Citation:

Ruchi Patel, Prit Patel, 2024. Machine Learning-Driven Predictive Maintenance for Early Fault Prediction and Detection in Smart Manufacturing Systems , ESP Journal of Engineering & Technology Advancements 4(1): 141-149.

Abstract:

Numerous pieces of equipment have been introduced as a result of the increase in industrialization and digitization. Nonetheless, the equipment has to be carefully maintained and watched after. Any deviation results in the occurrence of fault. The stability and effectiveness of the system depend heavily on the discovery of faults at the outset. By implementing the suggested fault diagnostic method, the shortcomings of the traditional systems are addressed. This study presents a robust fault detection methodology for smart manufacturing, leveraging the Dense Net deep learning model on the CWRU bearing dataset. Through comprehensive data preprocessing, including noise filtering, normalization, and outlier removal, the model achieved an impressive accuracy of 98.57%, outperforming traditional ML models like MLP, CNN, and Bi-LSTM. The high precision (98.54%) and recall (98.55%) demonstrate the model’s effectiveness in minimizing false positives and accurately detecting faulty conditions. Training and validation performance trends indicate strong generalization, with minor overfitting but stable loss values. Comparative analysis highlights Dense Net’s superior capability in capturing complex fault patterns, surpassing MobileNetv2, which achieved 97.9% accuracy. This research proves that the Dense Net deep learning model can accurately anticipate and detect smart manufacturing system faults at an early stage.

References:

[1] M. Abdallah, B. Joung, W. J. Lee, C. Mousoulis, J. W. Sutherland, and S. Bagchi, “Anomaly Detection and Inter-Sensor Transfer Learning on Smart Manufacturing Datasets arXiv : 2206 . 06355v1 [ cs . LG ] 13 Jun 2022,” pp. 1–23, 2022.

[2] K. Murugandi and R. Seetharaman, “Analysing the Role of Inventory and Warehouse Management in Supply Chain Agility : Insights from Retail and Manufacturing Industries,” Int. J. Curr. Eng. Technol., vol. 12, no. 6, pp. 583–590, 2022.

[3] N. Daurenbayeva, A. Nurlanuly, L. Atymtayeva, and M. Mendes, “Survey of Applications of Machine Learning for Fault Detection, Diagnosis and Prediction in Microclimate Control Systems,” Energies, vol. 16, no. 8, pp. 1–21, 2023, doi: 10.3390/en16083508.

[4] H. Shao, H. Jiang, X. Li, and T. Liang, “Rolling bearing fault detection using continuous deep belief network with locally linear embedding,” Comput. Ind., vol. 96, pp. 27–39, 2018, doi: https://doi.org/10.1016/j.compind.2018.01.005.

[5] A. Gogineni, “Artificial intelligence-Driven Fault Tolerance Mechanisms for Distributed Systems Using Deep Learning Model,” J. Artif. Intell. Mach. Learn. Data Sci., vol. 1, no. 4, 2023.

[6] M. Fernandes, J. M. Corchado, and G. Marreiros, “Machine learning techniques applied to mechanical fault diagnosis and fault prognosis in the context of real industrial manufacturing use-cases: a systematic literature review,” Appl. Intell., vol. 52, no. 12, pp. 14246–14280, 2022, doi: 10.1007/s10489-022-03344-3.

[7] N. Bharot, M. Soderi, P. Verma, and J. G. Breslin, “Improving Product Quality Control in Smart Manufacturing through Transfer Learning-Based Fault Detection,” in 2023 IEEE International Conference on Smart Computing (SMARTCOMP), 2023, pp. 213–215. doi: 10.1109/SMARTCOMP58114.2023.00051.

[8] M. G. Albayati, J. Faraj, A. Thompson, P. Patil, R. Gorthala, and S. Rajasekaran, “Semi-Supervised Machine Learning for Fault Detection and Diagnosis of a Rooftop Unit,” Big Data Min. Anal., vol. 6, no. 2, pp. 170–184, 2023, doi: 10.26599/BDMA.2022.9020015.

[9] C. F. Mbey, V. J. Foba Kakeu, A. T. Boum, and F. G. Y. Souhe, “Fault detection and classification using deep learning method and neuro‐fuzzy algorithm in a smart distribution grid,” J. Eng., vol. 2023, no. 11, pp. 1–19, 2023, doi: 10.1049/tje2.12324.

[10] D. Shetve, I. Raju, R. V. Prasad, R. Trestian, H. Nguyen, and H. Venkataraman, “Adaptive N-Step Technique for Real-Time Anomaly Detection in Smart Manufacturing,” in 2022 IEEE 5th International Conference on Industrial Cyber-Physical Systems (ICPS), 2022, pp. 1–6. doi: 10.1109/ICPS51978.2022.9816882.

[11] K. Khalil, O. Eldash, A. Kumar, and M. Bayoumi, “Machine Learning-Based Approach for Hardware Faults Prediction,” IEEE Trans. Circuits Syst. I Regul. Pap., vol. 67, no. 11, pp. 3880–3892, Nov. 2020, doi: 10.1109/TCSI.2020.3010743.

[12] E. C. Ang and S. A. Suandi, “Smart Manufacturing with An Artificial Neural Network to Predict Manufacturing Healthiness,” in 2019 IEEE 15th International Colloquium on Signal Processing & Its Applications (CSPA), 2019, pp. 120–123. doi: 10.1109/CSPA.2019.8695975.

[13] A. Rahman, “Statistics-based data preprocessing methods and machine learning algorithms for big data analysis,” Int. J. Artif. Intell., 2019.

[14] D. C. R. Aniket Deshpande Dr. Arshey M, Ravuri Daniel, Deepak Dasaratha Rao, Dr. Emerson Raja, “Optimizing Routing in Nature-Inspired Algorithms to Improve Performance of Mobile Ad-Hoc Network,” Int. J. Intell. Syst. Appl. Eng., pp. 508–516, 2023.

[15] Y. H. Rajarshi Tarafdar, “Finding majority for integer elements,” J. Comput. Sci. Coll., vol. 33, no. 5, pp. 187–191, 2018.

[16] S. Mathur and S. Gupta, “Classification and Detection of Automated Facial Mask to COVID-19 based on Deep CNN Model,” in 2023 IEEE 7th Conference on Information and Communication Technology, CICT 2023, 2023. doi: 10.1109/CICT59886.2023.10455699.

[17] Y. Yoo, H. Jo, and S. Ban, “Lite and Efficient Deep Learning Model for Bearing Fault Diagnosis Using the CWRU Dataset,” 2023.

[18] D. Zhang and T. Zhou, “Deep Convolutional Neural Network Using Transfer Learning for Fault Diagnosis,” vol. 9, no. Dl, 2021, doi: 10.1109/ACCESS.2021.3061530.

Keywords:

Smart Manufacturing, Fault Detection, Failure Prediction, Industrial Automation, Maintenance Optimization, Predictive Maintenance (PDM), Machine Learning (ML), CWRU Data.