Abstract
The efficiency of oil combusting and gas facilities deals with energy expenses as well as operational costs and the overall carbon footprint. Other approaches use simplistic dynamic control and process automation, but these approaches are neither flexible enough to account for drifts and dynamics in real-time, nor performant enough for process deviation in real-time to respond. This paper describes a transformer internal combustion engine with a scalable, platform agnostic AI architecture for combustion IT forecasting combined with real-time hardware integration from enterprise systems like SAP S/4HANA, Oracle, and Siemens MindSphere, using hybrid GRU machine learning with dense GRU neural networks. The process unites level balance thermodynamic models with sequential learning to physically integrated geo-temporal coupling learning. Operational data spanning 6 months and 3 plants (6.5 million samples) was used to train the system. The system beat conventional machine learning approaches with RMSE 2.1–2.4, MAE 1.7–1.9, and R2 > 0.91 for combustion-efficiency forecasting. The models were robust as they kept the mean +/- SD and 5% confidence intervals on all metrics with temporally disjoint folds. Real-time availability of the entire network was confirmed with mean latency of 0.1 s and availability metrics of 99.7%. Using SHAP-based feature attribution for interpretability allowed operators to identify the sensors that impacted gaps in the driven efficiencies, thus improving trust in the AI-based control. From the sustainability perspective, the recorded 2–5% efficiency improvements directly translate to fuel savings and lowered CO₂ emissions authoritative to the ISO 50,001 energy efficiency guidelines. This research provides a trustworthy and detailed explainable AI foundation for combustion systems that combines data-centric modeling and process engineering. Upcoming advances will add reinforcement-learning controllers and edge-only inference units for fully autonomous, transparent, and compliant autonomous optimization of industrial systems.
Data availability
The data supporting the findings of this study are provided within the manuscript. Any additional data required will be made available upon reasonable request from the corresponding author.
References
No, S. et al. An introduction to combustion concepts and applications. McGraw-Hill Korea (2011).
Lin, T. et al. Industrial equipment optimization for combustion performance enhancement: a real-world case study. Front. Energy Res. 12, 1364538 (2024).
Čampara, L. Nermin Hasanspahić, and Srđan Vujičić. Overview of MARPOL ANNEX VI regulations for prevention of air pollution from marine diesel engines. SHS web of conferences. Vol. 58. EDP Sciences, (2018).
Yao, Z., Romero, C. & Jonas Baltrusaitis. Combustion optimization of a coal-fired power plant boiler using artificial intelligence neural networks. Fuel 344, 128145 (2023).
Meng, Y. et al. Application of machine learning in industrial boilers: fault detection, diagnosis, and prognosis. ChemBioEng Reviews. 8 (5), 535–544 (2021).
Pourbabaee, B., Meskin, N. & Khorasani, K. Sensor fault detection, isolation, and identification using multiple-model-based hybrid Kalman filter for gas turbine engines. IEEE Trans. Control Syst. Technol. 24 (4), 1184–1200 (2015).
Vaughan, A. Adaptive Machine Learning for Modeling and Control of Non-Stationary, Near Chaotic Combustion in Real-Time. Diss. (2015).
Zhang, Y. et al. A big data driven analytical framework for energy-intensive manufacturing industries. J. Clean. Prod. 197, 57–72 (2018).
Li, J. et al. Data-driven enabling technologies in soft sensors of modern internal combustion engines. Perspect. Energy. 272, 127067 (2023).
Shaik, M. SAP-ERP software’s pivotal role in shaping industry 4.0: transforming the future of enterprise operations. Comput. Sci. Eng. 13 (1), 8–14 (2023).
Zhang, L. et al. Analysis and neural network prediction of combustion stability for industrial gases. Fuel 287, 119507 (2021).
Yassine, M. Multi-physics Modeling of the Intake Line of an Internal Combustion Engine (Diss. École centrale de Nantes, 2019).
Abouel-Seoud, S. A., Mohamed, S., Shiba & Ahmed, S. Abdallah. Real world evaluation and control of vehicle engine exhaust air pollution using adaptive neural fuzzy inference system. Int. J. Engine Res. 24 (5), 2233–2250 (2023).
