Authors : Saima Anjum; Dr. Neelambike S.

Volume/Issue : Volume 11 - 2026, Issue 9 - September

Google Scholar : https://tinyurl.com/3jz9hjsn

DOI : https://doi.org/10.38124/ijisrt/26sep084

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The increasing adoption of Industry 4.0 technologies has made Manufacturing Execution Systems (MES) an essential component of modern manufacturing environments by enabling the collection, integration, and analysis of production and quality data from machines, sensors, operators, and enterprise systems. However, the effectiveness of MESdriven analytics and decision-making depends heavily on the quality, consistency, and reliability of the underlying data. Incomplete records, duplicate entries, inconsistent formats, abnormal production values, and synchronization issues can negatively affect production monitoring, process optimization, and quality management. To address these challenges, the present study proposes a Manufacturing Execution System Data Quality Assessment Framework that integrates data preprocessing, multidimensional quality evaluation, anomaly detection, standardization, and quality monitoring. The proposed workflow begins with the ingestion and normalization of MES data, followed by structural validation, data-type standardization, missing-value identification, outlier detection, temporal synchronization, and metadata-based quality flagging. Data quality is evaluated using three major dimensions: Operational Integrity, Standardization, and Optimization Impact, which are combined to calculate an overall MES data quality score. The implementation uses Python-based data processing and a dashboard-based visualization approach to identify duplicate records, defective records, production anomalies, and machine-wise defect patterns. The evaluation considers dimensions such as accuracy, completeness, consistency, timeliness, standardization, interoperability, and production alignment. The proposed framework provides a systematic and transparent approach for identifying MES data-quality issues and supports reliable manufacturing analytics and data-driven decision-making. By integrating preprocessing, quality assessment, anomaly identification, and visualization, the study provides a practical foundation for improving the reliability and usability of manufacturing data in Industry 4.0 environments.

Keywords : Anomaly Detection; Data Preprocessing; Data Quality; Industry 4.0; Machine Learning; Manufacturing Analytics; Manufacturing Execution System.

References :

1. J. Lee, B. Bagheri, and H. A. Kao, “A Cyber-Physical Systems architecture for Industry 4.0-based manufacturing systems,” Manufacturing Letters, vol. 3, pp. 18-23, 2015.
2. J. Wan, S. Tang, Z. Shu, D. Li, S. Wang, M. Imran, and A. Vasilakos, “Software-defined industrial Internet of Things in the context of Industry 4.0,” IEEE Sensors Journal, vol. 16, no. 20, pp. 7373-7380, 2016.
3. F. Tao, Q. Qi, A. Liu, and A. Kusiak, “Data-driven smart manufacturing,” Journal of Manufacturing Systems, vol. 48, pp. 157-169, 2018.
4. Y. Zhang, S. Ren, Y. Liu, and S. Si, “A big data analytics architecture for cleaner manufacturing and maintenance processes,” Journal of Cleaner Production, vol. 142, pp. 626-641, 2017.
5. A. Kusiak, “Fundamentals of smart manufacturing: A multi-dimensional approach,” Annual Reviews in Control, vol. 47, pp. 214-220, 2019.
6. J. Qin, Y. Liu, and R. Grosvenor, “A categorical framework of manufacturing for Industry 4.0 and beyond,” Procedia CIRP, vol. 52, pp. 173-178, 2016.