Designing a Causal–Stage Model of Artificial Intelligence–Based World-Class Total Productive Maintenance for the Iranian Automotive Industry

Saeed  Mohammadi Rad; Hassan Farsijani; Seyyed Hosein  Seyyed Esfahani; Maryam  Khademi

Authors

Saeed Mohammadi Rad Department of Management, NT.C., Islamic Azad University, Tehran, Iran Author
Hassan Farsijani Associate Professor, Department of Industrial Management, Faculty of Management and Accounting, Shahid Beheshti University, Tehran, Iran Corresponding author
Seyyed Hosein Seyyed Esfahani Department of Management, NT.C., Islamic Azad University, Tehran, Iran Author
Maryam Khademi Department of Mathematics, ST.C., Islamic Azad University, Tehran, Iran Author

Keywords:

Automotive Industry, Artificial Intelligence, Total Productive Maintenance, World, Class Management

Abstract

In the era of Industry 5.0, the transformation of Total Productive Maintenance (TPM) in the automotive industry extends far beyond the adoption of conventional maintenance practices or the fragmented use of artificial intelligence applications. Such a transformation requires an integrated model that explains how AI-based maintenance capabilities should be identified, causally structured, sequenced, and translated into an executable architecture for achieving world-class performance. Although research on intelligent maintenance and predictive analytics has expanded considerably, much of the existing literature has focused on algorithmic accuracy, condition monitoring, or narrowly defined technological applications, while paying limited attention to how artificial intelligence capabilities can be structured and implemented to support World-Class Total Productive Maintenance. To address this gap, the present study designs a causal–stage model of Artificial Intelligence–Based World-Class Total Productive Maintenance (AI-WCTPM) for the Iranian automotive industry. The findings reveal a six-level architecture in which the real-time communication network and cyber–physical security constitute the foundational layer; edge processing and smart sensors form the perception and data-processing layer; intelligent knowledge management functions as the central knowledge platform; dynamic failure prediction and resilient supply chain operate as advanced analytical engines; preventive quality control and intelligent continuous improvement constitute the optimization and action layer; and world-class performance indicators represent the final outcome layer. The proposed AI-WCTPM model integrates causal influence, implementation sequencing, AI-tool alignment, and performance monitoring into a coherent data–knowledge–decision architecture. Expert validation confirms the structural coherence, content adequacy, and practical applicability of the model. This study advances intelligent maintenance research by shifting the focus from isolated algorithmic applications toward a stage-based architecture for World-Class TPM and provides automotive managers with a structured roadmap for prioritizing AI investments, reducing implementation risk, and aligning maintenance transformation with world-class performance objectives.

Downloads

Download data is not yet available.

References

Achouch, M., Dimitrova, M., Ziane, K., Sattarpanah Karganroudi, S., Dhouib, R., Ibrahim, H., & Adda, M. (2022). On predictive maintenance in Industry 4.0: Overview, models, and challenges. Applied Sciences, 12(16), 8081. https://doi.org/10.3390/app12168081

Ardehi, A., Javanmard, H., & Pilevari, N. (2023). Designing a model for implementing the fourth-generation industry to achieve sustainable development goals in the automotive industry: Case study: Iran Khodro Company. Journal of System Management, 9(1), 37-52. https://doi.org/10.30495/JSM.2022.1964456.1671

Cinar, E., Kalay, S., & Saricicek, I. (2022). A predictive maintenance system design and implementation for intelligent manufacturing. Machines, 10(11), 1006. https://doi.org/10.3390/machines10111006

de Andrade, C. T. A., de Gusmão, A. P. H., & Silva, W. (2021). World Class Manufacturing performance measurement using a maturity model and the FlowSort method. International Journal of Production Research, 59(24), 7374-7389. https://doi.org/10.1080/00207543.2021.1970845

Ebrahimi, S. H. (2023). Some equations to identify the threshold value in the DEMATEL method. Operations Research and Decisions, 33(2), 5-19. https://doi.org/10.37190/ord230201

Farsijani, H., & Dehghan, A. (2016). Performance evaluation for achieving world-class products based on the VU method. Industrial Management Perspective, 6(2), 45-65.

