|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | A guidance method for coplanar orbital interception based on reinforcement learning显示文摘This paper investigates the guidance method based on reinforcement learning(RL)for the coplanar orbital interception in a continuous low-thrust scenario.The problem is formulated into a Markov decision process(MDP)model,then a welldesigned RL algorithm,experience based deep deterministic policy gradient(EBDDPG),is proposed to solve it.By taking the advantage of prior information generated through the optimal control model,the proposed algorithm not only resolves the convergence problem of the common RL algorithm,but also successfully trains an efficient deep neural network(DNN)controller for the chaser spacecraft to generate the control sequence.Numerical simulation results show that the proposed algorithm is feasible and the trained DNN controller significantly improves the efficiency over traditional optimization methods by roughly two orders of magnitude. | ZENG Xin ZHU Yanwei YANG Leping ZHANG Chengming | 2021 | Journal of Systems Engineering and Electronics2021，32，4： | 2 |
| 2 | Spatiotemporal alterations of presynaptic elements in the retina after high intraocular pressure显示文摘A rat model of acute high intraocular pressure was established by injecting saline into the anterior chamber of the left eye.Synaptophysin expression was increased in the inner plexiform layer at 2 hours following injury,and was widely distributed in the outer plexiform layer at 3-7 days,and then decreased to the normal level at 14 days.This suggests that expression of this presynaptic functional protein experienced spatiotemporal alterations after elevation of intraocular pressure.There was no significant change in the fluorescence intensity and distribution pattern for synapse-associated protein 102 following elevated intraocular pressure.Synapse-associated protein 102 immunoreactivity was confined to the outer plexiform layer,while synaptophysin immunoreactivity spread into the outer plexiform layer and the outer nuclear layer at 3 and 7 days following injury.These alterations in presynaptic elements were not accompanied by changes in postsynaptic components. | Jufang Huang Lihong Zhou Hui Wang Jia Luo Kun Xiong Leping Zeng Dan Chen | 2012 | Neural Regeneration Research2012，7，16： | 2 |
| 3 | Regulatory effects of inhibiting the activation of glial cells on retinal synaptic plasticity显示文摘Various retinal injuries induced by ocular hypertension have been shown to induce plastic changes in retinal synapses,but the potential regulatory mechanism of synaptic plasticity after retinal injury was still unclear.A rat model of acute ocular hypertension was established by injecting saline intravitreally for an hour,and elevating the intraocular pressure to 14.63 kPa(110 mmHg).Western blot assay and immunofluorescence results showed that synaptophysin expression had a distinct spatiotemporal change that increased in the inner plexiform layer within 1 day and spread across the outer plexiform layer after 3 days.Glial fibrillary acidic protein expression in retinae was greatly increased after 3 days,and reached a peak at 7 days,which was also consistent with the peak time of synaptophysin expression in the outer plexiform layer following the increased intraocular pressure.Fluorocitrate,a glial metabolic inhibitor,was intravitreally injected to inhibit glial cell activation following high intraocular pressure.This significantly inhibited the enhanced glial fibrillary acidic protein expression induced by high intraocular pressure injury.Synaptophysin expression also decreased in the inner plexiform layer within a day and the widened distribution in the outer plexiform layer had disappeared by 3 days.The results suggested that retinal glial cell activation might play an important role in the process of retinal synaptic plasticity induced by acute high intraocular pressure through affecting the expression and distribution of synaptic functional proteins,such as synaptophysin. | Lihong Zhou Hui Wang Jia Luo Kun Xiong Leping Zeng Dan Chen Jufang Huang | 2014 | Neural Regeneration Research2014，9，4： | 2 |
