A Residual-Driven Framework for Integrating Digital Twins and AI-Based Fault Detection in Chemical Process Automation
DOI:
https://doi.org/10.61978/catalyx.v1i2.1265Keywords:
Digital Twin, Fault Detection, Anomaly Detection, Process Automation, Hybrid Modeling, Industry 4.0, Chemical EngineeringAbstract
The increasing complexity of chemical process operations necessitates more intelligent monitoring and control systems. This study presents an integrated framework that combines hybrid Digital Twin (DT) models with AI-based Fault Detection and Diagnosis (FDD) for real-time anomaly detection and process optimization. The proposed architecture leverages residuals from DT predictions as inputs to machine learning models, enhancing fault detection accuracy and reducing operational inefficiencies. The methodology adopts a multi-layer industrial architecture, incorporating ISA-95 and O-PAS principles for interoperability. DT models integrate first-principles physics with machine learning for predictive accuracy, while AI models such as CNN-LSTM hybrids and autoencoders detect anomalies based on residual patterns. Validation was conducted using synthetic and benchmark datasets, including the Tennessee Eastman Process. Results demonstrate that the integrated DT–AI system significantly outperforms traditional methods, with detection delay reduced by over 50%, false alarm rates cut by two-thirds, and energy intensity decreased by 13%. Additional benefits include improved product quality, reduced off-spec production, and enhanced operator response. The study concludes that combining DT and AI technologies within a standards-compliant framework enhances predictive capabilities, operational safety, and sustainability. This integration offers a scalable solution for modernizing brownfield chemical plants and advancing toward Industry 4.0.
References
Al-Mutayeb, Y., Almobaied, M., & Ouda, M. (2024). Real-Time Simulation and Experimental Implementation of Luenberger Observer-Based Speed Sensor Fault Detection of BLDC Motors. Acta Mechanica Et Automatica, 18(1), 144–157. https://doi.org/10.2478/ama-2024-0019 DOI: https://doi.org/10.2478/ama-2024-0019
Amin, A. A., Maqsood, M. T., & Mahmood-ul-Hasan, K. (2021). Surge Protection of Centrifugal Compressors Using Advanced Anti-Surge Control System. Measurement and Control, 54(5–6), 967–982. https://doi.org/10.1177/0020294020983372 DOI: https://doi.org/10.1177/0020294020983372
Caiza, G., & Sanz, R. (2023). Digital Twin to Control and Monitor an Industrial Cyber-Physical Environment Supported by Augmented Reality. Applied Sciences, 13(13), 7503. https://doi.org/10.3390/app13137503 DOI: https://doi.org/10.3390/app13137503
Chakraborty, S., & Adhikari, S. (2021). Machine Learning Based Digital Twin for Dynamical Systems With Multiple Time-Scales. Computers & Structures, 243, 106410. https://doi.org/10.1016/j.compstruc.2020.106410 DOI: https://doi.org/10.1016/j.compstruc.2020.106410
Chen, P.-H., Chen, W., Lee, C., & Wu, J. (2023). Comprehensive Review of Crystalline Silicon Solar Panel Recycling: From Historical Context to Advanced Techniques. Sustainability, 16(1), 60. https://doi.org/10.3390/su16010060 DOI: https://doi.org/10.3390/su16010060
Chew, M. Y. L., & Yan, K. (2022). Enhancing Interpretability of Data-Driven Fault Detection and Diagnosis Methodology With Maintainability Rules in Smart Building Management. Journal of Sensors, 2022, 1–48. https://doi.org/10.1155/2022/5975816 DOI: https://doi.org/10.1155/2022/5975816
Correa, O. C., Mariano, J. S., Amaro, E. P., & Santos, E. d. N. (2023). Process Safety Management in Oil and Gas Operating Units Through Digital Twin Platform: A Digital Approach for Safety Control and Process Intervention. https://doi.org/10.4043/32894-ms DOI: https://doi.org/10.4043/32894-MS
Daley, J. M., Khan, F., & Amin, Md. T. (2023). Process Safety Analysis Using Operational Data and Bayesian Network. Process Safety Progress, 42(2), 269–280. https://doi.org/10.1002/prs.12441 DOI: https://doi.org/10.1002/prs.12441
