Abstract

A hybrid approach is then introduced in this paper to combine the DT technology with XAI to detect the anomaly in IIoT environment in real time. The system also integrates high-fidelity simulation models with sensor data in order to increase the accuracy of detection and decrease the number of false positives. It leverages SHAP-based explanations, counterfactual deliberation, and natural language normalization to render the system interpretable for the engineers or operators in charge of decision making. Experimental results on real industrial datasets achieve a detection accuracy of 95.3% and 78% of reduction in false positives with respect to the state of the art. The promising performance of XAI-DT integration with a decision-supported mechanism demonstrates its application value for reliable and transparent predictive maintenance in industrial domain.

References

• L. Monostori, "Cyber-physical production systems: Roots, expectations and R&D challenges," Procedia CIRP, vol. 17, pp. 9–13, 2014.
• M. Grieves and J. Vickers, "Digital Twin: Mitigating Unpredictable, Undesirable Emergent Behavior in Complex Systems," in Transdisciplinary Perspectives on Complex Systems, Springer, 2017, pp. 85–113.
• F. Doshi-Velez and B. Kim, "Towards a rigorous science of interpretable machine learning," arXiv preprint arXiv:1702.08608, 2017.
• Md. Abu Kausar, V. S. Dhaka, and S. K. Singh, "Web Crawler: A Review," International Journal of Computer Applications, vol. 63, no. 2, pp. 31–36, 2013.
• E. Mikołajewska, D. Mikołajewski, T. Mikołajczyk, and T. Paczkowski, “Generative AI in AI-Based Digital Twins for Fault Diagnosis for Predictive Maintenance in Industry 4.0/5.0,” Applied Sciences, vol. 15, no. 6, p. 3166, 2025. [Online]. Available: https://www.mdpi.com/2076-3417/15/6/3166
• ResearchGate, “Digital Twins in the IIoT: Current Practices and Future Directions Toward Industry 5.0,” ResearchGate, 2025. [Online]. Available: https://www.researchgate.net/publication/391211780
• Frontiers, “Explainable correlation-based anomaly detection for Industrial Control Systems,” Frontiers in Artificial Intelligence, 2025. [Online]. Available: https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1508821/full
• Brage NMBU, “Anomaly detection in industrial time series sensor data,” Master’s Thesis, 2025. [Online]. Available: https://nmbu.brage.unit.no/nmbu-xmlui/bitstream/handle/11250/3076750/no.nmbu%3Awiseflow%3A6839553%3A54592050.pdf
• PROMPT, “Lesson 114: SHAP and LIME,” AI-Prompt Journal, 2024. [Online]. Available: https://service.ai-prompt.jp/en/article/ai365-114/
• I. Taha and R. Barham, “Explainable AI: Using Shapley Value to Explain Complex Anomaly Detection ML-Based Systems,” ResearchGate, 2020. [Online]. Available: https://www.researchgate.net/publication/347324639
• BIG Conferences, “AI Explainability Methods in Digital Twins: A Model and a Use Case,” BIWEEK 2024 Conference Proceedings, 2024. [Online]. Available: https://conferences.big.tuwien.ac.at/biweek2024/pdfs/biweek2024_paper_91.pdf
• A. De Benedictis, F. Flammini, N. Mazzocca, A. Somma, and F. Vitale, “Digital Twins for Anomaly Detection in the Industrial Internet of Things: Conceptual Architecture and Proof-of-Concept,” IEEE Trans. Ind. Informat., accepted for publication, 2025. [Online]. Available: https://www.researchgate.net/publication/368728148
• InnovateEnergy, “How Digital Twins and AI Are Powering the Next Industrial Leap,” InnovateEnergy Journal, 2025. [Online]. Available: https://innovateenergynow.com/resources/how-digital-twins-and-ai-are-powering-the-next-industrial-leap
• ResearchGate, “Digital Twin-Assisted Anomaly Detection for Industrial Scenarios,” Int. J. Crit. Infrastruct. Prot., vol. 47, no. 4, p. 100721, 2025. [Online]. Available: https://www.researchgate.net/publication/385191780
• E. Mikołajewska, D. Mikołajewski, T. Mikołajczyk, and T. Paczkowski, “Generative AI in AI-Based Digital Twins for Fault Diagnosis for Predictive Maintenance in Industry 4.0/5.0,” Applied Sciences, vol. 15, no. 6, p. 3166, 2025. [Online]. Available: https://www.mdpi.com/2076-3417/15/6/3166
• ResearchGate, “Digital Twin-Assisted Anomaly Detection for Industrial Scenarios,” Int. J. Crit. Infrastruct. Prot., vol. 47, no. 4, p. 100721, 2025. [Online]. Available: https://www.researchgate.net/publication/385191780
• C. Alcaraz and J. Lopez, “Digital Twin-Assisted Anomaly Detection for Industrial Scenarios,” Int. J. Crit. Infrastruct. Prot., vol. 47, p. 100721, 2024. [Online]. Available: https://ideas.repec.org/a/eee/ijocip/v47y2024ics1874548224000623.html
