Yazar "Uluocak, Ihsan" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • [ X ]
    Öğe
    Artificial Intelligence-Based prediction of engine noise and vibration in Biodiesel-Diesel engines with hydrogen injection
    (Elsevier Sci Ltd, 2025) Uludamar, Erinc; Uluocak, Ihsan
    This paper studies the prediction of vibration and noise levels in a four-stroke, four-cylinder diesel engine fueled with biodiesel and diesel, alongside hydrogen injection through the inlet manifold using three distinct artificial intelligence techniques: Radial Basis Function Neural Network, Adaptive Neuro-Fuzzy Inference System, and Least-Squares Boosting. The objective of this study is to forecast noise and vibration at varied engine speed, biodiesel ratio, and hydrogen flowrate. In the study, the optimal number of learners for Least-Squares Boosting was determined to be 88, while the best spread number for Radial Basis Function Neural Network was 100. In addition, Adaptive Neuro-Fuzzy Inference System is configured with three Gbell membership functions. The results indicate that Radial Basis Function Neural Network and Least-Squares Boosting outperform Adaptive Neuro-Fuzzy Inference System, with the best mean average percent errors and R2 values for the developed models being 0.9929, 0.9973, and 0.9233 for vibration acceleration and 0.9991, 0.9971, and 0.9901 for noise, respectively. Ultimately, it is concluded that the Radial Basis Function Neural Network and Least-Squares Boosting methods are effective choices for simulating and predicting the noise and vibration of biodiesel fueled, hydrogen aspirated diesel engine.
  • [ X ]
    Öğe
    Comparative evaluation of machine learning models for predicting noise and vibration of a biodiesel-CNG fuelled diesel engine
    (Elsevier Sci Ltd, 2025) Uluocak, Ihsan; Uludamar, Erinc
    Improving engine operation through the implementation of intelligent modelling is crucial for reducing vibration and noise. For this reason, In the present study, advanced machine learning models including Radial Basis Function Neural Network (RBFNN), General Regression Neural Network (GRNN), Support Vector Machine (SVM), and ensemble models with Least Squares Boosting (LSboost) are employed to predict noise and vibration of a diesel engine. The engine is fuelled with low-sulphur diesel, sunflower biodiesel-diesel blends at 20 % and 40 % by volume and compressed natural gas (CNG) added through the intake manifold at various flow rates. Noise and vibration data were gathered at intervals of 300 rpm between 1200 rpm and 2400 rpm. Results show that the among proposed models, for noise predictions, GRNN yield the best results among all models with R2 accuracy of 0.9983 and Theil U2 of 0.073. Meanwhile, in the lights of vibration results, RBFNN outperforms other models with R2 accuracy of 0.9968 and Theil U2 of 0.214.
  • [ X ]
    Öğe
    Future forecast of global mean surface temperature using machine learning and conventional time series methods
    (Springer Wien, 2025) Durhasan, Tahir; Pinar, Engin; Uluocak, Ihsan; Bilgili, Mehmet
    One of the most important indicators of climate change and, consequently, global warming is the rise in the average surface temperature of the entire world. As observed in this light, forecasting the global mean surface temperature is an essential issue that must be addressed to develop adaptation measures for climate change. Many models have been developed to forecast the temperature of the air; however, these models often concentrate on local areas or use a restricted amount of station data. In this study, seasonal autoregressive integrated moving average (SARIMA), long-short-term memory (LSTM), and gated recurrent unit (GRU) models are used to predict global mean surface temperature (GMST) data. The data sets used in the study are GISTEMP and HardCRUT datasets and consist of land surface air temperature and water surface temperature. An evaluation of the performance of the models is carried out using various error measures to guarantee a high level of prediction accuracy. All models' results indicate that the yearly GMST value increase relative to 1961-1990 will be between 0.94 oC and 1.45 oC in 2050. In addition, the yearly GMST value, measured as approximately 14.8-15.00 oC in 2022, will be between 15.15 oC and 15.43 oC in 2050, according to the obtained models.