With the rapid development of economy,air pollution caused by industrial expansion has caused serious harm to human health and social development.Therefore,establishing an effective air pollution concentration predict...With the rapid development of economy,air pollution caused by industrial expansion has caused serious harm to human health and social development.Therefore,establishing an effective air pollution concentration prediction system is of great scientific and practical significance for accurate and reliable predictions.This paper proposes a combination of pointinterval prediction system for pollutant concentration prediction by leveraging neural network,meta-heuristic optimization algorithm,and fuzzy theory.Fuzzy information granulation technology is used in data preprocessing to transform numerical sequences into fuzzy particles for comprehensive feature extraction.The golden Jackal optimization algorithm is employed in the optimization stage to fine-tune model hyperparameters.In the prediction stage,an ensemble learning method combines training results frommultiplemodels to obtain final point predictions while also utilizing quantile regression and kernel density estimation methods for interval predictions on the test set.Experimental results demonstrate that the combined model achieves a high goodness of fit coefficient of determination(R^(2))at 99.3% and a maximum difference between prediction accuracy mean absolute percentage error(MAPE)and benchmark model at 12.6%.This suggests that the integrated learning system proposed in this paper can provide more accurate deterministic predictions as well as reliable uncertainty analysis compared to traditionalmodels,offering practical reference for air quality early warning.展开更多
Wet granulation-a unit operation involving mixing polymeric binders with powdered formulations-is well established in the pharmaceutical industry,playing a major role in the manufacturing of oral solid dosage forms an...Wet granulation-a unit operation involving mixing polymeric binders with powdered formulations-is well established in the pharmaceutical industry,playing a major role in the manufacturing of oral solid dosage forms and improving the physical properties of granules(size,density,shape factor,etc.)before tableting.The foaming properties of aqueous polymeric binders prove useful for binder delivery within the mixing vessel,with foamed binders leading to enhanced process efficiency(binder distribution,drying time,and temperature)and product quality(heat-sensitive components)during granulation.Given the importance of this stage in producing oral solid dosage forms,understanding the relationship between critical process parameters and critical quality attributes is essential.The process analytical technology(PAT)framework enables process design,analysis,and control and facilitates process development via in-line spectroscopy combined with multivariate data analysis to yield critical product information during the unit operation.Herein,we used in-line NIR spectroscopy to monitor granule size in foam granulations of a pharmaceutical compound.The mean granule diameter was predicted using a partial least squares regression(PLSR)model(with a prediction error of 11.8μm)and combined with a batch statistical process control(BSPC)approach for the temporal monitoring of granule size during three foam granulations.展开更多
Semantic segmentation provides important technical support for Land cover/land use(LCLU)research.By calculating the cosine similarity between feature vectors,transformer-based models can effectively capture the global...Semantic segmentation provides important technical support for Land cover/land use(LCLU)research.By calculating the cosine similarity between feature vectors,transformer-based models can effectively capture the global information of high-resolution remote sensing images.However,the diversity of detailed and edge features within the same class of ground objects in high-resolution remote sensing images leads to a dispersed embedding distribution.The dispersed feature distribution enlarges feature vector angles and reduces cosine similarity,weakening the attention mechanism’s ability to identify the same class of ground objects.To address this challenge,remote sensing image information granulation transformer for semantic segmentation is proposed.The model employs adaptive granulation to extract common semantic features among objects of the same class,constructing an information granule to replace the detailed feature representation of these objects.Then,the Laplacian operator of the information granule is applied to extract the edge features of the object as represented by the information granule.In the experiments,the proposed model was validated on the Beijing Land-Use(BLU),Gaofen Image Dataset(GID),and Potsdam Dataset(PD).In particular,the model achieves 88.81%for mOA,82.64%for mF1,and 71.50%for mIoU metrics on the GID dataset.Experimental results show that the model effectively handles high-resolution remote sensing images.Our code is available at https://github.com/sjmp525/RSIGT(accessed on 16 April 2025).展开更多
The so-called close-coupled gas atomization process involves melting a metal and using a high-pressure gas jet positioned close to the melt stream to rapidly break it into fine,spherical powder particles.This techniqu...The so-called close-coupled gas atomization process involves melting a metal and using a high-pressure gas jet positioned close to the melt stream to rapidly break it into fine,spherical powder particles.This technique,adapted for blast furnace slag granulation using a circular seam nozzle,typically aims to produce solid slag particles sized 30–140μm,thereby allowing the utilization of slag as a resource.This study explores the atomization dynamics of liquid blast furnace slag,focusing on the effects of atomization pressure.Primary atomization is simulated using a combination of the Volume of Fluid(VOF)method and the Shear Stress Transport k-ωturbulence model,while secondary atomization is analyzed through the Discrete Phase Model(DPM).The results reveal that primary atomization progresses in three stages:the slag column transforms into an umbrella-shaped liquid film,whose leading edge fragments into particles while forming a cavity-like structure,which is eventually torn into ligaments.This primary deformation is driven by the interplay of airflow velocity in the recirculation zone and the guide tube outlet pressure(Fp).Increasing the atomization pressure amplifies airflow velocity,recirculation zone size,expansion and shock waves,though the guide tube outlet pressure variations remain irregular.Notably,at 4.5 MPa,the primary deformation is most pronounced.Secondary atomization yields finer slag particles as a result of more vigorous primary atomization.For this pressure,the smallest average particle size and the highest yield of particles within the target range(30–140μm)are achieved.展开更多
基金supported by General Scientific Research Funding of the Science and Technology Development Fund(FDCT)in Macao(No.0150/2022/A)the Faculty Research Grants of Macao University of Science and Technology(No.FRG-22-074-FIE).
