Optimization of a Jet Engine Compressor Disc with Application of Artificial Neural Networks for Calculations Related to Time and Mass

• Autorzy: Kieszek Rafał , Kozakiewicz Adam , Rogólski Robert

Identyfikatory

DOI

10.12913/22998624/134061

• Języki publikacji: EN

Abstrakty

EN

The paper presents the results of a series of numerical research on the possibility of applying Artificial Neural Networks (ANNs) for ultimate strength calculations of selected parts of rotating machines. The layout and the principle of the algorithm operation were described, beginning from the general assumptions and then moving to the detailed description of the subsequent modules. The effects of applying the algorithm were presented on the example of the analysis of the compressor disc. The significant benefits of using it were the reduction of optimization time by about 40% and the disc weight reduction by 0.5 kg. Accuracy of ANNs was different in each iteration of a presented algorithm. Finally, high accuracy of neural networks was achieved with the following mean values of relevant indices reached in the last iteration: RMSE=0.5983, MAPA=0.0733 and R^2=0.99895. The further perspectives of undertaken research were defined at the end.

Słowa kluczowe

EN

optimization; artificial neural networks; axial compressors; turbine jet engines; aerospace engineering

• Wydawca: Lublin University of Technology ; Polish Society of Ecological Engineering (PTIE), Branch of PTIE in Lublin
• Czasopismo: Advances in Science and Technology. Research Journal
• Rocznik: 2021
• Tom: Vol. 15, no 2
• Strony: 208--218
• Opis fizyczny: Bibliogr. 20 poz., fig., tab.

Twórcy

autor

Kieszek Rafał

• Institute of Aviation Technology, Faculty of the Mechatronics, Armament and Aerospace, Military University of Technology, ul. S. Kaliskiego 2, 00-908 Warszawa, Poland

• https://orcid.org/0000-0002-7775-2564

autor

Kozakiewicz Adam

• Institute of Aviation Technology, Faculty of the Mechatronics, Armament and Aerospace, Military University of Technology, ul. S. Kaliskiego 2, 00-908 Warszawa, Poland

• https://orcid.org/0000-0002-1607-5715

autor

Rogólski Robert

• Institute of Aviation Technology, Faculty of the Mechatronics, Armament and Aerospace, Military University of Technology, ul. S. Kaliskiego 2, 00-908 Warszawa, Poland

• https://orcid.org/0000-0002-3729-6680

Bibliografia

• 1. Jahangir H. and Eidgahee A., New and robust hybrid artificial bee colony algorithm – ANN model for FRP-concrete bond strength evaluation, Composite Structures, 2021, 257.
• 2. Naderpour H., Rafiean A.H. and Fakharian, P., Compressive strength prediction of environmentally friendly concrete using artificial neural networks. Journal of Building Engineering, 2018, 16, 213–219.
• 3. Abdulla N.A., Using the artificial neural network to predict the axial strength and strain of concretefilled plastic tube. Journal of Soft Computing in Civil Engineering, 2020, 4(2), 63–86.
• 4. Naderpour H., Nagai K., Fakharian P. and Haji M., Innovative models for prediction of compressive strength of FRP-confined circular reinforced concrete columns using soft computing methods. Composite Structures, 2019, 215, 69–84.
• 5. Eidgahee D.R., Rafiean A.H. and Haddad, A., A novel formulation for the compressive strength of IBP-based geopolymer stabilized clayey soils using ANN and GMDH-NN approaches. Iranian Journal of Science and Technology, Transactions of Civil Engineering, 2020, 44(1), 219–229.
• 6. Pierret S. and Van den Braembussche R.A., Turbomachinery Blade Design Using a Navier–Stokes Solver and Artificial Neural Network. J. Turbomach. 1999, 121(2), 326–332.
• 7. Roberts R. and Eastbourn S. Modeling techniques for a computational efficient dynamic turbofan engine model. International Journal of Aerospace Engineering. 2014.
• 8. Waszczyszyn Z. and Ziemiański L. Neural networks in mechanics of structures and materials– new results and prospects of applications. Computers & Structures, 2001, 79(22-25), 2261–2276.
• 9. Pabisek E. Systemy hybrydowe integrujące MES i SSN w analizie wybranych problemow mechaniki konstrukcji i materialow. Wydawnictwo Politechniki Krakowskiej, 2008.
• 10. Grzymowska A. Model neuronowy jako alternatywa dla numerycznego modelu okołodźwiękowego przepływu pary przez palisadę turbinową. Mechanik, 2014, 87, 217–224.
• 11. Głuch J. and Butterweck A. Zastosowanie sztucznych sieci neuronowych do diagnostyki cieplnoprzepływowej wieńców turbin parowych. Mechanik, 2014, 7, 173–180.
• 12. Koff L.B. Gas Turbine Technology Evolution: A Designers Perspective. Journal of Propulsion and Power. 2004, 20(4), 577–595.
• 13. Pierret S., Filomeno Coelho R. and Kato H. Multidisciplinary and multiple operating points shape optimization of three-dimensional compressor blades. Struct Multidisc Optim. 2007, 61–70.
• 14. Lee S.Y. and Kim K.Y. Design optimization of axial flow compressor blades with three-dimensional Navier-Stokes solver. KSME International Journal, 2000, 14(9), 1005-1012.
• 15. Panchenko V., Moustapha H., Mah S., Patel K. and Dowhan M. J. Preliminary multi-disciplinary optimization in turbomachinery design. Pratt and Whitney Canada Corp Longueuil (Quebec), 2003.
• 16. Abhishek S. and Goud B.N. Compressor Design optimization for a High speed Jet engine. IOP Conference Series: Materials Science and Engineering. 2018, 455, 1.
• 17. Schnoes M., Voß Ch. and Nicke E. Design optimization of a multi-stage axial compressor using throughflow and a database of optimal airfoils. Journal of the Global Power and Propulsion Society, 2018, 2, 516-528.
• 18. Kozakiewicz A. and Kieszek R. Zastosowanie sztucznych sieci neuronowych do obliczeń wytrzymałościowych maszyn wirnikowych. Przegląd Mechaniczny, 2018, LXXVII, 9, 28–30.
• 19. Nowotarski I. Obliczenia statyczne i dynamiczne turbinowych silników lotniczych metodą elementów skończonych. Wydawnictwa Naukowe Instytutu Lotnictwa, Warszawa 2001.
• 20. Møller M.F. A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning. Neural Networks. 1993, 6, 525–533.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).