Dhirani, L. L., Armstrong, E., & Newe, T. (2021). Industrial IoT, Cyber Threats, and Standards Landscape: Evaluation and Roadmap. Sensors, 21(11), 3901. https://doi.org/10.3390/s21113901 DOI: https://doi.org/10.3390/s21113901
Elnour, M., Ahmad, A. M., Abdelkarim, S. B., Fadli, F., & Naji, K. K. (2024). Empowering Smart Cities With Digital Twins of Buildings: Applications and Implementation Considerations of Data-Driven Energy Modelling in Building Management. Building Services Engineering Research and Technology, 45(4), 475–498. https://doi.org/10.1177/01436244241239290 DOI: https://doi.org/10.1177/01436244241239290
Forooghi, A., Trudvang, Christian. F., Gupta, G., Kjoerrefjord, G., & Karimi, H. (2022). Fenja Digital Twin With Automated Advisory: A Solution for Operational Excellence. https://doi.org/10.2118/211101-ms DOI: https://doi.org/10.2118/211101-MS
Fortoul-Diaz, J. A., Carrillo-Martinez, L. A., Centeno-Téllez, A., Cortés-Santacruz, F., Olmos-Pineda, I., & Quintero, R. R. F. (2023). A Smart Factory Architecture Based on Industry 4.0 Technologies: Open-Source Software Implementation. IEEE Access, 11, 101727–101749. https://doi.org/10.1109/access.2023.3316116 DOI: https://doi.org/10.1109/ACCESS.2023.3316116
Goudarzi, S., Anisi, M. H., Abdullah, A. H., Lloret, J., Soleymani, S. A., & Hassan, W. H. (2019). A Hybrid Intelligent Model for Network Selection in the Industrial Internet of Things. Applied Soft Computing, 74, 529–546. https://doi.org/10.1016/j.asoc.2018.10.030 DOI: https://doi.org/10.1016/j.asoc.2018.10.030
Harrison, R., Vera, D., & Ahmad, B. (2021). A Connective Framework to Support the Lifecycle of Cyber-Physical Production Systems. Proceedings of the IEEE, 109(4), 568–581. https://doi.org/10.1109/jproc.2020.3046525 DOI: https://doi.org/10.1109/JPROC.2020.3046525
Hodavand, F., Ramaji, I. J., & Sadeghi, N. (2023). Digital Twin for Fault Detection and Diagnosis of Building Operations: A Systematic Review. Buildings, 13(6), 1426. https://doi.org/10.3390/buildings13061426 DOI: https://doi.org/10.3390/buildings13061426
Huang, Z., Shen, Y., Li, J., Fey, M., & Brecher, C. (2021). A Survey on AI-Driven Digital Twins in Industry 4.0: Smart Manufacturing and Advanced Robotics. Sensors, 21(19), 6340. https://doi.org/10.3390/s21196340 DOI: https://doi.org/10.3390/s21196340
Iqbal, M. Z., Khan, A. H., Iqbal, M., & Sulaiman, S. A. S. (2019). A Review of Pharmacist-Led Interventions on Diabetes Outcomes: An Observational Analysis to Explore Diabetes Care Opportunities for Pharmacists. Journal of Pharmacy and Bioallied Sciences, 11(4), 299. https://doi.org/10.4103/jpbs.jpbs_138_19 DOI: https://doi.org/10.4103/jpbs.JPBS_138_19
Khan, M. S. U. (2024). Digital Twin-Driven Optimization of Bioenergy Production From Waste Materials. Itej, 1(01), 187–204. https://doi.org/10.70937/itej.v1i01.19 DOI: https://doi.org/10.70937/itej.v1i01.19
Kulvatunyou, B., Ivezic, N., & Srinivasan, V. (2016). On Architecting and Composing Engineering Information Services to Enable Smart Manufacturing. Journal of Computing and Information Science in Engineering, 16(3). https://doi.org/10.1115/1.4033725 DOI: https://doi.org/10.1115/1.4033725
Lin, G., Pritoni, M., Chen, Y., & Granderson, J. (2020). Development and Implementation of Fault-Correction Algorithms in Fault Detection and Diagnostics Tools. Energies, 13(10), 2598. https://doi.org/10.3390/en13102598 DOI: https://doi.org/10.3390/en13102598
Mowbray, M., Vallerio, M., Perez-Galvan, C., Zhang, D., Río-Chanona, E. A. d., & Navarro-Brull, F. J. (2022). Industrial Data Science - A Review of Machine Learning Applications for Chemical and Process Industries. Reaction Chemistry & Engineering, 7(7), 1471–1509. https://doi.org/10.1039/d1re00541c DOI: https://doi.org/10.1039/D1RE00541C
Mozaffari, F. S., Karimipour, H., & Parizi, R. M. (2020). Learning Based Anomaly Detection in Critical Cyber-Physical Systems (pp. 107–130). https://doi.org/10.1007/978-3-030-45541-5_6 DOI: https://doi.org/10.1007/978-3-030-45541-5_6
Nandhini, R., & Ramanathan, L. (2023). A Novel Ensemble Learning Approach for Fault Detection of Sensor Data in Cyber-Physical System. Journal of Intelligent & Fuzzy Systems, 45(6), 12111–12122. https://doi.org/10.3233/jifs-235809 DOI: https://doi.org/10.3233/JIFS-235809
