[Objective]Real-time monitoring of cow ruminant behavior is of paramount importance for promptly obtaining relevant information about cow health and predicting cow diseases.Currently,various strategies have been propo...[Objective]Real-time monitoring of cow ruminant behavior is of paramount importance for promptly obtaining relevant information about cow health and predicting cow diseases.Currently,various strategies have been proposed for monitoring cow ruminant behavior,including video surveillance,sound recognition,and sensor monitoring methods.How‐ever,the application of edge device gives rise to the issue of inadequate real-time performance.To reduce the volume of data transmission and cloud computing workload while achieving real-time monitoring of dairy cow rumination behavior,a real-time monitoring method was proposed for cow ruminant behavior based on edge computing.[Methods]Autono‐mously designed edge devices were utilized to collect and process six-axis acceleration signals from cows in real-time.Based on these six-axis data,two distinct strategies,federated edge intelligence and split edge intelligence,were investigat‐ed for the real-time recognition of cow ruminant behavior.Focused on the real-time recognition method for cow ruminant behavior leveraging federated edge intelligence,the CA-MobileNet v3 network was proposed by enhancing the MobileNet v3 network with a collaborative attention mechanism.Additionally,a federated edge intelligence model was designed uti‐lizing the CA-MobileNet v3 network and the FedAvg federated aggregation algorithm.In the study on split edge intelli‐gence,a split edge intelligence model named MobileNet-LSTM was designed by integrating the MobileNet v3 network with a fusion collaborative attention mechanism and the Bi-LSTM network.[Results and Discussions]Through compara‐tive experiments with MobileNet v3 and MobileNet-LSTM,the federated edge intelligence model based on CA-Mo‐bileNet v3 achieved an average Precision rate,Recall rate,F1-Score,Specificity,and Accuracy of 97.1%,97.9%,97.5%,98.3%,and 98.2%,respectively,yielding the best recognition performance.[Conclusions]It is provided a real-time and effective method for monitoring cow ruminant behavior,and the proposed federated edge intelligence model can be ap‐plied in practical settings.展开更多
ZrB_(2)-based ceramics typically necessitate high temperature and pressure for sintering,whereas ZrB_(2)-SiC ceramics can be fabricated at 1500℃using the process of reactive melt infiltration with Si.In comparison to...ZrB_(2)-based ceramics typically necessitate high temperature and pressure for sintering,whereas ZrB_(2)-SiC ceramics can be fabricated at 1500℃using the process of reactive melt infiltration with Si.In comparison to the conventional preparation method,reactive synthesis allows for the more facile production of ultra-high temperature ceramics with fine particle size and homogeneous composition.In this work,ZrSi_(2),B4C,and C were used as raw materials to prepare ZrB_(2)-SiC via combination of tape casting and reactive melt infiltration herein referred to as ZBC ceramics.Control sample of ZrB_(2)-SiC was also prepared using ZrB_(2)and SiC as raw materials through an identical process designated as ZS ceramics.Microscopic analysis of both ceramic groups revealed smaller and more uniformly distributed particles of the ZrB_(2)phase in ZBC ceramics compared to the larger particles in ZS ceramics.Both sets of ceramics underwent cyclic oxidation testing in the air at 1600℃for a cumulative duration of 5 cycles,each cycle lasting 2 h.Analysis of the oxidation behavior showed that both ZBC ceramics and ZS ceramics developed a glassy SiO_(2)-ZrO_(2)oxide layer on their surfaces during the oxidation.This layer severed as a barrier against oxygen.In ZBC ceramics,ZrO_(2)is finely distributed in SiO_(2),whereas in ZS ceramics,larger ZrO_(2)particles coexist with glassy SiO_(2).The surface oxide layer of ZBC ceramics maintains a dense structure because the well-dispersed ZrO_(2)increases the viscosity of glassy SiO_(2),preventing its crystallization during the cooling.Conversely,some SiO_(2)in the oxide layer of ZS ceramics may crystallize and form a eutectic with ZrO_(2),leading to the formation of ZrSiO_(4).This leads to cracking of the oxide layer due to differences in thermal expansion coefficients,weakening its barrier effect.An analysis of the oxidation resistance shows that ZBC ceramics exhibit less increase in oxide layer thickness and mass compared to ZS ceramics,suggesting superior oxidation resistance of ZBC ceramics.展开更多
