Modeling of Stress Concentration Factor Using Artificial Neural Networks for a Flat Tension Bar with Opposite V-Shaped Notches

Öz

Machine parts are exposed to stress accumulation due to geometric differences. Determining the stress accumulation locations is crucial to the design procedures. Studies on stress concentrations have been conducted in the past using a variety of theoretical and experimental methodologies, and distinct interpretations have been offered depending on the geometry of the machine part to be produced. The ability to complete activities with the least amount of effort and in the shortest amount of time has emerged as a result of the new computer technologies and software that have impacted many aspects of our everyday lives. One of these methods is the artificial neural networks (ANN) model, which is a branch of artificial intelligence. It is argued as a thesis in this study that fast and low-cost solutions can be found to problems in the field of solid mechanics by using the ANN model. For this purpose, a model has been developed to determine the SCF value with the ANN model of a plate with symmetrical V-shaped notch. The graphs obtained from previous experimental studies were converted to digital format and the Kt values obtained for the V-shaped notch problem with different parameters were converted into a data file. In this file, the SCF values to be obtained according to the strength upper limit safety factor value of the machine part, depending on the dimensional dimensions and material type required for the design, are calculated numerically in the form of an Excel file. An ANN-based code was created in MATLAB software and a new solution method was presented for parts containing a V-shaped notch.

Anahtar Kelimeler

• Stress concentration factor (scf)
• artificial neural network (ann)
• opposite v-shaped notches
• stress-strain analysis
• computational methods

Proje Numarası

Mevcut değil

Simetrik V Şekilli Plakadaki Gerilme Yığılma Faktörünün Yapay Sinir Ağı ile Modellenmesi

Öz

Machine parts are exposed to stress accumulation due to geometric differences. Determining the stress accumulation locations is crucial to the design procedures. Studies on stress concentrations have been conducted in the past using a variety of theoretical and experimental methodologies, and distinct interpretations have been offered depending on the geometry of the machine part to be produced. The ability to complete activities with the least amount of effort and in the shortest amount of time has emerged as a result of the new computer technologies and software that have impacted many aspects of our everyday lives. One of these methods is the artificial neural networks (ANN) model, which is a branch of artificial intelligence. It is argued as a thesis in this study that fast and low-cost solutions can be found to problems in the field of solid mechanics by using the ANN model. For this purpose, a model has been developed to determine the SCF value with the ANN model of a plate with symmetrical V-shaped notch. The graphs obtained from previous experimental studies were converted to digital format and the Kt values obtained for the V-shaped notch problem with different parameters were converted into a data file. In this file, the SCF values to be obtained according to the strength upper limit safety factor value of the machine part, depending on the dimensional dimensions and material type required for the design, are calculated numerically in the form of an Excel file. An ANN-based code was created in MATLAB software and a new solution method was presented for parts containing a V-shaped notch.

Anahtar Kelimeler

• Stress concentration factor (scf)
• artificial neural network (ann)
• opposite v-shaped notches
• stress-strain analysis
• computational methods

Destekleyen Kurum

Mevcut değil

Proje Numarası

Mevcut değil

Teşekkür

Mevcut değil

Kaynakça

1. [1] Noda N., Takase Y, “Stress concentration formula useful for all notch shape in a round bar (comparison between torsion, tension and bending), International Journal of Fatigue, 28:151-163, (2006).
2. [2] Nisitani H., Noda N., “Stress concentration of a cylindrical bar with a V-shaped circumferential groove under torsion, tension or bending”, Engineering Fracture Mechanics, 20:743-766,(1984).
3. [3] Ortega-Herrera F. J., Lozano-Luna A., Razón-González J. P., García-Guzmán J. M., Figueroa-Godoy F., “Mathematical Model to Predict the Stress Concentration Factor on a Notched Flat Bar in Axial Tension”, Emerging Challenges for Experimental Mechanics in Energy and Environmental Applications, Proceedings of the 5th International Symposium on Experimental Mechanics and 9th Symposium on Optics in Industry (ISEM-SOI), 265-272,(2015).
4. [4] Gomes C. J., Troyani N., Morillo C., Gregory S., Gerardo V., Pollonais Y., “Theoretical stress concentration factors for short flat tension bars with opposite U-shaped notches”, Institution of Mechanical Engineers, 40:345-355,(2005).
5. [5] Noda N., Takase Y., Monda K., “Formula of stress concentration factors for round and flat bars with notches”, WIT Transactions on Engineering Sciences, 13(8).
6. [6] Ozkan M. T., Toktas I., “Determination of The Stress Concentration Factor Kt in A Rectangular Plate With a Hole Under Tensile Stress Using Different Methods” Materials Testing, 58(10): 839-847,(2016).
7. [7] Ozkan M. T., Erdemir F., “Determination oftheoretical stress concentration factor forcircular/elliptical holes with reinforcementusing analytical, finite element method andartificial neural network techniques”, NeuralComputing and Applications, 33(19): 12641-12659,(2021).
8. [8] Karakurt H.B., Kocak C., Ozkan M.T. Prediction of Channel Utilization with Artificial Neural Networks Model in Mac Layer in Wireless Local Area Networks Wireless Personal Communications. 126 (4), 2022, 3389-3418.

