The semiconductor industry is known for its complex production. Thousands of machines (tools) perform thousands of operations over a diverse range of products with re-entrant flows and shifting bottlenecks. Detecting and predicting these bottlenecks in real-time and promptly responding to them at the shop-floor level can make a big difference in terms of efficiently utilizing the high capital equipment and achieving operational excellence. So far, approaches to this problem have used traditional optimization methods. This paper pioneers the application of big data ML models to the problem, tested on industry data. We propose a dual-phased approach that leverages Machine Learning (ML) for this task. The first phase involves evaluating the most relevant production parameters (features) in the production line, along with their predefined target values, while the second phase enhances and refines these parameters at the segment level of the production line to reflect aspects of balancing and leveling. We show that the most effective ML model is attained using the XGBoost algorithm, which achieves 95% accuracy. This outcome enables a more precise classification of the dynamically shifting bottlenecks within the production line relative to other methods in practice, thereby allowing production staff better control and performance in the long run.
References
[1]
Ehm, H. and Ponsignon, T. (2012) Future Research Directions for Mastering End-to-End Semiconductor Supply Chains. 2012 IEEE International Conference on Automation Science and Engineering (CASE), Seoul, 20-24 August 2012, 641-645. https://doi.org/10.1109/coase.2012.6386323
[2]
Schmenner, R.W. and Swink, M.L. (1998) On Theory in Operations Management. Journal of Operations Management, 17, 97-113. https://doi.org/10.1016/s0272-6963(98)00028-x
[3]
Alavian, P., Eun, Y., Meerkov, S.M. and Zhang, L. (2019) Smart Production Systems: Automating Decision-Making in Manufacturing Environment. International Journal of Production Research, 58, 828-845. https://doi.org/10.1080/00207543.2019.1600765
[4]
Goldratt, E.M. (1990) Theory of Constraints. North River, 159 p.
[5]
Mahmoodi, E., Fathi, M. and Ghobakhloo, M. (2022) The Impact of Industry 4.0 on Bottleneck Analysis in Production and Manufacturing: Current Trends and Future Perspectives. Computers & Industrial Engineering, 174, Article ID: 108801. https://doi.org/10.1016/j.cie.2022.108801
[6]
Tang, J., Dai, Z., Jiang, W., Wu, X., Zhuravkov, M.A., Xue, Z., et al. (2024) A Comprehensive Review of Theories, Methods, and Techniques for Bottleneck Identification and Management in Manufacturing Systems. Applied Sciences, 14, Article 7712. https://doi.org/10.3390/app14177712
[7]
Ibidunmoye, O., Hernández-Rodriguez, F. and Elmroth, E. (2015) Performance Anomaly Detection and Bottleneck Identification. ACM Computing Surveys, 48, 1-35. https://doi.org/10.1145/2791120
[8]
Kacar, N.B., Munch, L. and Uzsoy, R. (2018) Problem Reduction Approaches for Production Planning Using Clearing Functions. 2018 IEEE 14th International Conference on Automation Science and Engineering (CASE), Munich, 20-24 August 2018, 931-938. https://doi.org/10.1109/coase.2018.8560429
[9]
Su, X., Lu, J., Chen, C., Yu, J. and Ji, W. (2022) Dynamic Bottleneck Identification of Manufacturing Resources in Complex Manufacturing System. Applied Sciences, 12, Article 4195. https://doi.org/10.3390/app12094195
[10]
Fang, W., Guo, Y., Liao, W., Huang, S., Yang, N. and Liu, J. (2020) A Parallel Gated Recurrent Units (P-Grus) Network for the Shifting Lateness Bottleneck Prediction in Make-to-Order Production System. Computers & Industrial Engineering, 140, Article ID: 106246. https://doi.org/10.1016/j.cie.2019.106246
[11]
Wedel, M., Noessler, P. and Metternich, J. (2016) Development of Bottleneck Detection Methods Allowing for an Effective Fault Repair Prioritization in Machining Lines of the Automobile Industry. Production Engineering, 10, 329-336. https://doi.org/10.1007/s11740-016-0672-9
[12]
Subramaniyan, M., Skoogh, A., Salomonsson, H., Bangalore, P. and Bokrantz, J. (2018) A Data-Driven Algorithm to Predict Throughput Bottlenecks in a Production System Based on Active Periods of the Machines. Computers & Industrial Engineering, 125, 533-544. https://doi.org/10.1016/j.cie.2018.04.024
[13]
Yan, C., Monch, L. and Meerkov, S.M. (2019) Characteristic Curves and Cycle Time Control of Re-Entrant Lines. IEEE Transactions on Semiconductor Manufacturing, 32, 140-153. https://doi.org/10.1109/tsm.2019.2908721
[14]
Li, L., Chang, Q. and Ni, J. (2009) Data Driven Bottleneck Detection of Manufacturing Systems. International Journal of Production Research, 47, 5019-5036. https://doi.org/10.1080/00207540701881860
[15]
Hopp, W.J. and Spearman, M.L. (2011) Factory Physics: Foundations of Manufacturing Management. Waveland Press.
