AI-Driven Automation for Safety Monitoring in the Chemical Industry: A Review of Hazard Detection, Anomaly Detection, and Predictive Risk Assessment

1. Alviz-Meza, A. Valencia-Arias, F. Diaz, B. Motta, and G. Sanchez, “Selective reporting and evaluation protocol shape the evidence on deep learning fault detection in the Tennessee Eastman Process: A systematic review and meta-analysis,” Machine Learning and Knowledge Extraction, vol. 8, no. 11, Art. no. 349, 2026, doi: 10.3390/make8110349.
2. H. Yang, T. L. Kareck, and Q. Wang, “New era of AI in chemical process safety: Foundation models,” ACS Chemical Health & Safety, vol. 33, pp. 171–179, 2026, doi: 10.1021/acs.chas.5c00227.
3. N. Tamascelli, A. Campari, T. Parhizkar, and N. Paltrinieri, “Artificial intelligence for safety and reliability: A descriptive, bibliometric and interpretative review on machine learning,” Journal of Loss Prevention in the Process Industries, vol. 90, Art. no. 105343, 2024, doi: 10.1016/j.jlp.2024.105343. L. Eydam, H. Lange, and L. Urbas, “Hybrid fault diagnosis in the process and chemical industries: A review,” Annual Reviews in Control, vol. 62, Art. no. 101064, 2026, doi: 10.1016/j.arcontrol.2026.101064.
4. X. Jiang, H. Xie, J. Wang, Z. Yang, Y. Zhou, L. Yao, and Z. Zhu, “Agentic AI for safety-aware process monitoring and fault diagnosis: A review,” Processes, vol. 14, no. 13, Art. no. 2112, 2026, doi: 10.3390/pr14132112.
5. Yang, T. Amin, Z. Sajid, and F. Khan, “Generative artificial intelligence (Gen-AI)-driven method for hazard scenario generation in chemical process systems,” Process Safety and Environmental Protection, vol. 213, Art. no. 108977, 2026, doi: 10.1016/j.psep.2026.108977.
6. J. B. Avanashilingam and B. P. Velayudhan, “Explainable and trustworthy AI for fault classification in the Tennessee Eastman Process: A step toward industrial autonomy,” in Proceedings of the Annual Conference of the Prognostics and Health Management Society, 2025.
7. Y. Devarajan et al., “A review of model uncertainty, cyber–physical threats and assurance frameworks for safety-critical AI in process industries,” IET Cyber-Physical Systems: Theory & Applications, vol. 11, Art. no. e70062, 2026, doi: 10.1049/cps2.70062.
8. Ji and W. Sun, “A review on data-driven process monitoring methods: Characterization and mining of industrial data,” Processes, vol. 10, no. 2, Art. no. 335, 2022, doi: 10.3390/pr10020335.
9. Ji et al., “Bridging the gap in chemical process monitoring: Beyond algorithm-centric research toward industrial deployment,” Processes, vol. 13, Art. no. 3809, 2025, doi: 10.3390/pr13123809.
10. Hartung et al., “Deep anomaly detection on Tennessee Eastman Process data,” Chemie Ingenieur Technik, 2023, doi: 10.1002/cite.202200238.
11. S. Umer, N. Ullah, and J.-M. Kim, “Attention mechanism-based CNN-LSTM hybrid deep learning model for industrial pipeline leak detection,” Scientific Reports, vol. 16, Art. no. 22763, 2026, doi: 10.1038/s41598-026-53776-x.
12. J. H. Lee, Y. Kim, A. Rehman, I. Kim, J. Lee, and H. Yun, “Development of an AI-based image/ultrasonic convergence camera system for accurate gas leak detection in petrochemical plants,” Heliyon, vol. 10, no. 7, Art. no. e28905, 2024, doi: 10.1016/j.heliyon.2024.e28905.
13. P. Salunkhe, A. Tilak, M. Shirole, and N. Mehendale, “Autonomous gas leak detection in hazardous environments using gradient-guided depth-first search algorithm,” Automation, vol. 7, no. 1, Art. no. 13, 2026, doi: 10.3390/automation7010013.
14. Morales-Medina and S. Reyes-Angarita, “Detection of operational failures with artificial neural networks: Application to the Tennessee Eastman process,” Revista Ingenierías Universidad de Medellín, vol. 23, no. 44, pp. 1–19, 2024, doi: 10.22395/rium.v23n44a1.
15. F. Koçak, A. Saygın, F. Türk, and A. M. Karadeniz, “Run-level fault detection and SHAP-based diagnosis of persistent classification difficulty in the Tennessee Eastman Process,” Processes, vol. 14, no. 16, Art. no. 2569, 2026, doi: 10.3390/pr14162569. . Li, Y. Xue, J. Fu, T. Tan, Y. Yang, and J. Nie, “An evolutionary weighted feature influence factor feature selection method for fault detection in the Tennessee Eastman complex chemical process,” Scientific Reports, vol. 16, Art. no. 19405, 2026, doi: 10.1038/s41598-026-49874-5.
16. M. Mudasir et al., “RBC-AD: Conformal anomaly detection with explicit false-alarm control for the Tennessee Eastman Process,” Connection Science, vol. 38, no. 1, Art. no. 2707826, 2026, doi: 10.1080/09540091.2026.2707826.
17. Alrowaie, “Digital twins and artificial intelligence for HAZOP enhancement in process safety: A critical literature review,” Processes, vol. 14, Art. no. 2334, 2026, doi: 10.3390/pr14142334.
18. P. Gavali and J. S. Banu, “A novel approach to Indian bird species identification: Employing visual-acoustic fusion techniques for improved classification accuracy,”Frontiers in Artificial Intelligence, vol. 8, Art. no. 1527299, 2025, doi: 10.3389/frai.2025.1527299.
19. P. Gavali and J. S. Banu, “Deep convolutional neural network for automated bird species classification,” Traitement du Signal, vol. 41, no. 1, pp. 261–271, 2024, doi: 10.18280/ts.410121.
20. P. R. Gavali and J. S. Banu, “DQFCNN: A new deep learning architecture for bird species classification based on images,” Journal of Circuits, Systems and Computers, vol. 34, no. 12, 2025, doi: 10.1142/S0218126625502895.
21. P. R. Gavali and J. S. Banu, “Energy Valley Flamingo Search optimization trained hybrid deep learning for bird species classification,” International Journal of Biomathematics, 2025, doi: 10.1142/S1793524525501086.
22. P. Gavali and J. S. Banu, “Deep convolutional neural network for image classification on CUDA platform,” in Deep Learning and Parallel Computing Environment for Bioengineering Systems. Academic Press, 2019, pp. 99–122, doi: 10.1016/B978-0-12-816718-2.00013-0.
23. P. Gavali and J. S. Banu, “Bird species identification using deep learning on GPU platform,” in Proc. 2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE), 2020, pp. 1–6, doi: 10.1109/ic-ETITE47903.2020.85.