Time-Based Production Quality Degradation Analysis Using K-Means Clustering for Adaptive Inspection Strategy

Citra dwi kusumawardani; Henry Hafidz Anbiya; A. Anas Haikal

doi:10.35891/vmv3z709

Authors

Citra dwi kusumawardani Universitas Islam Kadiri
Henry Hafidz Anbiya Universitas Islam Kadiri
A. Anas Haikal Universitas Islam Kadiri

DOI:

https://doi.org/10.35891/vmv3z709

Keywords:

K-Means Clustering, Quality Degradation, Adaptive Inspection, Manufacturing Quality Control, Silhouette Score

Abstract

This study analyzes production quality degradation patterns at ACME Manufacturing using the K-Means clustering method combined with Silhouette Score evaluation. The research was conducted using periodic production defect inspection data collected every 15 minutes during manufacturing operations. The study aims to identify production quality phases based on defect characteristics and evaluate the potential implementation of adaptive inspection strategies in manufacturing quality control systems. The analysis process was performed using Orange Data Mining software through data preprocessing, clustering analysis, visualization, and cluster validation stages. The results showed that production defect conditions fluctuated dynamically during operational activities and formed four production quality phases consisting of the Stable Phase, Moderate Phase, High-Risk Phase, and Critical Degradation Phase. The four-cluster configuration produced the best clustering performance with a Silhouette Score value of 0.376. Temporal analysis also indicated that production quality degradation developed progressively during manufacturing operations. Based on the identified production phases, the proposed adaptive inspection strategy demonstrated the potential to reduce inspection activities from 32 inspections to 28 inspections per production shift while maintaining production quality monitoring effectiveness. The findings indicate that clustering-based temporal analysis can support more adaptive and data-driven manufacturing quality control systems.

Downloads

Download data is not yet available.

References

Bartova, B., & Bina, V. (2019). Early Defect Detection Using Clustering Algorithms. 27(1), 3–20.

Cahaya, D. T., Puspita, D., Syahri, R., Informatika, T., Teknologi, I., Alam, P., Masik, J., No, S., 75, S., Mbacang, K. P., Alam, S., & Selatan, I. (2024). Penerapan Metode K-Means Clustering Untuk Pengelompokan Potensi Padi Di Kota Pagar Alam. In Jurnal Mahasiswa Teknik Informatika (Vol. 8, Issue 2).

Darmayanti, I., Adhimah, L. F., Sadewo, R., Hidayati, N., & Subarkah, P. (2024). Improving K-Means Clustering Accuracy for Academic Success Investigation With Extreme Gradient Boosting Algorithm. Indonesian Journal of Artificial Intelligence and Data Mining, 7(1), 104. https://doi.org/10.24014/ijaidm.v7i1.26657

Haekal, J., & Mu’min, R. (2024). Structured Defect Data-Based K-Means Clustering Analysis and Framework for Quality Control (QC) Prioritization in Manufacturing. XVIII(3), 405–416.

Hasan, Y. (2024). Pengukuran Silhouette Score dan Davies-Bouldin Index pada Hasil Cluster K-Means dan Dbscan (Vol. 06, Issue 01).

Ji, H., Hwang, I., Kim, J., Lee, S., & Lee, W. (2024). Leveraging feature extraction and risk-based clustering for advanced fault diagnosis in equipment. PLoS ONE, 19(12 December). https://doi.org/10.1371/journal.pone.0314931

Kim, M., & Chung, K. (2019). Adaptive quality control scheme based on VBR characteristics to improve QoE of UHD streaming service. Advances in Electrical and Computer Engineering, 19(1), 89–98. https://doi.org/10.4316/AECE.2019.01012

Kusniah, Q., & Munir, M. (2025). Analysis of the Defect Level of Paving Stone DC 06 Products Using Six Sigma and FMEA Methods at PT. Duta Beton Mandiri Pasuruan. JKIE (Journal Knowledge Industrial Engineering), 11(3), 134–146. https://doi.org/10.35891/jkie.v11i3.6168

Liakos, K. G., Athanasiadis, V., Bozinou, E., & Lalas, S. I. (2025). Machine Learning for Quality Control in the Food Industry: A Review. In Foods (Vol. 14, Issue 19). Multidisciplinary Digital Publishing Institute (MDPI). https://doi.org/10.3390/foods14193424

Muhamad Ihsan Nudin, Sukanta, & Adrian Yudistira. (2025). Quality Control of 3KG LPG Gas Cylinder Production with Six Sigma Approach at PT XYZ. JKIE (Journal Knowledge Industrial Engineering), 12(1), 40–52. https://doi.org/10.35891/jkie.v12i1.6023

Oleka, C. J., Aikhuele, D. O., & Omorogiuwa, E. (2022). Data-Driven Intelligent Model for the Classification, Identification, and Determination of Data Clusters and Defect Location in a Welded Joint. Processes, 10(10). https://doi.org/10.3390/pr10101923

Riyanto. (2025). Quality Control of 240 Ml Cup Product Packaging Using Six Sigma and Fmea Methods To Reduce Product Reject Failure At PT. XYZ. JKIE (Journal Knowledge Industrial Engineering), 11(1), 31–35. https://doi.org/10.35891/jkie.v11i1.6172

Schötz, S., Butzer, S., Molenda, P., Drews, T., & Steinhilper, R. (2017). An Approach Towards an Adaptive Quality Assurance. Procedia CIRP, 63, 189–194. https://doi.org/10.1016/j.procir.2017.03.096

Wahyu Purnomo, D., & Hermansyah, M. (2025). Quality Control Analysis on 100ML Bottle Products with Fault Tree Analysis Method Approach and Failur Mode and Effect Analysis. JKIE (Journal Knowledge Industrial Engineering), 11(3), 153–161. https://doi.org/10.35891/jkie.v11i3.6164

Wicaksono, R. A., Momon, A. S., Malik Ij, F. A., & Ulfi Akhsan Setyanto. (2026). Analisis Pengendalian Kualitas Produk Cacat Menggunakan Metode Lean Six Sigma dengan Konsep DMAIC di PT. PQR. Industrika, 10(1).

Yulisasih, B. N., Herman, H., Sunardi, S., & Yuliansyah, H. (2024). Evaluation of K-Means Clustering Using Silhouette Score Method on Customer Segmentation. ILKOM Jurnal Ilmiah, 16(3), 330–342. https://doi.org/10.33096/ilkom.v16i3.2325.330-342