A DI-SRM Model for Production Bottleneck Prediction in Flexible Production Line

Desheng  Liu; Shuanglong  Shi; Kun  li; Zhiguo  Dai

doi:10.6180/jase.202507_28(7).0017

A DI-SRM Model for Production Bottleneck Prediction in Flexible Production Line

Electrical Engineering Computer Science and Information Engineering

Desheng LiuThis email address is being protected from spambots. You need JavaScript enabled to view it., Shuanglong Shi, Kun li, and Zhiguo Dai

School of Information and Electronic Technology, Jiamusi University, Heilongjiang, 154007, China

Received: August 15, 2024
Accepted: September 20, 2024
Publication Date: October 13, 2024

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202507_28(7).0017

In the context of Industrial Internet of Things (IIoT) flexible production lines, accurately predicting production bottlenecks is crucial for optimizing efficiency and resource allocation. However, the dynamic and uncertain nature of these processes poses significant challenges. This study introduces a novel bottleneck prediction method by integrating the Drift Index (DI) with a Stacked Regression Model (SRM). This study marks the first application of stacked ensemble learning techniques in predicting bottlenecks within IIoT-enabled flexible production lines, leading to notable improvements in prediction accuracy and model robustness. The proposed method utilizes both real-time and historical data collected from IoT devices, encompassing three core steps: bottleneck data analysis, quantification of the drift index, and construction of the stacked regression model. By incorporating multiple production parameters such as equipment utilization and queue length, the method employs advanced time series analysis to forecast potential bottleneck drifts. Experimental results confirm that the DI-SRM model achieves high prediction accuracy and real-time responsiveness, effectively addressing the challenges of dynamic production environments. This approach provides reliable decision support for production scheduling and resource allocation, thereby optimizing production efficiency and enhancing market competitiveness.

Keywords: Production line; Drift index; Stacked model; Production bottleneck prediction

