Yazar "Yilmaz, Ozgur" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • [ X ]
    Öğe
    Investigation of the Relationship between Vibration Signals Due to Oil Impurity and Cavitation Bubbles in Hydraulic Pumps
    (Mdpi, 2022) Yilmaz, Ozgur; Aksoy, Murat; Kesilmis, Zehan
    Although hydraulic pumps are frequently used in daily life, improper use due to oil analysis or oil contamination is ignored. There is no instantaneous inspection; instead, the oil is changed periodically at certain times, whether it is contaminated or not. Hydraulic systems operate based on Pascal's law, which states that the fluid will distribute the pressure equally to every point in a closed area. The fluid oil taken from an oil reservoir is moved into the pump by engine power. During this movement, as it passes through different pressure areas and different sections, undesirable events such as viscosity change and gas formation occur in the hydraulic oil. These formations collide with the outer walls and cause cavitation with respect to unwanted oil impurities. This cavitation causes unwanted vibration signals to occur in the normal working order of the system. As a result of cavitation, the particles that affect the lubricity and fluidity of the oil in the oil are mixed into the liquid and circulate freely. At the connection points, the blockage caused by the liquid in the pump cylinder block or the valve plate and the collisions of particles is effective. As a result, it creates vibrations of different frequencies. The frequency and amplitudes of these vibrations differ according to the degree of oil contamination. A method has been developed to find the degree of contamination of the oil circulating in the pump by looking at the amplitude and frequency of these vibrations measured from the motor body. There exist standards about the pollution of hydraulic fluid. With these standards, the maximum number of particles allowed for a given pollution level is defined. This topic is discussed in the conclusion to this study. This method has also been proven experimentally. Error and vibration analysis studies on pumps using a different approach are available in the literature. In these studies, pressure variation, total energy transmission, or artificial intelligence models were used to detect anomalies in the pump. In this study, the impurity rate of the oil was set at five different levels and the operating regime of the pump at each level was investigated experimentally. Rayleigh-Plesset and Zwart-Gerber-Belamri models, which are the most common cavitation models, were used to explain the bubble formation in the moving oil and the relationship of these bubbles with vibration. Frequency components were examined by the Discrete Fast Fourier Analysis method, where the operation of the pump was affected by the increase in oil impurity.
  • [ X ]
    Öğe
    Prediction of severe erectile dysfunction after penile fracture repair: machine learning analysis results from the reconstruction and trauma working group of the society of urological surgery (RAT-SUS)
    (Oxford University Press, 2025) Geyik, Serdar; Onder Yilmaz, Ismail; Zubaroglu, Mehmet; Deger, Mutlu; Kavak, Rahmi; Sari, Hilmi; Danacioglu, Yavuz Onur; Sertkaya, Caglar; Yilmaz, Mehmet; Haciobey, Ibrahim; Tipirdamaz, Mustafa; Dundar, Mehmet; Duran, Mesut Berkan; Sinirsiz, Can; Bayrak, Omer; Zeytun, Onur; Albaz, Alican; Demir, Murat; Goger, Yunus Emre; Ucar, Murat; Akgul, Burak; Arda, Ersan; Akarken, Ilker; Guzel, Ahmet; Kayra, Mehmet Vehbi; Kartal, Ibrahim Guven; Girgin, Reha; Baba, Dursun; Ceker, Gokhan; Ozen, Mehmet; Gurbuz, Ahmet; Yilmaz, Ozgur; Bozkurt, Ozan
    Background Erectile dysfunction (ED) is a significant complication following penile fracture repair, and early prediction is critical for clinical management.] Aim To evaluate the effectiveness of machine learning (ML) algorithms in predicting the development of severe ED after penile fracture repair and to identify complex risk factors beyond the scope of traditional statistical methods. Methods A retrospective analysis was conducted using data from 547 patients who underwent surgical repair for penile fracture between January 2020 and June 2024 at 23 urology centers affiliated with the Reconstructive Urology and Trauma Study Group of the Urological Surgery Society. Patients were categorized into two groups based on their International Index of Erectile Function-5 scores at six months postoperatively: severe ED (+) (<= 7) and ED (-) (>7). Eleven different ML classifiers were evaluated to determine the most predictive models. Four distinct resampling techniques were employed to address class imbalance in the dataset. Feature importance analysis was also performed to identify the most influential variables contributing to ED risk. Outcomes This study was conducted to enable the early identification of patients at high risk of developing severe ED following penile fracture surgery. Results Logistic Regression, Gaussian Naive Bayes, and Linear Support Vector Machine emerged as the best-performing algorithms on the original dataset, with Area Under the Curve (AUC) scores of 0.81, 0.78, and 0.76, respectively. On the Synthetic Minority Over-sampling Technique (SMOTE)-resampled dataset, Quadratic Discriminant Analysis (QDA) achieved an AUC of 0.85, while the Artificial Neural Network (ANN) reached an AUC of 0.84. On the SMOTE-resampled dataset, QDA achieved a ROC-AUC of 0.85 (95% CI: 0.75-0.93), whereas on the SMOTE-Tomek Link-resampled dataset, the ANN attained a ROC-AUC of 0.84 (95% CI: 0.71-0.94). The most critical predictors of severe ED were age, comorbidities, tunical tear length, and time to surgery. Urethral injuries were not significant contributors, as all were minor and managed conservatively without urethroplasty. Clinical Implications Integration of ML-based prediction models into clinical workflows could support early risk stratification and individualized patient care, ultimately improving postoperative functional outcomes. Strengths and Limitations This study benefits from a large, multicenter dataset and a comparative analysis of multiple ML algorithms. However, its retrospective nature and inter-center variability in data reporting may limit generalizability. Conclusion ML algorithms are effective and reliable tools for predicting severe ED after penile fracture repair and may enhance personalized postoperative management. Eliminating class imbalance in the data with resampling techniques improves model performance.