In this paper,a fusion model based on a long short-term memory(LSTM)neural network and enhanced search ant colony optimization(ENSACO)is proposed to predict the power degradation trend of proton exchange membrane fuel...In this paper,a fusion model based on a long short-term memory(LSTM)neural network and enhanced search ant colony optimization(ENSACO)is proposed to predict the power degradation trend of proton exchange membrane fuel cells(PEMFC).Firstly,the Shapley additive explanations(SHAP)value method is used to select external characteristic parameters with high contributions as inputs for the data-driven approach.Next,a novel swarm optimization algorithm,the enhanced search ant colony optimization,is proposed.This algorithm improves the ant colony optimization(ACO)algorithm based on a reinforcement factor to avoid premature convergence and accelerate the convergence speed.Comparative experiments are set up to compare the performance differences between particle swarm optimization(PSO),ACO,and ENSACO.Finally,a data-driven method based on ENSACO-LSTM is proposed to predict the power degradation trend of PEMFCs.And actual aging data is used to validate the method.The results show that,within a limited number of iterations,the optimization capability of ENSACO is significantly stronger than that of PSO and ACO.Additionally,the prediction accuracy of the ENSACO-LSTM method is greatly improved,with an average increase of approximately 50.58%compared to LSTM,PSO-LSTM,and ACO-LSTM.展开更多
Mg–Zn–Ag alloys have been extensively studied in recent years for potential biodegradable implants due to their unique mechanical properties,biodegradability and biocompatibility.In the present study,Mg–3Zn-x Ag（w...Mg–Zn–Ag alloys have been extensively studied in recent years for potential biodegradable implants due to their unique mechanical properties,biodegradability and biocompatibility.In the present study,Mg–3Zn-x Ag（wt%,x=0.2,0.5 and0.8）alloys with single-phase crystal structure were prepared by backward extrusion at 340°C.The addition of Ag element into Mg–3Zn slightly influences the ultimate tensile strength and microstructure,but the elongation firstly increases from12%to 19.8%and then decreases from 19.8%to 9.9%with the increment of Ag concentration.The tensile yield strength,ultimate tensile strength and elongation of Mg–3Zn–0.2Ag alloy reach up to 142,234 MPa and 19.8%,respectively,which are the best mechanical performance of Mg–Zn–Ag alloys in the present work.The extruded Mg–3Zn–0.2Ag alloy also possesses the best corrosion behavior with the corresponding corrosion rate of 3.2 mm/year in immersion test,which could be explained by the single-phase and uniformly distributed grain structure,and the fewer twinning.展开更多
This paper presents results from investigating the ageing behaviour and performance of different warm mix asphalt （WMA） pavement mixtures also called energy reduced pavements. The mixtures were either prepared in th...This paper presents results from investigating the ageing behaviour and performance of different warm mix asphalt （WMA） pavement mixtures also called energy reduced pavements. The mixtures were either prepared in the laboratory or taken directly from a mixing plant. The study compared the rutting and fatigue behaviours of unaged material in comparison to long term laboratory aged material. In order to conduct the long term ageing, a special laboratory ageing protocol with different heating, cooling and watering cycles had been developed. The investigation revealed a quite controversial rutting behavior which could not be explained with the available data. While most aged energy reduced pavements showed increased rutting for other mixtures, lower rut depths could be found. As opposed to this finding, fatigue and stiffness of all aged energy reduced pave- ment samples compared to unaged samples improved significantly. The overall results led to the conclusion that the ageing of energy reduced pavement simulated in the laboratory is not very critical regarding their mechanical performance. Therefore, it was confrmed that the application of this type of pavement provides a good solution for saving on CO2 emissions. Another advantage is that by using energy reduced pavements the road con- struction season can be significantly prolonged.展开更多
基金Supported by the Major Science and Technology Project of Jilin Province(20220301010GX)the International Scientific and Technological Cooperation(20240402071GH).
文摘In this paper,a fusion model based on a long short-term memory(LSTM)neural network and enhanced search ant colony optimization(ENSACO)is proposed to predict the power degradation trend of proton exchange membrane fuel cells(PEMFC).Firstly,the Shapley additive explanations(SHAP)value method is used to select external characteristic parameters with high contributions as inputs for the data-driven approach.Next,a novel swarm optimization algorithm,the enhanced search ant colony optimization,is proposed.This algorithm improves the ant colony optimization(ACO)algorithm based on a reinforcement factor to avoid premature convergence and accelerate the convergence speed.Comparative experiments are set up to compare the performance differences between particle swarm optimization(PSO),ACO,and ENSACO.Finally,a data-driven method based on ENSACO-LSTM is proposed to predict the power degradation trend of PEMFCs.And actual aging data is used to validate the method.The results show that,within a limited number of iterations,the optimization capability of ENSACO is significantly stronger than that of PSO and ACO.Additionally,the prediction accuracy of the ENSACO-LSTM method is greatly improved,with an average increase of approximately 50.58%compared to LSTM,PSO-LSTM,and ACO-LSTM.
基金supported by the National Natural Science Foundation of China (Nos. 51371046 and 51525101)the National Key Research and Development Program of China (No. 2016YFB0701202)the Fundamental Research Funds of the Central Universities (No. N141008001)
文摘Mg–Zn–Ag alloys have been extensively studied in recent years for potential biodegradable implants due to their unique mechanical properties,biodegradability and biocompatibility.In the present study,Mg–3Zn-x Ag（wt%,x=0.2,0.5 and0.8）alloys with single-phase crystal structure were prepared by backward extrusion at 340°C.The addition of Ag element into Mg–3Zn slightly influences the ultimate tensile strength and microstructure,but the elongation firstly increases from12%to 19.8%and then decreases from 19.8%to 9.9%with the increment of Ag concentration.The tensile yield strength,ultimate tensile strength and elongation of Mg–3Zn–0.2Ag alloy reach up to 142,234 MPa and 19.8%,respectively,which are the best mechanical performance of Mg–Zn–Ag alloys in the present work.The extruded Mg–3Zn–0.2Ag alloy also possesses the best corrosion behavior with the corresponding corrosion rate of 3.2 mm/year in immersion test,which could be explained by the single-phase and uniformly distributed grain structure,and the fewer twinning.
文摘This paper presents results from investigating the ageing behaviour and performance of different warm mix asphalt （WMA） pavement mixtures also called energy reduced pavements. The mixtures were either prepared in the laboratory or taken directly from a mixing plant. The study compared the rutting and fatigue behaviours of unaged material in comparison to long term laboratory aged material. In order to conduct the long term ageing, a special laboratory ageing protocol with different heating, cooling and watering cycles had been developed. The investigation revealed a quite controversial rutting behavior which could not be explained with the available data. While most aged energy reduced pavements showed increased rutting for other mixtures, lower rut depths could be found. As opposed to this finding, fatigue and stiffness of all aged energy reduced pave- ment samples compared to unaged samples improved significantly. The overall results led to the conclusion that the ageing of energy reduced pavement simulated in the laboratory is not very critical regarding their mechanical performance. Therefore, it was confrmed that the application of this type of pavement provides a good solution for saving on CO2 emissions. Another advantage is that by using energy reduced pavements the road con- struction season can be significantly prolonged.
