Digital Twin and AI Powered Optimization Framework for Smart Petrochemical Operations under Saudi Vision 2030

References

[1] Ali, M., Mahmood, T., & Khan, F. (2025). Review of artificial intelligence applications in sustainable chemical engineering. Discover Sustainability, 6, 1-32.

[2] Ansari, T., Taqvi, S. A. A., & Almansoori, A. (2024). Artificial intelligence for chemical process safety and sustainable operations: A review. Process Safety and Environmental Protection, 181, 1250-1268.

[3] Aramco Careers. (2025). Process simulation twin and optimization engineer: Refinery operations and online process digital twins. Saudi Aramco Careers.

[4] Bortz, M., Tinsley, A., & Reklaitis, G. (2024). Artificial intelligence in process industries: Current practice, limitations, and industrial opportunities. Computers & Chemical Engineering, 186, 108613.

[5] Das, A., Date, A., & Alami, A. H. (2023). AI-powered approaches for water desalination and process sustainability: A review. Desalination, 563, 116793.

[6] Elgarahy, A. M., Elwakeel, K. Z., & Elgarahy, A. M. (2024). Circular valorization of biowaste using AI-assisted optimization frameworks. Journal of Environmental Management, 362, 121004.

[7] Goel, P., & Singh, S. P. (2024). Enterprise data integration and real-time process analytics for intelligent operations. International Journal of Information Technology, 16(3), 1451-1464.

[8] Hydrocarbon Processing. (2024). Deliver sustainable benefits through site-wide process digital twins. Hydrocarbon Processing, 103(9), 41-47.

[9] Jafari, M., Ghaffari, A., & Khorasani, M. (2024). Artificial intelligence for membrane separation and fouling control: State of the art and future opportunities. Separation and Purification Technology, 340, 127948.

[10] Jampani, S., Cheruku, S. R., Thakur, D., Prasad, M. S. R., Kaushik, S., & Goel, P. (2023). Leveraging AI in SAP for real-time data processing. International Journal of Progressive Research in Engineering Management and Science, 3(11), 428-448.

[11] Jiao, Y., Zhang, H., & Liu, X. (2021). Digital twin-driven optimization and control for intelligent industrial systems. Journal of Manufacturing Systems, 61, 229-243.

[12] Karkaria, V., Skoogh, A., & Johansson, B. (2025). An optimization-centric review on integrating artificial intelligence and digital twins in manufacturing. International Journal of Production Research, 63(4), 1021-1048.

[13] Kim, J., Lee, H., & Park, S. (2024). AI-assisted sustainability optimization in petrochemical process systems. Chemical Engineering Research and Design, 204, 357-371.

[14] Li, X., Zhao, Y., & Chen, Q. (2024). Multiscale modelling and optimization for sustainable process operations using digital twins. Industrial & Engineering Chemistry Research, 63(18), 7614-7629.

[15] Mahamod, I., Shayea, I., & Ergen, M. (2023). Intelligent optimization strategies for future industrial cyber-physical systems. IEEE Access, 11, 77412-77439.

[16] Marquez, F. P. G., Schmitt, R. H., & Wang, Z. (2024). Digital twins for predictive maintenance and resource efficiency in process and manufacturing industries. Machines, 12(4), 221.

[17] Meng, J., Suo, H., & Gao, L. (2023). Development and analysis of a petrochemical smart factory utilizing digital twin technology. ESCAPE Proceedings, 34, 1-6.

[18] Mousavi, S. H., Mirjalili, S., & Ahmadianfar, I. (2025). Generative AI and digital intelligence for optimizing renewable and industrial energy systems. Energy AI, 12, 100261.

[19] Narayanan, P., Nair, A., & Rajan, K. (2024). AI techniques for intelligent wastewater and utility management in process industries. Journal of Cleaner Production, 452, 142157.

[20] Pascoschi, G., Cimini, C., & Cavalieri, S. (2024). AI-assisted energy optimization in manufacturing systems: Evidence from injection moulding and process plants. Journal of Manufacturing Technology Management, 35(7), 1061-1083.

