Estimating Types of Faults on Plastic Injection Molding Machines from Sensor Data for Predictive Maintenance

Abstract

Fault type detection for the plastic injection molding machines is an important problem in order to take failure-specific actions to prevent any problem in production, hence providing continuity in procurement. In this study, we treat this problem as a multi-class classification task and proposed a novel machine learning model to achieve reliable and accurate results. We applied the Random Forest (RF) and Extreme Gradient Boosting (XGBoost) algorithms with and without SMOTE (Synthetic Minority Over-sampling Technique) to a real-world dataset for predictive maintenance. According to the results, XGBoost performed better than RF. With the combination of SMOTE method, the performances of both methods increased in terms of accuracy. XGBoost with SMOTE outperformed other techniques by achieving about 98% accuracy on average.

Keywords

• machine learning
• predictive maintenance
• classification
• plastic injection molding machines
• manufacturing
• sensors

References

1. [1] Moradzadeh, A., Teimourzadeh, H., Mohammadi-Ivatloo, B., & Pourhossein, K. (2022). Hybrid CNN-LSTM approaches for identification of type and locations of transmission line faults. Electrical Power and Energy Systems, 135, 1-13.
2. [2] Leon-Medina, J.X., Anaya, M., Pares, N., Tibaduiza, D. A., & Pozo, F. (2021). Structural damage classification in a jacket-typewind-turbine foundation using principal component analysis and extreme gradient boosting. Sensors, 21(8), 1-29.
3. [3] Chen, Q., Wei, H., Rashid, M., & Cai, Z. (2021). Kernel extreme learning machine-based hierarchical machine learning for multi-type and concurrent fault diagnosis. Measurement, 184, 1-12.
4. [4] Bressan, G. A., de Azevedo, B. C. F., dos Santos, H. L., Endo, W., Agulhari, C. M., Goedtel, A., & Scalassara, P. R. (2021). Bayesian approach to infer types of faults on electrical machines from acoustic signal. Applied Mathematics & Information Sciences, 15(3), 353-364.
5. [5] Trinh, H-C., & Kwon, Y-K. (2020). A data-independent genetic algorithm framework for fault-type classification and remaining useful life prediction. Applied Sciences, 10(1), 1-20.
6. [6] Liu, Z., Xiao, C., Zhang, T., & Zhang, X. (2020). Research on fault detection for three types of wind turbine subsystems using machine learning. Energies, 13(2), 1-21.
7. [7] Liu, R., Yang, B., Zio, E., & Chen, X. (2018). Artificial intelligence for fault diagnosis of rotating machinery: A review. Mechanical Systems and Signal Processing, 108, 33-47.
8. [8] Morales, F. J., Reyes, A., Caceres, N., Romero, L., & Benitez, F. G. (2018). Automatic prediction of maintenance intervention types in roads using machine learning and historical records. Transportation Research Record, 2672(44), 43-54.

9. [9] Zhao, Z., Tang, C., Zhou, Q., Xu, L., Gui, Y., & Yao, C. (2017). Identification of power transformer winding mechanical fault types based on online IFRA by support vector machine. Energies, 10(12), 1-16.
10. [10] Palacios, R. H. C., da Silva, I. N., Goedtel, A., & Godoy, W. F. (2015). A comprehensive evaluation of intelligent classifiers for fault identification in three-phase induction motors. Electric Power Systems Research, 127, 249-258.
11. [11] Aydin, I., Karakose, M., & Akin, E. (2014). An approach for automated fault diagnosis based on a fuzzy decision tree and boundary analysis of a reconstructed phase space. ISA Transactions, 53, 220-229.
12. [12] Ertunc, H. M., Ocak, H., & Aliustaoglu, C. (2013). ANN- and ANFIS-based multi-staged decision algorithm for the detection and diagnosis of bearing faults. Neural Computing & Applications, 22(1), 435-446.
13. [13] Barzegaran, M., Mazloomzadeh, A., & Mohammed, O. A. (2013). Fault diagnosis of the asynchronous machines through magnetic signature analysis using finite-element method and neural networks. IEEE Transactions on Energy Conversion, 28(4), 1064-1071.
14. [14] Wang, J., Liua, S., Gaoa, R. X., Yanb, R. (2012). Current envelope analysis for defect identification and diagnosis in induction motors. Journal of Manufacturing Systems, 31, 380–387.
15. [15] Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). Smote: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16(1), 321–357.
16. [16] Zebari, R.R., Abdulazeez, A. M., Zeebaree, D. Q., Zebari, D. A., Saeed, J. N. (2020). A comprehensive review of dimensionality reduction techniques for feature selection and feature extraction. Journal of Applied Science and Technology Trends, 1(2), 56-70.
17. [17] Charoen-Ung, P., & Mittrapiyanuruk, P. (2019). Sugarcane yield grade prediction using random forest with forward feature selection and hyper-parameter tuning. In: Unger, H., Sodsee, S., & Meesad, P. (eds) Recent Advances in Information and Communication Technology 2018. Advances in Intelligent Systems and Computing, 769, 33-42.
18. [18] Wang, R. Gao, W., & Peng, W. (2021). Spatial downscaling method for air temperature through the correlation between land use/land cover and microclimate: A case study of the Greater Tokyo Area, Japan. Urban Climate, 40, 1-16.
19. [19] Peng, W., Yuan, X., Gao, W., Wang, R., & Chen, W. (2021). Assessment of urban cooling effect based on downscaled land surface temperature: A case study for Fukuoka, Japan. Urban Climate, 36, 1-18.
20. [20] Baitharu, T.R., & Pani, S.K. (2013). Effect of missing values on data classification. Journal of Emerging Trends in Engineering and Applied Sciences, 4(2), 311–316.