Vol. 1 No. 2 (2025)
Articles

Application of Agentive Artificial Intelligence and Retrieval-Augmented Generation for predictive Maintenance Operations

pdf
  • Salvador Perez-Garcia
Salvador Perez-Garcia
INE
JOINETECH, volume 1, issue 2, 2025

Published 2025-12-30

Keywords

  • Predictive Maintenance, Generative AI, AI Agent, Industry 5.0, Retrieval-Augmented Generation (RAG)

Copyright (c) 2025 JOINETECH provides immediate free access to its content, with the conviction that making this information available to the public favors a greater global knowledge exchange. In this sense, the journal follows the DOAJ definition of open access: "We define them as journals in which the copyright holder of a scholarly work grants the rights of use to others using an open licence (Creative Commons or equivalent) that allows immediate free access to the work and permits any user to read, download, copy, distribute, print, search or link to the full text of articles, crawl them for indexing, pass them as data to software or use them for any other lawful purpose. JOINETECH adheres to different initiatives that promote free access to knowledge, such as Plan S of the cOAlition S, or the principles of the communication infrastructure for academic publication and open science AmeliCA, so all JOINETECH contents edited by UTAMED are from free and open access and are published under a Creative Commons Attribution License (CC BY 4.0). Likewise, the journal provides information on the conditions of use and reuse of content (Creative Commons and Open Access). That is why the authors who publish in JOINETECH must accept the following conditions: - The authors retain the copyright, assigning to JOINETECH the right of the 1st publication, with the work registered with the Creative Commons attribution license (which allows third parties to use what is published as long as they mention the authorship of the work and the 1st publication in this journal). - Authors can make other independent and additional contractual agreements for the non-exclusive distribution of the version of the article published in JOINETECH (eg, publish it in a book or in an institutional repository) provided that it is clearly indicated that the work was published for the first time in JOINETECH. - Authors are allowed, and even recommended, to publish their work on the Internet (institutional, personal pages, social networks, etc.) since it can facilitate exchanges. - Authors are allowed, and even encouraged, to deposit supplementary material, at least the research data underlying publications, in institutional or thematic open access repositories federated in the European Open Science Cloud (EOSC)."

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite

Application of Agentive Artificial Intelligence and Retrieval-Augmented Generation for predictive Maintenance Operations. (2025). JOINETECH (International Journal of Economic and Technological Studies), 1(2), 98-102. https://doi.org/10.65479/joinetech.29

Downloads

Download data is not yet available.

Abstract

The advent of generative AI for the general public, and the fervor with which companies such as OpenAI, Google, Amazon, Microsoft, Meta, Alibaba, and High-Flyer (DeepSeek), among others, are competing to develop powerful solutions for generating text, images, audio, and video, has revolutionized the methods of obtaining and processing information.

Within this context of technological advancement, this rapid development contrasts with the challenges organizations face in harnessing this potential for the implementation of Industry 4.0 and its evolution towards Industry 5.0, with the aim of enhancing corporate performance and achieving significant differentiation from competitors. Furthermore, the impact on current organizational structures may be more profound than initially anticipated. As (Tomlinson et al., 2025) outline, the jobs with the highest applicability for AI are notably those involving knowledge and communication, such as roles in computer science, mathematics, sales, and administration. The adoption of such solutions can lead to employee apprehension regarding their implementation, consequently necessitating the reorganization and redefinition of corporate hierarchies. In light of this situation, (Anand and Wu, 2025) recommend prioritizing these solutions at a strategic level, as opposed to a more traditional operational approach focused merely on performing existing tasks more rapidly. This strategic focus aims to create a differentiation that fosters the development of a sustainable competitive advantage.

In this vein, the automation of tasks is increasingly highlighting the use of Retrieval-Augmented Generation (RAG). When combined with Large Language Models (LLMs), RAG facilitates collaboration and mutual learning with operators in administrative duties. This document presents the latest developments in the integration of generative and agentive AI for predictive maintenance tasks. However, such solutions are characterized by their requirement for specialized personnel for implementation and support, as well as the significant financial resources necessary for their deployment and ongoing maintenance.