The hot compression tests of 7Mo super austenitic stainless(SASS)were conducted to obtain flow curves at the temperature of 1000-1200℃and strain rate of 0.001 s^(-1)to 1 s^(-1).To predict the non-linear hot deformati...The hot compression tests of 7Mo super austenitic stainless(SASS)were conducted to obtain flow curves at the temperature of 1000-1200℃and strain rate of 0.001 s^(-1)to 1 s^(-1).To predict the non-linear hot deformation behaviors of the steel,back propagation-artificial neural network(BP-ANN)with 16×8×8 hidden layer neurons was proposed.The predictability of the ANN model is evaluated according to the distribution of mean absolute error(MAE)and relative error.The relative error of 85%data for the BP-ANN model is among±5%while only 42.5%data predicted by the Arrhenius constitutive equation is in this range.Especially,at high strain rate and low temperature,the MAE of the ANN model is 2.49%,which has decreases for 18.78%,compared with conventional Arrhenius constitutive equation.展开更多
The effects of fire exposure,reinforcement ratio and the presence of axial load under fire on the seismic behavior of reinforced concrete(RC) shear walls were investigated.Five RC shear walls were tested under low cyc...The effects of fire exposure,reinforcement ratio and the presence of axial load under fire on the seismic behavior of reinforced concrete(RC) shear walls were investigated.Five RC shear walls were tested under low cyclic loading.Prior to the cyclic test,three specimens were exposed to fire and two of them were also subjected to a constant axial load.Test results indicate that the ultimate load of the specimen with lower reinforcement ratio is reduced by 15.8%after exposure to elevated temperatures.While the reductions in the energy dissipation and initial stiffness are 59.2%and 51.8%,respectively,which are much higher than those in the ultimate load.However,this deterioration can be slowed down by properly increasing reinforcement due to the strength and stiffness recovery of steel bars after cooling.In addition,the combined action of elevated temperatures and axial load results in more energy dissipation than the action of fire exposure alone.展开更多
文摘[Objective]Real-time monitoring of cow ruminant behavior is of paramount importance for promptly obtaining relevant information about cow health and predicting cow diseases.Currently,various strategies have been proposed for monitoring cow ruminant behavior,including video surveillance,sound recognition,and sensor monitoring methods.How‐ever,the application of edge device gives rise to the issue of inadequate real-time performance.To reduce the volume of data transmission and cloud computing workload while achieving real-time monitoring of dairy cow rumination behavior,a real-time monitoring method was proposed for cow ruminant behavior based on edge computing.[Methods]Autono‐mously designed edge devices were utilized to collect and process six-axis acceleration signals from cows in real-time.Based on these six-axis data,two distinct strategies,federated edge intelligence and split edge intelligence,were investigat‐ed for the real-time recognition of cow ruminant behavior.Focused on the real-time recognition method for cow ruminant behavior leveraging federated edge intelligence,the CA-MobileNet v3 network was proposed by enhancing the MobileNet v3 network with a collaborative attention mechanism.Additionally,a federated edge intelligence model was designed uti‐lizing the CA-MobileNet v3 network and the FedAvg federated aggregation algorithm.In the study on split edge intelli‐gence,a split edge intelligence model named MobileNet-LSTM was designed by integrating the MobileNet v3 network with a fusion collaborative attention mechanism and the Bi-LSTM network.[Results and Discussions]Through compara‐tive experiments with MobileNet v3 and MobileNet-LSTM,the federated edge intelligence model based on CA-Mo‐bileNet v3 achieved an average Precision rate,Recall rate,F1-Score,Specificity,and Accuracy of 97.1%,97.9%,97.5%,98.3%,and 98.2%,respectively,yielding the best recognition performance.[Conclusions]It is provided a real-time and effective method for monitoring cow ruminant behavior,and the proposed federated edge intelligence model can be ap‐plied in practical settings.
