文献类型：期刊文献

英文题名：Deep learning-based source term estimation of hydrogen leakages from a hydrogen fueled gas turbine

作者：Li, Ang[1];Lang, Ziqiang[1,2];Ni, Chuantao[1];Tian, Hao[1];Wang, Bing[1];Cao, Chenxi[1];Du, Wenli[1];Qian, Feng[1]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]Univ Sheffield, Dept Automat Control & Syst Engn, Sheffield S1 3JD, England

年份：2024

卷号：86

起止页码：875

外文期刊名：INTERNATIONAL JOURNAL OF HYDROGEN ENERGY

收录：;EI(收录号：20243616985038);WOS:【SCI-EXPANDED(收录号:WOS:001306369600001)】；

基金：This work is supported by the National Natural Science Foundation of China (Basic Science Center Program 61988101) .

语种：英文

外文关键词：STE; Hydrogen fueled gas turbine; LSTM-AE; CFD

摘要：Hydrogen fueled gas turbine is an efficient and environmentally friendly energy conversion equipment. However, it is prone to gas leakages from corrosion-prone components and pipe connections. In order to address gas leakage problems, source term estimation (STE) can be applied to estimate the location and intensity of the leakage sources. Traditional STE methods are based on an optimization procedure using an atmospheric transport and dispersion model, which requires considerable computation efforts and cannot meet the need of realtime implementation. The complex flow field around the gas turbine, the possible existence of multiple leakage sources, and the high-dimensional time series data further increase the difficulty of the STE problem. To address these challenges, in the present study, a deep learning based STE approach is proposed. The basic idea is to use long short-term memory auto-encoder (LSTM-AE) network to extract the encoded features of multi-sensor data and then use a deep neural network (NN) to establish the relationship between the encoded features and the source term parameters of hydrogen leakages. The multi-sensor data are generated using computational fluid dynamics (CFD) analysis to simulate relevant hydrogen leakage scenarios of concern. The results show that compared with other machine learning algorithms, the proposed approach has an overall best performance in terms of the STE accuracy. Specifically, its hydrogen leakage source localization accuracy is 0.9798, and the leakage strength estimation R-squared (R2) can reach 0.9632. When the training data proportion is only 20-30%, the proposed approach can still perform well, indicating the ability of the model to effectively predict the location and strength of the leakage source even with relatively less training data.