Physics-Informed Neural Networks for Predicting Combustion Dynamics in Rocket Engine Chambers

Sheharyar Nasir; Shumail Sahibzada; Farrukh Sher Malik

doi:10.55524/ijircst.2025.13.4.4

Abstract

Accurately predicting combustion dynamics within rocket engine chambers is essential for ensuring propulsion system stability, efficiency, and safety. Traditional high-fidelity Computational Fluid Dynamics (CFD) methods offer detailed insights but are computationally expensive and often impractical for real-time applications. This study introduces Physics-Informed Neural Networks (PINNs) as a novel, efficient alternative for modeling combustion dynamics in rocket propulsion systems. PINNs integrate the governing partial differential equations (PDEs)—including mass, momentum, energy, and species transport—directly into the neural network's loss function, enabling data-efficient learning with limited reliance on extensive simulation datasets. We present a PINN framework trained on synthetic and benchmark CFD data from a hydrogen-oxygen combustor. The model captures complex physical phenomena such as temperature gradients, pressure oscillations, and flame front instabilities while significantly reducing computational cost. Our implementation employs a deep neural network architecture with eight hidden layers and 64 neurons per layer, using a combination of Adam and L-BFGS optimizers for training. The network achieves a validation root-mean-square error (RMSE) of 0.0029 MPa in pressure prediction, closely matching CFD results.Comparative analysis shows that the PINN model generalizes well to unseen temporal and spatial domains and offers predictions in under 0.5 seconds, in contrast to the 12-hour runtime of traditional CFD. These findings highlight PINNs as a promising surrogate modeling tool for real-time diagnostics, design optimization, and control in rocket propulsion systems. Future work will explore hybrid modeling, uncertainty quantification, and deployment in active combustion control frameworks.

Keywords

Physics-Informed Neural Networks (PINNs), Combustion Dynamics, Rocket Propulsion, Computational Fluid Dynamics (CFD), Surrogate Modeling.