9. [9] Toktas I., Ozkan M. T., Erdemir F. and Yuksel N., “Determination of stress concentration factor (Kt) for a crankshaft under bending loading: an artificial neural networks approach”, Journal of Polytechnic, 23(3):813-819,(2020).
10. [10] Ozkan M. T., Eldem, C. Koksal E.,“Notch Sensitivity Factor Determination with Artificial Neural Network for Shafts under Bending Stress” Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 19:24-32, (2013).
11. [11] Ozkan M.T., Toktas I. and Doganay S.K., “Estimations of stress concentration factors Cw/Kts for helical circular/square cross sectional tension-compression springs and artificial neural network modelling”, Politeknik Dergisi, 23(3): 901-908, (2020).
12. [12] Akkas G., Korkut I., Ozkan M.T.,”End effector position calculation with the ANN for tapping machine”. Journal of Engg. Research, 9(3B): 235-247,(2021).
13. [13] Serbest, K., Ozkan, M.T. & Cilli, M. “Estimation of joint torques using an artificial neural network model based on kinematic and anthropometric data”. Neural Comput & Applic. (2023).
14. [14] Apple F. J., Koerner D. R., “Stress Concentration Factors for U-Shaped, Hyperbolic and Rounded V-Shaped Notches” ASME Paper 69-DE-2, Eng. Soc. Library, United Eng. Center, New York, (1969).
15. [15] Leven M. M., Frocht M. M., “Stress Concentration Factors for a Single Notch in a Flat Plate in Pure and Central Bending”, System Engineering Society of Australia, 11(2):179.
16. [16] Pilkey W. D., Pilkey D. F., “Peterson’s Stress Concentration Factors, 3rd Edition”, John Wiley & Sons, Inc., Hoboken, New Jersey, (2008).
17. [17] Atsumi A, “Stress concentrations in a strip under tension and containing an infinite row of semi-circular notches”, Q. J. Mech. and Applied Math., 11(4), 478-490,(1958).
18. [18] Otaki H., “Spannungsverteilung im Gevindegrund der Schraubeeiner Schraube Mutter Verbindung. Konstruktion, 31: 121–126,(1979).
19. [19] Naik N. K., “Photoelastic investigation of finite plates with multi-holes”, Mech. Res. Commun, 15: 141–146,(1988).
20. [20] Savruk M. P., Kazberuk A. M. P., “A plane periodic boundary-value problem of elasticity theory for a half-plane with curvilinear edge” Mater. Sci., 44: 461–470,(2008).
21. [21] Heywood R. B., “Designing by photoelasticity”, 1st edition, 202–205,(1952).
22. [22] Matlab 2018b (Gazi University)
23. [23] Haykin S.“Neural Networks and Learning Machines” (3rd Edition ) McMaster University Hamilton, Ontario, Canada, ISBN-13: 978-0131471399 ISBN-10: 0131471392,(2008).
24. [24] Domany E., Hemmen J.L., Schulten K. (Eds.) “Models of Neural Networks II”, Springer-Verlag New York Springer-Verlag New York. Inc. (1995).
25. [25] Marquardt D. “An Algorithm for Least-Squares Estimation of Nonlinear Parameters”. SIAM Journal on Applied Mathematics, 11(2):431-441,(1963).
26. [26] Hagan M.T., Menhaj M., “Training feed-forward networks with the Marquardt algorithm”. IEEE Transactions on Neural Networks 5(6):989–993,(1994).
27. [27] Hagan M.T., Demuth H.B., Beale M.H. “Neural Network Design”, Boston, MA: PWS Publishing. (1996).
28. [28] Beale M.H., Martin T.H., Demufh H.B., “Neural Network Toolbox1” User's Guide R2018a. MathWorks, Inc.(2018).
29. [29] Smith J. “Neural Network Architectures”. Examples using MATLAB, (2017).
30. [30] Rosenblatt J., “Basic Statistical Methods and Models for the Sciences”, CHAPMAN & HALL/CRC A CRC Press Company Boca Raton London New York, (2002).
31. [31] Werbos P.J., “Beyond Regression: New Tools For Prediction And Analysis” In The Behavioral Sciences By Harvard University Cambridge, Massachusetts August, Ph.D Thesis,(1974).
32. [32] Perez C.,“Statistics And Data Analysis With Matlab”. Cluster Analysis and Applications, (2019).