Abstract: Structures can be formed downhole by accumulating already existing materials and/or materials introduced into a well to perform a specified function. The formed structures may be used to obstruct fluid flow of production or injection fluids, carry mechanical loads, control electrical or magnetic properties of components, mechanically actuate a component, as well as others. The materials may be induced to form the specified structure, such as by application of a potential downhole. For example, electrical, magnetic, sonic, biological potentials, or a combination thereof may be established downhole to form specified structures in specified locations to perform specified functions.

Abstract: A system for variably resisting flow of a fluid composition can include a flow passage and a set of one or more branch passages which intersect the flow passage, whereby a proportion of the fluid composition diverted from the passage to the set of branch passages varies based on at least one of a) viscosity of the fluid composition, and b) velocity of the fluid composition in the flow passage. Another variable flow resistance system can include a flow path selection device that selects which of multiple flow paths a majority of fluid flows through from the device, based on a ratio of desired fluid to undesired fluid in the fluid composition. Yet another variable flow resistance system can include a flow chamber, with a majority of the fluid composition entering the chamber in a direction which changes based on a ratio of desired fluid to undesired fluid in the fluid composition.

Abstract: A downhole oil and water separator for an oil well includes a water-selective membrane disposed in a production flowpath of the well. The water-selective membrane is operable to selectively pass water from the production flowpath to a disposal zone to increase the concentration of oil in the production flowpath at the surface.

Abstract: Construction of well screens utilizing pre-formed annular-shaped elements. A well screen includes a filter layer configured to filter fluid flowing through the well screen and a drainage layer which radially supports the filter layer, the drainage layer including multiple individual annular-shaped elements Another well screen includes a drainage layer configured to support the filter layer, with the drainage layer including at least one cavity molded therein. Another well screen includes a base pipe and a layer made up of multiple individual annular-shaped elements stacked coaxially on the base pipe. A cavity is formed in at least one of the elements.

Abstract: A real-time line management system and associated methods. A line management system for use in conjunction with an operation in a subterranean well includes a line installed in the well during the operation, and a computing device which indicates a used life of the line during the operation. A method of managing a line used in an operation in a subterranean well includes the steps of: installing the line in the well during the operation; and determining a used life of the line while the line is installed in the well. A method of managing a line used in multiple operations in one or more subterranean wells includes the steps of: estimating conditions which will be experienced by the line during a future operation; and predicting before the future operation what a used life of the line will be after the line is used in the future operation.

Abstract: Dimensionality reduction systems and methods facilitate visualization, understanding, and interpretation of high-dimensionality data sets, so long as the essential information of the data set is preserved during the dimensionality reduction process. In some of the disclosed embodiments, dimensionality reduction is accomplished using clustering, evolutionary computation of low-dimensionality coordinates for cluster kernels, particle swarm optimization of kernel positions, and training of neural networks based on the kernel mapping. The fitness function chosen for the evolutionary computation and particle swarm optimization is designed to preserve kernel distances and any other information deemed useful to the current application of the disclosed techniques, such as linear correlation with a variable that is to be predicted from future measurements. Various error measures are suitable and can be used.

Abstract: Methods of creating and using robust neural network ensembles are disclosed. Some embodiments take the form of computer-based methods that comprise receiving a set of available inputs; receiving training data; training at least one neural network for each of at least two different subsets of the set of available inputs; and providing at least two trained neural networks having different subsets of the available inputs as components of a neural network ensemble configured to transform the available inputs into at least one output. The neural network ensemble may be applied as a log synthesis method that comprises: receiving a set of downhole logs; applying a first subset of downhole logs to a first neural network to obtain an estimated log; applying a second, different subset of the downhole logs to a second neural network to obtain an estimated log; and combining the estimated logs to obtain a synthetic log.

Abstract: A device for monitoring the health state of hydrocarbon production equipment is disclosed. The device has a plurality of targets, which are associated with the hydrocarbon production equipment. A record of the initial target positions and/or dimensions relative to the hydrocarbon production equipment is created. A sensor that is compatible with the targets is used to observe the targets and produce a sensor output. An analysis device uses the record of the initial positions, dimensions and the sensor output to determine one or more health state parameters, which may be used to determine the health state of the hydrocarbon production equipment.

Abstract: A separating system for separating a fluid mixture incorporates a smart surface having reversibly switchable properties. A voltage is selectively applied to the smart surface to attract or repel constituents of a fluid mixture, such as oil and water produced from a hydrocarbon well. The smart surface can be used in a conditioner to increase droplet size prior to entering a conventional separator, or the smart surface and other elements of the invention can be incorporated into an otherwise conventional separator to enhance separation. In a related aspect, a concentration sensor incorporating smart surfaces senses concentration of the fluid mixture's constituents.

Abstract: A real-time line management system and associated methods. A line management system for use in conjunction with an operation in a subterranean well includes a line installed in the well during the operation, and a computing device which indicates a used life of the line during the operation. A method of managing a line used in an operation in a subterranean well includes the steps of: installing the line in the well during the operation; and determining a used life of the line while the line is installed in the well. A method of managing a line used in multiple operations in one or more subterranean wells includes the steps of: estimating conditions which will be experienced by the line during a future operation; and predicting before the future operation what a used life of the line will be after the line is used in the future operation.

