I developed deep-learning based methods for Li-ion battery State-of-Health estimation and solar power generation forecasting.

During my time as a postdoctoral researcher, I also worked in projects related with renewable energies, such as Li-ion batteries and solar power generation forecasting. Below I present the details of each research.

Project Synopsis
Title: Development of two-stage deep learning architecture for state-of-health estimation in li-ion batteries
Highlights:
  • The first stage uses a Convolutional Autoencoder to extract features from electrochemical data.
  • The second stage uses a neural network for charge capacity estimation.
  • The average performance of the model in test cells was better than previous methods (R^2=0.98)
Period: August 2020- July 2021
Outputs:
  • The results are currently under revision in the top-ranked Journal of Power Sources
Skills
&
Technologies:
  • Deep learning
  • Convolutional Autoencoder
  • Li-ion Batteries
  • State-of-health estimation
  • Academic writing
Project Synopsis
Title:Application of deep learning for multistep solar power generation forecasting
Highlights:
  • The average performance of the model in test data was better than other methods (R^2≈0.82)
Period: August 2020- July 2021
Outputs:
  • Best Paper Award in the International Conference on Innovation Convergence Technology (ICICT2021)
Skills
&
Technologies:
  • Deep learning
  • Transformer networks
  • Time series forecasting
  • Solar power generation forecasting
  • Academic writing