mohyunho / NAS_convELM

Evolutionary optimization of convolutional ELM for remaining useful life prediction

Evolutionary optimization of convolutional ELM for remaining useful life prediction

This is the repo for the paper "Evolutionary optimization of convolutional ELM for remaining useful life prediction " which is an extension of its previous work specified in https://github.com/mohyunho/MOO_ELM

MOO CELM

The objective of this study is to search for the best convolutional ELM, so-called conv ELM or CELM, architectures in terms of a trade-off between RUL prediction error and training time, the latter being determined by the number of trainable parameters, on the CMAPSS dataset.
you can find the trade-off solution by running the python codes below:

python3 enas_convELM_CMAPSS.py

Our experimental results on the CMAPSS dataset are shown as below: (a) FD001, (b) FD002, (c) FD003, and (d) FD004.

To cite this code use

@article{mo2023celm,
  title={Evolutionary Optimization of Convolutional Extreme Learning Machine for Remaining Useful Life Prediction},
  author={Mo, Hyunho and Iacca, Giovanni},
  journal={SN Computer Science},
  year={2023},
  publisher={Springer},
  note={to appear},
}

References

[1] Hyunho Mo and Giovanni Iacca. Evolutionary optimization of convolutional extreme learning machine for remaining useful life prediction. SN Computer Science, 2023. to appear.