PIPELINE DESCALING AND ROCK STRATUM FRACTURING DEVICE BASED ON ELECTRO-HYDRAULIC PULSE SHOCK WAVES

    公开(公告)号:US20190017362A1

    公开(公告)日:2019-01-17

    申请号:US15749583

    申请日:2016-09-29

    Abstract: The invention discloses a pipeline descaling and rock stratum fracturing device based on electro-hydraulic pulse shock waves, comprising a ground low-voltage control device, a transmission cable and an electro-hydraulic pulse shock wave transmitter. The invention generates available high-strength shock waves with repetition frequency to bombard a specific position of the pipeline or rock stratum so as to achieve the effect of pipeline descaling and rock stratum fracturing; the breakdown field strength of the liquid gap can be effectively reduced to improve the conversion efficiency of the electrical energy to the mechanical energy of the electro-hydraulic pulse shock wave so as to obtain a high-strength electro-hydraulic pulse shock wave; the transmitting cavity adopts a parabolic focusing cavity, and through refraction and reflection of the rotating parabolic cavity, the shock wave is focused in a preset direction and radiates outwards to act on the pipeline dirt or rock stratum while ensuring that the shock wave has no longitudinal component and does not will not damage the liquid within the pipeline and the pipeline sheath, so that the effect of pipeline descaling or rock stratum fracturing is improved after focusing. The invention has the advantages of effectively removing the pipeline dirt, fracturing the rock stratum and improving the permeability as well as high reliability, environmental friendliness and low cost.

    SPATIOTEMPORAL ACTION DETECTION METHOD

    公开(公告)号:US20210248378A1

    公开(公告)日:2021-08-12

    申请号:US16965015

    申请日:2020-01-07

    Abstract: A spatiotemporal action detection method includes performing object detection on all frames of a sample video to obtain a candidate object set; calculating all interframe optical flow information on the sample video to obtain a motion set; constructing a spatiotemporal convolution-deconvolution network of an attention mechanism and a motion attention mechanism of an additional object; adding both a corresponding sparse variable and a sparse constraint to obtain a network structure S after performing spatiotemporal convolution processing on each time segment of the sample video; training the network structure S with an objective function based on classification loss and loss of the sparse constraint of cross entropy; and calculating an action category and a sparse coefficient corresponding to each time segment of a test sampled video to obtain an object action spatiotemporal location.

Patent Agency Ranking