Hostname: page-component-78c5997874-8bhkd Total loading time: 0 Render date: 2024-11-08T05:09:10.176Z Has data issue: false hasContentIssue false
  • English
  • Français

TURBOMACHINERY DESIGN: CHECKING ARTIFICIAL NEURAL NETWORKS SUITABILITY FOR DESIGN AUTOMATION

Published online by Cambridge University Press:  19 June 2023

Niccolo' Batini ,
Niccolo Becattini  and
Gaetano Cascini
Niccolo' Batini
Affiliation:
Politecnico di Milano; Baker Hughes
Niccolo Becattini*
Affiliation:
Politecnico di Milano;
Gaetano Cascini
Affiliation:
Politecnico di Milano;
*
Becattini, Niccolo, Politecnico di Milano, Italy, [email protected]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

This paper explores the suitability of Artificial Neural Networks (ANNs) as an enabler of Design Automation in the turbomachinery industry. Specifically, the paper provides 1) a preliminary estimation of the effectiveness of ANNs to define values for design variables of reciprocating compressors (RC) and 2) a comparison of ANNs performance with traditional and more computationally demanding methods like CFD. A tailored ANN trained on a dataset composed by 350+ Baker Hughes’ RC automatically assigns values to 8 geometrical variables belonging to multiple parts of the RC in order to satisfy two target conditions linked to their thermodynamic performance. The results highlight that the ANN-assigned parameters return an optimal solution for RC also when the target values do not belong to the training dataset. Their predictive capacity for RC thermodynamic performance, with respect to CFD, are comparable (i.e. less than 2% in terms of calculated absorbed power) and the approach enables a significant gain in terms of computational time (i.e. 2 minutes vs 10 hours). Future perspectives of this work may involve the integration of this tool in an advanced DA method to lead Design Engineers (DEs) during the whole design process.

Keywords

Artificial intelligenceComputational design methodsEmbodiment designTurbomachineryOptimisation
Type
Article
Information
Proceedings of the Design Society , Volume 3: ICED23 , July 2023 , pp. 3651 - 3660
Creative Commons
Creative Common License - CCCreative Common License - BYCreative Common License - NCCreative Common License - ND
This is an Open Access article, distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives licence (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is unaltered and is properly cited. The written permission of Cambridge University Press must be obtained for commercial re-use or in order to create a derivative work.
Copyright
The Author(s), 2023. Published by Cambridge University Press

References

Amadori, K., Tarkian, M., Ölvander, J., & Krus, P. (2012). Flexible and robust CAD models for design automation. Advanced Engineering Informatics, 26(2), 180–195.CrossRefGoogle Scholar
Ascheri, Andrea & Colombo, Giorgio & Ippolito, Massimo & Atzeni, Eleonora & Furini, Francesco. (2014). Feasibility of an assembly line layout automatic configuration based on a KBE approach. 324–329. 10.1109/IDAM.2014.6912715.Google Scholar
Bishop, Chris M. (1994). Neural networks and their applications. Review of Scientific Instruments / Volume 65 / Issue 6.Google Scholar
Che, Zhen-Guo & Chiang, Tzu-An & Che, Z. (2011). Feed-forward neural networks training: A comparison between genetic algorithm and back-propagation learning algorithm. International Journal of Innovative Computing, Information and Control. 7.Google Scholar
Du, Qiuwan, Yunzhu Li, Like Yang, Tianyuan Liu, Di Zhang, Yonghui Xie. (2022). Performance prediction and design optimisation of turbine blade profile with deep learning method, Energy, Volume 254, Part ACrossRefGoogle Scholar
Entner, D., Prante, T., Vosgien, T., Zavoianu, A., Saminger-Platz, S., Schwarz, M., & Fink, K. (2019). Potential identification and industrial evaluation of an integrated design automation workflow. Journal of Engineering, Design and Technology, 17, 1085–1109.CrossRefGoogle Scholar
Ghorbanian, K. & Gholamrezaei, Mohammad. (2009). An artificial neural network approach to compressor performance prediction. Applied Energy. 86. 1210–1221. 10.1016/j.apenergy.2008.06.006.CrossRefGoogle Scholar
Ji, Cheng & Wang, Zhiheng & Tang, Yonghong & Xi, G. (2021). A Flow Information Based Prediction Model Applied to the Non-axisymmetric Hub Optimization of a Centrifugal Impeller. Journal of Mechanical Design. 143. 1–17. 10.1115/1.4050655.CrossRefGoogle Scholar
Jiang, Hongsheng & Dong, Sujun & Zheng, Liu & He, Yue & Ai, Fengming. (2019). Performance Prediction of the Centrifugal Compressor Based on a Limited Number of Sample Data. Mathematical Problems in Engineering. 2019. 1–13. 10.1155/2019/5954128.Google Scholar
Lazzaretto, Andrea & Toffolo, Andrea. (2001). Analytical and Neural Network Models for Gas Turbine Design and Off-Design Simulation. International Journal of Thermodynamics. 4. 10.5541/ijot.78.Google Scholar
Li, Z., & Zheng, X. (2017). Review of design optimisation methods for turbomachinery aerodynamics. Progress in Aerospace Sciences, 93, 1–23.CrossRefGoogle Scholar
Lindholm, J., Johansen, K. (2018). Is Design Automation a Feasible Tool for Improving Efficiency in Production Planning and Manufacturing Processes? Procedia Manufacturing, 194–201.CrossRefGoogle Scholar
Lopez, Diego & Ghisu, Tiziano & Shahpar, Shahrokh. (2021). Global Optimisation of a Transonic Fan Blade Through AI-Enabled Active Subspaces. Journal of Turbomachinery. 144. 1–33. 10.1115/1.4052136.Google Scholar
Luczynski, Piotr & Hohenberg, K & Freytag, C & Martinez-Botas, R & Wirsum, Manfred. (2021). Integrated design optimisation and engine matching of a turbocharger radial turbine. 10.1201/9781003132172.Google Scholar
Meireles, Magali & Almeida, Paulo & Simoes, Marcelo. (2003). A comprehensive review for industrial applicability of artificial neural networks. Industrial Electronics, IEEE Transactions on. 50. 585 - 601. 10.1109/TIE.2003.812470.Google Scholar
Rojas, R. (1996). Neural Networks: a Systematic Introduction. Berlin: Springer-Verlag.CrossRefGoogle Scholar
Sobieszczanski-Sobieski, J. & Morris, Alan & Van Tooren, Michael. (2015). Multidisciplinary Design Optimization Supported by Knowledge Based Engineering.CrossRefGoogle Scholar
Van der Velden, Alex, and Koch, Pat. “Isight design optimisation methodologies.” ASM handbook 22 (2010): 79.Google Scholar
Woldemariam, Endashaw Tesfaye, and Lemu, Hirpa G.. (2019). “A Machine Learning Based Framework for Model Approximation Followed by Design Optimisation for Expensive Numerical Simulation-Based Optimisation Problems.” Paper presented at the The 29th International Ocean and Polar Engineering Conference, Honolulu, Hawaii, USA, June 2019.Google Scholar
Yu, L., Wang, S., & Lai, K. K. (2008). Credit risk assessment with a multistage neural network ensemble learning approach. Expert systems with applications, 34(2), 1434–1444.CrossRefGoogle Scholar
Yu, Youhong & Sun, Fengrui & Wu, Chih-Hang. (2007). Neural-network based analysis and prediction of a compressor's characteristic performance map. Applied Energy. 84. 48–55. 10.1016/j.apenergy.2006.04.005.CrossRefGoogle Scholar