pdf

References

  1. Anand, B. N., & Wu, A. (2025, November–December). The Gen AI playbook for organizations: Where to use it, where not to, and why strategy still wins. Harvard Business Review. https://hbr.org/2025/11/the-gen-ai-playbook-for-organizations
  2. Apeiranthitis, S., Zacharia, P., Chatzopoulos, A., & Papoutsidakis, M. (2024). Predictive maintenance of machinery with rotating parts using convolutional neural networks. Electronics, 13, 460. https://doi.org/10.3390/electronics13020460
  3. Azyus, A. F., Wijaya, S. K., & Naved, M. (2023). Prediction of remaining useful life using the CNN-GRU network: A study on maintenance management. Software Impacts, 17, 100535.
  4. Belcic, I., & Stryker, C. (2025). What is Agentic RAG? IBM. https://www.ibm.com/es-es/think/topics/agentic-rag
  5. Deloitte. (2025). Now decides next: Generating a new future. Deloitte’s State of Generative AI in the Enterprise. Quarter four report (p. 19). https://www.deloitte.com/content/dam/assets-shared/docs/about/2025/quarter-4.pdf
  6. European Commission. (2021). Industry 5.0: Towards a sustainable, human-centric and resilient European industry. https://doi.org/10.2777/308407
  7. Feuerriegel, S., Hartmann, J., Janiesch, C., & Zschech, P. (2024). Generative AI. Business & Information Systems Engineering, 66(1), 111–126.
  8. Finn, T., & Downie, A. (2025). Agentive AI vs generative AI. IBM. https://www.ibm.com/es-es/think/topics/agentic-ai-vs-generative-ai
  9. Guo, H., Ping, D., Wang, L., Zhang, W., Wu, J., Ma, X., ... & Lu, Z. (2025). Fault diagnosis method of rolling bearing based on 1D multi-channel improved convolutional neural network in noisy environment. Sensors, 25(7), 2286.
  10. Harkar, S. (2025). RAG techniques. IBM. https://www.ibm.com/es-es/think/topics/rag-techniques
  11. Intuit Blog. (2024). AI skills to boost your tech career. https://www.intuit.com/blog/innovative-thinking/ai-skills-to-boost-your-tech-career/
  12. Ivanov, D., Tang, C. S., Dolgui, A., Battini, D., & Das, A. (2021). Researchers’ perspectives on Industry 4.0: Multi-disciplinary analysis and opportunities for operations management. International Journal of Production Research, 59(7), 2055–2078.
  13. Jagerman, R., Zhuang, H., Qin, Z., Wang, X., & Bendersky, M. (2023). Query expansion by prompting large language models (arXiv:2305.03653). arXiv. https://arxiv.org/abs/2305.03653
  14. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., ... & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474.
  15. Lin, Z., Cheng, L., & Huang, G. (2020). Electricity consumption prediction based on LSTM with attention mechanism. IEEJ Transactions on Electrical and Electronic Engineering, 15. https://doi.org/10.1002/tee.23088
  16. Ma, X., Gong, Y., He, P., Zhao, H., & Duan, N. (2023, December). Query rewriting in retrieval-augmented large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (pp. 5303–5315).
  17. Oldemeyer, L., Jede, A., & Teuteberg, F. (2025). Investigation of artificial intelligence in SMEs: A systematic review of the state of the art and the main implementation challenges. Management Review Quarterly, 75(2), 1185–1227.
  18. Perez-Garcia, S., Gonzalez-Gaya, C., & Sebastian, M. A. (2025). Enhancing asset reliability and sustainability: A comparative study of neural networks and ARIMAX in predictive maintenance. Applied Sciences, 15(10), 5266.
  19. Tomlinson, K., Jaffe, S., Wang, W., Counts, S., & Suri, S. (2025). Working with AI: Measuring the applicability of generative AI to occupations (arXiv:2507.07935). arXiv. https://arxiv.org/abs/2507.07935
  20. Vial, G. (2021). Understanding digital transformation: A review and a research agenda. In Managing digital transformation (pp. 13–66).
  21. Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., ... & Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824–24837.
  22. Wu, X., Zhu, X., Wu, G., & Ding, W. (2014). Data mining with big data. IEEE Transactions on Knowledge and Data Engineering, 26, 97–107.
  23. Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K. R., & Cao, Y. (2022, October). ReAct: Synergizing reasoning and acting in language models. In The Eleventh International Conference on Learning Representations.
  24. Zhou, C., Fang, Z., Xu, X., Zhang, X., Ding, Y., & Jiang, X. (2020). Using long short-term memory networks to predict energy consumption of air-conditioning systems. Sustainable Cities and Society, 55, 102000.