References

Mahmood, T., Asif, M., and Raza, Z. H., “Smart forestry: The role of AI and bioengineering in revolutionizing timber production and biodiversity protection,” Revista de Inteligencia Artificial en Medicina, vol. 15, no. 1, pp. 1176–1202, 2024. Available from: https://tinyurl.com/5n64k2dx
Asif, M., Raza, Z. H., and Mahmood, T., “Bioengineering applications in forestry: Enhancing growth, disease resistance, and climate resilience,” Revista Espanola de Documentacion Cientifica, vol. 17, no. 1, pp. 62–88, 2023.
Bhatti, I., Rafi, H., and Rasool, S., “Use of ICT Technologies for the Assistance of Disabled Migrants in USA,” Revista Espanola de Documentacion Cientifica, vol. 18, no. 1, pp. 66–99, 2024.
Li, Z., Rasool, S., Cavus, M. F., and Shahid, W., “Sustaining the future: How green capabilities and digitalization drive sustainability in modern business,” Heliyon, vol. 10, no. 1, 2024. Available from: https://tinyurl.com/bhb26hry
Saeed, A., Husnain, A., Rasool, S., and Gill, A. Y., “Healthcare Revolution: How AI and Machine Learning Are Changing Medicine,” Journal Research of Social Science, Economics & Management, vol. 3, no. 3, 2023. Available from: https://tinyurl.com/uxx7u684
Rasool, D., Ghafoor, A., and Fareed, D., “Forecasting the Trends and Patterns of Crime in San Francisco using Machine Learning Model,” International Journal of Science and Engineering Research, 2021. Available from: https://tinyurl.com/5n7rxe2r
Rasool, S., Khaja, A. M., Hayat, Y., and Khan, A. H., “AI-Based Predictive Tools for Managing and Preventing Cardiovascular Diseases,” 2025. Available from: https://tinyurl.com/yc4pz2n8
Khaja, A. M., Arikhad, M., Hayat, Y., and Rasool, S., “Predictive Modeling for Chemotherapy Response Using Machine Learning,” 2025. Available from: https://tinyurl.com/4h9wtva3
Rafi, H., Ahmad, F., Anis, J., Khan, R., Rafiq, H., and Farhan, M., “Comparative effectiveness of agmatine and choline treatment in rats with cognitive impairment induced by AlCl3 and forced swim stress,” Current Clinical Pharmacology, vol. 15, no. 3, pp. 251–264, 2020. Available from: https://doi.org/10.2174/1574884714666191016152143
Farhan, M., Rafi, H., and Rafiq, H., “Behavioral evidence of neuropsychopharmacological effect of imipramine in animal model of unpredictable stress induced depression,” International Journal of Biology and Biotechnology, vol. 15, no. 22, pp. 213–221, 2018. Available from: https://tinyurl.com/4s2hhxen
Rafi, H., Rafiq, H., and Farhan, M., “Pharmacological profile of agmatine: An in-depth overview,” Neuropeptides, 102429, 2024. Available from: https://doi.org/10.1016/j.npep.2024.102429
Rafiq, H., Farhan, M., Rafi, H., Rehman, S., Arshad, M., and Shakeel, S., “Inhibition of drug induced Parkinsonism by chronic supplementation of quercetin in haloperidol-treated wistars,” Pak J Pharm Sci, vol. 35, pp. 1655–1662, 2022. Available from: https://tinyurl.com/4p2nkrmt
Rafi, H., Rafiq, H., and Farhan, M., “Inhibition of NMDA receptors by agmatine is followed by GABA/glutamate balance in benzodiazepine withdrawal syndrome,” Beni-Suef University Journal of Basic and Applied Sciences, vol. 10, pp. 1–13, 2021. Available from: https://tinyurl.com/3fccpt6s
Ghulam, T., Rafi, H., Khan, A., Gul, K., and Yusuf, M. Z., “Impact of SARS-CoV-2 Treatment on Development of Sensorineural Hearing Loss: Impact of SARS-CoV-2 treatment on SNHL,” Proceedings of the Pakistan Academy of Sciences: B. Life and Environmental Sciences, vol. 58(S), pp. 45–54, 2021. Available from: https://tinyurl.com/5n73pdne
Rafi, H., Rafiq, H., Khan, R., Ahmad, F., Anis, J., and Farhan, M., “Neuroethological study of ALCL3 and chronic forced swim stress induced memory and cognitive deficits in albino rats,” The Journal of Neurobehavioral Sciences, vol. 6, no. 2, pp. 149–158, 2019.
Rafi, H., and Farhan, M., “Dapoxetine: An innovative approach in therapeutic management in animal model of depression,” Pakistan Journal of Pharmaceutical Sciences, vol. 2, no. 1, pp. 15–22, 2015. Available from: https://tinyurl.com/y5ybvda5
Farhan, M., Rafi, H., and Rafiq, H., “Dapoxetine treatment leads to attenuation of chronic unpredictable stress induced behavioral deficits in rats model of depression,” Journal of Pharmacy and Nutrition Sciences, vol. 5, no. 4, pp. 222–228, 2015. Available from: https://tinyurl.com/3y8fz9uy
Rafi, H., Rafiq, H., and Farhan, M., “Antagonization of monoamine reuptake transporters by agmatine improves anxiolytic and locomotive behaviors commensurate with fluoxetine and methylphenidate,” Beni-Suef University Journal of Basic and Applied Sciences, vol. 10, pp. 1–14, 2021. Available from: https://tinyurl.com/bdc4nzf7
Farhan, M., Rafiq, H., Rafi, H., Rehman, S., and Arshad, M., “Quercetin impact against psychological disturbances induced by fat rich diet,” Pakistan Journal of Pharmaceutical Sciences, vol. 35, no. 5, 2022. Available from: https://tinyurl.com/2fzshp3z
Rafi, H., Rafiq, H., Hanif, I., Rizwan, R., and Farhan, M., “Chronic agmatine treatment modulates behavioral deficits induced by chronic unpredictable stress in wistar rats,” Journal of Pharmaceutical and Biological Sciences, vol. 6, no. 3, p. 80, 2018. Available from: https://tinyurl.com/4kh8tubz
Zuberi, S., Rafi, H., Hussain, A., and Hashmi, S., “Role of Nrf2 in myocardial infarction and ischemia-reperfusion injury,” Physiology, vol. 38(S1), 5734743, 2023. Available from: https://doi.org/10.1152/physiol.2023.38.S1.5734743
Farhan, M., Rafiq, H., Rafi, H., Ali, R., and Jahan, S., “Neuroprotective role of quercetin against neurotoxicity induced by lead acetate in male rats,” Int. J. Biol. Biotech, vol. 16, no. 2, pp. 291–29, 2019. Available from: https://tinyurl.com/ydddpz3j
Rafi, H., Rafiq, H., and Farhan, M., “Agmatine alleviates brain oxidative stress induced by sodium azide,” 2023. Available from: https://www.researchsquare.com/article/rs-3244002/v1
Farhan, M., Rafi, H., Rafiq, H., Siddiqui, F., Khan, R., and Anis, J., “Study of mental illness in rat model of sodium azide induced oxidative stress,” Journal of Pharmacy and Nutrition Sciences, vol. 9, no. 4, pp. 213–221, 2019. Available from: https://doi.org/10.29169/1927-5951.2019.09.04.3
Cell, Q. E., Self-Assessment Report Department of Biochemistry. Ph.D. dissertation, University of Karachi. Available from: https://tinyurl.com/mvzsjb7w
Farhan, M., Rafiq, H., and Rafi, H., “Prevalence of depression in animal models of high fat diet induced obesity,” Journal of Pharmacy and Nutrition Sciences, vol. 5, no. 3, pp. 208–215, 2015. Available from: https://doi.org/10.6000/1927-5951.2015.05.03.6

Cites this article as

S. Nasir, S. Sahibzada, F. S. Malik, "Physics-Informed Neural Networks for Predicting Combustion Dynamics in Rocket Engine Chambers", International Journal of Innovative Research in Engineering & Management (ijircst), Vol-13, Issue-4, Page No-41-44, 2025. Available from: https://doi.org/10.55524/ijircst.2025.13.4.4

Corresponding Author

Sheharyar Nasir

Doctoral Student, Department of Aerospace Engineering, University of Kansas, Lawrence, Kansas, USA

Download Full Paper

Download PDF

No. of Downloads: 9 | No. of Views: 146

Physics-Informed Neural Networks for Predicting Combustion Dynamics in Rocket Engine Chambers

Citations

Download Full Paper PDF

Total View 146

Total Download 9