Wu, Z. et al. The application of physics-informed machine learning in multiphysics modeling in chemical engineering. Ind. Eng. Chem. Res. 62, 18178–18204 (2023).
Tang, T. et al. Digital twin-enabled deep learning for real-time fire situation awareness. The Visual Computer : 1–13. (2025).
Islam, M., Tauhidul & Md Saiful, I. Design and optimization of a self-tuning PID controller based on Fuzzy Logic for Temperature Control System of Furnace. International Conference on Electronics, Communications and Information Technology (ICECIT). IEEE, 2021. IEEE, 2021. (2021).
Renault, M. et al. Investigating gas furnace control practices with reinforcement learning. Int. J. Heat Mass Transf. 209, 124147 (2023).
Neelis, M., Worrell, E. & Masanet, E. Energy efficiency improvement and cost saving opportunities for the petrochemical industry. An ENERGY STAR Guide for Energy and Plant Managers. LBNL-964E. Lawrence Berkeley National Laboratory, Berkeley, CA (2008).
Nguyen, L., Ahmed, T. & Krishnan, S. Neural-Symbolic models for explainable anomaly detection in SAP ERP systems. AI Enterp. Syst. Rev. 6 (1), 17–32 (2023).
Egbumokei, P. et al. The role of digital transformation in enhancing sustainability in oil and gas business operations. Int. J. Multidisciplinary Res. Growth Evaluation. 5, 2582–7138 (2024).
George, A. & Shaji The impact of IT/OT convergence on digital transformation in manufacturing. Partners Univers. Int. Innov. J. 2 (2), 18–38 (2024).
Mhaskey, S. V. Integration of Artificial Intelligence (AI) in Enterprise Resource Planning (ERP) Systems: Opportunities, Challenges, and Implications. Int. J. Comput. Eng. Res. Trends. 11 (12), 1–9 (2024).
Gupta, S., Chatterjee, A. & Lin, Y. Blockchain-Integrated SAP systems for Real-Time compliance and data integrity in industrial environments. J. Industrial Inform. Integr. 24, 100–112 (2023).
He, W. et al. A Novel Hybrid CNN-LSTM Scheme for Nitrogen Oxide Emission Prediction in FCC Unit. Math. Probl. Eng. 2020 (1), 8071810 (2020).
Batool, S., Naber, J. D. & Shahbakhti, M. Machine learning approaches for identification of heat release shapes in a low temperature combustion engine for control applications. Control Eng. Pract. 144, 105838 (2024).
Chen, Y. et al. Embedding-Figure-neural-network for transient NOx emissions prediction. Energies 16 (1), 3 (2022).
27 & Lamdjad Bouzidi. A Big Data-Driven Framework for Real-Time Quality Measurement and Predictive Control in Smart Manufacturing Systems. Available at SSRN 5645351.
28 et al. Explainable AI in manufacturing and industrial cyber–physical systems: A survey. Electronics 13, 3497 (2024).
Torres, M., Zhang, B. & Rao, P. Leveraging blockchain in SAP S/4HANA for Multi-Stakeholder supply chain traceability. IEEE Trans. Eng. Manage. 70 (2), 452–463 (2022).
Cação, J. José Santos, and Mário Antunes. Explainable Ai for Industrial Fault Diagnosis: A Systematic Review. Available at SSRN 5218920.
Funding
This research received no external funding. The APC was self-funded.
Author information
Authors and Affiliations
Contributions
S.R.K. and N.H.J. developed the research concept and conducted the primary investigations. N.S.J. and A.S. contributed to the data collection, analysis, and preparation of figures and tables. S.K.V. and S.E. assisted in literature review, manuscript formatting, and technical proofreading. G.V. contributed to the drafting of the manuscript and provided critical revisions.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethical approval
This research did not require ethical committee approval because it did not involve human participants.
Consent to participate
All authors confirmed that informed consent was obtained, and that no human subjects or human factors were involved in this study.
Consent to publish
All authors have given their consent for publication of this manuscript.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Keshireddy, S.R., Jamithireddy, N.H., Jamithireddy, N.S. et al. Combustion performance prediction in oil and gas plants using integrated neural network models and SAP S4HANA sensor analytics. Sci Rep (2026). https://doi.org/10.1038/s41598-026-35364-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-35364-1
