With the rapid development of electric power systems,load estimation plays an important role in system operation and planning.Usually,load estimation techniques contain traditional,time series,regression analysis-base...With the rapid development of electric power systems,load estimation plays an important role in system operation and planning.Usually,load estimation techniques contain traditional,time series,regression analysis-based,and machine learning-based estimation.Since the machine learning-based method can lead to better performance,in this paper,a deep learning-based load estimation algorithm using image fingerprint and attention mechanism is proposed.First,an image fingerprint construction is proposed for training data.After the data preprocessing,the training data matrix is constructed by the cyclic shift and cubic spline interpolation.Then,the linear mapping and the gray-color transformation method are proposed to form the color image fingerprint.Second,a convolutional neural network(CNN)combined with an attentionmechanism is proposed for training performance improvement.At last,an experiment is carried out to evaluate the estimation performance.Compared with the support vector machine method,CNN method and long short-term memory method,the proposed algorithm has the best load estimation performance.展开更多
As a promising new energy source, natural gas hydrates (NGHs) have attracted wide attention. The thermophysical properties of NGHs are of great significance to their exploitation. This work summarizes the progress of ...As a promising new energy source, natural gas hydrates (NGHs) have attracted wide attention. The thermophysical properties of NGHs are of great significance to their exploitation. This work summarizes the progress of laboratory measurements and models of NGH thermophysical parameters, such as phase equilibrium, thermal conductivity, dissociation enthalpy, thermal diffusivity, and specific heat capacity. The advantages and disadvantages of measurement methods, numerical models, typical experimental data, and characteristics are discussed. The measurement accuracy of hydrate phase equilibrium is closely related to the estimation (or prediction) of the temperature (pressure), at which gas hydrate may decompose, as well as the heating rate, pores, residual water, ice and additive, etc., affect the sample quality as well as the thermal conductivity. The randomness of hydrate nucleation and growth leads to the uncertainty of hydrate distribution in sediments, which directly affects the accuracy of thermophysical property prediction models. Moreover, some future perspectives are suggested.展开更多
Accounting fraud has never been rooted out, which brings a lot of trouble to our society. Only through strengthening user＇s ability to discern, decode and feedback the false information can we maximally understand th...Accounting fraud has never been rooted out, which brings a lot of trouble to our society. Only through strengthening user＇s ability to discern, decode and feedback the false information can we maximally understand the information behind. Therefore, devoting ourselves to setting up a framework of detecting the accounting fraud has become a feasible and efficient way to solve this problem. Based on the ＂Three Elements Theory＂, this paper demonstrates a new way to discern the fraud by researching its origins. The authors combine the theoretical model and the applied technology together to design a fraud recognization system.展开更多
A three-stageflue gas hydrate-based desalination system was designed using liquefied natural gas(LNG)cold energy.This system could increase the CO_(2)amount-of-substance fraction in theflue gas from 17%to 97%and produce...A three-stageflue gas hydrate-based desalination system was designed using liquefied natural gas(LNG)cold energy.This system could increase the CO_(2)amount-of-substance fraction in theflue gas from 17%to 97%and produce desalinated water with a desalting rate of approximately 95%.Four system operating plans were simulated as follows:CO_(2)+N_(2)+seawater at 0.6 MPa,CO_(2)+N_(2)+seawater at 3 MPa,CO_(2)+N_(2)+tetra-n-butyl ammonium bromide(TBAB)+seawater at 0.6 MPa,and CO_(2)+N_(2)+tetrahydrofuran(THF)+seawater at 0.6 MPa.The energy consumption,LNG cold energy consumption,energy loss,and environmental friendliness were calculated and analyzed.The compression energy consumption was the highest contributor to the total energy consumption,and the highest percentage of total energy loss was heat exchange loss.Reducing the formation pressure in thefirst stage effectively reduced the total energy consumption,LNG cold energy consumption,and energy loss by 21.28%,24.41%,and 23.99%,respectively.Addition of TBAB/THF reduced the total energy consumption,LNG cold energy consumption,and energy loss by 18.45%/17.88%,32.30%/32.73%,and 24.65%/23.54%,respectively.The CO_(2)+CO_(2)+N_(2)+seawater operation at 0.6 MPa did not produce pollution.The CO_(2)+N_(2)+seawater operation at 3 MPa had the highest total energy consumption and LNG cold energy consumption.Operation with TBAB/THF had obvious advantages in terms of total energy consumption but suffered from the generation of pollution.Comprehensive analysis indicated that the CO_(2)+N_(2)+seawater operation at 0.6 MPa was the optimum system.展开更多
