Fault detection and isolation in the DAMADICS system using recurrent neural networks

---

Authors

Maria Fernanda Avila-Diaz¹ , Marco Antonio Márquez-Vera¹

1. Polyechnic University of Pachuca

Conference / event

SIMCI, November 2023 (Hidalgo, Mexico)

Poster summary

An industry is required that the dispositives work free of faults. A fault is an undesired behavior of a system, being the fault detection the capability in recognizing an anomalous behavior, and the fault isolation is to know what fault is affecting the system. There are some approaches used for fault detection and isolation (FDI) like principal component analysis, artificial neural networks, fuzzy systems. In this work is shown the use of recurrent neural networks (RNN) which are simplets than deep learning and they can use past information to recognize the signals evolution early in time.

Keywords

Fault diagnosis, Recurrent neural networks, Fault isolation, DAMADICS

Research areas

Electrical Engineering

References

1. M.A. Márquez-Vera et al. 2021. Adaptive threshold PCA for fault detection and isolation. J. of Robotics and Control 2(3): 119-125.
2. K.A. Q and Y. Du. 2023. Simultaneous fault detection and isolation based on multi-task long short-term memory neural networks. Chemometrics and Intelligent Laboratory Syst. 240: 104881.
3. J. Choi and S.J. Lee. 2023. RNN-based integrated system for real-time sensor fault detection and fault-informed accident diagnosis in nuclear power plant accidents. Nuclear Eng. and Tech. 55(3): 814-826.
4. M.A. Márquez-Vera et al. 2021. Inverse fuzzy fault model for fault detection and isolation with least angle regression for variable selection. Comp. & Industrial Eng. 159: 107499.

Funding

No data provided

Supplemental files

No data provided

Additional information

Competing interests

No competing interests were disclosed.

Data availability statement

The datasets generated during and / or analyzed during the current study are available from the corresponding author on reasonable request.

Creative Commons license

Copyright © 2023 Avila-Diaz et al. This is an open access work distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.