Enhancing Predictive Maintenance in Manufacturing Using Deep Learning-Based Anomaly Detection
DOI:
https://doi.org/10.63876/ijtm.v3i1.112Keywords:
predictive maintenance, anomaly detection, deep learning, manufacturing, autoencoders, recurrent neural networks, convolutional neural networksAbstract
Predictive maintenance has become a critical strategy in modern manufacturing to reduce downtime, optimize operational efficiency, and minimize maintenance costs. Traditional approaches, such as rule-based and statistical methods, often fail to detect complex patterns and early signs of system failures. This paper explores the application of deep learning-based anomaly detection techniques to enhance predictive maintenance in manufacturing. Specifically, we investigate the use of autoencoders, recurrent neural networks (RNNs), and convolutional neural networks (CNNs) for identifying anomalies in sensor data collected from industrial equipment. Our proposed framework enables early fault detection by learning complex temporal and spatial patterns in machinery behavior. Experimental results demonstrate that deep learning models significantly improve anomaly detection accuracy compared to conventional methods, thereby facilitating timely maintenance interventions and reducing unexpected failures. The findings highlight the potential of deep learning in revolutionizing predictive maintenance, ensuring higher reliability and efficiency in manufacturing systems.
Downloads
References
G. C. Paul, Tauhida, and D. Kumar, “Revisiting Fisher-KPP model to interpret the spatial spreading of invasive cell population in biology,” Heliyon, vol. 8, no. 10, p. e10773, Oct. 2022, doi: https://doi.org/10.1016/j.heliyon.2022.e10773.
B. Tjahjadi, N. Soewarno, H. Hariyati, L. N. Nafidah, N. Kustiningsih, and V. Nadyaningrum, “The Role of Green Innovation between Green Market Orientation and Business Performance: Its Implication for Open Innovation,” J. Open Innov. Technol. Mark. Complex., vol. 6, no. 4, p. 173, Dec. 2020, doi: https://doi.org/10.3390/joitmc6040173.
H. Wu, A. Huang, and J. W. Sutherland, “Avoiding Environmental Consequences of Equipment Failure via an LSTM-Based Model for Predictive Maintenance,” Procedia Manuf., vol. 43, pp. 666–673, 2020, doi: https://doi.org/10.1016/j.promfg.2020.02.131.
O. O. Aremu, A. S. Palau, A. K. Parlikad, D. Hyland-Wood, and P. R. McAree, “Structuring Data for Intelligent Predictive Maintenance in Asset Management,” IFAC-PapersOnLine, vol. 51, no. 11, pp. 514–519, 2018, doi: https://doi.org/10.1016/j.ifacol.2018.08.370.
T. Zonta, C. A. da Costa, R. da Rosa Righi, M. J. de Lima, E. S. da Trindade, and G. P. Li, “Predictive maintenance in the Industry 4.0: A systematic literature review,” Comput. Ind. Eng., vol. 150, p. 106889, Dec. 2020, doi: https://doi.org/10.1016/j.cie.2020.106889.
O. O. Aremu, R. A. Cody, D. Hyland-Wood, and P. R. McAree, “A relative entropy based feature selection framework for asset data in predictive maintenance,” Comput. Ind. Eng., vol. 145, p. 106536, Jul. 2020, doi: https://doi.org/10.1016/j.cie.2020.106536.
U. Ahmed, S. Carpitella, and A. Certa, “An integrated methodological approach for optimising complex systems subjected to predictive maintenance,” Reliab. Eng. Syst. Saf., vol. 216, p. 108022, Dec. 2021, doi: https://doi.org/10.1016/j.ress.2021.108022.
J. Cabessa and A. E. P. Villa, “Expressive power of first-order recurrent neural networks determined by their attractor dynamics,” J. Comput. Syst. Sci., vol. 82, no. 8, pp. 1232–1250, Dec. 2016, doi: https://doi.org/10.1016/j.jcss.2016.04.006.
K. M. Tiplady et al., “Comparison of the genetic characteristics of directly measured and Fourier-transform mid-infrared-predicted bovine milk fatty acids and proteins,” J. Dairy Sci., vol. 105, no. 12, pp. 9763–9791, Dec. 2022, doi: https://doi.org/10.3168/jds.2022-22089.
N. El Assri, M. A. Jallal, S. Chabaa, and A. Zeroual, “Enhancing building energy consumption prediction using LSTM, Kalman filter, and continuous wavelet transform,” Sci. African, vol. 27, p. e02560, Mar. 2025, doi: https://doi.org/10.1016/j.sciaf.2025.e02560.
A. Farias, N. W. Paschoalinoto, E. C. Bordinassi, F. Leonardi, and S. Delijaicov, “Predictive modelling of residual stress in turning of hard materials using radial basis function network enhanced with principal component analysis,” Eng. Sci. Technol. an Int. J., vol. 55, p. 101743, Jul. 2024, doi: https://doi.org/10.1016/j.jestch.2024.101743.
S. Dilmi, “A combined water quality classification model based on kernel principal component analysis and machine learning techniques,” Desalin. Water Treat., vol. 279, pp. 61–67, Dec. 2022, doi: https://doi.org/10.5004/dwt.2022.29069.
C. Chen, H. Fu, Y. Zheng, F. Tao, and Y. Liu, “The advance of digital twin for predictive maintenance: The role and function of machine learning,” J. Manuf. Syst., vol. 71, pp. 581–594, Dec. 2023, doi: https://doi.org/10.1016/j.jmsy.2023.10.010.
J. Park and J. Oh, “A machine learning based predictive maintenance algorithm for ship generator engines using engine simulations and collected ship data,” Energy, vol. 285, p. 129269, Dec. 2023, doi: https://doi.org/10.1016/j.energy.2023.129269.
