Person:
ÖZTÜRK, FERRUH

Loading...
Profile Picture

Email Address

Birth Date

Research Projects

Organizational Units

Job Title

Last Name

ÖZTÜRK

First Name

FERRUH

Name

Search Results

Now showing 1 - 10 of 18
  • Publication
    Smart cooling design using dual loop cooling to increase engine efficiency and decrease fuel emissions with artificial intelligence
    (Elsevier, 2022-10-26) Kula, Sinan; Bulut, Emre; Altay, Esad; Sümer, Osman; Öztürk, Ferruh; Kula, Sinan; BULUT, EMRE; ÖZTÜRK, FERRUH; Mühendislik Fakültesi; Otomotiv Mühendisliği Bölümü; 0000-0001-9159-5000; JCO-2416-2023; HGN-4395-2022; JGV-6240-2023
    In this study, smart cooling design and optimization, which is based on dual loop cooling system, is used to increase the efficiency of the engine and decrease the fuel emission levels with the artificial intelligence approach. Dual circuit cooling system is used to cool down the charged air and condenser for the 1.6 lt turbocharged diesel engine. The main objective is to increase the efficiency of the engine and decrease the fuel emission levels with smart cooling system design using 1D analysis, experimental tests and neural networks. Water-cooled air charger and condenser are placed separately on engine bay. Whereas, similar applications have been used for these modules integrated on the engine itself. Artificial Neural Network approach is applied in order to optimize the water cooled air charger sizing. Input data is generated by using 1D model within the correlation of experimental test results both on dyno and road conditions. Experimental and 1D analysis data comparison shows that they are very coherent. Results showed that efficiency of the engine is increased and CO2 (g/km) emission levels are decreased about 4,1% in WLTP cycle. It's obtained with efficient dual loop cooling system and optimization based on 1D model and ANN approach.
  • Publication
    A comparative study on conventional and hybrid quenching hot forming methods of 22mnb5 steel for mechanical properties and microstructure
    (Springer, 2022-08-01) Eşiyok, Ferdi; Ertan, Rukiye; Sevilgen, Gökhan; Bulut, Emre; Özturk, Ferruh; Alyay, İlhan; Abi, Tuğçe Turan; ERTAN, RUKİYE; SEVİLGEN, GÖKHAN; BULUT, EMRE; ÖZTÜRK, FERRUH; Mühendislik Fakültesi; Otomotiv Mühendisliği Bölümü; 0000-0002-7746-2014; 0000-0001-9159-5000; KIH-2391-2024; JIW-7185-2023; JCO-2416-2023; ABG-3444-2020
    In this paper, the conventional hot forming and hybrid quenching hot forming processes of Al-Si-coated 22MnB5 steel sheet were investigated and compared at 0.5 s-15 s holding times in the press tool related to the mechanical properties, microstructure, and dimensional accuracy. The conventional hot forming method is classified as a direct method and an indirect method. Both methods have limitations due to processing time and cooling of the press tool. To speed up the process, an alternative cooling method based on spray or jet cooling was used outside of the die tool. The hybrid quenching method involves hot forming and spray cooling process. This method, using spray parameters, provides more effective control in mechanical properties and microstructure compared to the conventional method by using spray parameters. Vickers hardness tests and tensile tests were carried out to compare mechanical properties. Changes in the microstructure of the materials were investigated using an optical microscope. The results show that spray cooling can be used as part of quenching in the hot forming process by reducing the holding time in the press tool by 97%. However, the microstructure, mechanical properties, and geometry deviations of the stamped parts are still below tolerances after the hybrid quenching hot forming process. The use of the hybrid quenching method with multi-point nozzles in the hot forming process resulted in sheet hardness up to 470 HV1 and 8% elongation with tensile strength of 1500 MPa.
  • Publication
    Correlation between objective and subjective tests for vehicle ride comfort evaluations
    (Sage Publications Ltd, 2022-02-23) Boke, Tevfik Ali; Bozkurt, Rasim; Ergül, Murat; Özturk, Dogan; Emiroğlu, Sinan; KAYA, NECMETTİN; Albak, Emre Isa; Öztürk, Ferruh; ALBAK, EMRE İSA; ÖZTÜRK, FERRUH; Gemlik Asım Kocabıyık Meslek Yüksekokulu; Makine Mühendisliği Bölümü; 0000-0001-9215-0775; 0000-0002-8297-0777; I-9483-2017
