Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Iterative Classification of Graph-Set-Based Designs (IC-GSBD) for the Down-Selection of Aircraft Thermal Management Systems (2312.03270v2)

Published 6 Dec 2023 in cs.CE

Abstract: In this paper, we present Iterative Classification of Graph-Set-Based Design (IC-GSBD), a framework utilizing graph-based techniques with geometric deep learning (GDL) integrated within a set-based design (SBD) approach for the classification and down-selection complex engineering systems represented by graphs. We demonstrate this approach on aircraft thermal management systems (TMSs) utilizing previous datasets created using an enumeration or brute-force graph generation procedure to represent novel aircraft TMSs as graphs. However, as with many enumerative approaches, combinatorial explosion limits its efficacy in many real-world problems, particularly when simulations and optimization must be performed on the many (automatically-generated) physics models. Therefore, the approach uses the directed graphs representing aircraft TMSs and GDL to predict on a subset of the graph-based dataset through graph classification. This paper's findings demonstrate that incorporating additional graph-based features using principle component analysis (PCA) enhances GDL model performance, achieving an accuracy of 98% for determining a graph's compilability and simulatability while using only 5% of the data for training. By applying iterative classification methods, we also successfully segmented the total set of graphs into more specific groups with an average inclusion of 75.5 of the top 100 highest-performing graphs, achieved by training on 40% of the data.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. van Heerden, A., Judt, D., Jafari, S., Lawson, C., Nikolaidis, T., and Bosak, D., “Aircraft thermal management: Practices, technology, system architectures, future challenges, and opportunities,” Progress in Aerospace Sciences, Vol. 128, 2022, p. 100767. 10.1016/j.paerosci.2021.100767.
  2. Huang, H., Spadaccini, L. J., and Sobel, D. R., “Fuel-Cooled Thermal Management for Advanced Aeroengines,” Journal of Engineering for Gas Turbines and Power, Vol. 126, No. 2, 2004, pp. 284–293. 10.1115/1.1689361.
  3. Coutinho, M., Bento, D., Souza, A., Cruz, R., Afonso, F., Lau, F., Suleman, A., Barbosa, F. R., Gandolfi, R., Affonso, W., Odaguil, F. I., Westin, M. F., dos Reis, R. J., and da Silva, C. R., “A review on the recent developments in thermal management systems for hybrid-electric aircraft,” Applied Thermal Engineering, Vol. 227, 2023, p. 120427. 10.1016/j.applthermaleng.2023.120427.
  4. Herber, D. R., Allison, J. T., Buettner, R., Abolmoali, P., and Patnaik, S. S., “Architecture generation and performance evaluation of aircraft thermal management systems through graph-based techniques,” AIAA 2020 Science and Technology Forum and Exposition, Orlando, FL, USA, 2020. 10.2514/6.2020-0159.
  5. Buettner, R., Herber, D. R., Abolmoali, P., and Patnaik, S. S., “An automated design tool for the generation and selection of optimal aircraft thermal management system architectures,” AIAA Propulsion and Energy 2021 Forum, 2021. 10.2514/6.2021-3718.
  6. Bronstein, M. M., Bruna, J., Cohen, T., and Velickovic, P., “Geometric deep learning: grids, groups, graphs, geodesics, and gauges,” preprint v2, 2021. arXiv:2104.13478
  7. Herber, D. R., “Advances in combined architecture, plant, and control design,” Ph.D. Dissertation, University of Illinois at Urbana-Champaign, Urbana, IL, USA, 2017. URL http://hdl.handle.net/2142/99394.
  8. Selva, D., Cameron, B., and Crawley, E., “Patterns in system architecture decisions,” Systems Engineering, Vol. 19, No. 6, 2016, pp. 477–497. 10.1002/sys.21370.
  9. Arney, D. C., and Wilhite, A. W., “Modeling space system architectures with graph theory,” Journal of Spacecraft and Rockets, Vol. 51, No. 5, 2014, pp. 1413–1429. 10.2514/1.A32578.
  10. Sirico, A., and Herber, D. R., “On the use of geometric deep learning for the iterative classification and down-selection of analog electric circuits,” Journal of Mechanical Design, Vol. 146, No. 6, 2024, p. 051703. 10.1115/1.4063659.
  11. Bronstein, M. M., Bruna, J., LeCun, Y., Szlam, A., and Vandergheynst, P., “Geometric deep learning: going beyond euclidean data,” IEEE Signal Processing Magazine, Vol. 34, No. 4, 2017, pp. 18–42. 10.1109/msp.2017.2693418.
  12. 10.1007/978-3-662-53622-3.
