Development of an Integrated Quality Control Model for Outer Gear Couplings Based on Six Sigma DMAIC and J48 Decision Tree

Heru Ambrose Sinaga; Aulia Ishak; Nurhayati

doi:10.70716/reswara.v4i3.570

Authors

Heru Ambrose Sinaga Magister Teknik Industri, Universitas Sumatera Utara, Medan, Indonesia Author
Aulia Ishak Magister Teknik Industri, Universitas Sumatera Utara, Medan, Indonesia Author
Nurhayati Magister Teknik Industri, Universitas Sumatera Utara, Medan, Indonesia Author

DOI:

https://doi.org/10.70716/reswara.v4i3.570

Keywords:

Quality Control, Six Sigma DMAIC, J48 Algorithm

Abstract

Producing precision components like outer gear couplings requires high geometric and surface quality to maintain mechanical transmission performance in machinery. However, CV Adi Makmur Metalindo experiences recurring quality issues with these specific components. Between July and October 2025, the overall defect rate reached 16.94% (62 defective units out of 366 total units). These issues are primarily geometric defects (62.90%) and surface defects (37.10%). This comprehensive study evaluates production quality performance, identifies dominant process attributes triggering defects, and develops a robust decision support model for quality control. The methodology utilizes a quantitative case study approach, integrating the Six Sigma DMAIC framework with the J48 decision tree algorithm to reinforce the Analyze stage. Results indicate a Defect Per Million Opportunities (DPMO) value of 169,399 and a Defect Per Unit (DPU) of 0.1694, confirming an unstable production process with a high probability of defects. The J48 algorithm modeling clearly identified rough turning RPM (rpm_bubut_kasar) as the dominant predictor classifying product quality. Extracted decision rules reveal that setting machine RPM too low (under 53.9 RPM) or too high (over 65.5 RPM) heavily correlates with geometric defects, whereas the intermediate range triggers surface defects. Consequently, the Improve phase proposes standardizing operational parameters within an optimal range of 55 to 65 RPM. For the Control phase, a mockup of a smart monitoring dashboard interface was designed to efficiently support targeted quality control decisions. Ultimately, integrating Six Sigma DMAIC and the J48 algorithm successfully transforms manufacturing process data into practical decision rules, effectively supporting product quality optimization.

References

Bártová, B., Bína, V., & Váchová, L. (2022). A PRISMA-driven systematic review of data mining methods used for defects detection and classification in the manufacturing industry. Production , 32 . https://doi.org/10.1590/0103-6513.20210097

Elbany, Z.A., Zaher, A., Abdel-magied, R.K., & Elkhouly, H.I. (2024). Improving plastic manufacturing processes with the integration of Six Sigma and machine learning techniques : a case study. Journal of Industrial and Production Engineering , 41 (1), 1–18.

Guo, Y., Lambert, S., Wallen, R., Errichello, R., & Keller, J. (2016). Theoretical and experimental study on gear-coupling contact and loads considering misalignment, torque, and friction influences. Mechanism and Machine Theory , 98 , 242–262. https://doi.org/10.1016/j.mechmachtheory.2015.11.015

Sensors . https://doi.org/https://doi.org/10.3390/s21082849

Köksal, G., Batmaz, I., & Testik, M. C. (2011). Expert Systems with Applications A review of data mining applications for quality improvement in manufacturing industry. Expert Systems with Applications , 38 , 13448–13467. https://doi.org/10.1016/j.eswa.2011.04.063

Lestari, A., & Alamsyah. (2020). Increasing Accuracy of C4 . 5 Algorithms Using Information Gain Ratio and Adaboost for Classification of Chronic Kidney Disease. Journal of Soft Computing Exploration , 1 (1), 32–38. https://doi.org/https://doi.org/10.52465/joscex.v1i1.6

Panigrahi, R., & Borah, S. (2018). Rank Allocation to J48 Group of Decision Tree Classifiers using Binary and Multiclass Intrusion Detection Datasets. Procedia Computer Science , 132 , 323–332. https://doi.org/10.1016/j.procs.2018.05.186

Psarommatis, F., Sousa, J., Mendonça, J.P., & Kiritsis, D. (2022). Zero-defect manufacturing the approach for higher manufacturing sustainability in the industrial era 4 . 0 : a position paper. International Journal of Production Research ISSN: , 7543 . https://doi.org/10.1080/00207543.2021.1987551

