Remaining useful life (RUL) prediction is a key enabler for predictive maintenance. In fact, the possibility of accurately and reliably predicting the RUL of a system, based on a record of its monitoring data, can allow users to schedule maintenance interventions before faults occur. In the recent literature, several data-driven methods for RUL prediction have been proposed. However, most of them are based on traditional (connectivist) neural networks, such as convolutional neural networks, and alternative mechanisms have barely been explored. Here, we tackle the RUL prediction problem for the first time by using a membrane computing paradigm, namely that of Spiking Neural P (in short, SN P) systems. First, we show how SN P systems can be adapted to handle the RUL prediction problem. Then, we propose the use of a neuro-evolutionary algorithm to optimize the structure and parameters of the SN P systems. Our results on two datasets, namely the CMAPSS and new CMAPSS benchmarks from NASA, are fairly comparable with those obtained by much more complex deep networks, showing a reasonable compromise between performance and number of trainable parameters, which in turn correlates with memory consumption and computing time.
Evolutionary Optimization of Spiking Neural P Systems for Remaining Useful Life Prediction / Custode, Leonardo Lucio; Mo, Hyunho; Ferigo, Andrea; Iacca, Giovanni. - In: ALGORITHMS. - ISSN 1999-4893. - 15:3(2022), pp. 9801-9818. [10.3390/a15030098]
Evolutionary Optimization of Spiking Neural P Systems for Remaining Useful Life Prediction
Custode, Leonardo Lucio;Mo, Hyunho;Ferigo, Andrea;Iacca, Giovanni
2022-01-01
Abstract
Remaining useful life (RUL) prediction is a key enabler for predictive maintenance. In fact, the possibility of accurately and reliably predicting the RUL of a system, based on a record of its monitoring data, can allow users to schedule maintenance interventions before faults occur. In the recent literature, several data-driven methods for RUL prediction have been proposed. However, most of them are based on traditional (connectivist) neural networks, such as convolutional neural networks, and alternative mechanisms have barely been explored. Here, we tackle the RUL prediction problem for the first time by using a membrane computing paradigm, namely that of Spiking Neural P (in short, SN P) systems. First, we show how SN P systems can be adapted to handle the RUL prediction problem. Then, we propose the use of a neuro-evolutionary algorithm to optimize the structure and parameters of the SN P systems. Our results on two datasets, namely the CMAPSS and new CMAPSS benchmarks from NASA, are fairly comparable with those obtained by much more complex deep networks, showing a reasonable compromise between performance and number of trainable parameters, which in turn correlates with memory consumption and computing time.File | Dimensione | Formato | |
---|---|---|---|
algorithms-15-00098.pdf
accesso aperto
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Creative commons
Dimensione
570.92 kB
Formato
Adobe PDF
|
570.92 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione