Search

In recent years, the research of face age features has achieved rapid development driven by deep learning. The faces generated by the Conditional Adversarial Auto-encoder (CAAE) model are not only highly credible, but also closer to the target age. However, there are many problems, such as low resolution of human face image generation and poor local feature retention effect of human face features. To this end, this paper improves on the CAAE network. Firstly, referring to the LSGAN network structure, the 4 convolution layers of the encoder are added to 5 layers and the 4 convolution layers of the generator are added to 7 layers. Secondly, on the basis of the original loss function, the image gradient difference loss function is added to ensure the output face image quality. Meanwhile, the data set were preprocessed for face correction. Finally, this paper performs face similarity analysis on the Eye-key platform and contrasts the generated image quality using structural similarity and peak signal to noise ratio metrics. In addition, the generated results were tested for their robustness. The experimental results show that the average similarity of faces generated by the Improved Conditional Adversarial Auto-encoder (I-CAAE) network was increased by 3.9. And the average peak signal to noise ratio of the generated pictures was reduced by 1.8. Confirming the superiority of the proposed method. &nbsp

Low permeability reservoir has low permeability and slow seepage velocity, long shut-in time affect well production, but too short shut-in testing time will cause strong multi-solution of interpretation results since the effects of skin effect and well storage effect. In order to improve the reliability of well test interpretation, shorten the shut-in time and reduce the production loss, this paper gives the determination method of conventional shut-in time based on the pressure buildup curve, considering the influence of wellbore storage effect and skin effect. Considering the influence of boundary or oil supply radius on shut-in time, the mathematical model of detection radius and shut-in time is obtained by pressure buildup semi-log plot regression. The determination method of reasonable shut-in time for low permeability reservoir is given: The minimum value of reasonable shut-in time and adjacent well interference time is adopted. Based on the analysis and interpretation of Block A and B in an oilfield, the reasonable shut-in time of the two blocks is given. The reasonable shut-in time determined by this method in this paper can guide the effective implementation of well test program and deepen the understanding of the dynamic characteristics of low permeability reservoirs.

Waste semi-coke powder generated in semi-coke production and transportation was doped with 8 mass% boron by a high temperature treatment at 2300 °C. Results indicate that the doping overcomes the shortcomings of low coulombic efficiency, short cycle life, and there are no charge and discharge platforms due to a high content (15 mass%) of impurity in the raw materials. The first discharge capacity is 361 mAh/g at a rate of 0.1 C and the reversible capacity is 314 mAh/g after 300 cycles at charge and discharge rates of 1 C, showing excellent cycling performance. [New Carbon Materials 2014, 29(6): 503–507]