Searching for maritime moving targets using satellites is an attracting but rather difficult problem due to the satellites' orbits and discontinuous visible time windows.From a long term cyclic view,a non-myopic m...Searching for maritime moving targets using satellites is an attracting but rather difficult problem due to the satellites' orbits and discontinuous visible time windows.From a long term cyclic view,a non-myopic method based on reinforcement learning(RL)for multi-pass multi-targets searching was proposed.It learnt system behaviors step by step from each observation which resulted in a dynamic progressive way.Then it decided and adjusted optimal actions in each observation opportunity.System states were indicated by expected information gain.Neural networks algorithm was used to approximate parameters of control policy.Simulation results show that our approach with sufficient training performs significantly better than other myopic approaches which make local optimal decisions for each individual observation opportunity.展开更多
Wedge-shaped copper casting experiment was conducted to study the engulfment behavior of TiB2 particle and the interaction between particle or cluster and the solid/liquid front in commercial pure aluminum matrix. The...Wedge-shaped copper casting experiment was conducted to study the engulfment behavior of TiB2 particle and the interaction between particle or cluster and the solid/liquid front in commercial pure aluminum matrix. The experimental results show that the particle size distribution obeys two separate systems in the whole wedge-cast sample. Furthermore, it is found that the big clusters are pushed to the center of the wedge shaped sample and the single particle or small clusters consisting of few particles are engulfed into the α-Al in the area of the sample edge. The cluster degree of particles varies in different areas, and its value is 0.2 and 0.6 for the cluster fraction in the edge and in the center of the wedge sample, respectively. The cluster diameter does not obey the normal distribution but approximately obeys lognormal distribution in the present work. More importantly, in the whole sample, the particle size obeys two separate log-normal distributions.展开更多
基金National Natural Science Foundation of China(No.61203180)
文摘Searching for maritime moving targets using satellites is an attracting but rather difficult problem due to the satellites' orbits and discontinuous visible time windows.From a long term cyclic view,a non-myopic method based on reinforcement learning(RL)for multi-pass multi-targets searching was proposed.It learnt system behaviors step by step from each observation which resulted in a dynamic progressive way.Then it decided and adjusted optimal actions in each observation opportunity.System states were indicated by expected information gain.Neural networks algorithm was used to approximate parameters of control policy.Simulation results show that our approach with sufficient training performs significantly better than other myopic approaches which make local optimal decisions for each individual observation opportunity.
文摘Wedge-shaped copper casting experiment was conducted to study the engulfment behavior of TiB2 particle and the interaction between particle or cluster and the solid/liquid front in commercial pure aluminum matrix. The experimental results show that the particle size distribution obeys two separate systems in the whole wedge-cast sample. Furthermore, it is found that the big clusters are pushed to the center of the wedge shaped sample and the single particle or small clusters consisting of few particles are engulfed into the α-Al in the area of the sample edge. The cluster degree of particles varies in different areas, and its value is 0.2 and 0.6 for the cluster fraction in the edge and in the center of the wedge sample, respectively. The cluster diameter does not obey the normal distribution but approximately obeys lognormal distribution in the present work. More importantly, in the whole sample, the particle size obeys two separate log-normal distributions.
