Use of the Ensemble Kalman Filter for the identification of hybrid fuel cell models

Q: What does this research mean for the field?

An Ensemble Kalman Filter approach adapted with the adjoint sensitivity method can effectively identify the high number of parameters in hybrid models that combine physical components and artificial neural networks, such as fuel cell degradation models. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

Michael Mangold; Abdulrahman Allam; Simon Lenz

doi:10.1016/j.compchemeng.2026.109719

May 1, 2026Computers & Chemical EngineeringOpen Access

Use of the Ensemble Kalman Filter for the identification of hybrid fuel cell models

View Full Paper

Ask AI

Bookmark

Share

Key Points

This research aims to improve parameter identification methods for hybrid models using the Ensemble Kalman Filter (EnKF).
Adapted adjoint sensitivity method to Ensemble Kalman Filter to manage ANN parameters.
Applied the method to a simple pendulum model and a fuel cell model with degradation.
Utilized physical model parts combined with artificial neural networks in the study.
Successfully identified parameters for the simple pendulum model using EnKF.
Achieved accurate parameter identification for the fuel cell model, indicating robustness of the method.
Demonstrated that incorporating the adjoint sensitivity method enhanced the EnKF's performance.

Implication

Evaluates the Ensemble Kalman Filter for identifying parameters in hybrid models, suggesting improved accuracy.

Abstract

• The parameter identification of hybrid models consisting of a physical model part and an artificial neural network (ANN) is considered. • An approach based on an Ensemble Kalman Filter (EnKF) is suggested. • The adjoint sensitivity method is adapted to the EnKF in order to cope with the high number of ANN parameters to be identified. • The method is applied to a simple pendulum model from literature and to a fuel cell model with degradation.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Mangold et al. (2026) studied this question.

synapsesocial.com/papers/6a1a827f0307b785094342e8 https://doi.org/10.1016/j.compchemeng.2026.109719

View Full Paper

Ask AI

Bookmark

Share

Use of the Ensemble Kalman Filter for the identification of hybrid fuel cell models

Key Points

Implication

Abstract

Discussion

Cite This Study

Use of the Ensemble Kalman Filter for the identification of hybrid fuel cell models

Key Points

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading