A critical pathway towards enhancing pulp mill biorefineries is to integrate the extraction and utilization of hemicelluloses into the pulping processes.Hence,an industrial pre-extraction strategy for hemicelluloses t...A critical pathway towards enhancing pulp mill biorefineries is to integrate the extraction and utilization of hemicelluloses into the pulping processes.Hence,an industrial pre-extraction strategy for hemicelluloses targeting eucalyptus kraft pulping process was developed.Alkaline solution or pulping white liquor was used to pre-extract hemicelluloses before the actual pulping process.The response surface methodology(RSM)technique was applied to investigate the most suitable conditions to maximize the yield of these hemicelluloses while simultaneously minimizing the damage to pulp yields and properties.Temperature(105 to 155℃),alkali concentration(3%to 8%),sulfidity(20%to 30%)and retention time(19 to 221 min)were combined to evaluate their effects on hemicellulose yields and chemical structures.The optimal pre-extraction conditions identified in this work(5.75%NaOH concentration,25%sulfidity at 135℃for 60 min)successfully allowed recovering 4.8%of hemicelluloses(based on the wood dry mass)and limited damages to pulp yields and properties.The cellulose content in pulp can even be increased by about 10%.Hemicellulose emulsification properties were also evaluated,which were comparable to synthetic emulsifiers.This study provides an industrial pathway to effectively separate and utilize wood hemicelluloses from the pulping process,which has the potential to improve the economy and material utilization of pulp and paper mills.展开更多
In the field of intelligent air combat,real-time and accurate recognition of within-visual-range(WVR)maneuver actions serves as the foundational cornerstone for constructing autonomous decision-making systems.However,...In the field of intelligent air combat,real-time and accurate recognition of within-visual-range(WVR)maneuver actions serves as the foundational cornerstone for constructing autonomous decision-making systems.However,existing methods face two major challenges:traditional feature engineering suffers from insufficient effective dimensionality in the feature space due to kinematic coupling,making it difficult to distinguish essential differences between maneuvers,while end-to-end deep learning models lack controllability in implicit feature learning and fail to model high-order long-range temporal dependencies.This paper proposes a trajectory feature pre-extraction method based on a Long-range Masked Autoencoder(LMAE),incorporating three key innovations:(1)Random Fragment High-ratio Masking(RFH-Mask),which enforces the model to learn long-range temporal correlations by masking 80%of trajectory data while retaining continuous fragments;(2)Kalman Filter-Guided Objective Function(KFG-OF),integrating trajectory continuity constraints to align the feature space with kinematic principles;and(3)Two-stage Decoupled Architecture,enabling efficient and controllable feature learning through unsupervised pre-training and frozen-feature transfer.Experimental results demonstrate that LMAE significantly improves the average recognition accuracy for 20-class maneuvers compared to traditional end-to-end models,while significantly accelerating convergence speed.The contributions of this work lie in:introducing high-masking-rate autoencoders into low-informationdensity trajectory analysis,proposing a feature engineering framework with enhanced controllability and efficiency,and providing a novel technical pathway for intelligent air combat decision-making systems.展开更多
基金supported by the Natural Science Foundation of Guangdong Province(2023A1515030211)the National Natural Science Foundation of China(22278157)Guangzhou Science and Technology Program(2023B03J1365).
文摘A critical pathway towards enhancing pulp mill biorefineries is to integrate the extraction and utilization of hemicelluloses into the pulping processes.Hence,an industrial pre-extraction strategy for hemicelluloses targeting eucalyptus kraft pulping process was developed.Alkaline solution or pulping white liquor was used to pre-extract hemicelluloses before the actual pulping process.The response surface methodology(RSM)technique was applied to investigate the most suitable conditions to maximize the yield of these hemicelluloses while simultaneously minimizing the damage to pulp yields and properties.Temperature(105 to 155℃),alkali concentration(3%to 8%),sulfidity(20%to 30%)and retention time(19 to 221 min)were combined to evaluate their effects on hemicellulose yields and chemical structures.The optimal pre-extraction conditions identified in this work(5.75%NaOH concentration,25%sulfidity at 135℃for 60 min)successfully allowed recovering 4.8%of hemicelluloses(based on the wood dry mass)and limited damages to pulp yields and properties.The cellulose content in pulp can even be increased by about 10%.Hemicellulose emulsification properties were also evaluated,which were comparable to synthetic emulsifiers.This study provides an industrial pathway to effectively separate and utilize wood hemicelluloses from the pulping process,which has the potential to improve the economy and material utilization of pulp and paper mills.
文摘In the field of intelligent air combat,real-time and accurate recognition of within-visual-range(WVR)maneuver actions serves as the foundational cornerstone for constructing autonomous decision-making systems.However,existing methods face two major challenges:traditional feature engineering suffers from insufficient effective dimensionality in the feature space due to kinematic coupling,making it difficult to distinguish essential differences between maneuvers,while end-to-end deep learning models lack controllability in implicit feature learning and fail to model high-order long-range temporal dependencies.This paper proposes a trajectory feature pre-extraction method based on a Long-range Masked Autoencoder(LMAE),incorporating three key innovations:(1)Random Fragment High-ratio Masking(RFH-Mask),which enforces the model to learn long-range temporal correlations by masking 80%of trajectory data while retaining continuous fragments;(2)Kalman Filter-Guided Objective Function(KFG-OF),integrating trajectory continuity constraints to align the feature space with kinematic principles;and(3)Two-stage Decoupled Architecture,enabling efficient and controllable feature learning through unsupervised pre-training and frozen-feature transfer.Experimental results demonstrate that LMAE significantly improves the average recognition accuracy for 20-class maneuvers compared to traditional end-to-end models,while significantly accelerating convergence speed.The contributions of this work lie in:introducing high-masking-rate autoencoders into low-informationdensity trajectory analysis,proposing a feature engineering framework with enhanced controllability and efficiency,and providing a novel technical pathway for intelligent air combat decision-making systems.
