FactoryGuard AI: An IoT-Based Predictive Maintenance Engine for Industrial Robotic Arms Using XGBoost, SMOTE, and SHAP Explainability

References

[1] Aberdeen Group, "The True Cost of Downtime in Manufacturing," Industry Report, 2023.

[2] Z. Zhao, T. Li, R. Yu, et al., "Deep Learning and Its Applications to Machine Health Monitoring," Mechanical Systems and Signal Processing, vol. 115, pp. 213-237, 2019.

[3] G. A. Susto, A. Schirru, S. Pampuri, S. McLoone, and A. Beghi, "Machine Learning for Predictive Maintenance: A Multiple Classifier Approach," IEEE Trans. Ind. Inform., vol. 11, no. 3, pp. 812-820, 2015.

[4] S. Karabadji, S. Beldjehem, L. Kheddouci, and H. Seridi, "Accuracy and Diversity-Based Strategies in Classifier Ensemble Construction for Evolving Data Streams," Information Sciences, vol. 360, pp. 204-233, 2016.

[5] T. Chen and C. Guestrin, "XGBoost: A Scalable Tree Boosting System," Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, pp. 785-794, 2016.

[6] S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997.

[7] A. Vaswani, N. Shazeer, N. Parmar, et al., "Attention Is All You Need," Advances in Neural Information Processing Systems, vol. 30, 2017.

[8] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, "SMOTE: Synthetic Minority Over-sampling Technique," Journal of Artificial Intelligence Research, vol. 16, pp. 321-357, 2002.

[9] H. Han, W. Wang, and B. Mao, "Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning," Proc. ICIC, pp. 878-887, 2005.

[10] H. He, Y. Bai, E. A. Garcia, and S. Li, "ADASYN: Adaptive Synthetic Sampling Approach for Imbalanced Learning," Proc. IEEE IJCNN, pp. 1322-1328, 2008.

[11] H. He and E. A. Garcia, "Learning from Imbalanced Data," IEEE Trans. Knowledge and Data Engineering, vol. 21, no. 9, pp. 1263-1284, 2009.

[12] S. M. Lundberg and S. Lee, "A Unified Approach to Interpreting Model Predictions," Advances in Neural Information Processing Systems, vol. 30, 2017.

[13] G. Ancona, E. Ceolini, C. Oztireli, and M. Gross, "Towards Better Understanding of Gradient-Based Attribution Methods for Deep Neural Networks," ICLR, 2018.

[14] D. Alvarez-Melis and T. S. Jaakkola, "On the Robustness of Interpretability Methods," Proc. ICML Workshop on Human Interpretability in Machine Learning, 2018.

[15] M. T. Ribeiro, S. Singh, and C. Guestrin, "'Why Should I Trust You?': Explaining the Predictions of Any Classifier," Proc. 22nd ACM SIGKDD, pp. 1135-1144, 2016.

[16] R. B. Randall, Vibration-Based Condition Monitoring: Industrial, Automotive and Aerospace Applications, 2nd ed. Wiley, 2021.

[17] L. Prokhorenkova, G. Gusev, A. Vorobev, A. V. Dorogush, and A. Gulin, "CatBoost: Unbiased Boosting with Categorical Features," NIPS, 2018.

[18] T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, "Optuna: A Next-Generation Hyperparameter Optimization Framework," Proc. 25th ACM SIGKDD, pp. 2623-2631, 2019.

[19] S. M. Lundberg, G. Erion, H. Chen, et al., "From Local Explanations to Global Understanding with Explainable AI for Trees," Nature Machine Intelligence, vol. 2, no. 1, pp. 56-67, 2020.

[20] J. Davis and M. Goadrich, "The Relationship Between Precision-Recall and ROC Curves," Proc. 23rd ICML, pp. 233-240, 2006.

[21] F. Pedregosa, G. Varoquaux, A. Gramfort, et al., "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825-2830, 2011.

[22] G. Lemaître, F. Nogueira, and C. K. Aridas, "Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning," Journal of Machine Learning Research, vol. 18, pp. 559-563, 2017.

@article{1718462,
      author = {Pratik Joshi, Vrushali Shinde},
      title = {FactoryGuard AI: An IoT-Based Predictive Maintenance Engine for Industrial Robotic Arms Using XGBoost, SMOTE, and SHAP Explainability},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {11},
      pages = {4755-4766},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1718462.pdf},
      abstract = {Unplanned equipment failure in large-scale manufacturing facilities inflicts enormous operational and financial consequences, with downtime costs estimated at $10,000 per hour per production line. This paper presents FactoryGuard AI, a comprehensive IoT-driven predictive maintenance engine designed to forecast binary failure events of industrial robotic arms with a 24-hour lead time. The system ingests streaming sensor telemetry—vibration, temperature, and pressure—from a fleet of 500 critical robotic arms and transforms raw signals into rich temporal feature representations through sliding-window statistics and exponential moving averages. The inherent class imbalance of failure events (< 1% positive class prevalence) is addressed via Synthetic Minority Over-sampling Technique (SMOTE) combined with scale-position weighting. A Logistic Regression baseline is established for benchmarking, after which an optimised XGBoost gradient-boosted ensemble is trained, achieving an Area Under the Receiver Operating Characteristic Curve (AUC-ROC) of 0.9847, a Precision of 0.923, a Recall of 0.917, and an F1-Score of 0.920 on held-out test data. SHapley Additive exPlanations (SHAP) are integrated to deliver local and global model interpretability, enabling maintenance engineers to understand and trust individual failure predictions. The system reduces false negatives by 78.4% compared to the baseline, translating to an estimated annual saving of $4.2 million in avoided downtime for a 500-robot facility.},
      keywords = {Predictive Maintenance, IoT Sensor Fusion, XGBoost, SMOTE, SHAP, Explainable AI, Rolling Window Features, Binary Classification, Industrial IoT, Robotic Arm Monitoring},
      month = {May},
      doi = {https://doi.org/10.64388/IREV9I11-1718462}
  }