A. H. Zamzam, K. Hasikin, and A. K. A. Wahab, “Integrated failure analysis using machine learning predictive system for smart management of medical equipment maintenance,” Eng. Appl. Artif. Intell., vol. 125, p. 106715, Oct. 2023, doi: https://doi.org/10.1016/j.engappai.2023.106715.
M.-H. Le-Nguyen, F. Turgis, P.-E. Fayemi, and A. Bifet, “Real-time learning for real-time data: online machine learning for predictive maintenance of railway systems,” Transp. Res. Procedia, vol. 72, pp. 171–178, 2023, doi: https://doi.org/10.1016/j.trpro.2023.11.391.
T. Wang, P. Reiffsteck, C. Chevalier, C.-W. Chen, and F. Schmidt, “Machine learning (ML) based predictive maintenance policy for bridges crossing waterways,” Transp. Res. Procedia, vol. 72, pp. 1037–1044, 2023, doi: https://doi.org/10.1016/j.trpro.2023.11.533.
Y. An, S. Ding, S. Shi, and J. Li, “Discrete space reinforcement learning algorithm based on support vector machine classification,” Pattern Recognit. Lett., vol. 111, pp. 30–35, Aug. 2018, doi: https://doi.org/10.1016/j.patrec.2018.04.012.
I. Sinha, D. P. Aluthge, E. S. Chen, I. N. Sarkar, and S. H. Ahn, “Machine Learning Offers Exciting Potential for Predicting Postprocedural Outcomes: A Framework for Developing Random Forest Models in IR,” J. Vasc. Interv. Radiol., vol. 31, no. 6, pp. 1018-1024.e4, Jun. 2020, doi: https://doi.org/10.1016/j.jvir.2019.11.030.
B. D. Hansen, S. H. Rasmussen, T. B. Moeslund, M. Uggerby, and D. G. Jensen, “Sewer Deterioration Modeling: The Effect of Training a Random Forest Model on Logically Selected Data-groups,” Procedia Comput. Sci., vol. 176, pp. 291–299, 2020, doi: https://doi.org/10.1016/j.procs.2020.08.031.
A. Yokoyama and N. Yamaguchi, “Comparison between ANN and random forest for leakage current alarm prediction,” Energy Reports, vol. 6, pp. 150–157, Dec. 2020, doi: https://doi.org/10.1016/j.egyr.2020.11.271.
A. Shehadeh, O. Alshboul, M. M. Taamneh, A. Q. Jaradat, and A. H. Alomari, “Enhanced clash detection in building information modeling: Leveraging modified extreme gradient boosting for predictive analytics,” Results Eng., vol. 24, p. 103439, Dec. 2024, doi: https://doi.org/10.1016/j.rineng.2024.103439.
S. L. P, S. S, and M. S. Rayudu, “IoT based solar panel fault and maintenance detection using decision tree with light gradient boosting,” Meas. Sensors, vol. 27, p. 100726, Jun. 2023, doi: https://doi.org/10.1016/j.measen.2023.100726.
C. Wang, W. Xiao, and J. Liu, “Developing an improved extreme gradient boosting model for predicting the international roughness index of rigid pavement,” Constr. Build. Mater., vol. 408, p. 133523, Dec. 2023, doi: https://doi.org/10.1016/j.conbuildmat.2023.133523.
R. Zheng et al., “Optimizing feature selection with gradient boosting machines in PLS regression for predicting moisture and protein in multi-country corn kernels via NIR spectroscopy,” Food Chem., vol. 456, p. 140062, Oct. 2024, doi: https://doi.org/10.1016/j.foodchem.2024.140062.
I. A. Zulfauzi, N. Y. Dahlan, H. Sintuya, and W. Setthapun, “Anomaly detection using K-Means and long-short term memory for predictive maintenance of large-scale solar (LSS) photovoltaic plant,” Energy Reports, vol. 9, pp. 154–158, Nov. 2023, doi: https://doi.org/10.1016/j.egyr.2023.09.159.
S. Potharaju, R. K. Tirandasu, S. N. Tambe, D. B. Jadhav, D. A. Kumar, and S. S. Amiripalli, “A two-step machine learning approach for predictive maintenance and anomaly detection in environmental sensor systems,” MethodsX, vol. 14, p. 103181, Jun. 2025, doi: https://doi.org/10.1016/j.mex.2025.103181.
D. López, I. Aguilera-Martos, M. García-Barzana, F. Herrera, D. García-Gil, and J. Luengo, “Fusing anomaly detection with false positive mitigation methodology for predictive maintenance under multivariate time series,” Inf. Fusion, vol. 100, p. 101957, Dec. 2023, doi: https://doi.org/10.1016/j.inffus.2023.101957.
H. Dehghan Shoorkand, M. Nourelfath, and A. Hajji, “A hybrid CNN-LSTM model for joint optimization of production and imperfect predictive maintenance planning,” Reliab. Eng. Syst. Saf., vol. 241, p. 109707, Jan. 2024, doi: https://doi.org/10.1016/j.ress.2023.109707.
J. Dalzochio et al., “Machine learning and reasoning for predictive maintenance in Industry 4.0: Current status and challenges,” Comput. Ind., vol. 123, p. 103298, Dec. 2020, doi: https://doi.org/10.1016/j.compind.2020.103298.
A.-Q. Gbadamosi et al., “IoT for predictive assets monitoring and maintenance: An implementation strategy for the UK rail industry,” Autom. Constr., vol. 122, p. 103486, Feb. 2021, doi: https://doi.org/10.1016/j.autcon.2020.103486.