• L. Lamberti, F. Cignetti, and M. Sacco, “Integration of Digital Twin, Machine-Learning and Industry 4.0 Tools for Anomaly Detection: An Application to a Food Plant,” Sensors, vol. 22, no. 11, p. 4143, 2022. [Online]. Available: https://www.mdpi.com/1424-8220/22/11/4143
• M. A. Faheem and N. U. Prince, “AI-Driven Anomaly Detection in IT Systems Using Digital Twins and NLP,” ResearchGate, 2025. [Online]. Available: https://www.researchgate.net/publication/388959580
• F. Malm, “Explainable AI for Time Series Anomaly Detection,” Master’s Thesis, DiVA portal, 2025. [Online]. Available: http://www.diva-portal.org/smash/get/diva2:1972404/FULLTEXT01.pdf
• Y. Zhan and J. Chen, “Explainable Deep Learning for Time Series Analysis: Integrating SHAP and LIME in LSTM-Based Models,” J. Inf. Syst. Eng. Manag., vol. 9, no. 3, p. 2627, 2024. [Online]. Available: https://jisem-journal.com/index.php/journal/article/view/2627/1031
• F. Rossi, “AI and Digital Twins,” People – UNIPI, 2023. [Online]. Available: https://people.unipi.it/federico_rossi/ai-and-digital-twins/
• Y. Wang and J. Huang, “Interpretable Anomaly Detection for Industrial Equipment based on Attention Mechanism,” J. Manuf. Syst., preprint, 2024.
• G. Vasileiadis et al., “Interactive Explainable Anomaly Detection for Industrial Settings,” arXiv preprint, arXiv:2410.12817, 2024. [Online]. Available: https://arxiv.org/html/2410.12817v1
• P. Kumar and A. Singh, “A Survey on Explainable AI for Predictive Maintenance in Industry 4.0,” J. Manuf. Technol. Manag., preprint, 2024.
• A. Abbas et al., “Explainable AI for Forensic Analysis: A Comparative Study of SHAP and LIME in Intrusion Detection Models,” Sensors, vol. 24, no. 13, p. 7329, 2024. [Online]. Available: https://www.mdpi.com/2076-3417/15/13/7329
• BIG Conferences, “AI Explainability Methods in Digital Twins: A Model and a Use Case,” BIWEEK 2024 Conf. Proc., 2024. [Online]. Available: https://conferences.big.tuwien.ac.at/biweek2024/pdfs/biweek2024_paper_91.pdf
• Y. Wu and Q. Zhang, “A Digital Twin-Enabled Cyber-Physical System for Smart Manufacturing with Enhanced Anomaly Detection and Interpretability,” Int. J. Prod. Res., preprint, 2024.
• L. Zhou and Y. Liu, “Real-time Anomaly Detection and Diagnosis in Industrial Systems using Digital Twin and Causal Inference with XAI,” IEEE Trans. Syst., Man, Cybern.: Syst., accepted for publication, 2024.
• J. Park and S. Kim, “An Explainable Digital Twin Framework for Anomaly Detection in Autonomous Industrial Robots,” Robot. Comput.-Integr. Manuf., accepted for publication, 2024.
• R. Niu and S. Guo, “Knowledge Graph and Digital Twin based Explainable Anomaly Detection for Complex Industrial Equipment,” J. Intell. Manuf., accepted for publication, 2024.
• M. Franco de la Peña et al., “ShaTS: A Shapley-based Explainability Method for Time Series Artificial Intelligence Models applied to Anomaly Detection in Industrial Internet of Things,” arXiv preprint, arXiv:2506.01450, 2025. [Online]. Available: https://arxiv.org/abs/2506.01450
• S. Gao and Y. Li, “Counterfactual Explanations for Anomaly Detection in Multivariate Time Series Data,” Expert Syst. Appl., preprint, 2024.
• X. Li et al., “Towards Transparent and Trustworthy Anomaly Detection in IIoT: A Federated Learning and XAI Approach,” IEEE Trans. Ind. Informat., accepted for publication, 2024.
• Md. Abu Kausar, Md. Nasar, and S. K. Singh, "Information Retrieval using Soft Computing: An overview," 2013.
• NASA Prognostics Center of Excellence, “Prognostics Data Set Repository,” Ames Intelligent Systems Division, NASA Ames Research Center, accessed: Jul. 25, 2025. [Online]. Available: https://www.nasa.gov/intelligent-systems-division/discovery-and-systems-health/pcoe/pcoe-data-set-repository/
• C. A. Rieth, B. D. Amsel, R. Tran, and M. B. Cook, “Additional Tennessee Eastman Process Simulation Data for Anomaly Detection Evaluation,” Harvard Dataverse, Jul. 2017, doi: 10.7910/DVN/6C3JR1 [Online]. Available: https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/6C3JR1
• V. Arzamasov, “Electrical Grid Stability Simulated Data,” UCI Machine Learning Repository, Dataset no. 471, Nov. 15, 2018. [Dataset]. Available: https://archive.ics.uci.edu/ml/datasets/Electrical+Grid+Stability+Simulated+Data (DOI: 10.24432/C5PG66)
• Md. Abu Kausar, Md. Nasar, and S. K. Singh, "Maintaining the repository of search engine from irregular web pages," in Proc. Int. Conf. Emerging Trends in Computer and Electronics Engineering, 2013, pp. 1–6.
• Md. Abu Kausar, V. S. Dhaka, and S. K. Singh, "Web crawler based on mobile agent and java aglets," IJ Information Technology and Computer Science, vol. 5, no. 10, pp. 85–91, 2013.