  13. Herber, D. R., Guo, T., and Allison, J. T., “Enumeration of architectures with perfect matchings,” Journal of Mechanical Design, Vol. 139, No. 5, 2017, p. 051403. 10.1115/1.4036132.
  14. Herber, D. R., “Enhancements to the perfect matching approach for graph enumeration-based engineering challenges,” ASME International Design Engineering Technical Conferences, 2020. 10.1115/DETC2020-22774.
  15. Krizhevsky, A., Sutskever, I., and Hinton, G. E., “ImageNet Classification with Deep Convolutional Neural Networks,” Advances in Neural Information Processing Systems 25, 2012, pp. 1097–1105.
  16. Wang, T., Wu, D. J., Coates, A., and Ng, A. Y., “End-to-end text recognition with convolutional neural networks,” International Conference on Pattern Recognition, 2012, pp. 3304–3308.
  17. Deng, L., Li, J., Huang, J.-T., Yao, K., Yu, D., Seide, F., Seltzer, M., Zweig, G., He, X., Williams, J., Gong, Y., and Acero, A., “Recent advances in deep learning for speech research at Microsoft,” IEEE International Conference on Acoustics, Speech and Signal Processing, 2013, pp. 8604–8608. 10.1109/ICASSP.2013.6639345.
  18. Nickel, M., and Kiela, D., “Poincaré embeddings for learning hierarchical representations,” , 2017. arXiv:1705.08039
  19. Chamberlain, B. P., Clough, J., and Deisenroth, M. P., “Neural embeddings of graphs in hyperbolic space,” preprint v2, 2017. arXiv:1705.10359
  20. Cohen, T. S., and Welling, M., “Steerable CNNs,” preprint v1, 2016. arXiv:1612.08498
  21. Cohen, T. S., Geiger, M., Koehler, J., and Welling, M., “Spherical CNNs,” preprint v3, 2018. arXiv:1801.10130
  22. Lecun, Y., Bottou, L., Bengio, Y., and Haffner, P., “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, Vol. 86, No. 11, 1998, pp. 2278–2324. 10.1109/5.726791.
  23. Zhang, M., Cui, Z., Neumann, M., and Chen, Y., “An end-to-end deep learning architecture for graph classification,” AAAI Conference on Artificial Intelligence, Vol. 32, 2018, pp. 4438–4445. 10.1609/aaai.v32i1.11782.
  24. Kipf, T. N., and Welling, M., “Semi-supervised classification with graph convolutional networks,” preprint v4, 2016. arXiv:1609.02907
  25. Ma, Y., Wang, S., Aggarwal, C. C., and Tang, J., “Graph convolutional networks with eigenpooling,” preprint v2, 2019. arXiv:1904.13107
  26. Ying, R., You, J., Morris, C., Ren, X., Hamilton, W. L., and Leskovec, J., “Hierarchical graph representation learning with differentiable pooling,” preprint v4, 2018. arXiv:1806.08804
  27. Duvenaud, D., Maclaurin, D., Aguilera-Iparraguirre, J., Gómez-Bombarelli, R., Hirzel, T., Aspuru-Guzik, A., and Adams, R. P., “Convolutional networks on graphs for learning molecular fingerprints,” preprint v2, 2015. arXiv:1509.09292
  28. Rousseau, F., Kiagias, E., and Vazirgiannis, M., “Text categorization as a graph classification problem,” Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, 2015, pp. 1702–1712. 10.3115/v1/P15-1164.
  29. Shen, M., Zhang, J., Zhu, L., Xu, K., and Du, X., “Accurate decentralized application identification via encrypted traffic analysis using graph neural networks,” IEEE Transactions on Information Forensics and Security, Vol. 16, 2021, pp. 2367–2380. 10.1109/TIFS.2021.3050608.
  30. Hashemi, A., and Pilevar, A. H., “Mass detection in lung CT images by using graph classification,” International Journal of Electronics and Electrical Engineering, Vol. 3, No. 3, 2013.
  31. 10.1007/978-1-0716-1418-1.
  32. Morris, C., Ritzert, M., Fey, M., Hamilton, W. L., Lenssen, J. E., Rattan, G., and Grohe, M., “Weisfeiler and Leman go neural: higher-order graph neural networks,” preprint v5, 2018. arXiv:1810.02244
  33. Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R., “Improving neural networks by preventing co-adaptation of feature detectors,” preprint v1, 2012. arXiv:1207.0580
  34. Bengio, Y., “Practical recommendations for gradient-based training of deep architectures,” preprint v2, 2012. arXiv:1206.5533
  35. Jurman, G., Riccadonna, S., and Furlanello, C., “A comparison of MCC and CEN error measures in multi-class prediction,” PLOS One, Vol. 7, No. 8, 2012, p. e41882. 10.1371/journal.pone.0041882.
  36. Chicco, D., “Ten quick tips for machine learning in computational biology,” BioData Mining, Vol. 10, No. 35, 2017. 10.1186/s13040-017-0155-3.
  37. Boldi, P., and Vigna, S., “Axioms for Centrality,” preprint v2, 2013. arXiv:1308.2140

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now