Solid oxide fuel cells(SOFCs)have attracted a great deal of interest because they have the highest efficiency without using any noble metal as catalysts among all the fuel cell technologies.However,traditional SOFCs s...Solid oxide fuel cells(SOFCs)have attracted a great deal of interest because they have the highest efficiency without using any noble metal as catalysts among all the fuel cell technologies.However,traditional SOFCs suffer from having a higher volume,current leakage,complex connections,and difficulty in gas sealing.To solve these problems,Rolls-Royce has fabricated a simple design by stacking cells in series on an insulating porous support,resulting in the tubular segmented-in-series solid oxide fuel cells(SIS-SOFCs),which achieved higher output voltage.This work systematically reviews recent advances in the structures,preparation methods,perform-ances,and stability of tubular SIS-SOFCs in experimental and numerical studies.Finally,the challenges and future development of tubular SIS-SOFCs are also discussed.The findings of this work can help guide the direction and inspire innovation of future development in this field.展开更多
基金supported by the National Natural Science Foundation of China (Nos.21701083 and 22179054).
文摘Solid oxide fuel cells(SOFCs)have attracted a great deal of interest because they have the highest efficiency without using any noble metal as catalysts among all the fuel cell technologies.However,traditional SOFCs suffer from having a higher volume,current leakage,complex connections,and difficulty in gas sealing.To solve these problems,Rolls-Royce has fabricated a simple design by stacking cells in series on an insulating porous support,resulting in the tubular segmented-in-series solid oxide fuel cells(SIS-SOFCs),which achieved higher output voltage.This work systematically reviews recent advances in the structures,preparation methods,perform-ances,and stability of tubular SIS-SOFCs in experimental and numerical studies.Finally,the challenges and future development of tubular SIS-SOFCs are also discussed.The findings of this work can help guide the direction and inspire innovation of future development in this field.
文摘为了解决单个神经网络预测的局限性和时间序列的波动性,提出了一种奇异谱分析(singular spectrum analysis,SSA)和Stacking框架相结合的短期负荷预测方法。利用随机森林筛选出与历史负荷相关性强烈的特征因素,采用SSA为负荷数据降噪,简化模型计算过程;基于Stacking框架,结合长短期记忆(long and short-term memory,LSTM)-自注意力机制(self-attention mechanism,SA)、径向基(radial base functions,RBF)神经网络和线性回归方法集成新的组合模型,同时利用交叉验证方法避免模型过拟合;选取PJM和澳大利亚电力负荷数据集进行验证。仿真结果表明,与其他模型比较,所提模型预测精度高。