article · Energy Reports
This research focuses on identifying the unknown parameters of a PEM fuel cell (PEMFC) to create accurate performance forecasting models. Since manufacturers' datasheets may not always provide these crucial parameters, six optimisation techniques were employed to compute them. The Rime-Ice algorithm (RIME) was compared against the Grey Wolf Optimizer (GWO), Moth Flam Optimizer (MFO), Tunicate Swarm Algorithm (TSA), Sine Cosine Algorithm (SCA), and Osprey Optimization Algorithm (OOA). The objective was to minimise the sum square error (SSE) between estimated and measured cell voltages. Using a real-world PEM fuel cell model, the RIME algorithm achieved the lowest SSE and demonstrated faster convergence speed compared to the other methods, with its estimated voltage-current curves showing good agreement with experimental data.
Accurate prediction of PEM fuel cell performance is vital for their design, operation, and integration into various applications. This research improves the methods for precisely determining the underlying characteristics of these fuel cells, leading to more reliable and efficient energy systems and potentially accelerating their development and adoption.
This research presents an improved optimisation algorithm for accurately identifying PEM fuel cell parameters, which is an early-stage development in fuel cell modelling. It could be used by engineers and researchers in the energy sector to develop more precise simulation tools for PEM fuel cells, leading to more efficient designs and better performance prediction. The abstract does not indicate a direct, near-market application.
AI-generated from the published abstract. Always read the original work before citing.
The process of employing optimization techniques to identify the optimum unknown variables appropriate for the creation of a precision fuel-cell performance forecasting model is known as parameter identification of a PEM fuel cell (PEMFC). The manufacturer's datasheet may not always provide these parameters, thus it is necessary to ascertain them to precisely estimate and forecast the fuel cell's performance. six unknown parameters of a PEMFC are computed using six optimization techniques: The Rime-Ice algorithm (RIME), the Grey Wolf Optimizer (GWO), the Moth Flam Optimizer (MFO), the Tunicate Swarm Algorithm (TSA), the Sine Cosine Algorithm (SCA), and the Osprey Optimization Algorithm (OOA). These six parameters serve as choice variables during optimization, and the sum square error (SSE) between the estimated and measured cell voltages is the fitness function that needs to be minimized. Ned Stack PS6, a real-world PEM fuel cell model, is used to verify the functionality of all comparator algorithms, including the suggested RIME method. The RIME algorithm yielded an SSE of 1.945417827, which was followed by MFO, GWO, TSA, SCA, and OOA. In addition, it was concluded that RIME's convergence speed was quicker than that of the other methods examined. The comparative analysis is conducted using the same dataset and the same computation burden for each of the several optimization techniques to provide a fair performance evaluation. The performance of the suggested RIME against the alternative optimization algorithms is further examined using statistical analysis. The results demonstrate a good degree of agreement between the experimental data and the estimated voltage-current curves produced by the suggested RIME.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.egyr.2024.03.006
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