Liquefaction of sandy soils is a big threat to the stability and the safety of an earth embankment laid on saturated soils.A large number of liquefaction-induced damages on embankment due to different types of earthqu...Liquefaction of sandy soils is a big threat to the stability and the safety of an earth embankment laid on saturated soils.A large number of liquefaction-induced damages on embankment due to different types of earthquakes have been reported worldwide.In this research,the dynamic behaviors of earth embankment and the reinforcement effects of grouting as remediation method,subjected to moderate earthquake EQ1 and strong earthquake EQ2,were numerically investigated.The seismic behaviors of ground composed of cohesionless sandy soil and cohesive clayey soil were uniformly described by the cyclic mobility(CM)model,which is capable of describing accurately the mechanical property of the soil due to monotonic and cyclic loadings by accounting for stress-induced anisotropy,over-consolidation,and soil structure.It is known from the numerical investigation that the embankment would experience destructive deformation,and that the collapse mode was closely related to the properties of input seismic motion because high intensities and long durations of an earthquake motion could lead to significant plastic deformation and prolonged soil liquefaction.Under the strong seismic loading of EQ2,a circular collapse surface,combined with huge settlement and lateral spread,occurred inside the liquefication zone and extended towards the embankment crest.In contrast,in moderate earthquake EQ1,upheaval was observed at each toe of the embankment,and instability occurred only in the liquefied ground.An anti-liquefaction remediation via grouting was determined to significantly reduce liquefaction-induced deformation(settlement,lateral spreading,and local uplift)and restrain the deep-seated circular sliding failure,even though the top sandy soil liquefied in both earthquakes.When the structure was subjected to EQ2 motion,local failure occurred on the embankment slope reinforced with grouting,and thus,an additional appropriate countermeasure should be implemented to further strengthen the slope.For both input motions,the surface deformation of the considered embankment decreased gradually as the thickness of reinforcement was increased,although the reinforcement effect was no longer significant once the thickness exceeded 6 m.展开更多
文摘With the rapid development of electric power systems,load estimation plays an important role in system operation and planning.Usually,load estimation techniques contain traditional,time series,regression analysis-based,and machine learning-based estimation.Since the machine learning-based method can lead to better performance,in this paper,a deep learning-based load estimation algorithm using image fingerprint and attention mechanism is proposed.First,an image fingerprint construction is proposed for training data.After the data preprocessing,the training data matrix is constructed by the cyclic shift and cubic spline interpolation.Then,the linear mapping and the gray-color transformation method are proposed to form the color image fingerprint.Second,a convolutional neural network(CNN)combined with an attentionmechanism is proposed for training performance improvement.At last,an experiment is carried out to evaluate the estimation performance.Compared with the support vector machine method,CNN method and long short-term memory method,the proposed algorithm has the best load estimation performance.
基金funded by the National Natural Science Foundation of China(52074165)Natural Science Foundation of Shandong Province(ZR2019MEE116,ZR2020ME187)Source Innovation Special Project of Qingdao West Coast New Area(2020-93).
文摘As a promising new energy source, natural gas hydrates (NGHs) have attracted wide attention. The thermophysical properties of NGHs are of great significance to their exploitation. This work summarizes the progress of laboratory measurements and models of NGH thermophysical parameters, such as phase equilibrium, thermal conductivity, dissociation enthalpy, thermal diffusivity, and specific heat capacity. The advantages and disadvantages of measurement methods, numerical models, typical experimental data, and characteristics are discussed. The measurement accuracy of hydrate phase equilibrium is closely related to the estimation (or prediction) of the temperature (pressure), at which gas hydrate may decompose, as well as the heating rate, pores, residual water, ice and additive, etc., affect the sample quality as well as the thermal conductivity. The randomness of hydrate nucleation and growth leads to the uncertainty of hydrate distribution in sediments, which directly affects the accuracy of thermophysical property prediction models. Moreover, some future perspectives are suggested.