    One of the most important criteria that vehicle customers take into consideration when buying vehicles is ride comfort. Ride comfort is determined in two different ways, called objective and subjective methods. This research presents an approach for subjective and objective evaluations of vehicle ride comfort through road tests. In this study, first, reliable driver evaluation for subjective tests is made and tests are performed with these reliable drivers. Correlation between objective and subjective test results is achieved for different vehicle types and road groups and software is developed to evaluate subjective ride comfort by using objective test data acquired from the vehicle. This software is intended to be used instead of subjective tests in future vehicle development studies.
  • Publication
    Predictions of the design decisions for vehicle alloy wheel rims using neural network
    (Sage Publications Ltd, 2022-08-02) Topaloğlu, Anıl; Kaya, Necmettin; Öztürk, Ferruh; Topaloğlu, Anıl; KAYA, NECMETTİN; ÖZTÜRK, FERRUH; Mühendislik Fakültesi; Otomotiv Mühendisliği Bölümü; 0000-0002-8297-0777; GPL-5775-2022; R-4929-2018; JIW-7185-2023
    The weight and modal performance of the vehicle wheels are two essential factors that affect the driving comfort of a vehicle. The main objective of this study is to present an efficient approach to reduce the weight and enhance the modal performance of the wheel by reducing the design time and computational cost. The alloy wheel rim is often used for lightweight wheel design. In this study, an approach is presented for the lightweight design of alloy wheel rims. An intelligent approach based on neural networks (NNs) is introduced to predict the optimum design parameters of the wheel rim during the wheel design phase and to improve the wheel optimization process. The Latin hypercube and Hammersley designs of the experimental methods were used to obtain a training dataset with finite element analysis. The NN and multiple linear regression (MLR) models were trained to predict the weight, first-mode frequency, and displacement values. A multi-objective genetic algorithm was employed to optimize the design decisions based on the predicted values. It was used to compute the optimum results with both the NN and MLR models for a better prediction accuracy of the wheel rim design parameters. The proposed approach allows designers to optimize design decisions and evaluate design modifications during the early stages of the wheel development phase. The surrogate-based optimization method plays an important role in the wheel rim optimization process, particularly when the optimization model is established based on computationally expensive finite element simulations, testing, and prototypes. The results show the effectiveness of the NN-combined genetic optimization approach in predicting the responses and optimizing the design decisions for the alloy wheel rim design by reducing engineering time and computational cost.
  • Publication
    Prediction of self-loosening mechanism and behavior of bolted joints on automotive chassis using artificial intelligence
    (MDPI, 2023-09-01) Güler, Birtan; Sengör, Özgür; Yavuz, Onur; Öztürk, Ferruh; Güler, Birtan; ÖZTÜRK, FERRUH; Otomotiv Mühendisliği Bölümü; EXX-4814-2022; FRD-1816-2022
    The tightening torque values considered in the assembly of vehicle subparts are of great importance in terms of connection safety. The torque value to be selected is different for each bolted joint type with respect to mechanical features. While the tightening torque value is an important indicator, the bolt preloading value is always a more reliable parameter in terms of whether a secure tightening can be achieved or not. For this reason, when it is desired to create reliable joints, the preloading value that the tightening torque input will create on the connection package should be calculated well. This study presents an integrated approach using Taguchi method (TM) and neural network (NN) to predict the self-loosening mechanism of bolted joints in automotive chassis engine suspension connections. External loading acting on the joints of the engine suspension was collected from bench tests. NN was applied to establish the relationship between controlled factors and loosening rate. The results showed that the proposed approach can be used to predict mechanism of self-loosening and behavior of bolted joints without additional tests, and it is possible to make predictions with very low error rates using artificial intelligence techniques.