[16]
Cao, Z., Deng, J., Liu, M. and Wang, Y. (2012) Bottleneck Prediction Method Based on Improved Adaptive Network-Based Fuzzy Inference System (ANFIS) in Semiconductor Manufacturing System. Chinese Journal of Chemical Engineering, 20, 1081-1088. https://doi.org/10.1016/s1004-9541(12)60590-4
[17]
Mönch, L. and Zimmermann, J. (2010) A Computational Study of a Shifting Bottleneck Heuristic for Multi-Product Complex Job Shops. Production Planning & Control, 22, 25-40. https://doi.org/10.1080/09537287.2010.490015
[18]
Subramaniyan, M., Skoogh, A., Muhammad, A.S., Bokrantz, J., Johansson, B. and Roser, C. (2020) A Generic Hierarchical Clustering Approach for Detecting Bottlenecks in Manufacturing. Journal of Manufacturing Systems, 55, 143-158. https://doi.org/10.1016/j.jmsy.2020.02.011
[19]
Thomas, T.E., Koo, J., Chaterji, S. and Bagchi, S. (2018) Minerva: A Reinforcement Learning-Based Technique for Optimal Scheduling and Bottleneck Detection in Distributed Factory Operations. 2018 10th International Conference on Communication Systems & Networks (COMSNETS), Bengaluru, 3-7 January 2018, 129-136. https://doi.org/10.1109/comsnets.2018.8328189
[20]
Subramaniyan, M., Skoogh, A., Bokrantz, J., Sheikh, M.A., Thürer, M. and Chang, Q. (2021) Artificial Intelligence for Throughput Bottleneck Analysis—State-of-the-Art and Future Directions. Journal of Manufacturing Systems, 60, 734-751. https://doi.org/10.1016/j.jmsy.2021.07.021
[21]
Muhammad, I. and Yan, Z. (2015) Supervised Machine Learning Approaches: A Sur-vey. ICTACT Journal on Soft Computing, 5, 946-952.
[22]
Grandini, M., Bagli, E. and Visani, G. (2020) Metrics for Multi-Class Classification: An Overview. arXiv: 2008.05756.
[23]
Vieira, S.M., Kaymak, U. and Sousa, J.M.C. (2010) Cohen’s Kappa Coefficient as a Performance Measure for Feature Selection. International Conference on Fuzzy Systems, Barcelona, 18-23 July 2010, 1-8. https://doi.org/10.1109/fuzzy.2010.5584447
[24]
Gavrylenko, S., Vladislav, Z. and Khatsko, N. (2023) Methods for Improving the Quality of Classification on Imbalanced Data. 2023 IEEE 4th KhPI Week on Advanced Technology (KhPIWeek), Kharkiv, 2-6 October 2023, 1-5. https://doi.org/10.1109/khpiweek61412.2023.10312879