[21] Pham, T., Nguyen, M., & Tran, H. (2024). Machine learning and digital twins for circular petrochemical operations and polymer recycling. Resources, Conservation and Recycling, 207, 107609.

[22] Rangel-Martinez, D., Martinez, N., & Ponce, P. (2024). Artificial intelligence in sustainable energy systems and catalysis: A review. Energy Reports, 10, 5168-5190.

[23] Redchuk, A., Kliueva, I., & Boichenko, S. (2025). Industry 5.0 and digital twins in the chemical industry. ChemEngineering, 9(4), 78.

[24] Rivera, J., Gomez, M., & Serrano, D. (2024). Computer-aided sustainability improvement in bioethanol and process industries. Sustainable Production and Consumption, 46, 437-451.

[25] Sun, H., Diao, C., & Zhao, M. (2024). Data-centric optimization for smart chemical operations under Industry 5.0. AIChE Journal, 70(11), e18482.

[26] Usman, M., Khan, M. U., & Imran, M. (2024). Artificial intelligence for sustainable treatment and separation operations in industrial wastewater systems. Journal of Water Process Engineering, 61, 105063.

[27] Wang, S., Zhang, Y., & Liu, Z. (2022). Process digital twin and its application in petrochemical industry. Journal of Service Science and Management, 15(4), 308-321.

[28] Xuan, Y., Li, P., & Zhao, J. (2025). Intelligent membrane and process monitoring with AI-enhanced digital twins. Membranes, 15(2), 131.

[29] Zhang, H., Li, Y., & Xu, J. (2025). Artificial intelligence-enhanced digital twin systems for intelligent industry: Concepts, architecture, and optimization. International Journal of Advanced Manufacturing Technology, 136, 1123-1145.

[30] Zhou, Y., Zhu, K., & Du, Z. (2024). Intelligent process digital twins for real-time optimization, diagnostics, and decision support. Computers in Industry, 159, 104058.

@article{1719700,
      author = {Syed Arif Ali Bukharee},
      title = {Digital Twin and AI Powered Optimization Framework for Smart Petrochemical Operations under Saudi Vision 2030},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {10},
      number = {1},
      pages = {1042-1053},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1719700.pdf},
      abstract = {Digital transformation is reshaping petrochemical value creation as producers seek higher reliability, lower energy intensity, safer operations, and stronger environmental performance under increasingly volatile market conditions. Within this shift, digital twins and artificial intelligence have moved from isolated pilots to an integrated capability that can synchronize plant data, process models, asset histories, and optimization logic across the full operating lifecycle. This review examines how digital twin architectures, AI techniques, and industrial connectivity can be combined into an optimization framework for smart petrochemical operations aligned with Saudi Vision 2030. The study has three objectives: to synthesize the technological foundations of digital twins for petrochemical plants; to assess how AI supports prediction, diagnosis, control, maintenance, and decision optimization; and to develop an implementation framework tailored to Saudi industrial priorities, including productivity, localization, sustainability, and workforce capability. A structured review methodology inspired by recent review designs in chemical engineering and future industrial systems was used to organize evidence published between 2020 and 2025. The analysis indicates that the strongest operational value emerges when physics-based process knowledge is fused with machine learning, historian data, IIoT streams, and enterprise systems rather than when AI or digital twins are deployed as stand-alone tools. Across the literature, high-value applications include soft sensing, abnormal situation detection, energy optimization, predictive maintenance, production scheduling, emissions monitoring, and operator decision support. Yet the review also finds persistent barriers in model governance, cyber risk, data quality, semantic interoperability, and organizational readiness. To address these gaps, the paper proposes a layered framework linking sensing, contextualization, hybrid modelling, AI analytics, prescriptive optimization, and human-in-the-loop governance. The framework is discussed in relation to petrochemical complexes in Saudi Arabia, where integration with process simulation, SAP-like enterprise workflows, reliability systems, and sustainability reporting can accelerate both operational excellence and Vision 2030 outcomes.},
      keywords = {Digital Twin, Artificial Intelligence, Petrochemical Operations, Hybrid Modelling, Predictive Maintenance, Energy Optimization, Saudi Vision 2030},
      month = {July},
      doi = {https://doi.org/10.64388/IREV10I1-1719700}
  }