| 4 | Degenerative alterations in noradrenergic neurons of the locus coeruleus in Alzheimer's disease显示文摘Mice carrying mutant amyloid-β precursor protein and presenilin-1 genes (APP/PS1 double transgenic mice) have frequently been used in studies of Alzheimer's disease; however, such studies have focused mainly on hippocampal and cortical changes. The severity of Alzheimer's disease is known to correlate with the amount of amyloid-β protein deposition and the number of dead neurons in the locus coeruleus. In the present study, we assigned APP/PS1 double transgenic mice to two groups according to age: young mice (5-6 months old) and aged mice (16-17 months old). Age-matched wild-type mice were used as controls. Immunohistochemistry for tyrosine hydroxylase (a marker of catecholaminergic neurons in the locus coeruleus) revealed that APP/PS1 mice had 23% fewer cells in the locus coeruleus compared with aged wild-type mice. APP/PS1 mice also had increased numbers of cell bodies of neurons positive for tyrosine hydroxylase, but fewer tyrosine hydroxylase-positive fibers, which were also short, thick and broken. Quantitative analysis using unbiased stereology showed a significant age-related increase in the mean volume of tyrosine hydroxylase-positive neurons in aged APP/PS1 mice compared with young APP/PS1 mice. Moreover, the mean volume of tyrosine hydroxylase-positive neurons was positively correlated with the total volume of the locus coeruleus. These findings indicate that noradrenergic neurons and fibers in the locus coeruleus are predisposed to degenerative alterations in APP/PS1 double transgenic mice. | Lihua Liu Saiping Luo Leping Zeng Weihong Wang Liming Yuan Xiaohong Jian | 2013 | Neural Regeneration Research2013，8，24： | 1 |
| 5 | An effective method of DNA extraction for bioleaching bacteria from acid mine drainage显示文摘 | Leping Zeng Jufang Huang Yanfei Zhang Guanzhou Qiu Jianbin Tong Dan Chen Jin Zhou Xuegang Luo | 2008 | Applied Microbiology and Biotechnology2008，，5： | 1 |
| 6 | An optimal guidance method for free-time orbital pursuit-evasion game显示文摘With the development of space rendezvous and proximity operations(RPO)in recent years,the scenarios with noncooperative spacecraft are attracting the attention of more and more researchers.A method based on the costate normalization technique and deep neural networks is presented to generate the optimal guidance law for free-time orbital pursuit-evasion game.Firstly,the 24-dimensional problem given by differential game theory is transformed into a three-parameter optimization problem through the dimension-reduction method which guarantees the uniqueness of solution for the specific scenario.Secondly,a close-loop interactive mechanism involving feedback is introduced to deep neural networks for generating precise initial solution.Thus the optimal guidance law is obtained efficiently and stably with the application of optimization algorithm initialed by the deep neural networks.Finally,the results of the comparison with another two methods and Monte Carlo simulation demonstrate the efficiency and robustness of the proposed optimal guidance method. | ZHANG Chengming ZHU Yanwei YANG Leping ZENG Xin | 2022 | Journal of Systems Engineering and Electronics2022，33，6： | 0 |
| 7 | A DNN based trajectory optimization method for intercepting non-cooperative maneuvering spacecraft显示文摘Current successes in artificial intelligence domain have revitalized interest in neural networks and demonstrated their potential in solving spacecraft trajectory optimization problems. This paper presents a data-free deep neural network(DNN) based trajectory optimization method for intercepting noncooperative maneuvering spacecraft, in a continuous low-thrust scenario. Firstly, the problem is formulated as a standard constrained optimization problem through differential game theory and minimax principle. Secondly, a new DNN is designed to integrate interception dynamic model into the network and involve it in the process of gradient descent, which makes the network endowed with the knowledge of physical constraints and reduces the learning burden of the network. Thus, a DNN based method is proposed, which completely eliminates the demand of training datasets and improves the generalization capacity. Finally, numerical results demonstrate the feasibility and efficiency of our proposed method. | YANG Fuyunxiang YANG Leping ZHU Yanwei ZENG Xin | 2022 | Journal of Systems Engineering and Electronics2022，33，2： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员