Iranian Chemical Engineering Journal

Iranian Chemical Engineering Journal

Data-Driven Fault Diagnosis in Gas Refining Processes: A Case Study Using Support Vector Regressionand Gaussian Process Regression

Document Type : Original Article

Authors
Seyed Hossein Ahmadi 1
M. J. Khosrowjerdi 2
1 PhD. Student of Control Engineering, Tabriz University of Technology
2 Professor of Control Engineering, Tabriz University of Technology
10.22034/ijche.2025.495041.1482
Abstract
Rapid fault diagnosis in complex processes of gas refineries is a key challenge in process engineering and control, due to the strategic importance of this equipment and the high maintenance costs. Despite the vast amount of data generated in these processes, the effective exploitation of this data has been limited so far. In data-driven fault detection methods, two main approaches exist: fault detection and classification, and fault diagnosis and fault measurement, with the latter being achievable through regression techniques or accurate models. This paper presents a machine learning-based approach for the regression modeling of industrial systems with outlier and noisy data, tailored for fault diagnosis applications. For fault diagnosis, two regression methods, including Support Vector Machine Regression and Gaussian Process Regression, have been utilized. These models are capable of predicting the behavior of industrial systems and diagnosis faults without the need for precise physical models. The main innovation of this paper is the introduction of a machine learning framework that can perform more accurately and rapidly compared to traditional expert fault diagnosis methods, particularly in scenarios with outlier and noisy data.
Keywords
Data Driven Fault Diagnosis
Machine Learning
Support Vector Machine Regression
Gaussian Process Regression
Distributed Control Systems
Gas Refining Processes
Subjects
[1]        Ahmadi, S. H., & Khosrowjerdi, M. J. (2021). Fault detection Automation in Distributed Control Systems using Data-driven methods : SVM and KNN. TechRxiv. Preprint.
[2]        Akbarpour, S., & Khosrowjerdi, M. J. (2024). Estimation of Combustor and Compressor Faults in Industrial Gas Turbines by Using Multiple Model Approach. Iranian Chemical Engineering Journal, 23(134), [In Persian].
[3]        Alzghoul, A., Backe, B., Löfstrand, M., Byström, A., & Liljedahl, B. (2014). Comparing a knowledge-based and a data-driven method in querying data streams for system fault detection: A hydraulic drive system application. Computers in Industry, 65(8), 1126–1135.
[4]        Chandrashekar, G., & Sahin, F. (2014). A survey on feature selection methods. Computers and Electrical Engineering, 40(1), 16–28.
[5]        Cheliotis, M., Lazakis, I., & Theotokatos, G. (2020). Machine learning and data-driven fault detection for ship systems operations. Ocean Engineering, 216.
[6]        Chen, Z., O’Neill, Z., Wen, J., Pradhan, O., Yang, T., Lu, X., Lin, G., Miyata, S., Lee, S., Shen, C., Chiosa, R., Piscitelli, M. S., Capozzoli, A., Hengel, F., Kührer, A., Pritoni, M., Liu, W., Clauß, J., Chen, Y., & Herr, T. (2023). A review of data-driven fault detection and diagnostics for building HVAC systems. Applied Energy, 339. 
[7]        Clavijo, N., Melo, A., Câmara, M. M., Feital, T., Anzai, T. K., Diehl, F. C., Thompson, P. H., & Pinto, J. C. (2019). Development and application of a data-driven system for sensor fault diagnosis in an oil processing plant. Processes, 7(7).
[8]        Donald R. Woods. (2021). Troubleshooting Guide for Process Engineers: A Complete Course with Applied Examples and Glossary.
[9]        Habibi, H., Howard, I., & Simani, S. (2019). Reliability improvement of wind turbine power generation using model-based fault detection and fault tolerant control: A review. In Renewable Energy, 135, 877–896, Elsevier Ltd.
[10]      M. J. Khosrowjerdi, & Mahdi Aliyari-Shoorehdeli. (2014). Fault Diagnosis and Compensation in Control Systems. Sahand University of Technology (SUT), [In Persian].
[11]      Mohsen Maleki Douz-Zadeh, & Hamid, M. (2013). Investigation of the Effect of Changing the Location of Heat Exchangers in the Abadan Refinery Distillation Unit on the Performance of the Furnace and Flash Drum. Iranian Chemical Engineering Journal, 12(66),58-65, [In Persian].
[12]      Norman P. Lieberman - Troubleshooting Process Plant Control_ A Practical Guide to Avoiding and Correcting Mistakes-John Wiley & Sons (2024).
[13]     Sarmast Alizadeh, F., & Esfandiari, N. (2024). Measuring the Quality of Industrial Water Used in a Chemical Plant Using arTificial Intelligence (Logistic Regression, Naive Bayesian, Support Vector Machine, Random forest, and Decision Tree). Iranian Chemical Engineering Journal, 23(135), 90–101,[In Persian].
[14]      Sayadmosleh, E., Shirazi, L., Soleimani, M., & Sarmad, M. (2022). Comparison of the Thermodynamic Effect of Ethane and Ethylene in the Mixed Refrigerant Cycle of the Natural Gas Liquefaction Process. Iranian Chemical Engineering Journal, 21(123), 7–21, [In Persian].
[15]      Tidriri, K., Chatti, N., Verron, S., & Tiplica, T. (2016). Bridging data-driven and model-based approaches for process fault diagnosis and health monitoring: A review of researches and future challenges. In Annual Reviews in Control, 42, 63-81, Elsevier Ltd.
[16]      Yan, F., Zhang, X., Yang, C., Hu, B., Qian, W., & Song, Z. (2023). Data-driven modelling methods in sintering process: Current research status and perspectives. In Canadian Journal of Chemical Engineering, 101(8), 4506-4522, John Wiley and Sons Inc.
[17]      Zhao, Y., Wang, S., & Xiao, F. (2013). A system-level incipient fault-detection method for HVAC systems. HVAC and R Research, 19(5), 593–601.
Iranian Chemical Engineering Journal
Volume 24, Issue 143
March and April 2026
Pages 50-59