In view of the failure of GNSS signals,this paper proposes an INS/GNSS integrated navigation method based on the recurrent neural network(RNN).This proposed method utilizes the calculation principle of INS and the mem...In view of the failure of GNSS signals,this paper proposes an INS/GNSS integrated navigation method based on the recurrent neural network(RNN).This proposed method utilizes the calculation principle of INS and the memory function of the RNN to estimate the errors of the INS,thereby obtaining a continuous,reliable and high-precision navigation solution.The performance of the proposed method is firstly demonstrated using an INS/GNSS simulation environment.Subsequently,an experimental test on boat is also conducted to validate the performance of the method.The results show a promising application prospect for RNN in the field of positioning for INS/GNSS integrated navigation in the absence of GNSS signal,as it outperforms extreme learning machine(ELM)and EKF by approximately 30%and 60%,respectively.展开更多
Recently, two dimensional In Se attracts great attentions as potential hydrogen production photocatalysts.Here, comprehensive investigations on the hydrogen evolution reaction activity of In Se monolayer with3 d trans...Recently, two dimensional In Se attracts great attentions as potential hydrogen production photocatalysts.Here, comprehensive investigations on the hydrogen evolution reaction activity of In Se monolayer with3 d transition metal doping and biaxial strain were performed based on the density functional theory.Transition metal dopants significantly increase the bonding strength between H and Se, and then adjust the hydrogen adsorption free energy to 0.02 e V by Zn doping. The enhanced hydrogen evolution reaction activity results from less electron occupying H 1 s-Se 4 pzanti-bonding states, which is well correlated with the pzband center level. Importantly, the universal scalling law was proposed to descript the evolution of hydrogen adsorption free energy including both doping and strain effects. Moreover, with appropriate band alignment, optical absorption, and carriers separation ability, Zn doped In Se monolayer is considered as a promising candidate of visible-light photocatalyst for hydrogen production.展开更多
A neural adaptive proportion sum differential (PSD) algorithm with errors prediction is researched. It is applied in inertial navigation system(INS) temperature control. The algorithm do not need the process's pre...A neural adaptive proportion sum differential (PSD) algorithm with errors prediction is researched. It is applied in inertial navigation system(INS) temperature control. The algorithm do not need the process's precise mathematical model and can adapt to the process parameters changing, and can deal with the process with nonlinearity. According to the Smith predictor, author developed a method that takes the predicted process error and error change as neural adaptive PSD algorithm's input. The method is effective to the system with long dead time. The results of compute simulation show that this system has characters of quickly reaction, low overshoot and good stability. It can meet the requirements of temperature control of INS.展开更多
基金supported in part by the National Natural Science Foundation of China(No.41876222)。
文摘In view of the failure of GNSS signals,this paper proposes an INS/GNSS integrated navigation method based on the recurrent neural network(RNN).This proposed method utilizes the calculation principle of INS and the memory function of the RNN to estimate the errors of the INS,thereby obtaining a continuous,reliable and high-precision navigation solution.The performance of the proposed method is firstly demonstrated using an INS/GNSS simulation environment.Subsequently,an experimental test on boat is also conducted to validate the performance of the method.The results show a promising application prospect for RNN in the field of positioning for INS/GNSS integrated navigation in the absence of GNSS signal,as it outperforms extreme learning machine(ELM)and EKF by approximately 30%and 60%,respectively.
基金supported by the National Natural Science Foundation of China(11804023)the Natural Science Foundation of Tianjin(18JCQNJC02700)。
文摘Recently, two dimensional In Se attracts great attentions as potential hydrogen production photocatalysts.Here, comprehensive investigations on the hydrogen evolution reaction activity of In Se monolayer with3 d transition metal doping and biaxial strain were performed based on the density functional theory.Transition metal dopants significantly increase the bonding strength between H and Se, and then adjust the hydrogen adsorption free energy to 0.02 e V by Zn doping. The enhanced hydrogen evolution reaction activity results from less electron occupying H 1 s-Se 4 pzanti-bonding states, which is well correlated with the pzband center level. Importantly, the universal scalling law was proposed to descript the evolution of hydrogen adsorption free energy including both doping and strain effects. Moreover, with appropriate band alignment, optical absorption, and carriers separation ability, Zn doped In Se monolayer is considered as a promising candidate of visible-light photocatalyst for hydrogen production.
文摘A neural adaptive proportion sum differential (PSD) algorithm with errors prediction is researched. It is applied in inertial navigation system(INS) temperature control. The algorithm do not need the process's precise mathematical model and can adapt to the process parameters changing, and can deal with the process with nonlinearity. According to the Smith predictor, author developed a method that takes the predicted process error and error change as neural adaptive PSD algorithm's input. The method is effective to the system with long dead time. The results of compute simulation show that this system has characters of quickly reaction, low overshoot and good stability. It can meet the requirements of temperature control of INS.