基金National Key R&D Program of China(2022YFB3707700)Shanghai Science and Technology Innovation Action Plan(21511104800)+3 种基金National Natural Science Foundation of China(52172111)National Science and Technology Major Project(2017-IV-0005-0042)Key Research Program of the Chinese Academy of Sciences(ZDRW-CN-2021-2-2)Science Center for Gas Turbine Project(P2022-B-IV-001-001)。
文摘ZrB_(2)-based ceramics typically necessitate high temperature and pressure for sintering,whereas ZrB_(2)-SiC ceramics can be fabricated at 1500℃using the process of reactive melt infiltration with Si.In comparison to the conventional preparation method,reactive synthesis allows for the more facile production of ultra-high temperature ceramics with fine particle size and homogeneous composition.In this work,ZrSi_(2),B4C,and C were used as raw materials to prepare ZrB_(2)-SiC via combination of tape casting and reactive melt infiltration herein referred to as ZBC ceramics.Control sample of ZrB_(2)-SiC was also prepared using ZrB_(2)and SiC as raw materials through an identical process designated as ZS ceramics.Microscopic analysis of both ceramic groups revealed smaller and more uniformly distributed particles of the ZrB_(2)phase in ZBC ceramics compared to the larger particles in ZS ceramics.Both sets of ceramics underwent cyclic oxidation testing in the air at 1600℃for a cumulative duration of 5 cycles,each cycle lasting 2 h.Analysis of the oxidation behavior showed that both ZBC ceramics and ZS ceramics developed a glassy SiO_(2)-ZrO_(2)oxide layer on their surfaces during the oxidation.This layer severed as a barrier against oxygen.In ZBC ceramics,ZrO_(2)is finely distributed in SiO_(2),whereas in ZS ceramics,larger ZrO_(2)particles coexist with glassy SiO_(2).The surface oxide layer of ZBC ceramics maintains a dense structure because the well-dispersed ZrO_(2)increases the viscosity of glassy SiO_(2),preventing its crystallization during the cooling.Conversely,some SiO_(2)in the oxide layer of ZS ceramics may crystallize and form a eutectic with ZrO_(2),leading to the formation of ZrSiO_(4).This leads to cracking of the oxide layer due to differences in thermal expansion coefficients,weakening its barrier effect.An analysis of the oxidation resistance shows that ZBC ceramics exhibit less increase in oxide layer thickness and mass compared to ZS ceramics,suggesting superior oxidation resistance of ZBC ceramics.
文摘The hot compression tests of 7Mo super austenitic stainless(SASS)were conducted to obtain flow curves at the temperature of 1000-1200℃and strain rate of 0.001 s^(-1)to 1 s^(-1).To predict the non-linear hot deformation behaviors of the steel,back propagation-artificial neural network(BP-ANN)with 16×8×8 hidden layer neurons was proposed.The predictability of the ANN model is evaluated according to the distribution of mean absolute error(MAE)and relative error.The relative error of 85%data for the BP-ANN model is among±5%while only 42.5%data predicted by the Arrhenius constitutive equation is in this range.Especially,at high strain rate and low temperature,the MAE of the ANN model is 2.49%,which has decreases for 18.78%,compared with conventional Arrhenius constitutive equation.
基金Project(200801410005) supported by Doctoral Foundation of Ministry of Education of China
文摘The effects of fire exposure,reinforcement ratio and the presence of axial load under fire on the seismic behavior of reinforced concrete(RC) shear walls were investigated.Five RC shear walls were tested under low cyclic loading.Prior to the cyclic test,three specimens were exposed to fire and two of them were also subjected to a constant axial load.Test results indicate that the ultimate load of the specimen with lower reinforcement ratio is reduced by 15.8%after exposure to elevated temperatures.While the reductions in the energy dissipation and initial stiffness are 59.2%and 51.8%,respectively,which are much higher than those in the ultimate load.However,this deterioration can be slowed down by properly increasing reinforcement due to the strength and stiffness recovery of steel bars after cooling.In addition,the combined action of elevated temperatures and axial load results in more energy dissipation than the action of fire exposure alone.
