Yazar "Soyler, Huseyin" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • [ X ]
    Öğe
    A New Approach for Improving Biodiesel Conversion Efficiency: A Stacking Ensemble Model Based on Linear Regression Approach with GAN-Enhanced
    (Springer Heidelberg, 2025) Karaoglu, Ahmet; Soyler, Huseyin
    This study employs a Linear Regression-based stacking ensemble learning approach as a novel method to enhance biodiesel conversion efficiency. Initially, a dataset derived from the literature was used to train an ensemble model that combines predictions from Random Forest, XGBoost, and Deep Neural Network (DNN) through a Linear Regression-based fusion approach. This model outperformed individual models (Random Forest: - 0.16, XGBoost: - 0.67, and DNN: 0.36) by achieving an R2 score of 0.45. To further improve model performance, 4900 synthetic data samples were generated and integrated into the dataset. Leveraging the stacking ensemble learning approach with this expanded dataset, the model demonstrated a significant improvement in predictive accuracy, achieving an R2 score of 0.81. This corresponds to an approximate 4% increase in performance compared to individual models (Random Forest: 0.78, XGBoost: 0.78, and DNN: 0.77), highlighting the effectiveness of ensemble learning in optimizing biodiesel conversion efficiency. Additionally, the model exhibited high accuracy with low error rates (MAE: 1.16 and MAPE: 1.24%), effectively compensating for the weaknesses of individual models and providing more stable and generalized predictions. To the best of our knowledge, this is the first study to incorporate a Linear Regression-based stacking method to enhance biodiesel conversion efficiency. These findings underscore the potential of ensemble learning techniques and synthetic data integration in improving renewable fuel efficiency. Future research can further enhance model performance by incorporating larger datasets and exploring more advanced ensemble strategies.
  • [ X ]
    Öğe
    Chemical fingerprinting and cluster-based evaluation of vegetable oils for biodiesel applications
    (Elsevier, 2025) Soyler, Huseyin; Balki, Mustafa Kemal
    This study evaluates the biodiesel potential of five vegetable oils-safflower, flaxseed, rapeseed, niger seed, and perilla through detailed analysis of their fatty acid composition and key fuel properties. Gas chromatography mass spectrometry (GC-MS/MS) was used to characterize the oils and quantify their saturated, monounsaturated, and polyunsaturated fatty acid contents. The impact of fatty acid profiles on cetane number, oxidative stability, viscosity, and cold-flow behavior was assessed. Hierarchical and K-Means clustering techniques identified chemical similarities and guided the development of optimized blending strategies. Results showed that rapeseed and safflower oils, with high monounsaturated fatty acid content, provided superior oxidative stability and combustion performance. In contrast, flaxseed and perilla oils offered improved cold-flow properties but required stabilization to enhance storage life. Based on these findings, nine biodiesel blend formulations were proposed to balance fuel quality and adapt to different operational conditions. This research demonstrates that integrating chemical fingerprinting and clustering analysis can effectively support feedstock selection and biodiesel optimization.
  • [ X ]
    Öğe
    Determination of optimum parameters for esterification in high free fatty acid olive oil and ultrasound-assisted biodiesel production
    (Springer Heidelberg, 2023) Soyler, Huseyin; Balki, Mustafa Kemal; Sayin, Cenk
    In this study, biodiesel was produced from high free fatty acid (FFA) oil obtained from waste olives, whose food quality deteriorated by falling from the tree to the ground. The FFA value of the oil obtained from waste olives was determined as 23% by titration method. In order to produce biodiesel with high conversion efficiency, esterification process was carried out to reach at least 1% FFA value in the first stage of the study. Acid esterification experiments were designed according to Taguchi's L-16 (4(2) 2(1)) orthogonal array. The amount of sulfuric acid catalyst, methanol ratio, and mixing speed were taken as the test variables for the esterification process. For the lowest FFA value, optimum test parameters were determined using the signal-to-noise (S/N) ratio. In the biodiesel production stage, ultrasound-assisted transesterification method was preferred in terms of high conversion efficiency and short reaction duration. According to the results, it was determined that the optimum reaction conditions in the esterification process were 25% by weight acid catalyst (according to the weight of the FFA in the oil), 22:1 methanol molar ratio in terms of fatty acids, and 400 rpm mixing speed. At these reaction conditions, the FFA of the oil was reduced from 23 to 0.608% in a single step. In the ultrasound-assisted process, Waste olive oil methyl ester (WOOME) conversion yield of 98.7% was achieved in a reaction time of 10 min. The fuel properties of WOOME (also called biodiesel) were determined to be within the EN 14214 standard. As a result, optimization was made to minimize the use of alcohol and catalyst in the acid esterification process. Also, time and energy savings were achieved in biodiesel production with ultrasound-assisted.