Browsing by Author "Ulucak, Oğuzhan"

Now showing 1 - 5 of 5

Citation Count: Kaak, Abdul Rahman Sabra...et al. (2024). "A novel CFD-ANN approach for plunger valve optimization: Cost-effective performance enhancement", Flow Measurement and Instrumentation, Vol. 97.
A novel CFD-ANN approach for plunger valve optimization: Cost-effective performance enhancement
(2024) Kaak, Abdul Rahman Sabra; Çelebioğlu, Kutay; Bozkuş, Zafer; Ulucak, Oğuzhan; Aylı, Ece; 265836
This paper introduces a novel computational fluid dynamics-artificial neural network (CFD-ANN) approach that has been devised to enhance the efficiency of plunger valves. The primary emphasis of this research is to achieve an optimal equilibrium between hydraulic flow and geometric configuration. This study is a novel contribution to the field as it explores the flow dynamics of plunger valves using Computational Fluid Dynamics (CFD) and proposes a unique methodology by incorporating Machine Learning (ML) for performance forecasting. An artificial neural network (ANN) architecture was developed using a thorough comprehension of flow physics and the impact of geometric parameters acquired through computational fluid dynamics (CFD). Using optimization, the primary aspects of the Artificial Neural Network (ANN), including the learning algorithm and the number of hidden layers, have been modified. This refinement has resulted in the development of an architecture exhibiting a remarkably high R2 value of 0.987. This architectural design was employed to optimize the plunger valve. By utilizing Artificial Neural Networks (ANN), a comprehensive analysis comprising 1000 distinct configurations was effectively performed, resulting in a significant reduction in time expenditure compared to relying on Computational Fluid Dynamics (CFD). The result was a refined arrangement that achieved maximum head loss, subsequently verified using computational fluid dynamics (CFD) simulations, resulting in a minimal discrepancy of 2.66%. The efficacy of artificial neural networks (ANN) becomes apparent due to their notable cost-efficiency, along with their capacity to produce outcomes that are arduous and expensive to get through conventional optimization research utilizing computational fluid dynamics (CFD).
Citation Count: Aylı, Ece; Ulucak, Oğuzhan (2020). "ANN and ANFIS Performance Prediction models for Francis type Turbines", Journal of Thermal Sciences and Technology, Vol. 40, No. 1, pp. 87-97.
ANN and ANFIS Performance Prediction models for Francis type Turbines
(2020) Aylı, Ece; Ulucak, Oğuzhan; 265836
Turbines can be operated under partial loading conditions due to the seasonal precipitation fluctuations and due to the needed electrical demand over time. According to this partial working need, designers generate hill chart diagrams to observe the system behavior under different flow rates and head values. In order to generate a hill chart, several numerical or experimental studies have been performed at different guide vane openings and head values which are very time consuming and expensive. In this study, the efficiency prediction of Francis turbines has been performed with ANN and ANFIS methods under different operating conditions and compared with simulation results. The obtained results indicate that it is possible to obtain a hill chart using ANFIS method instead of a costly experimental or numerical tests. ANN and ANFIS parameters which effect the output, have been optimized with trying 100 different cases. 75% of the numerical data set is used for training and 25 % is used for validation as testing data. To asses and compare the performance of multiple ANN and ANFIS models several statistical indicators have been used. Insight to the performance evaluation, it is seen that ANFIS can predict the efficiency distribution with higher accuracy than the ANN model. The developed ANFIS model predicts the efficiency with 1.41% mean average percentage error and 0.999 R-2 value. To the best of the author's knowledge, this is the first study in the literature that ANN and ANFIS are used in order to predict the efficiency distribution of the turbines at different loading conditions.
Citation Count: Ulucak, Oğuzhan...et al (2021). "Developing and Implementation of an Optimization Technique for Solar Chimney Power Plant With Machine Learning", Journal of Energy Resources Technology-Transactions of the ASME, Vol. 143, No. 5.
Developing and Implementation of an Optimization Technique for Solar Chimney Power Plant With Machine Learning
(2021) Ulucak, Oğuzhan; Koçak, Eyüp; Bayer, Özgür; Beldek, Ulaş; Yapıcı, Ekin Özgirgin; Aylı, Ece; 59950; 31329; 265836
Green energy has seen a huge surge of interest recently due to various environmental and financial reasons. To extract the most out of a renewable system and to go greener, new approaches are evolving. In this paper, the capability of Artificial Neural Network and Adaptive Neuro-Fuzzy Inference System in geometrical optimization of a solar chimney power plant (SCPP) to enhance generated power is investigated to reduce the time cost and errors when optimization is performed with numerical or experimental methods. It is seen that both properly constructed artificial neural networks (ANN) and adaptive-network-based fuzzy inference system (ANFIS) optimized geometries give higher performance than the numerical results. Also, to validate the accuracy of the ANN and ANFIS predictions, the obtained results are compared with the numerical results. Both soft computing methods over predict the power output values with MRE values of 12.36% and 7.25% for ANN and ANFIS, respectively. It is seen that by utilizing ANN and ANFIS algorithms, more power can be extracted from the SCPP system compared to conventional computational fluid dynamics (CFD) optimized geometry with trying a lot more geometries in a notably less time when it is compared with the numerical technique. It is worth mentioning that the optimization method that is developed can be implemented to all engineering problems that need geometric optimization to maximize or minimize the objective function.
