No abstract

Because of their fuel flexibility, Solid Oxide Fuel Cells (SOFCs) are promising candidates to coach the energy transition. Yet, SOFC performance are markedly affected by fuel composition and operative parameters. In order to optimize SOFC operation and to provide a prompt regulation, reliable performance simulation tools are required. Given the high variability ascribed to the fuel in the wide range of SOFC applications and the high non-linearity of electrochemical systems, the implementation of artificial intelligence techniques, like Artificial Neural Networks (ANNs), is sound. In this paper, several network architectures based on a feedforward-backpropagation algorithm are proposed and trained on experimental data-set issued from tests on commercial NiYSZ/8YSZ/LSCF anode supported planar button cells. The best simulator obtained is a 3-hidden layer ANN (25/22/18 neurons per layer, hyperbolic tangent sigmoid as transfer function, obtained with a gradient descent with adaptive learning rate backpropagation). This shows high accuracy (RMS = 0.67% in the testing phase) and successful application in the forecast of SOFC polarization behaviour in two additional experiments (RMS in the order of 3% is scored, yet it is reduced to about 2% if only the typical operating current density range of real application is considered, from 300 to 500 mA·cm−2). Therefore, the neural tool is suitable for system simulation codes/software whether SOFC operating parameters agree with the input ranges (anode feeding composition 0–48%vol H2, 0–38%vol CO, 0–45%vol CH4, 9–32%vol CO2, 0–54%vol N2, specific equivalent hydrogen flow-rate per unit cell active area 10.8–23.6 mL·min−1·cm−2, current density 0–1300 mA·cm−2 and temperature 700–800 °C).

No abstract

This paper develops a hydrogen generator prototype that is for fuel cell systems used in portable applications. This generator is designed based on the use of solid-state hydrides with high hydrogen storage capacity in the catalytic hydrolysis reaction. Some using problems such as unstable hydrogen production, one-off service life, heavy or large-volume storage system, and short duty time can be avoided in moveable applications when the use of the produced prototype. In addition, A simulation model and an autonomous control algorithm, which evaluates the hydrogen generation and temperature responses of the prototype, are developed. The results confirm that the performance of a portable and autonomous prototype with 4 parts and 1-hour hydrogen production capacity is enough for small fuel cell applications.

In this study, hydrolysis reaction performances of raw BFS powder and metal powders (which are ingredients of BFS) that are using as a catalyst are compared. Hydrogen generation by hydrolysis reaction of the Al and Fe2O3 Nano & Granule powders with sodium borohydride (NaBH4) addition in water was studied by using different catalysts amount at reaction vessels. The measured values of reaction temperatures and hydrogen flow rates were measured by using high-precision equipment. As a result of the obtained data, it was determined that Fe2O3 and Al catalysts have advantages over hydrogen production rate and fuel conversion, also, these experiments show a very high success in different parameters, and create promising effects in the reactions. Among the Al catalyst samples, the highest efficiency performances are achieved with Al Nano catalyst samples at 85.31 °C preheat with an instantaneous hydrogen generation rate of approximately 11.226 L / min for 33 minutes. Among the Fe2O3 catalyst samples, the highest efficiency performances are achieved with Fe2O3 Nano catalyst samples at 50 °C preheat with an instantaneous hydrogen generation rate of approximately 29.91 L / min for 12 minutes.