Citation :

Anurag Bhagat , 2024. "Applying Generative AI in Predictive Maintenance: A New Paradigm" ESP International Journal of Advancements in Computational Technology (ESP-IJACT)  Volume 2, Issue 4: 100-103.

Abstract :

Predictive maintenance (PdM) is an essential component of modern industrial operations, especially with the fourth Industrial Revolution (Industry 4.0). Traditional PdM relies on either rule-based algorithms or deep learning neural nets to predict downtimes, increasing uptime and productivity. Traditional PdM faces a lot of challenges owing to lack of sufficient high-quality data, leading to a high number of false positives. With the recent advancements in generative AI (GenAI) a new set of enablers have come forward which can enable higher quality PdM models enabled through advanced simulations and synthetic data generation. This paper highlights applications in manufacturing, transportation and energy, showcasing how the integration of GenAI with existing PdM frameworks can help unlock performance and ease adoption of these models. We also discuss specific applications of Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Transformers in PdM.

References :

[1] Ucar, A.; Karakose, M.; Kırımça, N. “Artificial Intelligence for Predictive Maintenance Applications: Key Components, Trustworthiness, and Future Trends”. Appl. Sci. 2024, 14, 898. https://doi.org/10.3390/app14020898

[2] H. Lu, M. Du, K. Qian, X. He and K. Wang, "GAN-Based Data Augmentation Strategy for Sensor Anomaly Detection in Industrial Robots," in IEEE Sensors Journal, vol. 22, no. 18, pp. 17464-17474, 15 Sept.15, 2022

[3] B. Tse, T. Wright, E. Nsiye, T. Azinord, D. Medina and S. Mondesire, "Semiconductor Manufacturing Data Synthesis through GANs," 2024 35th Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC), Albany, NY, USA, 2024, pp. 1-6

[4] Losi, E., Manservigi, L., Spina, P. R., and Venturini, M. (October 3, 2024). "Data-Driven Generative Model Aimed to Create Synthetic Data for the Long-Term Forecast of Gas Turbine Operation."

[5] Jakubowski, J.; Stanisz, P.; Bobek, S.; Nalepa, G.J. “Anomaly Detection in Asset Degradation Process Using Variational Autoencoder and Explanations”. Sensors 2022, 22, 291. https://doi.org/10.3390/s22010291

[6] Antonio L. Alfeo, Mario G.C.A. Cimino, Giuseppe Manco, Ettore Ritacco, Gigliola Vaglini, “Using an autoencoder in the design of an anomaly detector for smart manufacturing, Pattern Recognition Letters”, Volume 136, 2020, Pages 272-278, ISSN 0167-8655, https://doi.org/10.1016/j.patrec.2020.06.008.

[7] Sperandio Nascimento, Erick Giovani and Liang, Julian Santana and Figueiredo, Ilan Sousa and Guarieiro, Lilian Lefol Nani, “T4pdm: A Deep Neural Network Based on the Transformer Architecture for Fault Diagnosis of Rotating Machinery” , http://dx.doi.org/10.2139/ssrn.4267690

[8] Zhe Li, Qian He, Jingyue Li, “A survey of deep learning-driven architecture for predictive maintenance”, Engineering Applications of Artificial Intelligence, Volume 133, Part C, 2024 108285, ISSN 0952-1976, https://doi.org/10.1016/j.engappai.2024.108285.

[9] Yigin, B.; Celik, M. “A Prescriptive Model for Failure Analysis in Ship Machinery Monitoring Using Generative Adversarial Networks”. J. Mar. Sci. Eng. 2024, 12, 493. https://doi.org/10.3390/jmse12030493

[10] Reddy, K. K., Sarkar, S., Venugopalan, V., & Giering, M. (2016). “Anomaly Detection and Fault Disambiguation in Large Flight Data: A Multi-modal Deep Auto-encoder Approach”. Annual Conference of the PHM Society, 8(1). https://doi.org/10.36001/phmconf.2016.v8i1.2549

Keywords :

Artificial Intelligence, Generative AI, Industry 4.0, Machine Learning, PdM, Predictive Maintenance, Operations Improvements, GenAI