Qehaja, N., Jakupi, K., Bunjaku, A., Bruçi, M., & Osmani, H. (2015). Effect of Machining Parameters and Machining Time on Surface Roughness in Dry Turning Process. Procedia Engineering , 100 , 135–140. https://doi.org/10.1016/j.proeng.2015.01.351

Quinlan, J.R. (1996). Improved Use of Continuous Attributes in C4.5. Journal of Artificial Intelligence Research , 4 , 77–90. https://doi.org/https://doi.org/10.1613/jair.279

Saad, H., Nagarur, N., & Shamsan, A. (2021). Analysis of Data Mining Process for Improvement of Production Quality in Industrial Sector. Journal of Applied Sciences , 21 (1), 10–20. https://doi.org/10.3923/jas.2021.10.20

Saputra, S., Kurniawati, Y., & Kusuma, NK (2025). The Influence of Production Systems on Quality and Production Cost Efficiency. Journal of Artificial Intelligence and Digital Business (RIGGS) , 4 (2), 892–896.

Sinulingga, S. (2020). Research Methods 3rd Edition (3rd ed.). USU Press.

Siregar, K., & Elvira. (2020). Quality control analysis to reduce product defects and increase production speed using lean six sigma method Quality control analysis to reduce product defects and increase production speed using lean six sigma method. Materials Science and Engineering . https://doi.org/10.1088/1757-899X/801/1/012104

Sirine, H., Kurniawati, EP, Pengajar, S., Ekonomika, F., Bisnis, D., & Salatiga, U. (2017). Quality Control Using the Six Sigma Method. AJIE-Asian Journal of Innovation and Entrepreneurship , 02 (03), 2477–3824. http://www.dirasfurniture.com

Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing and Management , 45 (4), 427–437. https://doi.org/10.1016/j.ipm.2009.03.002

Stiglic, G., Kocbek, S., Pernek, I., & Kokol, P. (2012). Comprehensive decision tree models in bioinformatics. PLOS ONE , 7 (3). https://doi.org/10.1371/journal.pone.0033812

Su, C., Su, W., Cheng, F., Liou, G., & Hwang, S. (2022). Optimization process parameters and adaptive quality monitoring injection molding process for materials with different viscosity. Polymer Testing , 109 (1). https://doi.org/https://doi.org/10.1016/j.polymertesting.2022.107526

Supriyati, S., & Widyatri, H. (2024). Quality Control of Automotive Component Production Processes in the Manufacturing Industry Using the Six Sigma Approach. JURMATIS (Journal of Technology Management and Industrial Engineering) , 6 (2). https://doi.org/10.30737/jurmatis.v6i2.5507

Thomas, M., Mihaela, I., Andrianjaka, RM, Germain, DW, & Sorin, I. (2021). Metamodel based approach to generate user interface mockup from UML class diagram. Procedia Computer Science , 184 , 779–784. https://doi.org/10.1016/j.procs.2021.03.096

Ud, P., Kasih, S., & Wetan, G. (2019). PRODUCT QUALITY CONTROL AS AN EFFORT TO CONTROL THE LEVEL OF DAMAGE. Jurnal Eksis , 11 (2), 1–14.

Uluskan, M. (2016). A Comprehensive Insight Into The Six Sigma Dmaic Toolbox. International Journal of Lean Six Sigma , 7 (4). https://doi.org/http://dx.doi.org/10.1108/IJLSS-10-2015-0040

Wati, R. (2026). Implementation of Lean Manufacturing and Quality Control on Production Process Effectiveness: Systematic Literature Review. Al-Zayn: Journal of Social Sciences & Law , 4 (2), 7152–7169. https://doi.org/https://doi.org/10.61104/alz.v4i2.5448

Wu, Top 10 algorithms in data mining . https://doi.org/10.1007/s10115-007-0114-2

Zulka, Z., Perez, K., Vitolo, C., Buytaert, W., Clark, J., Karpouzoglou, T., Dewulf, A., Bi, B. De, Hannah, D.M., & Shaheed, S. (2017). User-driven design of decision support systems for polycentric environmental resources management. Environmental Modeling & Software , 88 , 58–73. https://doi.org/10.1016/j.envsoft.2016.10.012