A Machine Learning–Based Approach to Modeling Embroidery Machine Effectiveness Using Overall Equipment Effectiveness (OEE)
Abstrak
The embroidery process represents the initial stage of production at PT XXX; therefore, evaluating its performance is essential to prevent disruptions in subsequent manufacturing stages. To support decision-making related to embroidery machine performance, the company requires an effective machine performance monitoring system. This study aims to develop a predictive model of Overall Equipment Effectiveness (OEE) using a machine learning approach and to design a performance monitoring dashboard using Power BI. The results show that the average OEE value of the embroidery machines exceeds the World Class OEE standard. Among the OEE components, performance efficiency is the most dominant factor influencing OEE, primarily due to variations in product size, while machine downtime continues to contribute to fluctuations in OEE values. Among the evaluated machine learning models, Linear Regression demonstrates the best predictive performance, achieving an R² value of 45%. Furthermore, the developed Power BI dashboard effectively presents machine performance indicators and OEE prediction results in a visual and integrated manner, thereby supporting continuous monitoring and informed decision-making regarding embroidery machine performance.
Referensi
P. Muchiri and L. Pintelon, “Performance measurement using overall equipment effectiveness (OEE): Literature review and practical application discussion,” Int. J. Prod. Res., vol. 46, no. 13, pp. 3517–3535, (2008). doi: 10.1080/00207540601142645.
S. Nakajima, Introduction to TPM: Total Productive Maintenance. Portland, OR, USA: Productivity Press, (1988).
L. Turpin Jr., “A note on understanding cycle time,” Int. J. Prod. Econ., vol. 205, pp. 113–117, (2018). doi: 10.1016/j.ijpe.2018.09.004.
P. G. Yazdi, A. Azizi, and M. Hashemipour, “An empirical investigation of the relationship between overall equipment efficiency (OEE) and manufacturing sustainability in Industry 4.0 with time study approach,” Sustainability (MDPI), vol. 10, no. 9, Art. no. 3031, (2018). doi: 10.3390/su10093031.
S. Murugesan, S. T., V. G. V. Murugesan, and P. Muthuswamy, “Overall equipment effectiveness (OEE) analysis and improvement in a spinning unit,” SSRN Electron. J., (2022). doi: 10.2139/ssrn.4032186.
J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed. Burlington, MA, USA: Morgan Kaufmann, (2012).
D. C. Montgomery and G. C. Runger, Applied Statistics and Probability for Engineers, 6th ed. Hoboken, NJ, USA: Wiley, (2014).