Abstract: A separating system for separating a fluid mixture incorporates a smart surface having reversibly switchable properties. A voltage is selectively applied to the smart surface to attract or repel constituents of a fluid mixture, such as oil and water produced from a hydrocarbon well. The smart surface can be used in a conditioner to increase droplet size prior to entering a conventional separator, or the smart surface and other elements of the invention can be incorporated into an otherwise conventional separator to enhance separation. In a related aspect, a concentration sensor incorporating smart surfaces senses concentration of the fluid mixture's constituents.

Abstract: A real-time line management system and associated methods. A line management system for use in conjunction with an operation in a subterranean well includes a line installed in the well during the operation, and a computing device which indicates a used life of the line during the operation. A method of managing a line used in an operation in a subterranean well includes the steps of: installing the line in the well during the operation; and determining a used life of the line while the line is installed in the well. A method of managing a line used in multiple operations in one or more subterranean wells includes the steps of: estimating conditions which will be experienced by the line during a future operation; and predicting before the future operation what a used life of the line will be after the line is used in the future operation.

Abstract: Various neural-network based surrogate model construction methods are disclosed herein, along with various applications of such models. Designed for use when only a sparse amount of data is available (a “sparse data condition”), some embodiments of the disclosed systems and methods: create a pool of neural networks trained on a first portion of a sparse data set; generate for each of various multi-objective functions a set of neural network ensembles that minimize the multi-objective function; select a local ensemble from each set of ensembles based on data not included in said first portion of said sparse data set; and combine a subset of the local ensembles to form a global ensemble. This approach enables usage of larger candidate pools, multi-stage validation, and a comprehensive performance measure that provides more robust predictions in the voids of parameter space.

Abstract: An orbital downhole separator for separating well fluids into constituents of different specific gravities. Specifically, it is designed to separate water from oil or gas. The apparatus comprises a housing with a rotating member therein driven by a motor in the housing. Well fluid flows through the rotating member and is subjected to centrifugal force to separate the components. A flow conditioner is used to facilitate separation. The invention includes several different versions of the flow conditioner including an impeller, a stator and controllers for controlling the speed of the motor in response to signals related to the amount of petroleum in the water.

Abstract: A system and method for generating a neural network ensemble. Conventional algorithms are used to train a number of neural networks having error diversity, for example by having a different number of hidden nodes in each network. A genetic algorithm having a multi-objective fitness function is used to select one or more ensembles. The fitness function includes a negative error correlation objective to insure diversity among the ensemble members. A genetic algorithm may be used to select weighting factors for the multi-objective function. In one application, a trained model may be used to produce synthetic open hole logs in response to inputs of cased hole log data.

Abstract: Reservoir characterization based on observations of displacements at the earth's surface. One method of characterizing a reservoir includes the steps of: detecting a response of the reservoir to a stimulus, the stimulus causing a pressure change in the reservoir; and determining a characteristic of the reservoir from the response to the stimulus. The response may be the pressure change which varies periodically over time, or a set of displacements of a surface of the earth. In another example, a method includes the steps of: detecting a set of displacements of the earth's surface corresponding to a pressure change in the reservoir; and determining a characteristic of the reservoir from the surface displacements. In yet another example, a method includes the steps of: detecting a set of displacements of the earth's surface corresponding to a change in volume of the reservoir; and determining a characteristic of the reservoir from the surface displacements.

Abstract: A real-time line management system and associated methods. A line management system for use in conjunction with an operation in a subterranean well includes a line installed in the well during the operation, and a computing device which indicates a used life of the line during the operation. A method of managing a line used in an operation in a subterranean well includes the steps of: installing the line in the well during the operation; and determining a used life of the line while the line is installed in the well. A method of managing a line used in multiple operations in one or more subterranean wells includes the steps of: estimating conditions which will be experienced by the line during a future operation; and predicting before the future operation what a used life of the line will be after the line is used in the future operation.

Abstract: Methods of creating and using robust neural network ensembles are disclosed. Some embodiments take the form of computer-based methods that comprise receiving a set of available inputs; receiving training data; training at least one neural network for each of at least two different subsets of the set of available inputs; and providing at least two trained neural networks having different subsets of the available inputs as components of a neural network ensemble configured to transform the available inputs into at least one output. The neural network ensemble may be applied as a log synthesis method that comprises: receiving a set of downhole logs; applying a first subset of downhole logs to a first neural network to obtain an estimated log; applying a second, different subset of the downhole logs to a second neural network to obtain an estimated log; and combining the estimated logs to obtain a synthetic log.

Abstract: Construction and operation of an oilfield molten salt battery. A battery includes an outer case, an elongated mandrel positioned within the outer case, and the mandrel being an electrical component of the battery. Another battery includes an electrical pickup, and a polymer insulator providing insulation between the outer case and the pickup. A method of charging a battery for use in a subterranean well includes the steps of: providing the battery including an electrolyte, and anode and cathode electrodes, the electrolyte being a molten salt comprising lithium salt, and at least one of the electrodes comprising lithium atoms; positioning the battery within a wellbore; and then charging the battery. Another method includes the steps of: heating the lithium ion molten salt battery; then charging the battery; and then positioning the battery within a wellbore.

Abstract: An erosion resistant crossover which may be used in fracturing and/or gravel packing. In one aspect, a fluid delivery system for use in a subterranean well may comprise a fluid discharge apparatus including a flow passage, at least one discharge opening for discharging fluid from the flow passage to an exterior of the apparatus, and a flow diversion device operative to more evenly distribute flow through the opening by diverting fluid flow through the opening in a more upstream direction relative to fluid flow through the passage.