Fault Diagnosis of SOFC Stack Based on Neural Network Algorithm

Xue, Tao; Wu, Xiaolong; Xu, Yuanwu; Jing, Suwen; Li, Zehua; Deng, Zongquan; Fu, Xiaowei; Li, Xi

doi:10.1016/j.egypro.2019.01.423

Cited by 8 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It enhances system safety and efficiency by providing early warning of potential leaks. Xue 193 et al developed a neural network diagnostic model to diagnose hydrogen leakage inside a fuel cell. The type of neural network model chosen had four inputs and three outputs.…”

Section: Machine Learning-based Leakage Diagnosismentioning

confidence: 99%

Comprehensive Review of Hydrogen Leakage in Relation to Fuel Cell Vehicles and Hydrogen Refueling Stations: Status, Challenges, and Future Prospects

Hu,

Gao,

Cheng

et al. 2024

Energy Fuels

View full text Add to dashboard Cite

As fuel cell vehicles (FCVs) are increasingly put on the market and hydrogen refueling stations (HRSs) are built accordingly, fatal accidents caused by explosion due to hydrogen leakage are reported and have become a critical issue. The explosion results from complicated processes associated with the so-called hydrogen jet and diffusion when the hydrogen leaks from FCVs or HRSs, demonstrating its sophisticated characteristics and presenting significant technical challenges. Recently, particularly in the past a few years, researchers have established a variety of theoretical models to reveal the relevant mechanisms and introduced a series of monitoring/diagnostic approaches to detect and control the relevant hazards. This comprehensive review summarizes the major research outcomes and particularly the state-of-the-art progresses in relation to hydrogen leakage in FCVs and HRSs, including (1) subsonic jets, (2) underexpanded jets, (3) hydrogen diffusion behavior, (4) hazard reduction methods for confined and free spaces, (5) four types of widely used hydrogen detection technologies, and (6) the application of hydrogen leakage diagnostic methods in different systems. An insight of the review is that research on hydrogen leakage related to FCVs and HRSs should be combined with the relevant realistic characteristics. The characteristics of hydrogen jets generated in real gaps are discussed, and hazard reduction methods are proposed based on the characteristics of hydrogen diffusion in different confined and free spaces. It is suggested that, in order to integrate and evaluate multiple sensor data points and more accurately determine the leakage location and the leakage level, artificial intelligence technologies could be introduced to resolve the issues encountered currently.

show abstract

Section: Machine Learning-based Leakage Diagnosismentioning

confidence: 99%

Comprehensive Review of Hydrogen Leakage in Relation to Fuel Cell Vehicles and Hydrogen Refueling Stations: Status, Challenges, and Future Prospects

Hu,

Gao,

Cheng

et al. 2024

Energy Fuels

View full text Add to dashboard Cite

show abstract

“…Therefore, this study can transform a regression problem into a classification problem with higher tolerance. Xue et al 29 designed a solid oxide FC‐fault diagnosis model using the feedforward neural network. In their study, the output layer is classified as normal, layering, and manufacturing.…”

Section: Introductionmentioning

confidence: 99%

A novel predicting method on degree of catalytic reaction in fuel cells

Pan

et al. 2020

Int J Energy Res

View full text Add to dashboard Cite

Summary An accurate assessment of the utilization of a catalyst for fuel cells is beneficial for guiding the optimization of working conditions and adjustment of parameters. In this study, a composite model containing the numerical model of catalyst layers and improved support vector machine (SVM) is proposed to predict the catalyst utilization. The effectiveness factor of the field of catalytic reaction engineering is introduced into the numerical model. The adaptive learning factor and the differential evolution strategy are introduced to improve the ability of generalization and robustness of the distinguishing method in the SVM. The results indicate that the radial basis function is well‐suited as the kernel function of the SVM, and the accuracy of the prediction in the anode and cathode can be increased up to 99.31% and 99.65%, respectively. The increasing transfer coefficient leads to an enhancement of the catalytic reaction, and the particle size of the catalyst impacts the catalytic reaction mainly by changing the pattern of internal diffusion. Pressure has little impact on the Knudsen diffusion.

show abstract