Deep Learning and Anomaly Detection in Predictive Maintenance Platform

Bukun Ren

doi:10.71222/rhfyda40

Authors

Bukun Ren College of Engineering, University of California Berkeley, Berkeley, 94720, USA Author

DOI:

https://doi.org/10.71222/rhfyda40

Keywords:

predictive maintenance, deep learning, outlier detection

Abstract

With the development of intelligent manufacturing and industrial Internet of Things (IIoT), predictive maintenance has become an important technology to improve product reliability and reduce downtime. Establishing a predictive maintenance platform through deep learning algorithms, providing support for equipment fault prediction and anomaly detection through sensor technology, data collection and cleaning, feature extraction, etc. The architecture methods of deep learning such as Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Autoencoders, and Long Term Short Term Memory (LSTM) have been widely adopted in fields such as wind turbine fault prediction, intelligent manufacturing quality inspection, and equipment health assessment, which can improve equipment judgment accuracy, reduce maintenance costs, and ultimately enhance production capacity. This article will further explore the application and prospects of deep learning in predictive maintenance.

References

1. L. Shen, Z. Shao, Y. Yu, and X. Chen, "Hybrid approach combining modified gravity model and deep learning for short-term forecasting of metro transit passenger flows," Transportation Research Record, vol. 2675, no. 1, pp. 25-38, 2021.

2. S. Venkatachalam, and R. Kannan, "Optimizing dynamic keystroke pattern recognition with hybrid deep learning technique and multiple soft biometric factors," INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL, vol. 19, no. 2, 2024.

3. Y. Hu, X. Wei, X. Wu, J. Sun, Y. Huang, and J. Chen, "Three-dimensional cooperative inversion of airborne magnetic and gravity gradient data using deep-learning techniques," Geophysics, vol. 89, no. 1, pp. WB67-WB79, 2024. doi: 10.1190/geo2023-0225.1

4. O. V. Mandrikova, Y. A. Polozov, and B. S. Mandrikova, "Method of Natural Data Analysis and Anomaly Detection Based on a Collective of NARX Neural Networks," Pattern Recognition and Image Analysis, vol. 34, no. 4, pp. 1223-1232, 2024. doi: 10.1134/s1054661824701293

5. K. Gao, Z. D. Chen, S. Weng, H. P. Zhu, and L. Y. Wu, "Detection of multi-type data anomaly for structural health monitoring using pattern recognition neural network," Smart Struct. Syst, vol. 29, no. 1, pp. 129-140, 2022.