without following rules, are chosen for the COVID-19 cases. For this prediction process, 3 different neural network methods are used: Nonlinear autoregressive neural network (NAR-NN), Adaptive-Network Based Fuzzy Inference Systems (ANFIS) and Autoregressive integrated moving average (ARIMA). The results obtained for 3 different neural networks are given with graphs and tables. The conclusion of this study may be used to improve the precaution for the pandemic. © 2023, Cefin Publishing House. All rights reserved.
  • Küçük Resim Yok
    Öğe
    Oils quality and performance analysis of vehicle's engines using radial basis neural networks
    (EMERALD GROUP PUBLISHING LTD, 2009) Kalkat, Menderes; Yildirim, Sahin; Erkaya, Selcuk
    Purpose - The purpose of this paper is to improve the application of neural networks on vehicle engine systems for fault detecting and analysing engine oils. Design/methodology/approach - Three types of neural networks are employed to find exact neural network predictor of vehicle engine oil performance and quality. Nevertheless, two oil types are analysed for predicting performance in the engine. These oils are used and unused oils. In experimental work, two accelerometers are located at the bottom of the car engine to measure related vibrations for analysing oil quality of both cases. Findings - The results of both computer simulation and experimental work show that the radial basis neural network predictor gives good performance at adapting different cases. Research limitations/implications - The results of the proposed neural network analyser follow the desired results of the vehicle engine's vibration variation. However, this kind of neural network scheme can be used to analyse oil quality of the car in experimental applications. Practical implications - As theoretical and practical studies are evaluated together, it is hoped that oil analysers and interested researchers will obtain significant results in this application area. Originality/value - This paper is an original contribution on vehicle oil quality analysis using a proposed artificial neural network and it should be helpful for industrial applications of vehicle oil quality analysis and fault detection.
  • Küçük Resim Yok
    Öğe
    Tuning the Proportional-Integral-Derivative Control Parameters of Unmanned Aerial Vehicles Using Artificial Neural Networks for Point-to-Point Trajectory Approach
    (Mdpi, 2024) Ulu, Burak; Savas, Sertac; Ergin, Oemer Faruk; Ulu, Banu; Kirnap, Ahmet; Bingoel, Mehmet Safa; Yildirim, Sahin
    Nowadays, trajectory control is a significant issue for unmanned micro aerial vehicles (MAVs) due to large disturbances such as wind and storms. Trajectory control is typically implemented using a proportional-integral-derivative (PID) controller. In order to achieve high accuracy in trajectory tracking, it is essential to set the PID gain parameters to optimum values. For this reason, separate gain values are set for roll, pitch and yaw movements before autonomous flight in quadrotor systems. Traditionally, this adjustment is performed manually or automatically in autotune mode. Given the constraints of narrow orchard corridors, the use of manual or autotune mode is neither practical nor effective, as the quadrotor system has to fly in narrow apple orchard corridors covered with hail nets. These reasons require the development of an innovative solution specific to quadrotor vehicles designed for constrained areas such as apple orchards. This paper recognizes the need for effective trajectory control in quadrotors and proposes a novel neural network-based approach to tuning the optimal PID control parameters. This new approach not only improves trajectory control efficiency but also addresses the unique challenges posed by environments with constrained locational characteristics. Flight simulations using the proposed neural network models have demonstrated successful trajectory tracking performance and highlighted the superiority of the feed-forward back propagation network (FFBPN), especially in latitude tracking within 7.52745 x 10-5 RMSE trajectory error. Simulation results support the high performance of the proposed approach for the development of automatic flight capabilities in challenging environments.