Encrypted traffic plays a crucial role in safeguarding network security and user privacy.However,encrypting malicious traffic can lead to numerous security issues,making the effective classification of encrypted traff...Encrypted traffic plays a crucial role in safeguarding network security and user privacy.However,encrypting malicious traffic can lead to numerous security issues,making the effective classification of encrypted traffic essential.Existing methods for detecting encrypted traffic face two significant challenges.First,relying solely on the original byte information for classification fails to leverage the rich temporal relationships within network traffic.Second,machine learning and convolutional neural network methods lack sufficient network expression capabilities,hindering the full exploration of traffic’s potential characteristics.To address these limitations,this study introduces a traffic classification method that utilizes time relationships and a higher-order graph neural network,termed HGNN-ETC.This approach fully exploits the original byte information and chronological relationships of traffic packets,transforming traffic data into a graph structure to provide the model with more comprehensive context information.HGNN-ETC employs an innovative k-dimensional graph neural network to effectively capture the multi-scale structural features of traffic graphs,enabling more accurate classification.We select the ISCXVPN and the USTC-TK2016 dataset for our experiments.The results show that compared with other state-of-the-art methods,our method can obtain a better classification effect on different datasets,and the accuracy rate is about 97.00%.In addition,by analyzing the impact of varying input specifications on classification performance,we determine the optimal network data truncation strategy and confirm the model’s excellent generalization ability on different datasets.展开更多
Power consumption is the energy source of the impact on fibers or pulp during low-consistency(LC)pulp refining,and the strength of refining affects refining quality and efficiency.The pulp properties,operating paramet...Power consumption is the energy source of the impact on fibers or pulp during low-consistency(LC)pulp refining,and the strength of refining affects refining quality and efficiency.The pulp properties,operating parameters,and bar parameters of the refiner plates are important parameters affecting refining efficiency,which can be defined as the ratio of net to total refining power.In this study,LC refining trials for pulps with different consistencies and fiber lengths were conducted using five isometric straightbar plates with different bar angles to explore the influences of the plate bar angle and pulp properties on the no-load power,impact capacity on fibers and refining efficiency.It was found that the no-load power of the LC refining process decreased with an increase in the plate bar angle while increased when pulp with higher consistency was refined under the same refining conditions.However,the effect of pulp consistency on the no-load power can be neglected when refining is conducted using plates with larger bar angles.Meanwhile,a critical bar angle for straight-bar plates in LC refining may exist,which has the strongest impact on the pulp and highest refining efficiency under the same refining conditions.In addition,the impact capacity of the plate on the pulp and refining efficiency in LC refining can be enhanced by appropriately increasing the pulp consistency and average fiber length when the bar angle of the refiner plate with a sector angle of 40°is less than 30°.Therefore,the efficiency and power consumption of the LC refining process can be adjusted by optimizing the pulp consistency and bar parameters of the refining plates.展开更多
Straight-and curved-bar refining plates are two important types of plates commonly used in disc refiners in the papermaking industry.Theoretically,the curved-bar refining plate has a relatively uniform bar interaction...Straight-and curved-bar refining plates are two important types of plates commonly used in disc refiners in the papermaking industry.Theoretically,the curved-bar refining plate has a relatively uniform bar interaction angle,which indicates uniform refining effects.The bar angle of the curved bar was proposed and two typical curved-bar plates,the three-stage radial curved-bar plate and isometric curved-bar plate,were designed in this paper.The arc equations of the curved-bar center line and curved-bar edges were established and finally,the specific edge load(SEL)of the curved-bar plate was derived.The determination of bar parameters was discussed,which provides a theoretical basis for the design of curved-bar plates.展开更多
基金supported in part by the National Key Research and Development Program of China(No.2022YFB4500800)the National Science Foundation of China(No.42071431).
文摘Encrypted traffic plays a crucial role in safeguarding network security and user privacy.However,encrypting malicious traffic can lead to numerous security issues,making the effective classification of encrypted traffic essential.Existing methods for detecting encrypted traffic face two significant challenges.First,relying solely on the original byte information for classification fails to leverage the rich temporal relationships within network traffic.Second,machine learning and convolutional neural network methods lack sufficient network expression capabilities,hindering the full exploration of traffic’s potential characteristics.To address these limitations,this study introduces a traffic classification method that utilizes time relationships and a higher-order graph neural network,termed HGNN-ETC.This approach fully exploits the original byte information and chronological relationships of traffic packets,transforming traffic data into a graph structure to provide the model with more comprehensive context information.HGNN-ETC employs an innovative k-dimensional graph neural network to effectively capture the multi-scale structural features of traffic graphs,enabling more accurate classification.We select the ISCXVPN and the USTC-TK2016 dataset for our experiments.The results show that compared with other state-of-the-art methods,our method can obtain a better classification effect on different datasets,and the accuracy rate is about 97.00%.In addition,by analyzing the impact of varying input specifications on classification performance,we determine the optimal network data truncation strategy and confirm the model’s excellent generalization ability on different datasets.
基金funding from the National Natural Science Foundation of China (Grant No. 50745048)Shaanxi Provincial Key Research and Development Project (Grant No. 2020 GY-105)Natural Science Basic Research Program of Shaanxi (Grant No. 2023-JC-QN-0154)。
文摘Power consumption is the energy source of the impact on fibers or pulp during low-consistency(LC)pulp refining,and the strength of refining affects refining quality and efficiency.The pulp properties,operating parameters,and bar parameters of the refiner plates are important parameters affecting refining efficiency,which can be defined as the ratio of net to total refining power.In this study,LC refining trials for pulps with different consistencies and fiber lengths were conducted using five isometric straightbar plates with different bar angles to explore the influences of the plate bar angle and pulp properties on the no-load power,impact capacity on fibers and refining efficiency.It was found that the no-load power of the LC refining process decreased with an increase in the plate bar angle while increased when pulp with higher consistency was refined under the same refining conditions.However,the effect of pulp consistency on the no-load power can be neglected when refining is conducted using plates with larger bar angles.Meanwhile,a critical bar angle for straight-bar plates in LC refining may exist,which has the strongest impact on the pulp and highest refining efficiency under the same refining conditions.In addition,the impact capacity of the plate on the pulp and refining efficiency in LC refining can be enhanced by appropriately increasing the pulp consistency and average fiber length when the bar angle of the refiner plate with a sector angle of 40°is less than 30°.Therefore,the efficiency and power consumption of the LC refining process can be adjusted by optimizing the pulp consistency and bar parameters of the refining plates.
基金funding by the National Natural Science Foundation (Grant No. 50745048)
文摘Straight-and curved-bar refining plates are two important types of plates commonly used in disc refiners in the papermaking industry.Theoretically,the curved-bar refining plate has a relatively uniform bar interaction angle,which indicates uniform refining effects.The bar angle of the curved bar was proposed and two typical curved-bar plates,the three-stage radial curved-bar plate and isometric curved-bar plate,were designed in this paper.The arc equations of the curved-bar center line and curved-bar edges were established and finally,the specific edge load(SEL)of the curved-bar plate was derived.The determination of bar parameters was discussed,which provides a theoretical basis for the design of curved-bar plates.