Abstract: A method for pulling casing includes disposing a casing modification and pulling tool having an element therein that includes a profile, causing the element to move radially outwardly into contact with a casing disposed radially outwardly of the tool, deforming the casing with the element, applying a load to the casing, and failing the casing at the deformation. A system for pulling casing includes a casing modification tool having an element radially displaceable into a casing disposed radially outwardly thereof, the element configured to deform the casing, a casing spear operably connected to the casing modification tool, the spear configured to apply a load to the casing to fail the casing at the deformation. A borehole system includes a borehole in a subsurface formation, a casing disposed in the borehole, and a casing modification and pulling tool disposed in the casing.

Abstract: Disclosed herein is an image deep learning model training method. The method includes sampling a twin negative comprising a first negative sample and a second negative sample by selecting the first negative sample with a highest similarity out of an anchor sample and a positive sample constituting a matching pair in each class and by selecting the second negative sample with a highest similarity to the first negative sample, and training the samples to minimize a loss of a loss function in each class by utilizing the anchor sample, the positive sample, the first and second negative samples for each class. The first negative sample is selected in a different class from a class comprising the matching pair, and the second negative sample is selected in a different class from classes comprising the matching pair and the first negative sample.

Abstract: Disclosed herein are an apparatus and method for detecting a keypoint based on deep learning robust to scale changes based on information change across receptive fields. The apparatus for detecting a keypoint based on deep learning robust to scale changes based on information change across receptive fields includes a feature extractor for extracting a feature from an input image based on a pre-trained deep learning neural network, an information accumulation pyramid module for outputting, from the feature, at least two filter responses corresponding to receptive fields having different scales, an information change detection module for calculating an information change between the at least two filter responses, a keypoint detection module for creating a score map having a keypoint probability of each pixel based on the information change, and a continuous scale estimation module for estimating a scale of a receptive field having a biggest information change for each pixel.

Abstract: A single-trip cut and pull system for a wellbore including a cutter, a power section, and an anchor selectively actuable independently of the power section; a method for cutting and pulling casing in a single run including running a cut and pull system on a string to a target depth, rotating a cutter of the cut and pull system to cut a casing section, and actuating an anchor of the cut and pull system after cutting the casing section; and a method for cutting and pulling casing in a single run including running a cut and pull system on a string to a target depth, rotating a cutter of the cut and pull system by rotating the string to cut a casing section, and pulling the cut casing in the single run.

Abstract: A single-trip cut and pull system for a wellbore including a cutter, a power section, and an anchor selectively actuable independently of the power section; a method for cutting and pulling casing in a single run including running a cut and pull system on a string to a target depth, rotating a cutter of the cut and pull system to cut a casing section, and actuating an anchor of the cut and pull system after cutting the casing section; and a method for cutting and pulling casing in a single run including running a cut and pull system on a string to a target depth, rotating a cutter of the cut and pull system by rotating the string to cut a casing section, and pulling the cut casing in the single run.

Abstract: Disclosed herein is an image deep learning model training method. The method includes sampling a twin negative comprising a first negative sample and a second negative sample by selecting the first negative sample with a highest similarity out of an anchor sample and a positive sample constituting a matching pair in each class and by selecting the second negative sample with a highest similarity to the first negative sample, and training the samples to minimize a loss of a loss function in each class by utilizing the anchor sample, the positive sample, the first and second negative samples for each class. The first negative sample is selected in a different class from a class comprising the matching pair, and the second negative sample is selected in a different class from classes comprising the matching pair and the first negative sample.

Abstract: A combination tool allows delivery of a tool such as a packer or bridge plug with a variety of well cleanup tools that are retracted for running in. Once in the vicinity of where the plug or packer is to be set or if an internal diameter is to be targeted using clean up tools after passing a restriction, an inner mandrel can be activated such as in conjunction with a j-slot to selectively extend one or more cleaning tools against the force of a return spring out though openings in an outer housing. Circulation is established either through an open port or by opening a circulation port with mandrel movement. Just the zone near where the packer or bridge plug is to be set is cleaned. The cleaning tools retract after use with further mandrel movement. The packer or plug is picked up into position and set and the bottom hole assembly is removed. The plug or packer can be set in a variety of ways.

Abstract: The sequential compression device for treatment and prophylaxis of deep vein thromboses includes a compression sock having a plurality of electromechanical units positioned along the calf muscle of a user's leg. Each of the electromechanical units includes a front housing component and a back housing component. The front housing component of the unit includes a compressor piston positioned in communicating relation with the user's calf muscle and the back housing component of the unit includes a magnet and a copper coil. The magnet is positioned in communicating relation with the compressor piston of the front housing component. Upon activation, the compressor piston selectively compresses the small saphenous vein to simulate the effect of the calf muscle during walking and promote the flow of blood back to the user's heart.

Abstract: The storage tank cleaning machine is a mobile unit mounted on a trailer for towing by a suitable vehicle. The machine is positioned adjacent the access opening of the tank, e.g., a water tank, cistern, or other storage tank, and a support on the bed of the machine is raised to vertical over the opening. A multiple segment articulating arm extends from the support and is lowered through the opening to access the interior of the tank. A motorized rotary brush extends from the distal end of the arm. Distance sensors adjacent the brush detect the interior surfaces of the tank for accurately positioning the brush. An electronic control system is provided. A tank for water and/or other cleaning fluid and a disinfectant tank are also provided. Fluids used during the cleaning operation are suctioned back to the machine, where the fluids are cleaned and recycled.

Abstract: A valve and method of use wherein the valve includes a housing having an axial flowbore defined along its length. A lateral fluid flow port is disposed through the housing. A piston sleeve is disposed within the flowbore and is selectively moveable to block flow through the lateral flow port. The valve can be moved between operating positions wherein flow through the lateral flow port is blocked or allowed and axial flow through the flowbore is blocked or permitted.

Abstract: A valve and method of use wherein the valve includes a housing having an axial flowbore defined along its length. A lateral fluid flow port is disposed through the housing. A piston sleeve is disposed within the flowbore and is selectively moveable to block flow through the lateral flow port. The valve can be moved between operating positions wherein flow through the lateral flow port is blocked or allowed and axial flow through the flowbore is blocked or permitted.