  • Publication
    Estimation of energy management strategy using neural-network-based surrogate model for range extended vehicle
    (Mdpi, 2022-12-14) Türker, Erkan; Bulut, Emre; Kahraman, Arda; Çakıcı, Mehmet; Öztürk, Ferruh; Türker, Erkan; BULUT, EMRE; ÖZTÜRK, FERRUH; Mühendislik Fakültesi; Otomotiv Mühendisliği Bölümü; 0000-0001-9159-5000; 0000-0003-0150-8052; JCO-2416-2023; AAG-8907-2021; CDI-5654-2022; JIW-7185-2023
    In this paper, an energy-management strategy based on fuel economy is presented to achieve a further range increase for range-extended light commercial vehicles. Estimation of the energy-management strategy was carried out using a neural-network-based surrogate model for an range-extended vehicle. Surrogate-based optimization plays an important role in optimization problems, which are based on complex structures with uncertainties in data sets due to various conditions. Neural networks have advantages in creating surrogate-based models in cases of complex problems with uncertainties in data sets to evaluate the process and estimate the outputs. This study discusses additional power-unit applications and vehicle integration for a light commercial electric vehicle. It provides preliminary design work and techniques for identifying NVH problems in particular. SIMULINK and neural-network-based surrogate models are established, and the changeable parameters of the vehicle, such as mass, battery/fuel-tank capacity, internal combustion engine power and electric motor power units are simulated in different dynamic and static conditions to determine an energy-management strategy for a range-extended vehicle based on fuel economy under various conditions. It was seen that APU parameters and an energy-management strategy significantly affected the fuel consumption of REX. A neural-network-based surrogate-model approach gave high-precision results in predicting the operating strategy according to different loading conditions to reduce fuel consumption. In some cases, it can be required to determine the fuel consumption results in various conditions with the variables, which may be out-of-boundary conditions. It was seen that the proposed neural-network-model also offers higher prediction ability in cases of unexpected results in data sets of various conditions compared to regression analysis. The results show that estimation and optimization of energy management using a neural-network-based surrogate model can be achieved by adapting the operating strategy according to different loading conditions to reduce fuel consumption. This study presents an approach for future new vehicle projects by transforming a prototype light commercial electric vehicle to REX. The proposed approach was developed to design the most efficient range-extended vehicle by changing all variables without costly computations and time-consuming analysis. It is possible to generate variable data sets and to have reference knowledge for future vehicle projects.
  • Publication
    Simplified optimization model and analysis of twist beam rear suspension system
    (Sage Publications, 2021-04-01) Albak, Emre İsa; Solmaz, Erol; Öztürk, Ferruh; ALBAK, EMRE İSA; SOLMAZ, EROL; ÖZTÜRK, FERRUH; Mühendislik Fakültesi; Otomotiv Mühendisliği Bölümü; 0000-0001-9215-0775; 0000-0001-9369-3552; I-9483-2017; HRA-1531-2023; FRD-1816-2022
    Twist beam rear suspension systems are frequently used in front wheel drive cars owing to their compactness, lightweight and cost-efficiency. Since the kinematic behavior of twist beam rear suspension systems are determined by the elastic properties of the twist beam, the twist beam is the most critical component of this suspension system. In the study, a simplified optimization model is presented to offer designers the most suitable beam structure in the early stage of the vehicle system development. With the optimization model, designers will be able to obtain the most suitable twist beam structure in a very short time. Opposite wheel travel analysis based on finite element modeling of twist beam is conducted to examine the kinematic performance of the twist beam rear suspension. The cross-section, position and direction of the twist beam are the most important parameters affecting the performance of the twist beam rear suspension