Aiming at the research on mechanical mechanism of hard-inclusion earthquake preparation model, in this paper,experimental and contrast research on stress field and rupture feature of hard-inclusion model has been made...Aiming at the research on mechanical mechanism of hard-inclusion earthquake preparation model, in this paper,experimental and contrast research on stress field and rupture feature of hard-inclusion model has been made respectively, which contained en echelon and composite cracks systems in models, and was loaded under uniaxial compressive stress. The result shows that reverse en echelon and T-shape cracks systems in hard-inclusion are the favorable geological structures to trigger earthquakes.展开更多
Through calculating and analyzing of GPS continuous observation data and mobile gravity data,the study results from the data are as follows.( 1) The different movement rate of the fault ends provides conditions for st...Through calculating and analyzing of GPS continuous observation data and mobile gravity data,the study results from the data are as follows.( 1) The different movement rate of the fault ends provides conditions for stress accumulation.( 2) The high value zone of gravity anomaly appeared in the monitoring area before the earthquake,and gravity variation contour lines are parallel to the strike of fault; and the process of enhancingweakening-enhancing appeared in the regional gravity field before earthquake.展开更多
The automatic identification of underwater noncooperative targets without label records remains an arduous task considering the marine noise interference and the shortage of labeled samples.In particular,the data-driv...The automatic identification of underwater noncooperative targets without label records remains an arduous task considering the marine noise interference and the shortage of labeled samples.In particular,the data-driven mechanism of deep learning cannot identify false samples,aggravating the difficulty in noncooperative underwater target recognition.A semi-supervised ensemble framework based on vertical line array fusion and the sparse adversarial co-training algorithm is proposed to identify noncooperative targets effectively.The sound field cross-correlation compression(SCC)feature is developed to reduce noise and computational redundancy.Starting from an incomplete dataset,a joint adversarial autoencoder is constructed to extract the sparse features with source depth sensitivity,aiming to discover the unknown underwater targets.The adversarial prediction label is converted to initialize the joint co-forest,whose evaluation function is optimized by introducing adaptive confidence.The experiments prove the strong denoising performance,low mean square error,and high separability of SCC features.Compared with several state-of-the-art approaches,the numerical results illustrate the superiorities of the proposed method due to feature compression,secondary recognition,and decision fusion.展开更多
文摘Aiming at the research on mechanical mechanism of hard-inclusion earthquake preparation model, in this paper,experimental and contrast research on stress field and rupture feature of hard-inclusion model has been made respectively, which contained en echelon and composite cracks systems in models, and was loaded under uniaxial compressive stress. The result shows that reverse en echelon and T-shape cracks systems in hard-inclusion are the favorable geological structures to trigger earthquakes.
基金funded by the Xinjiang Earthquake Science Foundation,China(201211)
文摘Through calculating and analyzing of GPS continuous observation data and mobile gravity data,the study results from the data are as follows.( 1) The different movement rate of the fault ends provides conditions for stress accumulation.( 2) The high value zone of gravity anomaly appeared in the monitoring area before the earthquake,and gravity variation contour lines are parallel to the strike of fault; and the process of enhancingweakening-enhancing appeared in the regional gravity field before earthquake.
基金the National Natural Science Foundation of China(No.6210011631)in part by the China Postdoctoral Science Foundation(No.2021M692628)。
文摘The automatic identification of underwater noncooperative targets without label records remains an arduous task considering the marine noise interference and the shortage of labeled samples.In particular,the data-driven mechanism of deep learning cannot identify false samples,aggravating the difficulty in noncooperative underwater target recognition.A semi-supervised ensemble framework based on vertical line array fusion and the sparse adversarial co-training algorithm is proposed to identify noncooperative targets effectively.The sound field cross-correlation compression(SCC)feature is developed to reduce noise and computational redundancy.Starting from an incomplete dataset,a joint adversarial autoencoder is constructed to extract the sparse features with source depth sensitivity,aiming to discover the unknown underwater targets.The adversarial prediction label is converted to initialize the joint co-forest,whose evaluation function is optimized by introducing adaptive confidence.The experiments prove the strong denoising performance,low mean square error,and high separability of SCC features.Compared with several state-of-the-art approaches,the numerical results illustrate the superiorities of the proposed method due to feature compression,secondary recognition,and decision fusion.
