Development of Bolted Flange Design Tool Based on Finite Element Analysis and Artificial Neural Network

Yıldırım, Alper; Akay, Ahmet Arda; Gülaşık, Hasan; Çöker, Demirkan; Gürses, Ercan; Kayran, Altan

doi:10.1115/imece2015-51021

Cited by 3 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike probabilistic models, deterministic models do not allow for randomness, and one always gets the same output for a specific input. The quantity and quality of input data will affect the accuracy of the parameters correlation study [13]. In a parametric study, all the input parameters have a differential effect on the output parameters.…”

Section: Introductionmentioning

confidence: 99%

Parametric Correlation between Different Parameters of a Straight Subsoiler

Allaie

D’souza

Moses

et al. 2021

CJAST

View full text Add to dashboard Cite

Agricultural subsoilers are used to break the hardpans below the level of the tillage depth. Weight reduction without compromising safety is one of the primary design objectives of the subsoiler. The thickness, length of curve, and width of shank are all critical parameters in designing a straight subsoiler. Identifying the significance of geometrical parameters maximizes structural safety and minimizes weight. An analysis of the parametric correlation between the output and input parameters of a straight subsoiler is presented in this paper. Parameter correlation was conducted to detect the degree to which the output parameters are influenced by the input parameters and the sensitivity of the input parameters to the output parameters. Analysis was performed using the Parameter Correlation tool of ANSYS Workbench. Results indicated that the thickness of the shank and width of the shank influenced the output parameters significantly, whereas the length of the curve of the inclined subsoiler had no significant influence on the output parameters. The thickness of shank has the highest relevance with the straight subsoiler mass having a correlation value of 0.78919 and R2 contribution of 0.60063. The width of shank has the highest relevance with total deformation with a correlation value of -0.77197 and an R2 contribution of 0.59353. Increasing thickness and width of shank of the subsoiler leads to an increasing trend in the subsoiler mass, safety factor, and volume. Increasing thickness and width of shank lead to decreasing trends in total deformation, equivalent stress, and maximum principal stress. Changes in length of curve of the straight subsoiler did not lead to any trend in the output parameters. Thus, thickness and width of shank were designated as the major input parameters while length of curve was designated as the minor input parameter.

show abstract

Section: Introductionmentioning

confidence: 99%

Parametric Correlation between Different Parameters of a Straight Subsoiler

Allaie

D’souza

Moses

et al. 2021

CJAST

View full text Add to dashboard Cite

show abstract

Development of Bolted Flange Design Tool Based on Artificial Neural Network

Yıldırım

Akay

Gülaşık

et al. 2019

Journal of Pressure Vessel Technology

View full text Add to dashboard Cite

Finite element analysis (FEA) of bolted flange connections is the common methodology for the analysis of bolted flange connections. However, it requires high computational power for model preparation and nonlinear analysis due to contact definitions used between the mating parts. Design of an optimum bolted flange connection requires many costly finite element analyses to be performed to decide on the optimum bolt configuration and minimum flange and casing thicknesses. In this study, very fast responding and accurate artificial neural network-based bolted flange design tool is developed. Artificial neural network is established using the database which is generated by the results of more than 10,000 nonlinear finite element analyses of the bolted flange connection of a typical aircraft engine. The FEA database is created by taking permutations of the parametric geometric design variables of the bolted flange connection and input load parameters. In order to decrease the number of FEA points, the significance of each design variable is evaluated by performing a parameter correlation study beforehand, and the number of design points between the lower and upper and bounds of the design variables is decided accordingly. The prediction of the artificial neural network based design tool is then compared with the FEA results. The results show excellent agreement between the artificial neural network-based design tool and the nonlinear FEA results within the training limits of the artificial neural network.

show abstract

Helisel işleme yay sabitinin belirlenmesi amacıyla parametrik korelasyon tekniğini kullanarak bir yapay sinir ağı geliştirilmesi

Sabuncuoğlu

Demirtaş

2020

Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

 Development of artificial neural network for helical machined springs  Utilization of Parametric Correlation Technique  Confirmation of ANN results with FEA and Torsional testsDevelopment of an artificial neural network (ANN) for the determination of the spring constant of machined helical springs, which may be preferred over conventional springs due to their high performance and operating efficiency, is presented. Inıtially, finite element analyses were performed with various dimensional parameters and the obtained spring constant values were verified with the tests performed with the designed test setup. Parametric correlation analysis was performed using the confirmed finite element results and the effect of each spring dimensional parameter on the spring constant was determined. The parameters required for ANN training was determined according to the this correlation result. The spring constant results obtained from the developed ANN was compared with the finite element results confirmed by the tests and it was determined that the ANN was successful in the determination of the spring constant. The importance of parametric correlation analysis has been revealed in the development of ANN. Figure A. (Movement directions of the test setup)Purpose: The main purpose of this study is; To determine the effects of the design parameters of machining springs working under angular displacement on spring stiffness and stress by experimental and numerical methods, Verifying numerical approaches by experimental methods, To develop an artificial neural network that enables us to quickly obtain the torsion spring constant value depending on the processing spring design parameters.Theory and Methods: Torsion spring constants of different sizes of machining springs were determined by experimental and numerical methods. Results:In the results of this study; A maximum of 1.6% difference between the parameters in ANN training data set and finite element results and a maximum of 8% in intermediate values were observed. Considering the differences between the test and finite element analysis, this difference was observed to be at an acceptable level. The results obtained with the values selected outside the database set show an increase in% difference values. It is concluded that this developed ANN model is not suitable to be used for values outside the database. Conclusion:As a result of this study; An artificial neural network (ANN) based on parameter correlation was developed to determine the spring constants of the machined springs that are frequently used in the aviation industry.

show abstract

Development of Bolted Flange Design Tool Based on Finite Element Analysis and Artificial Neural Network

Cited by 3 publications

References 10 publications

Parametric Correlation between Different Parameters of a Straight Subsoiler

Parametric Correlation between Different Parameters of a Straight Subsoiler

Development of Bolted Flange Design Tool Based on Artificial Neural Network

Helisel işleme yay sabitinin belirlenmesi amacıyla parametrik korelasyon tekniğini kullanarak bir yapay sinir ağı geliştirilmesi

Contact Info

Product

Resources

About