Optimization of a thin-walled element geometry using a system integrating neural networks and finite element method

• Autorzy: Golewski P. , Gajewski J. , Sadowski T.

Identyfikatory

DOI

10.1515/amm-2017-0067

• Języki publikacji: EN

Abstrakty

EN

Artificial neural networks [ANNs] are an effective method for predicting and classifying variables. This article presents the application of an integrated system based on artificial neural networks and calculations by the finite element method [FEM] for the optimization of geometry of a thin-walled element of an air structure. To ensure optimal structure, the structure’s geometry was modified by creating side holes and ribs, also with holes. The main criterion of optimization was to reduce the structure’s weight at the lowest possible deformation of the tested object. The numerical tests concerned a fragment of an elevator used in the “Bryza” aircraft. The tests were conducted for networks with radial basis functions [RBF] and multilayer perceptrons [MLP]. The calculations described in the paper are an attempt at testing the FEM - ANN system with respect to design optimization.

Słowa kluczowe

EN

artificial neural networks; numerical modelling; thin-walled element

• Wydawca: Institute of Metallurgy and Materials Science of Polish Academy of Sciences ; Committee of Materials Engineering and Metallurgy of Polish Academy of Sciences
• Czasopismo: Archives of Metallurgy and Materials
• Rocznik: 2017
• Tom: Vol. 62, iss. 1
• Strony: 435--442
• Opis fizyczny: Bibliogr. 29 poz., rys., tab.

Twórcy

autor

Golewski P.

• Lublin University of Technology, 20-618 Lublin, 40 Nadbystrzycka Str., Poland

autor

Gajewski J.

• Lublin University of Technology, 20-618 Lublin, 40 Nadbystrzycka Str., Poland

autor

Sadowski T.

