EFFICIENT FAULT DETECTION IN INDUSTRIAL EQUIPMENT USING PCA AND SMOTE ENHANCED NEURAL NETWORKS
DOI:
https://doi.org/10.26906/SUNZ.2025.1.77-82Keywords:
fault detection, neural networks, PCA, SMOTE, dimensionality reductionAbstract
This research addresses the challenge of fault detection in industrial equipment using high-dimensional vibration
data with limited labeled examples. The goal was to develop a neural network model capable of accurately classifying
measurement vectors into normal and faulty categories. The dataset consisted of 1158 samples, each with 93,752 numerical
features, representing two classes: 865 normal and 293 faulty instances. A comprehensive preprocessing pipeline was
employed, including standardization, dimensionality reduction using Principal Component Analysis (PCA), and Synthetic
Minority Over-sampling Technique (SMOTE) for class balancing. The developed neural network achieved a baseline
accuracy of 94.40% with 100 PCA components. Further experiments demonstrated that reducing the architecture and using
only 50 PCA components improved accuracy to 98.81%, highlighting the effectiveness of the proposed approach. These
findings emphasize the utility of combining PCA, SMOTE, and neural networks for fault detection in industrial equipment
in high-dimensional, imbalanced datasets. Future research directions include exploring advanced neural network
architectures, investigating the impact of PCA component count on model performance, and studying the feasibility of
training effective models on synthetic data.
Downloads
References
1. B. Krawczyk, "Learning from imbalanced data: Open challenges and future directions," Progress in Artificial Intelligence, vol. 5, no. 4, Apr. 2016. doi:10.1007/s13748-016-0094-0. DOI: https://doi.org/10.1007/s13748-016-0094-0
2. 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, Jun. 2002. doi: 10.1613/jair.953. DOI: https://doi.org/10.1613/jair.953
3. Y. Zhang, and S. Wang, "Deep learning for time series forecasting: A survey," Big Data, vol. 9, no. 1, Dec. 2020. doi:10.1089/big.2020.0159. DOI: https://doi.org/10.1089/big.2020.0159
4. X. Chen, D. Liu, and H. Zha, "Predictive data mining techniques for fault diagnosis of electric equipment: A review," Applied Sciences, vol. 10, no. 3, p. 950, Feb. 2020. doi: 10.3390/app10030950. DOI: https://doi.org/10.3390/app10030950
5. B. S. Panigrahi, T. T, M. Tamilselvi, S. B. G. Tilak Babu, P. G and B. Shaik, "Deep Learning Techniques for Fault Detection in Industrial Machinery," 2024 5th International Conference on Recent Trends in Computer Science and Technology (ICRTCST), Jamshedpur, India, 2024, pp. 221-226, doi: 10.1109/ICRTCST61793.2024.10578499. DOI: https://doi.org/10.1109/ICRTCST61793.2024.10578499
6. Y. Zhang, et al., "Deep learning-based intelligent fault diagnosis methods toward rotating machinery," IEEE Access, vol. 8, pp. 9335–9346, 2019. doi: 10.1109/ACCESS.2019.2963092. DOI: https://doi.org/10.1109/ACCESS.2019.2963092
7. O. Matania, E. Bechhoefer, and J. Bortman, "Digital Twin of a Gear Root Crack Prognosis," Sensors, vol. 23, no. 24, p. 9883, Dec. 2023. doi: 10.3390/s23249883. DOI: https://doi.org/10.3390/s23249883
8. O. Matania, R. Cohen, E. Bechhoefer, and J. Bortman, "Anomaly Detection and Remaining Useful Life Estimation for the Health and Usage Monitoring Systems 2023 Data Challenge," PHM Society Proceedings, vol. 8, no. 1, Jun. 2024. doi:10.36001/phme.2024.v8i1.4125.
9. O. Matania, E. Bechhoefer, D. Blunt, W. Wang, and J. Bortman, "Anomaly Detection and Remaining Useful Life Estimation for the Health and Usage Monitoring Systems 2023 Data Challenge," Sensors, vol. 24, no. 13, p. 4258, Jun. 2024. doi:10.3390/s24134258. DOI: https://doi.org/10.3390/s24134258
10. O. Matania, L. Bachar, E. Bechhoefer, and J. Bortman, "Signal Processing for the Condition-Based Maintenance of Rotating Machines via Vibration Analysis: A Tutorial," Sensors, vol. 24, no. 2, p. 454, Jan. 2024. doi: 10.3390/s24020454. DOI: https://doi.org/10.3390/s24020454
11. T. Chistiakova, J. Zambrano, and B. Carlsson, “Application of machine learning methods for fault detection in wastewater treatment plants,”, in Reglermöte, 2014. doi: 10.13140/2.1.3733.4403.
12. S. Windmann, "Data-Driven Fault Detection in Industrial Batch Processes Based on a Stochastic Hybrid Process Model," in IEEE Transactions on Automation Science and Engineering, vol. 19, no. 4, pp. 3888-3902, Oct. 2022, doi:10.1109/TASE.2021.3138925. DOI: https://doi.org/10.1109/TASE.2021.3138925
13. Ukrainian hackathon of scientific works of young scientists in the field of intellectual information technologies URL:https://zp.edu.ua/vkiit
14. The dataset. URL: https://pz.zp.ua/files/vkiit/zeroShot_vkiit.rar
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
