Advancing Fault Prediction: A Comparative Study between LSTM and Spiking Neural Networks

Rute Souza de Abreu; Ivanovitch Silva; Yuri Thomas Nunes; Renan C. Moioli; Luiz Affonso Guedes

LAPSE

Living Archive for Process Systems Engineering

LAPSE:2024.0230

Published Article

LAPSE:2024.0230

Advancing Fault Prediction: A Comparative Study between LSTM and Spiking Neural Networks

Rute Souza de Abreu, Ivanovitch Silva, Yuri Thomas Nunes, Renan C. Moioli, Luiz Affonso Guedes

February 10, 2024

Predicting system faults is critical to improving productivity, reducing costs, and enforcing safety in industrial processes. Yet, traditional methodologies frequently falter due to the intricate nature of the task. This research presents a novel use of spiking neural networks (SNNs) in anticipating faults in syntactical time series, utilizing the generalized stochastic Petri net (GSPN) model. The inherent ability of SNNs to process both time and space aspects of data positions them as a prime instrument for this endeavor. A comparative evaluation with long short-term memory (LSTM) networks suggests that SNNs offer comparable robustness and performance.

Record ID

LAPSE:2024.0230

Keywords

generalized stochastic Petri net (GSPN), industrial processes, LSTM networks, spiking neural networks (SNNs), system fault prediction

Subject

Numerical Methods and Statistics

Suggested Citation

Souza de Abreu R, Silva I, Nunes YT, Moioli RC, Guedes LA. Advancing Fault Prediction: A Comparative Study between LSTM and Spiking Neural Networks. (2024). LAPSE:2024.0230

Author Affiliations

Souza de Abreu R: Postgraduate Program in Electrical and Computer Engineering, Technology Center, Federal University of Rio Grande do Norte, Natal 59078-970, Brazil [ORCID]
Silva I: Postgraduate Program in Electrical and Computer Engineering, Technology Center, Federal University of Rio Grande do Norte, Natal 59078-970, Brazil [ORCID]
Nunes YT: Postgraduate Program in Electrical and Computer Engineering, Technology Center, Federal University of Rio Grande do Norte, Natal 59078-970, Brazil [ORCID]
Moioli RC: Bioinformatics Multidisciplinary Environment, Digital Metropolis Institute, Federal University of Rio Grande do Norte, Natal 59078-970, Brazil [ORCID]
Guedes LA: Postgraduate Program in Electrical and Computer Engineering, Technology Center, Federal University of Rio Grande do Norte, Natal 59078-970, Brazil [ORCID]

Journal Name

Processes

Volume

11

Issue

9

First Page

2772

Year

2023

Publication Date

2023-09-16