• Lublin University of Technology, 20-618 Lublin, 40 Nadbystrzycka Str., Poland

Bibliografia

• [1] B. Wang, JH. Ma, YP. Wu. Application of artificial neural network in prediction of abrasion of rubber composites, Materials and Design 49, 802-807 (2013).
• [2] J. Jonak, J. Gajewski, Identifying the cutting tool type used in excavations using neural networks, Tunn. Undergr. Space Technol. 21, 185-189, (2006).
• [3] J. Jonak, J. Gajewski, Identification of ripping tool types with the use of characteristic statistical parameters of time graphs, Tunn. Undergr. Space Technol. 23, 18-24 (2008).
• [4] G. Litak, J. Gajewski, A. Syta, J. Jonak, Quantitative estimation of the tool wear effects in a ripping head by recurrence plots, Journal of Theoretical and Applied Mechanics 46, 521-530 (2008).
• [5] H. El Kadi. Modeling the mechanical behavior of fiber-reinforced polymeric composite materials using artificial neural networks - A review, Composite Structures 73, 1-23 (2006).
• [6] Ch.M. Bishop, Neural Networks for Pattern Recognition. Clarendon Press, Oxford, (1996).
• [7] L.H. Yam, Y.J. Yan, J.S. Jiang, Vibration-based damage detection for composite structures using wavelet transform and neural network identification, Composite Structures 60, 403-412 (2003).
• [8] Z. Su, L. Ye, Lamb wave-based quantitative identification of delamination in CF/EP composite structures using artificial neural algorithm, Composite Structures 66, 627-637 (2004).
• [9] Xu Y., You T., Du C.. An integrated micromechanical model and BP neural network for predicting elastic modulus of 3-D multi- -phase and multi-layer braided composite, Composite Structures 122, 308-315 (2015).
• [10] N.I.E. Farhana, M.S. Abdul Majid, M.P. Paulraj, E. Ahmadhilmi, M.N. Fakhzan Gibson A.G. A novel vibration based non-destructive testing for predicting glass fibre/matrix volume fraction in composites using a neural Network model, Composite Structures 144, 96-107 (2016).
• [11] A. De Fenza, A. Sorrentino, P. Vitiello, Application of Artificial Neural Networks and Probability Ellipse methods for damage detection using Lamb waves, Composite Structures 133, 390-403 (2015).
• [12] R. Perera, A. Arteaga, A. De Diego, Artificial intelligence techniques for prediction of the capacity of RC beams strengthened in shear with external FRP reinforcement, Composite Structures 92, 1169-1175 (2010).
• [13] H. Man, G. Prusty, Neural network modelling for damage behaviour of composites using full-field strain measurements, Composite Structures 93, 383-391 (2011).
• [14] M. Abouhamze, M. Shakeri. Multi-objective stacking sequence optimization of laminated cylindrical panels using a genetic algorithm and neural networks, Composite Structures 81, 253-263 (2007).
• [15] H. Naderpour, A. Kheyroddin, G. Ghodrati Amiri, Prediction of FRP-confined compressive strength of concrete Rusing artificial neural networks, Composite Structures 92, 2817-2829 (2010).
• [16] Kai Guan, Lina Jia, Xiaojun Chen, Junfei Weng, Fei Ding, Hu Zhang. Improvement of fracture toughness of directionally solidified Nb-silicide in situ composites using artificial neural network, Materials Science & Engineering A 605, 65-72 (2014).
• [17] Cao Jiuwen, Lin Zhiping, Huang Guang-bin. Composite function wavelet neural networks with extreme learning machine, Neurocomputing 73, 1405-1416 (2010).
• [18] P. Ramasamy, S. Sampathkumar, Prediction of impact damage tolerance of drop impacted WGFRP composite by artificial neural network using acoustic emission parameters, Composites: Part B 60, 457-462 (2014).
• [19] I. Mansouri, O. Kisi, Prediction of debonding strength for masonry elements retrofitted with FRP composites using neuro fuzzy and neural network approaches, Composites: Part B 70, 247-255 (2015).
• [20] M. Amirjan, H. Khorsand, M. Hossein Siadati, R Eslami Farsani, Artificial Neural Network prediction of Cu-Al2O3 composite properties prepared by powder metallurgy method, J. Mater. Res. Technol. 2, 351-355 (2013).
• [21] S. Fu X, Ricci, C. Bisagni Minimum-weight design for three dimensional woven composite stiffened panels using neural networks and genetic algorithms, Composite Structures 134, 708-715 (2015).
• [22] J. Gajewski , J. Podgorski, J. Jonak, Z. Szkudlarek, Numerical simulation of brittle rock loosening during mining process, Computational Materials Science 43, 115-118 (2008).
• [23] J. Gajewski, L. Jedliński, J. Jonak, Classification of wear level of mining tools with the use of fuzzy neural network, Tunn Undergr Space Technol. 35, 30-36 (2013).
• [24] J. Gajewski, J. Jonak, Towards the identification of worn picks on cutterdrumsbased on torque and power signals using Artificial Neural Networks. Tunn. Undergr. Space Technol. 26, 22-28 (2011).
• [25] T. Sadowski, J. Golewski, The influence of quantity and distribution of cooling channels of turbine elements on level of stresses in the protective layer TBC and the efficiency of cooling, Computational Materials Science 52, 293-297 (2012).
• [26] T. Sadowski, J. Golewski, Detection and numerical analysis of the most efforted places in turbine blades under real working conditions, Computational Materials Science 64, 285-288 (2012).
• [27] T. Sadowski, J. Golewski, Multidisciplinary analysis of the operational temperature increase of turbine blades in combustion engines by application of the ceramic thermal barrier coatings (TBC), Computational Materials Science 50, 1326-1335 (2011).
• [28] J Bieniaś, H. Dębski, B. Surowska, T. Sadowski, Analysis of microstructure damage in carbon/epoxy composites using FEM, Computational Materials Science 64, 168-172 (2012).
• [29] J. Gajewski, T. Sadowski, Sensitivity analysis of crack propagation in pavement bituminous layered structures using a hybrid system integrating Artificial Neural Networks and Finite Element Method, Computational Materials Science 82, 114-117 (2014).

Uwagi

EN

Financial support of Structural Funds – European Regional Development Funds (ERDF) Project No: INNOLOT/I/5/NCBiR/2013; program “INNOLOT – Innovative Aviation” coordinated by the National Center for Research and Development (NCBiR – Poland); Title: “Block Structures – Mechanical joining innovations to replace conventional fasteners in aerostructures” Period: 1.12.2013 – 31. 11.2018 is gratefully acknowledged, This work was financially supported by Ministry of Science and Higher Education within the statutory research number S/20/2016.

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017).