Developing a Framework to Prevent Over-Maintenance in Automated Assembly Lines
DOI:
https://doi.org/10.67308/irjist.044Keywords:
Maintenance Optimization, Fault Detection, Automated Assembly Lines, LoRA Fine-Tuning, Predictive Maintenance, Condition-Based Maintenance, Over-Maintenance PreventionAbstract
Automated assembly lines in modern manufacturing industries are often maintained using fixed time-based maintenance schedules without considering the actual operating condition of equipment. This practice can lead to unnecessary maintenance activities, increased spare parts usage, additional downtime, and higher operational cost. To address this issue, the present study proposes a condition-based maintenance (CBM) framework for reducing over-maintenance in automated assembly lines using sensor-based monitoring and AI-assisted predictive analysis. The proposed framework integrates LoRA fine-tuned predictive models, real-time sensor fusion, and an automated validation module aligned with ISO 55000 standards for maintenance decision support. The study utilizes 210 operational records collected from automated assembly systems for model training and validation. The developed system achieved 91% fault prediction accuracy while significantly reducing unnecessary maintenance recommendations through a three-stage validation process. Industrial validation conducted on four automated assembly lines showed improvement in maintenance efficiency, reduction in unplanned downtime, lower spare parts consumption, and improvement in Overall Equipment Effectiveness (OEE) when compared with conventional time-based maintenance practices. The framework also demonstrates potential applicability in other industrial sectors such as semiconductor manufacturing, pharmaceutical packaging, aerospace assembly, and food processing industries. The proposed approach provides a structured and practical framework for improving maintenance planning and reducing over-maintenance in data-constrained industrial environments.
Downloads
References
[1] EN 13306:2017. Maintenance — Maintenance Terminology. European Committee for Standardization; 2017.
[2] McKinsey & Company. Unlocking the value of predictive maintenance in industrial operations. McKinsey Operations Report; 2023.
[3] Mobley RK. An Introduction to Predictive Maintenance (2nd ed.). Butterworth-Heinemann; 2002.
[4] Lee J, Bagheri B, Kao HA. A Cyber-Physical Systems architecture for Industry 4.0-based manufacturing systems. Manuf Lett. 2015;3:18–23.
[5] Atzori L, Iera A, Morabito G. The Internet of Things: a survey. Comput Netw. 2010;54(15):2787–2805.
[6] Jardine AKS, Lin D, Banjevic D. A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech Syst Signal Process. 2006;20(7):1483–1510.
[7] Nakajima S. Introduction to TPM: Total Productive Maintenance. Productivity Press; 1988.
[8] Randall RB. Vibration-based Condition Monitoring: Industrial, Aerospace and Automotive Applications. Wiley; 2011.
[9] Lee J, Wu F, Zhao W, Ghaffari M, Liao L, Siegel D. Prognostics and health management design for rotary machinery systems. Mech Syst Signal Process. 2014;42(1-2):314–334.
[10] Wen L, Li X, Gao L, Zhang Y. A new convolutional neural network-based data-driven fault diagnosis method. IEEE Trans Ind Electron. 2018;65(7):5990–5998.
[11] Zio E. Prognostics and health management (PHM): Where are we and where do we (need to) go in theory and practice. Reliab Eng System Saf. 2022;218:108119.
[12] Hu E, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Chen W. LoRA: Low-rank adaptation of large language models. ICLR; 2022.
[13] Zhang W, Li C, Peng G, Chen Y, Zhang Z. A deep convolutional neural network with new training methods for bearing fault diagnosis. Mech Syst Signal Process. 2018;100:439–453.
[14] Koochaki A, Bokrantz J, Skoogh A, Bengtsson M. The application of condition-based maintenance in the manufacturing industry. J Qual Maint Eng. 2019;25(4):507–526.
[15] ISO 55000:2014. Asset Management — Overview, Principles and Terminology. International Organization for Standardization; 2014.
[16] AI-Driven Demand Forecasting and Inventory Optimization Using Prophet-Based Time Series Modelling. (2026). International Research Journal of Innovation in Science and Technology, 1(2), 1-7. DOI: 10.67308/irjist.009.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Pratik Das (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published in the International Research Journal of Innovation in Science and Technology (IRJIST) are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Authors retain the copyright of their work and grant the journal the right of first publication. Proper attribution to the authors and the journal is required for any reuse of the published content.