Farsijani, H., Shafiei Nikabadi, M., & Mojibian, F. (2012). The role of total productive maintenance in group technology to achieve world-class status. International Journal of Applied Industrial Engineering, 1(2), 25-35. https://doi.org/10.4018/ijaie.2012070103

Giordano, D., Giobergia, F., Pastor, E., La Macchia, A., Cerquitelli, T., Baralis, E., Mellia, M., & Tricarico, D. (2022). Data-driven strategies for predictive maintenance: Lessons learned from an automotive use case. Computers in Industry, 134, 103554. https://doi.org/10.1016/j.compind.2021.103554

Hector, I., & Panjanathan, R. (2024). Predictive maintenance in Industry 4.0: A survey of planning models and machine learning techniques. Peerj Computer Science, 10, e2016. https://doi.org/10.7717/peerj-cs.2016

Hershowitz, B., Hodkiewicz, M., Bikaun, T., Stewart, M., & Liu, W. (2024). Causal knowledge extraction from long text maintenance documents. Computers in Industry, 161, 104110. https://doi.org/10.1016/j.compind.2024.104110

Khan, T., Khan, U., Khan, A., Mollan, C., Morkvenaite-Vilkonciene, I., & Pandey, V. (2025). Data-driven digital twin framework for predictive maintenance of smart manufacturing systems. Machines, 13(6), 481. https://doi.org/10.3390/machines13060481

Li, J., Chen, M., Wang, Y., Liu, Y., & Zhang, H. (2025). Application of an integrated DEMATEL-ISM-BN and gray relational analysis model. Sustainability, 17(16), 7204. https://doi.org/10.3390/su17167204

Li, Z., He, Q., & Li, J. (2024). A survey of deep learning-driven architecture for predictive maintenance. Engineering Applications of Artificial Intelligence, 133, 108285. https://doi.org/10.1016/j.engappai.2024.108285

Mohammadi Rad, S., Farsijani, H., Seyedesfahani, S. H., & Khademi, M. (2026). Designing an Artificial Intelligence-Based World-Class Total Productive Maintenance Model for the Automotive Industry [Doctoral dissertation, Islamic Azad University, North Tehran Branch].

Mouhib, Z., Gallab, M., Merzouk, S., Soulhi, A., Di Nardo, M., & El Alami, J. (2025). Total Productive Maintenance and Industry 4.0: A literature-based path toward a proposed standardized framework. Applied System Innovation, 8(4), 98. https://doi.org/10.3390/asi8040098

Mozaffari Mehr, M. S., & Taghavi Fard, M. T. (2024). Designing and modeling digital transformation in the automotive industry: Leveraging the Fourth Industrial Revolution. Industrial Management, 16(1), 148-174. https://doi.org/10.22059/imj.2024.373674.1008135

Nyimbili, P. H., Erden, T., & Karaman, H. (2023). A DEMATEL-based approach of multi-criteria evaluation for urban disaster resilience. Frontiers in Environmental Economics, 2, 1198541. https://doi.org/10.3389/frevc.2023.1198541

Riccio, C., Menanno, M., Zennaro, I., & Savino, M. M. (2024). A new methodological framework for optimizing predictive maintenance using machine learning combined with product quality parameters. Machines, 12(7), 443. https://doi.org/10.3390/machines12070443

Somu, N., & Dasappa, N. S. (2025). An edge–cloud IIoT framework for predictive maintenance in manufacturing systems. Advanced Engineering Informatics, 65, 103388. https://doi.org/10.1016/j.aei.2025.103388

Taoufyq, H., El Guemmat, K., Mansouri, K., & Akef, F. (2025). Predictive maintenance approaches: A systematic literature review. Journal of Industrial Engineering and Management, 18(3), 427-458. https://doi.org/10.3926/jiem.8537

Toke, L. K., & Kalpande, S. D. (2023). An assessment of key performance indicators and its relationship for implementation of total productive maintenance in manufacturing sector. International Journal on Interactive Design and Manufacturing, 17(4), 1741-1753. https://doi.org/10.1007/s12008-023-01252-5

Tortorella, G. L., Saurin, T. A., Fogliatto, F. S., Tlapa Mendoza, D., Moyano-Fuentes, J., Gaiardelli, P., & Macias de Anda, E. (2024). Digitalization of maintenance: Exploratory study on the adoption of Industry 4.0 technologies and total productive maintenance practices. Production Planning & Control, 35(4), 352-372. https://doi.org/10.1080/09537287.2022.2083996

Tsang, A. H. C. (2002). Strategic dimensions of maintenance management. Journal of Quality in Maintenance Engineering, 8(1), 7-39. https://doi.org/10.1108/13552510210420577

Wang, Y., & Liang, X. (2025). Application of reinforcement learning methods combining graph neural networks and self-attention mechanisms in supply-chain route optimization. Sensors, 25(3), 955. https://doi.org/10.3390/s25030955

Wang, Y., Yuan, T., Yang, Y., He, M., Wu, R., & Birman, K. P. (2025). Accelerating visual anomaly detection in smart manufacturing with RDMA-enabled data infrastructure. Electronics, 14(12), 2427. https://doi.org/10.3390/electronics14122427