An application of k-means clustering method to identify bottlenecks in manufacturing process
Abstract: 297
| 
PDF: 182 
##plugins.themes.academic_pro.article.main##
Author
Keywords:
Abstract
Advances in machine learning (ML) techniques have provided new opportunities for manufacturing managers to support their decision-making through the analysis of manufacturing systems. Detecting bottlenecks on the production line is an important issue for manufacturing managers because bottlenecks reduce the productivity of the system. In addition, detecting bottlenecks in the manufacturing system also reduces costs and improves the overall efficiency of the entire production line. This study applies k-means clustering, one of the popular clustering methods of ML, to detect bottlenecks on production lines. The proposed method begins by identifying the operating state time at each machine/process on the production line. k-means clustering is used to classify the processes into different groups in which each group has similar machine characteristics. The analysis of clustered data based on its representative time series is conducted to detect bottlenecks.
References
-
[1] M. Miller, "AI: Augmentation, more so than automation”, Asian Management Insight, vol. 5, no. 1, pp. 1-20, 2018.
[2] J. Wilson and P. R. Daugherty, "Collaborative intelligence: Humans and AI are joining forces”, Harvard Business Review, vol. 96, no. 4, pp. 114-123, 2018.
[3] Wuest, D. Weimer, C. Irgens, and K.-D. Thoben, "Machine learning in manufacturing: advantages, challenges, and applications”, Production & Manufacturing Research, vol. 4, no. 1, pp. 23-45, 2016.
[4] Sharp, R. Ak, and T. Hedberg Jr, "A survey of the advancing use and development of machine learning in smart manufacturing”, Journal of manufacturing systems, vol. 48, pp. 170-179, 2018.
[5] Cimini, F. Pirola, R. Pinto, and S. Cavalieri, "A human-in-the-loop manufacturing control architecture for the next generation of production systems”, Journal of manufacturing systems, vol. 54, pp. 258-271, 2020.
[6] Alavian, Y. Eun, S. M. Meerkov, and L. Zhang, "Smart production systems: automating decision-making in manufacturing environment”, International Journal of Production Research, vol. 58, no. 3, pp. 828-845, 2020.
[7] Wu, Y. Zhou, and N. Zhao, "Variability and the fundamental properties of production lines”, Computers & Industrial Engineering, vol. 99, pp. 364-371, 2016.
[8] Roser, M. Nakano, and M. Tanaka, "A practical bottleneck detection method”, in Proceeding of the 2001 winter simulation conference (Cat. No. 01CH37304), 2001, pp. 949-953.
[9] Yu and A. Matta, "Data-driven bottleneck detection in manufacturing systems: A statistical approach”, in 2014 IEEE international conference on automation science and engineering (CASE), 2014, pp. 710-715.
[10] Subramaniyan, A. Skoogh, A. S. Muhammad, J. Bokrantz, B. Johansson, and C. Roser, "A generic hierarchical clustering approach for detecting bottlenecks in manufacturing”, Journal of Manufacturing Systems, vol. 55, pp. 143-158, 2020.
[11] K. Jain, "Data clustering: 50 years beyond K-means”, Pattern recognition letters, vol. 31, no. 8, pp. 651-666, 2010.
[12] P. Sinaga and M.-S. Yang, "Unsupervised K-means clustering algorithm”, IEEE access, vol. 8, pp. 80716-80727, 2020.
[13] Dogan and D. Birant, "Machine learning and data mining in manufacturing”, Expert Systems with Applications, vol. 166, p. 114060, 2021.
[14] Li, Q. Chang, and J. Ni, "Data driven bottleneck detection of manufacturing systems”, International Journal of production research, vol. 47, no. 18, pp. 5019-5036, 2009.
[15] E. Betterton and S. Silver, "Detecting bottlenecks in serial production lines–a focus on interdeparture time variance”, International Journal of Production Research, vol. 50, no. 15, pp. 4158-4174, 2012.
[16] H. Tang, "A new method of bottleneck analysis for manufacturing systems”, Manufacturing letters, vol. 19, pp. 21-24, 2019.
##plugins.themes.academic_pro.article.sidebar##