Citation Count: Akar,S.;...et.al. (2023). "Prediction of the onset of shear localization based on machine learning", Artificial Intelligence for Engineering Design, Analysis and Manufacturing: AIEDAM, Vol.37.
Prediction of the onset of shear localization based on machine learning
(2023) Akar, Samet; Aylı, Ece; Ulucak, Oğuzhan; Uğurer, Doruk; 315516; 265836
Predicting the onset of shear localization is among the most challenging problems in machining. This phenomenon affects the process outputs, such as machining forces, surface quality, and machined part tolerances. To predict this phenomenon, analytical, experimental, and numerical methods (especially finite element analysis) are widely used. However, the limitations of each method hinder their industrial applications, demanding a reliable and time-saving approach to predict shear localization onset. Additionally, since this phenomenon largely depends on the type and parameters of the constitutive material model, any change in these parameters requires a new set of simulations, which puts further restrictions on the application of finite element modeling. This study aims to overcome the computational efficiency of the finite element method to predict the onset of shear localization when machining Ti6Al4V using machine learning methods. The obtained results demonstrate that the FCM (fuzzy c-means) clustering ANFIS (adaptive network-based fuzzy inference system) has given better results in both training and testing when it is compared to the ANN (artificial neural network) architecture with an R2 of 0.9981. Regarding this, the FCM-ANFIS is a good candidate to calculate the critical cutting speed. To the best of the authors' knowledge, this is the first study in the literature that uses a machine learning tool to predict shear localization.
Citation Count: Ulucak, Oğuzhan (2020). Rehabilitation of old francis turbines using reverse engineering and computational fluid dynamics simulations / Tersine mühendislik ve hesaplamalı akışkanlar dinamiği kullanılarak eski francis turbinlerin rehabilitasyonu. Yayımlanmış yüksek lisans tezi. Ankara: Çankaya Üniversitesi, Fen Bilimleri Enstitüsü.
Rehabilitation of old francis turbines using reverse engineering and computational fluid dynamics simulations
(2020) Ulucak, Oğuzhan
Son yıllarda, performans kaybı, güvenilirlik azalması ve sıklıkla bakım ihtiyacı nedeniyle su türbinlerin yenilenmesi ve yükseltilmesi giderek daha fazla talep edilmektedir. Rehabilitasyon sürecine başlamadan önce, santralin mevcut durumunu gösteren çalışmalar yapılması önem arz etmektedir. Verimlilik, üretilen güç ve güvenilirlikte azalmaya neden olan mevcut sorunları anlamadan rehabilitasyon sürecini başlatmak, performansta önemli bir artış olmadan ünitelerde gereksiz masraflara ve değişikliklere neden olabilir. Bu araştırmanın amacı, iyileştirme potansiyelini değerlendirmek ve operasyonel özelliklerin belirlenmesi amacıyla seçilen hidroelektrik santrallerinin Hesaplamalı Akışkan Dinamiği analizlerini yapmaktır. Bu amaçla öncelikle türbin parçaları sahada taranmış ve geleneksel tersine mühendislik adımlarını hidrolik türbinlerin akış dinamikleri ile birleştiren hibrit bir tersine mühendislik metodolojisi geliştirilmiştir. Beşinci bölümde, türbinin verimini ve güç çıkışını belirlemek için zamandan bağımsız analizler yapılmıştır ve böylece türbinin farklı düşü ve debi değerlerinde davranışını incelemek için bir tepe diyagramı oluşturulmuştur. Elde edilen HAD sonuçları saha ölçümleri ile karşılaştırılmıştır. HAD sonuçları, tam yük durumunda türbinin, üreticinin garantili değerleri ile tutarlı olan 51,56 MW güç çıkışı ile%93,8 verimliliğe sahip olduğunu göstermektedir. Çalışmanın altıncı bölümünde, türbin verimini düşüren sorunlar zamana bağlı analizler yapılarak tespit edilmiştir. HAD sonuçlarına göre, çark kanatlarında kavitasyon bölgeleri görülmektedir. Farklı kavitasyon mekanizmalarının tanımlanmasını sağlayan türbin teşhisi için geçici analiz ve görselleştirme teknikleri kullanılmaktadır. Sonuçlar, saha fotoğraflarında da görüldüğü üzere, kanadın, kuyruk kenarına yakın noktalarda kavitasyon olduğunu göstermektedir. Buna ek olarak, özellikle kısmi yük koşullarında, emme borusunda şiddetli girdaplar olduğu görülmektedir ve bu olgu santraldeki şiddetli titreşimlerin sebebidir. Geleneksel çark kanadının X-kanadına değiştirilmesinin performansı artırması ve kavitasyonu önleyeceği öngörülmektedir. Emme borusu konisi üzerindeki ilave kanatçıklar veya basınçlı su enjeksiyon sistemi ile çekiş borusu performansı artırılabilir ve bu da türbinin daha kararlı ve verimli çalışmasına neden olacaktır. Anahtar Kelimeler: Rehabilitasyon, HAD, Tersine Mühendislik, Francis Türbini, Yenilenebilir Enerji, Zamana-Bağlı Simulasyon