Reducing Downtime and Errors in Manufacturing: AI-Integrated EDMS for SOP Access and Workflow Efficiency

This study shows that AI integrated EDMS improves the way operators access and use Standard Operating Procedures in manufacturing plants. The results confirm that the system reduces delays, improves accuracy, and supports faster decisions. The system replaces manual search with instant responses [14]. The operator does not need to open multiple files or search through folders. The system understands the query and shows the correct information [13]. The time taken to fetch knowledge dropped from 112 seconds to 29 seconds. This shows a 74 percent improvement. The number of documents opened per task dropped from 3.4 to 1. This means the operator stays focused and does not switch between files. The interruption time also dropped from 95 seconds to 22 seconds. This shows that the operator can complete tasks without delay. The system also reduces errors. The error risk score dropped from 0.78 to 0.21. This shows that the operator is less likely to read the wrong version or miss important steps. The system guides the operator with updated and correct content. The time taken to resolve cross reference queries dropped from 68 seconds to 14 seconds. This shows that the system understands the meaning of the query and finds the correct answer [14]. Downtime was reduced by 27 percent. This is a major improvement. The system helps the operator act faster and with more confidence. The mismatch count per month dropped from 18 to 4. This shows that the system keeps the document set clean and consistent [15]. The results confirm that AI integrated EDMS improves speed, clarity, and reliability. The system supports the operator in real time. The system reduces delays and errors. The system creates a strong link between knowledge and action. The system also supports audits, training, and compliance. The system helps new operators follow the correct steps. The system helps experienced staff work faster. The system improves the overall performance of the plant [16].

[1]               J. Lee, J. Ni, J. Singh, B. Jiang, M. Azamfar, and J. Feng, "Intelligent maintenance systems and predictive manufacturing," Journal of Manufacturing Science and Engineering, vol. 142, no. 11, p. 110805, 2020. [2]               E. Kabir, "Predictive and Prescriptive Analytics for Managing the Impact of Hazards on Power Systems," 2021. [3]               H. Algabroun, J. Bokrantz, B. Al-Najjar, and A. Skoogh, "Development of digitalised maintenance–a concept," Journal of Quality in Maintenance Engineering, vol. 28, no. 2, pp. 367-390, 2022. [4]               H. Erbiyik, "Definition of maintenance and maintenance types with due care on preventive maintenance," in Maintenance Management-Current Challenges, New Developments, and Future Directions: IntechOpen, 2022. [5]               J. Chamorro et al., "Health monitoring of a conveyor belt system using machine vision and real-time sensor data," CIRP Journal of Manufacturing Science and Technology, vol. 38, pp. 38-50, 2022. [6]               R. A. Ariyaluran Habeeb et al., "Clustering‐based real‐time anomaly detection—A breakthrough in big data technologies," Transactions on Emerging Telecommunications Technologies, vol. 33, no. 8, p. e3647, 2022. [7]               K. Wesendrup and B. Hellingrath, "A process-based review of post-prognostics decision-making," in PHM Society European Conference, 2020, vol. 5, no. 1, pp. 12-12. [8]               R. S. Pillai, P. Denny, and E. O'connell, "Optimizing Predictive and Prescriptive Maintenance Using Unified Namespace (UNS) for Industrial Equipments," 2024. [9]               Rojek, M. Jasiulewicz-Kaczmarek, M. Piechowski, and D. Mikołajewski, "An artificial intelligence approach for improving maintenance to supervise machine failures and support their repair," Applied Sciences, vol. 13, no. 8, p. 4971, 2023. [10]             M. H. Abuelenin, "Risk Based Maintenance Management System Achieving Operational Excellence," in Abu Dhabi International Petroleum Exhibition and Conference, 2020: SPE, p. D012S116R019.