Narayanan, H., Stosch, M. v., Feidl, F., Sokolov, M., Morbidelli, M., & Butté, A. (2023). Hybrid Modeling for Biopharmaceutical Processes: Advantages, Opportunities, and Implementation. Frontiers in Chemical Engineering, 5. https://doi.org/10.3389/fceng.2023.1157889 DOI: https://doi.org/10.3389/fceng.2023.1157889
Palanisamy, C., & Gangadharan, T. (2024). Review on Development of Digital Twins for Predicting, Mitigating Faults and Defects in Solar Plants. International Journal on Robotics Automation and Sciences, 6(2), 1–5. https://doi.org/10.33093/ijoras.2024.6.2.1 DOI: https://doi.org/10.33093/ijoras.2024.6.2.1
Park, Y.-H., Love, A., Behseresht, S., Pastrana, O. V, & Sakai, J. (2024). Digital Twin Development for Additive Manufacturing. https://doi.org/10.1115/pvp2024-122920 DOI: https://doi.org/10.1115/PVP2024-122920
Pontarolli, R. P., Bigheti, J. A., Domingues, F. O., Lucas Borges Rodrigues de Sá, & Godoy, E. P. (2022). Distributed I/O as a Service: A Data Acquisition Solution to Industry 4.0. HardwareX, 12, e00355. https://doi.org/10.1016/j.ohx.2022.e00355 DOI: https://doi.org/10.1016/j.ohx.2022.e00355
Radanliev, P., Roure, D. D., Nicolescu, R., Huth, M., & Santos, O. (2021). Artificial Intelligence and the Internet of Things in Industry 4.0. CCF Transactions on Pervasive Computing and Interaction, 3(3), 329–338. https://doi.org/10.1007/s42486-021-00057-3 DOI: https://doi.org/10.1007/s42486-021-00057-3
Represa, J. G., Larrinaga, F., Varga, P., Ochoa, W., Pérez, A., Kozma, D., & Delsing, J. (2023). Investigation of Microservice-Based Workflow Management Solutions for Industrial Automation. Applied Sciences, 13(3), 1835. https://doi.org/10.3390/app13031835 DOI: https://doi.org/10.3390/app13031835
Serôdio, C., Mestre, P., Cabral, J., Gomes, M. F., & Branco, F. (2024). Software and Architecture Orchestration for Process Control in Industry 4.0 Enabled by Cyber-Physical Systems Technologies. Applied Sciences, 14(5), 2160. https://doi.org/10.3390/app14052160 DOI: https://doi.org/10.3390/app14052160
Solle, D., Hitzmann, B., Herwig, C., Remelhe, M. P., Ulonska, S., Wuerth, L., Prata, A., & Steckenreiter, T. (2017). Between the Poles of Data-Driven and Mechanistic Modeling for Process Operation. Chemie Ingenieur Technik, 89(5), 542–561. https://doi.org/10.1002/cite.201600175 DOI: https://doi.org/10.1002/cite.201600175
Thorpe, P. A. (2022). A Dynamically Reconciled Digital Twin for Operations Optimization and Decision Support. https://doi.org/10.2118/210987-ms DOI: https://doi.org/10.2118/210987-MS
Todescato, M., Braholli, O., Chaltsev, D., Blasio, I. D., Don, D., Egger, G., Emig, J., Monizza, G. P., Sacco, P., Siegele, D., Steiner, D., Terzer, M., Riedl, M., Giusti, A., & Matt, D. T. (2023). Sustainable Manufacturing Through Application of Reconfigurable and Intelligent Systems in Production Processes: A System Perspective. Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023-49727-5 DOI: https://doi.org/10.1038/s41598-023-49727-5
Udugama, I. A., Öner, M., López, P. C., Beenfeldt, C., Bayer, C., Huusom, J. K., Gernaey, K. V, & Sin, G. (2021). Towards Digitalization in Bio-Manufacturing Operations: A Survey on Application of Big Data and Digital Twin Concepts in Denmark. Frontiers in Chemical Engineering, 3. https://doi.org/10.3389/fceng.2021.727152 DOI: https://doi.org/10.3389/fceng.2021.727152
Yahyaoui, Z., Hajji, M., Mansouri, M., & Bouzrara, K. (2023). One-Class Machine Learning Classifiers-Based Multivariate Feature Extraction for Grid-Connected PV Systems Monitoring Under Irradiance Variations. Sustainability, 15(18), 13758. https://doi.org/10.3390/su151813758 DOI: https://doi.org/10.3390/su151813758
Zhang, D., Rio-Chanona, E. A. d., Petsagkourakis, P., & Wagner, J. L. (2019). Hybrid Physics-based and Data-driven Modeling for Bioprocess Online Simulation and Optimization. Biotechnology and Bioengineering, 116(11), 2919–2930. https://doi.org/10.1002/bit.27120 DOI: https://doi.org/10.1002/bit.27120
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Catalyx : Journal of Process Chemistry and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