[1] Z. Tian, X. Jiang, W. Liu, and Z. Li, (2023) “Dynamic energy-efficient scheduling of multi-variety and small batch flexible job-shop: A case study for the aerospace industry" Computers & Industrial Engineering 178: 109111. DOI: 10.1016/j.cie.2023.109111.
[2] S. Kolasani, (2024) “Revolutionizing manufacturing, making it more efficient, flexible, and intelligent with Industry 4.0 innovations" International Journal of Sustainable Development Through AI, ML and IoT 3(1): 1–17.
[3] R. Wang, T. Xin, S. Jia, D. Ren, and M. Li, (2024) “Production line balance problem identification and improvement based on decision tree: A case study of commercial air conditioner production line" Science Progress 107(1): DOI: 10.1177/00368504241238612.
[4] M. Kumbhar, A. H. Ng, and S. Bandaru, (2023) “A digital twin based framework for detection, diagnosis, and improvement of throughput bottlenecks" Journal of manufacturing systems 66: 92–106. DOI: 10.1016/j.jmsy.2022.11.016.
[5] A. Skoogh, M. Thürer, M. Subramaniyan, A. Matta, and C. Roser, (2023) “Throughput bottleneck detection in manufacturing: a systematic review of the literature on methods and operationalization modes" Production & Manufacturing Research 11(1): 2283031. DOI: 10.1080/21693277.2023.2283031.
[6] C. Latsou, M. Farsi, and J. A. Erkoyuncu, (2023) “Digital twin-enabled automated anomaly detection and bottleneck identification in complex manufacturing systems using a multi-agent approach" Journal of Manufacturing Systems 67: 242–264. DOI: 10.1016/j.jmsy.2023.02.008.
[7] L. Ragazzini, E. Negri, L. Fumagalli, and M. Macchi, (2024) “Digital Twin-based bottleneck prediction for improved production control" Computers & Industrial Engineering 192: 110231. DOI: 10.1016/j.cie.2024.110231.
[8] W. Yan, J. Wang, S. Lu, M. Zhou, and X. Peng, (2023) “A review of real-time fault diagnosis methods for industrial smart manufacturing" Processes 11(2): 369. DOI: 10.3390/pr11020369.
[9] P. A. Tuan and N. M. Linh, (2024) “Trajectory Tracking Control Of Omnidirectional Mobile Robots: A Model-Free Control-based Apprroach" Journal of Applied Science and Engineering 27(12): 3687–3696. DOI: 10.6180/jase.202412_27(12).0009.
[10] Y. Pan and L. Zhang, (2021) “Automated process discovery from event logs in BIM construction projects" Automation in Construction 127: 103713. DOI: 10.1016/j.autcon.2021.103713.
[11] M. Subramaniyan, A. Skoogh, H. Salomonsson, P. Bangalore, and J. Bokrantz, (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. DOI: 10.1016/j.cie.2018.04.024.
[12] T. A. Do, Q. N. Le, Q. D. Nguyen, and P. Vu, (2024) “A PQ Control Strategy Using Feedback Linearization Theory For A Three-phase Four-wire Grid-Connected Inverter In An AC Battery" Journal of Applied Science and Engineering 28(4): 893–900. DOI: 10.6180/jase.202504_28(4).0019.
[13] F. K. A. Alazemi, M. K. A. B. M. Ariffin, F. B. Mustapha, and E. E. B. Supeni, (2022) “A new fuzzy TOPSIS-based machine learning framework for minimizing completion time in supply chains" International Journal of Fuzzy Systems 24(3): 1669–1695. DOI: 10. 1007/s40815-021-01226-3.
[14] X. Zhang and L. Pei, (2024) “Cooling Load Forecasting Based On Hybrid Machine-Learning Application With Integration Of Meta-heuristic Algorithm" Journal of Applied Science and Engineering 28(3): 601–614. DOI: 10.6180/jase.202503_28(3).0016.
[15] P. Dobra and J. Jósvai, (2022) “Assembly line overall equipment effectiveness (OEE) prediction from human estimation to supervised machine learning" Journal of Manufacturing and Materials Processing 6(3): 59. DOI: 10.3390/jmmp6030059.
[16] P. Agarwal, M. Aghaee, M. Tamer, and H. Budman, (2022) “A novel unsupervised approach for batch process monitoring using deep learning" Computers & Chemical Engineering 159: 107694. DOI: 10.1016/j.compchemeng.2022.107694.
[17] L. Teng and Y. Qiao, (2022) “BiSeNet-oriented context attention model for image semantic segmentation" Computer Science and Information Systems 19(3): 1409–1426. DOI: 10.2298/csis220321040t.
[18] C. Li, T. Yu, H.-t. Fan, G. Xiao, J. Arinez, and Q. Chang, (2023) “Dynamic bottleneck identification and production loss evaluation for assembly lines" Manufacturing Letters 35: 1089–1096. DOI: 10.1016/j.mfglet.2023.08.089.
[19] S. F. Ahmed, M. S. B. Alam, M. Hassan, M. R. Rozbu, T. Ishtiak, N. Rafa, M. Mofijur, A. Shawkat Ali, and A. H. Gandomi, (2023) “Deep learning modelling techniques: current progress, applications, advantages, and challenges" Artificial Intelligence Review 56(11): 13521–13617. DOI: 10.1007/s10462-023-10466-8.
[20] Z. Zhang and J. Li, (2023) “A review of artificial intelligence in embedded systems" Micromachines 14(5): 897. DOI: 10.3390/mi14050897.
[21] S. Lin, J. Liu, and S. Li. “Production bottleneck prediction of multi-variety and small batch production workshop”. In: Journal of Physics: Conference Series. 2187. 1. IOP Publishing. 2022, 012057. DOI: 10.1088/1742-6596/2187/1/012057.
[22] M. Del Giudice, (2024) “The prediction-explanation fallacy: a pervasive problem in scientific applications of machine learning" Methodology 20(1): 22–46. DOI: 10.5964/meth.11235.
[23] J. Hoxha, M. Y. Çodur, E. Mustafaraj, H. Kanj, and A. El Masri, (2023) “Prediction of transportation energy demand in Türkiye using stacking ensemble models: Methodology and comparative analysis" Applied Energy 350: 121765. DOI: 10.1016/j.apenergy.2023.121765.
[24] W. Su, F. Jiang, C. Shi, D. Wu, L. Liu, S. Li, Y. Yuan, and J. Shi, (2023) “An XGBoost-based knowledge tracing model" International Journal of Computational Intelligence Systems 16(1): 13. DOI: 10.1007/s44196-023-00192-y.
[25] E. Chung, K. Park, and P. Kang, (2023) “Fault classification and timing prediction based on shipment inspection data and maintenance reports for semiconductor manufacturing equipment" Computers & Industrial Engineering 176: 108972. DOI: 10.1016/j.cie.2022.108972.
[26] G. James, D. Witten, T. Hastie, R. Tibshirani, and J. Taylor. “Linear regression”. In: An introduction to statistical learning: With applications in python. Springer, 2023, 69–134. DOI: 10.1007/978-3-031-38747-0_3.
[27] M. Thürer, S. S. Li, C. Yang, T. Qu, and G. Q. Huang. “Does Regulating Work-In-Process Increase Throughput and Reduce Cycle Times? An Assessment by Lab Scale System Models”. In: IFIP International Conference on Advances in Production Management Systems. Springer. 2023, 649–661. DOI: 10.1007/978- 3-031-43670-3_45.
[28] Y. Zhou, Y. Wang, and Z. Ji, (2023) “Bottleneck Drift Fluctuation Analysis of Discrete Remanufacturing System under Disturbance" Journal of System Simulation 35(4): 809–821. DOI: 10.16182/j.issn1004731x.joss.21-1335.
[29] X. Lai, T. Qiu, H. Shui, D. Ding, and J. Ni, (2023) “Predicting future production system bottlenecks with a graph neural network approach" Journal of Manufacturing Systems 67: 201–212. DOI: 10.1016/j.jmsy.2023.01.010.
[30] S. Wang, Y. Wu, R. Li, and X. Wang, (2023) “Remote sensing-based retrieval of soil moisture content using stacking ensemble learning models" Land Degradation & Development 34(3): 911–925. DOI: 10.1002/ldr.4505.