文摘Accounting fraud has never been rooted out, which brings a lot of trouble to our society. Only through strengthening user＇s ability to discern, decode and feedback the false information can we maximally understand the information behind. Therefore, devoting ourselves to setting up a framework of detecting the accounting fraud has become a feasible and efficient way to solve this problem. Based on the ＂Three Elements Theory＂, this paper demonstrates a new way to discern the fraud by researching its origins. The authors combine the theoretical model and the applied technology together to design a fraud recognization system.
基金funded by National Natural Science Foun-dation of China(52074165)Natural Science Foundation of Shandong Province(ZR2019ME116)Source Innovation Special Project of Qingdao West Coast New Area(2020-93).
文摘A three-stageflue gas hydrate-based desalination system was designed using liquefied natural gas(LNG)cold energy.This system could increase the CO_(2)amount-of-substance fraction in theflue gas from 17%to 97%and produce desalinated water with a desalting rate of approximately 95%.Four system operating plans were simulated as follows:CO_(2)+N_(2)+seawater at 0.6 MPa,CO_(2)+N_(2)+seawater at 3 MPa,CO_(2)+N_(2)+tetra-n-butyl ammonium bromide(TBAB)+seawater at 0.6 MPa,and CO_(2)+N_(2)+tetrahydrofuran(THF)+seawater at 0.6 MPa.The energy consumption,LNG cold energy consumption,energy loss,and environmental friendliness were calculated and analyzed.The compression energy consumption was the highest contributor to the total energy consumption,and the highest percentage of total energy loss was heat exchange loss.Reducing the formation pressure in thefirst stage effectively reduced the total energy consumption,LNG cold energy consumption,and energy loss by 21.28%,24.41%,and 23.99%,respectively.Addition of TBAB/THF reduced the total energy consumption,LNG cold energy consumption,and energy loss by 18.45%/17.88%,32.30%/32.73%,and 24.65%/23.54%,respectively.The CO_(2)+CO_(2)+N_(2)+seawater operation at 0.6 MPa did not produce pollution.The CO_(2)+N_(2)+seawater operation at 3 MPa had the highest total energy consumption and LNG cold energy consumption.Operation with TBAB/THF had obvious advantages in terms of total energy consumption but suffered from the generation of pollution.Comprehensive analysis indicated that the CO_(2)+N_(2)+seawater operation at 0.6 MPa was the optimum system.
基金The financial support of National Natural Science Foundation of China(Grant Nos.51908288 and 42002266)the project of Key Laboratory of Impact and Safety Engineering(Ningbo University),Ministry of Education is appreciated.
文摘Liquefaction of sandy soils is a big threat to the stability and the safety of an earth embankment laid on saturated soils.A large number of liquefaction-induced damages on embankment due to different types of earthquakes have been reported worldwide.In this research,the dynamic behaviors of earth embankment and the reinforcement effects of grouting as remediation method,subjected to moderate earthquake EQ1 and strong earthquake EQ2,were numerically investigated.The seismic behaviors of ground composed of cohesionless sandy soil and cohesive clayey soil were uniformly described by the cyclic mobility(CM)model,which is capable of describing accurately the mechanical property of the soil due to monotonic and cyclic loadings by accounting for stress-induced anisotropy,over-consolidation,and soil structure.It is known from the numerical investigation that the embankment would experience destructive deformation,and that the collapse mode was closely related to the properties of input seismic motion because high intensities and long durations of an earthquake motion could lead to significant plastic deformation and prolonged soil liquefaction.Under the strong seismic loading of EQ2,a circular collapse surface,combined with huge settlement and lateral spread,occurred inside the liquefication zone and extended towards the embankment crest.In contrast,in moderate earthquake EQ1,upheaval was observed at each toe of the embankment,and instability occurred only in the liquefied ground.An anti-liquefaction remediation via grouting was determined to significantly reduce liquefaction-induced deformation(settlement,lateral spreading,and local uplift)and restrain the deep-seated circular sliding failure,even though the top sandy soil liquefied in both earthquakes.When the structure was subjected to EQ2 motion,local failure occurred on the embankment slope reinforced with grouting,and thus,an additional appropriate countermeasure should be implemented to further strengthen the slope.For both input motions,the surface deformation of the considered embankment decreased gradually as the thickness of reinforcement was increased,although the reinforcement effect was no longer significant once the thickness exceeded 6 m.
