The application of forced mercury oxidation technology would lead to an increase of Hg^(2+)concentration in the flue gas.Although Hg^(2+)can be easily removed in the WFGD,the mercury re-emission in the WFGD can decrea...The application of forced mercury oxidation technology would lead to an increase of Hg^(2+)concentration in the flue gas.Although Hg^(2+)can be easily removed in the WFGD,the mercury re-emission in the WFGD can decrease the total removal of mercury from coal-fired power plants.Hence,it is necessary to control Hg^(2+)concentration in the devices before the WFGD.Fly ash adsorbent is considered as a potential alternative for commercial activated carbon adsorbent.However,the adsorption efficiency of the original fly ash is low.Modification procedure is needed to enhance the adsorption performance.In this study,the adsorption of Hg^(2+)by brominated fly ash was studied.The fly ash was collected from the full-scale power plant utilizing bromide-blended coal combustion technology.The brominated fly ash exhibited excellent performance for Hg^(2+)removal.The flue gas component HBr and SO_(2)could improve adsorbent’s performance,while HCl would hinder its adsorption process.Also,it was demonstrated by Hg-TPD experiments that the adsorbed Hg^(2+)mainly existed on the fly ash surface in the form of HgBr_(2).In summary,the brominated fly ash has a broad application prospect for mercury control.展开更多
Accurately and quickly predicting hydrogen embrittlement performance is critical for the service of metal materials.However,due to multi-source heterogeneity,existing hydrogen embrittlement data are missing,making it ...Accurately and quickly predicting hydrogen embrittlement performance is critical for the service of metal materials.However,due to multi-source heterogeneity,existing hydrogen embrittlement data are missing,making it impractical to train reliable machine learning models.In this study,we proposed an ensemble learning training strategy for missing data based on the Adaboost algorithm.This method introduced a mask matrix with missing data and enabled each round of training to generate sub-datasets,considering missing value information.The strategy first trained a subset of features based on the existing dataset and a selected method and continuously focused on the combination of features with the highest error for iterative training,where the mask matrix of the missing data was used as the input to fit the weights of each base learner using a neural network.Compared with directly modeling on highly sparse data,the predictive ability of this strategy was significantly improved by approximately 20%.In addition,in the testing of new samples,the predicted mean absolute error of the new model was successfully reduced from 0.2 to 0.09.This strategy offers good adaptability to the hydrogen embrittlement sensitivity of different sizes and can avoid interference from feature importance caused by filling data.展开更多
基金financially supported by the National Key Research and Development Program of China(Grant No.2016YFB0600603)National Natural Science Foundation of China(Grant No.51776084)Shenzhen Science and Technology Innovation Committee(Grant No.JCYJ20190809095003718).
文摘The application of forced mercury oxidation technology would lead to an increase of Hg^(2+)concentration in the flue gas.Although Hg^(2+)can be easily removed in the WFGD,the mercury re-emission in the WFGD can decrease the total removal of mercury from coal-fired power plants.Hence,it is necessary to control Hg^(2+)concentration in the devices before the WFGD.Fly ash adsorbent is considered as a potential alternative for commercial activated carbon adsorbent.However,the adsorption efficiency of the original fly ash is low.Modification procedure is needed to enhance the adsorption performance.In this study,the adsorption of Hg^(2+)by brominated fly ash was studied.The fly ash was collected from the full-scale power plant utilizing bromide-blended coal combustion technology.The brominated fly ash exhibited excellent performance for Hg^(2+)removal.The flue gas component HBr and SO_(2)could improve adsorbent’s performance,while HCl would hinder its adsorption process.Also,it was demonstrated by Hg-TPD experiments that the adsorbed Hg^(2+)mainly existed on the fly ash surface in the form of HgBr_(2).In summary,the brominated fly ash has a broad application prospect for mercury control.
基金the support of National Key Research and Development Program of China(2022YFB3707500,2021YFB3802101).
文摘Accurately and quickly predicting hydrogen embrittlement performance is critical for the service of metal materials.However,due to multi-source heterogeneity,existing hydrogen embrittlement data are missing,making it impractical to train reliable machine learning models.In this study,we proposed an ensemble learning training strategy for missing data based on the Adaboost algorithm.This method introduced a mask matrix with missing data and enabled each round of training to generate sub-datasets,considering missing value information.The strategy first trained a subset of features based on the existing dataset and a selected method and continuously focused on the combination of features with the highest error for iterative training,where the mask matrix of the missing data was used as the input to fit the weights of each base learner using a neural network.Compared with directly modeling on highly sparse data,the predictive ability of this strategy was significantly improved by approximately 20%.In addition,in the testing of new samples,the predicted mean absolute error of the new model was successfully reduced from 0.2 to 0.09.This strategy offers good adaptability to the hydrogen embrittlement sensitivity of different sizes and can avoid interference from feature importance caused by filling data.