文摘With the rapid development of economy,air pollution caused by industrial expansion has caused serious harm to human health and social development.Therefore,establishing an effective air pollution concentration prediction system is of great scientific and practical significance for accurate and reliable predictions.This paper proposes a combination of pointinterval prediction system for pollutant concentration prediction by leveraging neural network,meta-heuristic optimization algorithm,and fuzzy theory.Fuzzy information granulation technology is used in data preprocessing to transform numerical sequences into fuzzy particles for comprehensive feature extraction.The golden Jackal optimization algorithm is employed in the optimization stage to fine-tune model hyperparameters.In the prediction stage,an ensemble learning method combines training results frommultiplemodels to obtain final point predictions while also utilizing quantile regression and kernel density estimation methods for interval predictions on the test set.Experimental results demonstrate that the combined model achieves a high goodness of fit coefficient of determination(R^(2))at 99.3% and a maximum difference between prediction accuracy mean absolute percentage error(MAPE)and benchmark model at 12.6%.This suggests that the integrated learning system proposed in this paper can provide more accurate deterministic predictions as well as reliable uncertainty analysis compared to traditionalmodels,offering practical reference for air quality early warning.
文摘Wet granulation-a unit operation involving mixing polymeric binders with powdered formulations-is well established in the pharmaceutical industry,playing a major role in the manufacturing of oral solid dosage forms and improving the physical properties of granules(size,density,shape factor,etc.)before tableting.The foaming properties of aqueous polymeric binders prove useful for binder delivery within the mixing vessel,with foamed binders leading to enhanced process efficiency(binder distribution,drying time,and temperature)and product quality(heat-sensitive components)during granulation.Given the importance of this stage in producing oral solid dosage forms,understanding the relationship between critical process parameters and critical quality attributes is essential.The process analytical technology(PAT)framework enables process design,analysis,and control and facilitates process development via in-line spectroscopy combined with multivariate data analysis to yield critical product information during the unit operation.Herein,we used in-line NIR spectroscopy to monitor granule size in foam granulations of a pharmaceutical compound.The mean granule diameter was predicted using a partial least squares regression(PLSR)model(with a prediction error of 11.8μm)and combined with a batch statistical process control(BSPC)approach for the temporal monitoring of granule size during three foam granulations.
基金supported by the National Natural Science Foundation of China(62462040)the Yunnan Fundamental Research Projects(202501AT070345)+2 种基金the Major Science and Technology Projects in Yunnan Province(202202AD080013)Sichuan Provincial Key Laboratory of Philosophy and Social Science Key Program on Language Intelligence Special Education(YYZN-2024-1)the Photosynthesis Fund Class A(ghfund202407010460).
文摘Semantic segmentation provides important technical support for Land cover/land use(LCLU)research.By calculating the cosine similarity between feature vectors,transformer-based models can effectively capture the global information of high-resolution remote sensing images.However,the diversity of detailed and edge features within the same class of ground objects in high-resolution remote sensing images leads to a dispersed embedding distribution.The dispersed feature distribution enlarges feature vector angles and reduces cosine similarity,weakening the attention mechanism’s ability to identify the same class of ground objects.To address this challenge,remote sensing image information granulation transformer for semantic segmentation is proposed.The model employs adaptive granulation to extract common semantic features among objects of the same class,constructing an information granule to replace the detailed feature representation of these objects.Then,the Laplacian operator of the information granule is applied to extract the edge features of the object as represented by the information granule.In the experiments,the proposed model was validated on the Beijing Land-Use(BLU),Gaofen Image Dataset(GID),and Potsdam Dataset(PD).In particular,the model achieves 88.81%for mOA,82.64%for mF1,and 71.50%for mIoU metrics on the GID dataset.Experimental results show that the model effectively handles high-resolution remote sensing images.Our code is available at https://github.com/sjmp525/RSIGT(accessed on 16 April 2025).
基金the Tangshan University Doctor Innovation Fund(Project Number:1402306).
文摘The so-called close-coupled gas atomization process involves melting a metal and using a high-pressure gas jet positioned close to the melt stream to rapidly break it into fine,spherical powder particles.This technique,adapted for blast furnace slag granulation using a circular seam nozzle,typically aims to produce solid slag particles sized 30–140μm,thereby allowing the utilization of slag as a resource.This study explores the atomization dynamics of liquid blast furnace slag,focusing on the effects of atomization pressure.Primary atomization is simulated using a combination of the Volume of Fluid(VOF)method and the Shear Stress Transport k-ωturbulence model,while secondary atomization is analyzed through the Discrete Phase Model(DPM).The results reveal that primary atomization progresses in three stages:the slag column transforms into an umbrella-shaped liquid film,whose leading edge fragments into particles while forming a cavity-like structure,which is eventually torn into ligaments.This primary deformation is driven by the interplay of airflow velocity in the recirculation zone and the guide tube outlet pressure(Fp).Increasing the atomization pressure amplifies airflow velocity,recirculation zone size,expansion and shock waves,though the guide tube outlet pressure variations remain irregular.Notably,at 4.5 MPa,the primary deformation is most pronounced.Secondary atomization yields finer slag particles as a result of more vigorous primary atomization.For this pressure,the smallest average particle size and the highest yield of particles within the target range(30–140μm)are achieved.
