Applying XGBoost for Fault Prediction in Industrial Production Line

DOI: https://doi.org/10.62517/jike.202404321

Author(s)

Chao Chen*, Xu Li, Kai Wang

Affiliation(s)

School of Artificial Intelligence, Guangzhou Huashang University, Guangzhou, Guangdong, China *Corresponding Author.

Abstract

In the era of Industry 4.0, the level of intelligence and automation of production lines is crucial for improving production efficiency. This study addresses the issue of fault prediction in industrial production lines by constructing an automatic alarm model using XGBoost and neural network technology to enhance the intelligence of production lines and optimize scheduling. By analyzing the characteristics of fault data and using correlation matrices and time series differencing methods to build feature engineering, the model achieves a precision rate of up to 97.99%, effectively predicting fault trends. Furthermore, the model is applied to actual data to automatically alarm faults and statistically analyze fault frequency and duration. At the same time, by using correlation analysis and multiple linear regression models, the study calculates production and qualification rates, revealing their relationships with production lines and operators, and presents them in graphical form. The models and methods in this study have practical application value for improving industrial production efficiency.

Keywords

XGBoost; Machine Learning; Fault Prediction; Industrial Automation

References

[1] Stojanović D, Joković J, Tomašević I, et al. Algorithmic approach for the confluence of lean methodology and industry 4.0 technologies: Challenges, benefits, and practical applications. Journal of Industrial Intelligence, 2023, 1(2): 125-135. [2] Kang, Z., Catal, C., & Tekinerdogan, B. (2020). Machine learning applications in production lines: A systematic literature review. Computers & Industrial Engineering, 149, 106773. https://doi.org/10.1016/j.cie.2020.106773 [3] Crespino, A. M., Corallo, A., Lazoi, M., Barbagallo, D., Appice, A., & Malerba, D. (2016). Anomaly detection in aerospace product manufacturing: Initial remarks. In 2016 IEEE 2nd International Forum on Research and Technologies for Society and Industry Leveraging a Better Tomorrow (RTSI), 1–4. https://doi.org/10.1109/RTSI.2016.7740644 [4] Nakazawa, T., & Kulkarni, D. V. (2019). Anomaly detection and segmentation for wafer defect patterns using deep convolutional encoder–decoder neural network architectures in semiconductor manufacturing. IEEE Transactions on Semiconductor Manufacturing, 32(2), 250–256. https://doi.org/10.1109/TSM.2019.2897690 [5] Paolanti, M., Romeo, L., Felicetti, A., Mancini, A., Frontoni, E., & Loncarski, J. (2018). Machine learning approach for predictive maintenance in industry 4.0. In 2018 14th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA), 1–6. https://doi.org/10.1109/MESA.2018.8449150 [6] Yu, W., Dillon, T., Mostafa, F., Rahayu, W., & Liu, Y. (2020). A global manufacturing big data ecosystem for fault detection in predictive maintenance. IEEE Transactions on Industrial Informatics, 16(1), 183–192. https://doi.org/10.1109/TII.2019.2915846 [7] Aydemir, G., & Paynabar, K. (2020). Image-based prognostics using deep learning approach. IEEE Transactions on Industrial Informatics, 16(9), 5956–5964. https://doi.org/10.1109/TII.2019.2956220 [8] Weber, C., & Reimann, P. (2020). MMP – A platform to manage machine learning models in Industry 4.0 environments. In 2020 IEEE 24th International Enterprise Distributed Object Computing Workshop (EDOCW), 91–94. https://doi.org/10.1109/EDOCW49879.2020.00025 [9] Elshaboury, N., Al-Sakkaf, A., Alfalah, G., & Abdelkader, E. M. (2022). Data-Driven Models for Forecasting Failure Modes in Oil and Gas Pipes. Processes, 10, 400. https://doi.org/10.3390/pr10020400 [10] Liu, W., Chen, Z., & Hu, Y. (2020). XGBoost algorithm-based prediction of safety assessment for pipelines. Journal of Natural Gas Science and Engineering, 73, 103377. https://doi.org/10.1016/j.jngse.2020.103377 [11] Pang, J. L. (2023). Adaptive Fault Prediction and Maintenance in Production Lines Using Deep Learning. International Journal of Simulation Modelling, 22(4), 734-745. https://doi.org/10.2507/IJSIMM22-4-CO20 [12] Zhang S, Zhu X, Anduv B, et al. Fault detection and diagnosis for the screw chillers using multi-region XGBoost model. Science and Technology for the Built Environment, 2021, 27(5): 608-623. [13] Zhang C, Wang D, Song C, et al. Interpretable learning algorithm based on XGBoost for fault prediction in optical network//2020 Optical Fiber Communications Conference and Exhibition (OFC). IEEE, 2020: 1-3.