The smart manufacturing has revolutionised the intelligent predictive maintenance by integrating IoT technologies with big data analytics, artificial intelligence, cloud computing and other evolving technologies. An effective predictive maintenance demands not only measuring equipment, but the underlying ecosystem that starts with data acquisition from sensors and propagates all the way to visualisation on engineer friendly dashboards. For process monitoring and performance optimization in a smart factory, it is important to recognise time series events like equipment peaks, changeovers and failures. In this article, a model proposed is a deep convolutional LSTM autoencoder architecture using an autoencoder approach to classify real world machine and sensor data to condition based label. The proposed model outperformed baseline architectures. A window size of 45 was used to determine that the model produced a RMSE of 58.45, an MAE of 22.48, and a sMAPE of 0.869, most of which represents significant improvements of up to 37% over existing methods. Having a window size 90, it remained on top with an RMSE score of 72.16 and MAE of 29.64 and sMAPE of 0.847. These results show that it processed a real world manufacturing data and correctly estimated RUL and its complete predictive maintenance.
M.-A. Filz, J. P. Bosse, and C. Herrmann, “Digitalization platform for data-driven quality management in multi-stage manufacturing systems,” Journal of Intelligent Manufacturing, vol. 35, no. 6, pp. 2699–2718, Jun. 2023, doi: 10.1007/s10845-023-02162-9.
C. Serôdio, P. Mestre, J. Cabral, M. Gomes, and F. Branco, “Software and Architecture Orchestration for Process Control in Industry 4.0 Enabled by Cyber-Physical Systems Technologies,” Applied Sciences, vol. 14, no. 5, p. 2160, Mar. 2024, doi: 10.3390/app14052160.
N. Nikolakis, P. Catti, A. Chaloulos, W. van de Kamp, M. P. Coy, and K. Alexopoulos, “A methodology to assess circular economy strategies for sustainable manufacturing using process eco-efficiency,” Journal of Cleaner Production, vol. 445, p. 141289, Mar. 2024, doi: 10.1016/j.jclepro.2024.141289.
M. R. Kabir and S. Ray, “Virtual Prototyping for Modern Internet-of-Things Applications: A Survey,” IEEE Access, vol. 11, pp. 31384–31398, 2023, doi: 10.1109/access.2023.3262499.
A. Entezami, H. Sarmadi, B. Behkamal, and S. Mariani, “Early warning of structural damage via manifold learning-aided data clustering and non-parametric probabilistic anomaly detection,” Mechanical Systems and Signal Processing, vol. 224, p. 111984, Feb. 2025, doi: 10.1016/j.ymssp.2024.111984.
C. Chen, J. Shi, M. Shen, L. Feng, and G. Tao, “A Predictive Maintenance Strategy Using Deep Learning Quantile Regression and Kernel Density Estimation for Failure Prediction,” IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1–12, 2023, doi: 10.1109/tim.2023.3240208.
A. Deekshith, “Scalable machine learning: Techniques for managing data volume and velocity in AI applications,” Int. Sci. J. Res., vol. 5, no. 5, 2023.
J. Lee, Y. Zhao, J. Roy, and D. Singh, “AI-enabled predictive maintenance for smart manufacturing: Concepts, implementations, and applications,” IEEE Trans. Ind. Electron., vol. 68, no. 6, pp. 4697–4711, Jun. 2021.
R. Carvalho, J. Guedes, and T. Pinho, “Deep learning architectures for predictive maintenance in manufacturing: A review,” J. Manuf. Syst., vol. 61, pp. 153–164, Mar. 2022.
Z. Wu, L. Zhang, and X. Zhou, “Transformer-based time-series forecasting for industrial IoT systems,” IEEE Internet Things J., vol. 9, no. 4, pp. 3201–3211, Feb. 2023.
S. Zonta, C. Fagorzi, and P. Pedrazzoli, “Predictive maintenance using sequence-to-sequence learning: Applications and trends,” Appl. Soft Comput., vol. 136, Art. no. 110758, Jul. 2023.
Y. Vaswani, S. Ma, and A. Luo, “Enhancing RNN performance for predictive maintenance with GRU-LSTM hybrids,” Neural Comput. Appl., vol. 34, no. 9, pp. 6811–6823, Sep. 2022.
D. Entezami and P. Chuang, “Data-driven techniques for equipment condition monitoring and RUL prediction in industrial systems,” Reliab. Eng. Syst. Saf., vol. 219, Art. no. 108149, Jan. 2023.
M. Zhang, H. Li, and Y. Xiao, “Deep convolutional LSTM networks for multistep industrial process forecasting,” IEEE Trans. Cybern., vol. 54, no. 3, pp. 1451–1463, Mar. 2024.
S. Huang and Y. Chen, “LSTM-autoencoders for time-series prediction in smart manufacturing,” J. Intell. Manuf., vol. 33, no. 4, pp. 1051–1063, Jul. 2023.
A. Roy and K. Sarkar, “Time-series forecasting using stacked autoencoders in manufacturing processes,” Comput. Ind., vol. 145, Art. no. 103749, Aug. 2023.
C. Wang, Y. Qiu, and X. Zhao, “Hybrid deep learning for industrial predictive analytics,” Expert Syst. Appl., vol. 201, Art. no. 117522, Apr. 2022.
M. Wang and J. Shen, “Improved LSTM-autoencoders for multivariate RUL prediction,” IEEE Access, vol. 11, pp. 45312–45323, May 2023.
L. Zhou and R. Wang, “Smart manufacturing with ConvLSTM-based PdM models,” Procedia CIRP, vol. 117, pp. 81–86, Mar. 2024.
J. Li, X. Zhang, and H. Guo, “Bidirectional LSTM networks for industrial time-series predictions,” J. Big Data, vol. 10, no. 1, pp. 12–25, Jan. 2023.
X. Xu, H. Liu, and W. Gao, “Sliding-window ConvLSTM for real-time predictive maintenance,” Future Gener. Comput. Syst., vol. 139, pp. 184–195, Nov. 2023.
J. K. Brown and A. Patel, “Real-time applications of deep learning for predictive maintenance in manufacturing plants,” Comput. Ind. Eng., vol. 174, Art. no. 108462, Feb. 2024.
CRediT Author Statement
The author reviewed the results and approved the final version of the manuscript.
Acknowledgements
This work was supported by Dongseo University, "Dongseo Frontier Project" Research Fund of 2023.
Funding
The Dongseo Frontier Project Research Fund of 2023.
Ethics declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of data and materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding author
Young Jun Park
Department of Game, Dong-Seo University, Global village building 6th floor, Dongseo University, 47 Jurye-ro, Sasang-gu, Busan, South Korea.
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this article
Young Jun Park, “Convolutional LSTM Neural Network Autoencoder Based Fault Detection in Manufacturing Predictive Maintenance”, Journal of Machine and Computing, pp. 914-923, April 2025, doi: 10.53759/7669/jmc202505072.