system. In this study, optimization studies with 25 design variables including variable cross-sections, twist beam position and twist beam orientation are performed. Nine different optimization studies are carried out to investigate the effects of design variables better. In optimization studies carried out with the genetic algorithm, the objective and constraint functions are obtained with the moving least squares meta-modeling method. In the study, toe angle, camber angle and roll steer are decided as constraints, and mass as the objective function. With the optimization models, lightweight designs up to 25% have been obtained according to the initial design. It is validated that the proposed simplified model and analysis of twist beam rear suspension with connecting bushing is a quite efficient approach in terms of accuracy and to speed up the optimum design process.
  • Publication
    Kinematics & compliance validation of a vehicle suspension and steering kinematics optimization using neural networks
    (Kaunas Univ Technol, 2023-01-01) Agakisi, Gurur; Öztürk, Ferruh; ÖZTÜRK, FERRUH; Mühendislik Fakültesi; Otomotiv Mühendisliği Bölümü; FRD-1816-2022
    Physical and virtual K & C analyses are performed to achieve the vehicle dynamics targets by finding the opti-mum variables such as the position of hardpoints or stiff-nesses of bushings. However, finding appropriate design variables that meet all the aims is challenging. This paper evaluates a hardpoint optimization approach to attain sus-pension K & C characteristic objectives with the design of experiments, neural networks, and genetic algorithm, based on a reference compact-sized prototype vehicle. The MBD model correlation is provided to optimize the hardpoints to improve the vehicle's steering kinematics concerning Ackerman error and camber angle variation that are out of target in baseline suspension. The results showed that NN based optimization strategy to define the hardpoints has sig-nificantly improved targeted characteristics compared to conventional response surface methods in the limited design space.
  • Publication
    Multiobjective crashworthiness optimization of graphene type multi-cell tubes under various loading conditions (vol 43, 266, 2021)
    (Springer Heidelberg, 2021-06-01) Albak, Emre İsa; ALBAK, EMRE İSA; Solmaz, Erol; SOLMAZ, EROL; Öztürk, Ferruh; ÖZTÜRK, FERRUH; Yıldız, Ali Rıza; YILDIZ, ALİ RIZA; Mühendislik Fakültesi; Otomotiv Mühendisliği Bölümü; 0000-0001-9215-0775; 0000-0003-1790-6987; F-7426-2011; I-9483-2017
  • Publication
    Optimal design of differential mount using nature-inspired optimization methods
    (Walter de Gruyter Gmbh, 2021-08-31) Albak, Emre İsa; Solmaz, Erol; Öztürk, Ferruh; ALBAK, EMRE İSA; SOLMAZ, EROL; ÖZTÜRK, FERRUH; Hibrit ve Elektrikli Araç Teknolojisi Programı; 0000-0001-9215-0775; I-9483-2017; DTV-6021-2022; JHZ-3155-2023
    Structural performance and lightweight design are a significant challenge in the automotive industry. Optimization methods are essential tools to overcome this challenge. Recently, nature-inspired optimization methods have been widely used to find optimum design variables for the weight reduction process. The objective of this study is to investigate the best differential mount design using nature-based optimum design techniques for weight reduction. The performances of the nature-based algorithms are tested using convergence speed, solution quality, and robustness to find the best design outlines. In order to examine the structural performance of the differential mount, static analyses are performed using the finite element method. In the first step of the optimization study, a sampling space is generated by the Latin hypercube sampling method. Then the radial basis function metamodeling technique is used to create the surrogate models. Finally, differential mount optimization is performed by using genetic algorithms (GA), particle swarm optimization (PSO), grey wolf optimizer (GWO), moth-flame optimization (MFO), ant lion optimizer (ALO) and dragonfly algorithm (DA), and the results are compared. All methods except PSO gave good and close results. Considering solution quality, robustness and convergence speed data, the best optimization methods were found to be MFO and ALO. As a result of the optimization, the differential mount weight is reduced by 14.6 wt.-% compared to the initial design.