Abstract: The present disclosure provides techniques to identify material properties from measured physical response data in ways that are more efficient than conventional numerical inversion. Systems and techniques of the present disclosure may use machine learning (ML) techniques to generate mappings that map specific physical responses to specific material properties based on knowledge of factors that may be inherent to certain types of sensing equipment. Data generated by a ML computer model may be constrained, altered, or filtered to more closely correspond to characteristics known to be associated with a certain type of sensing equipment. Such a constrained model may identify fewer possible results as compared to an unconstrained model, thereby, solving problems that may be encountered when using ML techniques to identify material properties from measured responses.

Abstract: A transition in the fluid composition of a production fluid is detectable downhole based on a rotational response of a rotor through which flow is directed. The transition is detectable, at least in part, based on different rotational speeds of different fluid compositions. The transition may be detected or confirmed by an anomaly in the rotational response (e.g., a temporary dip) due to an emulsion between two or more fluid components. The non-Newtonian behavior of the emulsion makes its presence easily detectable in a rotor chamber. The disclosed principles may enable a rotor to act not only as a power source but as a water cut sensor.

Abstract: A system, method, and apparatus for ameliorating deposits in selective catalytic reduction systems for the reduction of nitrogen oxide emissions in steam methane reformers. The system includes positioning a dual stage refractory particulate (RP) filter placed in an upstream airflow from a Selective Catalytic Reduction System (SCRS). The first stage is formed of a perforated steel plate with a second stage formed of a wire mesh screen. The system may employ air cannons to clean each of the first stage and the second stages.

Abstract: A patient support apparatus may include a mattress configured to receive a fluid from a pneumatic system, a graphical user interface, and a controller configured to control the pneumatic system and to communicate with the graphical user interface. The controller may control the graphical user interface to selectively display a home screen comprising a plurality of icons, the icons comprising a mattress function menu icon and a mattress function screen accessible via the mattress function menu icon. The mattress function screen may include at least one control input configured to activate a first state and a second state of the controller.

Abstract: Aspects of the disclosed technology provide solutions for analyzing and interpreting geophysical and petrophysical data and in particular, for using generative machine learning models to characterize and predict reservoir properties. A process of the disclosed technology can include steps for providing a set of formation measurement data to a generative machine learning model and generating, via the generative machine learning model, a set of latent space data corresponding to the set of formation measurement data. The process can further include steps for clustering the set of latent space data to generate a set of clusters and determining a petrophysical interpretation based on the clusters. Systems and machine-readable media are also provided.

Abstract: A method includes receiving subject training data comprising a plurality of images of subjects in a plurality of positions on a person support apparatus, labeling the plurality of images based on the positions of the subjects to generate labeled subject training data, generating synthetic training data comprising computer generated images of artificial subjects in a plurality of positions on an artificial person support apparatus, labeling the synthetic training data based on the positions of the artificial subjects to generate labeled synthetic training data, and training a machine learning model based on the labeled subject training data and the labeled synthetic training data, using supervised learning techniques, to generate a trained model to predict a subject position based on an image of the subject.

Abstract: The present disclosure teaches systems and methods for robotic welding of studs onto the surface of I-beams. The systems and methods use machine vision to identify and locate welding sites on a surface of a beam or girder, moves and aligns studs to the welding sites, and welds studs to the surface at these sites.

Abstract: One disclosed system includes a processor, a network interface in communication with the processor, a data storage device in communication with the processor, and computer-executable instructions stored in computer storage. The instructions are configured, when executed by the processor, to cause computer hardware to perform operations comprising: (1) matching a consumer lead comprising information about a consumer with one or more vendors selected from a set of vendors identified in data records stored on the data storage device; (2) sending, via the network interface, the lead to the matched vendors; (3) receiving a real-time indication of a rejection from one of the matched vendors; (4) matching the lead with a replacement vendor; and (5) sending the lead to the replacement vendor.

Abstract: An electric submersible pump (ESP) assembly. The ESP assembly comprises an electric motor; a seal section coupled to an uphole end of the electric motor; a fluid intake coupled to an uphole end of the seal section, wherein the fluid intake defines a plurality of inlet ports; a gas separator coupled to an uphole end of the fluid intake, wherein the gas separator has a plurality of gas phase discharge ports; a pump assembly coupled to an uphole end of the gas separator; and an intake extension tubular, wherein an uphole end of the intake extension tubular is coupled to the fluid intake uphole of the inlet ports, and wherein an annulus defined between an inside of the intake extension tubular and an outside of the seal section defines a fluid flow path from a downhole end of the intake extension tubular to the inlet ports of the fluid intake.

Abstract: A system for delivering a fluid to a fluid consuming asset having a fluid tank is disclosed. An inlet of a manifold is fluidically coupled to a storage tank that contains the fluid to be delivered. A first distal end of a fluid transporting mechanism is fluidically coupled to an outlet of the manifold. A second distal end of the fluid transporting mechanism is fluidically coupled to the fluid tank. A primary valve is fluidically coupled to the fluid transporting mechanism and restricts fluid flow to the fluid tank when fluid level in the fluid tank reaches a first fluid level threshold. A secondary valve is fluidically coupled to the fluid transporting mechanism and restricts fluid flow to the fluid tank when fluid level in the fluid tank reaches a second fluid level threshold. The first fluid level threshold is lower than the second fluid level threshold.

Abstract: Apparatus and methods for measuring the oil to water ratio of a wellbore fluid. An example method includes flowing the wellbore fluid into a flow path of a fluid identification device disposed on the outside of a wellbore tubing and within a wellbore annulus. The fluid identification device comprises a shroud, the flow path disposed within the shroud that opens to the wellbore annulus and fluidically links the wellbore annulus to the wellbore tubing thereby allowing fluid flow through the flow path from the wellbore annulus to the wellbore tubing, and an alternating current electrical sensor disposed within the flow path. The method further includes measuring a property of the wellbore fluid with the alternating current electrical sensor when the wellbore fluid has flowed into the flow path and determining the oil to water ratio of the wellbore fluid that flowed through the flow path.

Abstract: In some embodiments, a method includes selecting a flip angle of refocusing pulses of a pulse sequence equal to a tip angle of an excitation pulse of the pulse sequence, wherein the flip angle is selected based on a lateral motion parameter of a nuclear magnetic resonance (NMR) sensor of a logging tool positioned in a wellbore formed in a subsurface formation. The method further includes emitting, from a transmitter of the logging tool into the subsurface formation, the pulse sequence comprising the tip angle and selected flip angle, and acquiring, by the NMR sensor, transversal NMR relaxation data generated in response to the emitted pulse sequence. The method also includes processing the transversal NMR relaxation data to assess a petrophysical parameter.

Abstract: An array of sensors provided on the outside of a tubular string for measuring a property within the tubular string. The array of sensors may include a plurality of connected sensors, wherein at least one of the plurality of connected sensors is at least partially encompassed in a shroud. A snorkel line may extend from the shroud, the snorkel line capable of coupling with a sensor port in a tubular of the tubular string. The snorkel line may establish fluid communication between one of the sensors at least partially encompassed in the shroud and a corresponding sensor port of a tubular in the tubular string.

Abstract: A system and a method for a look-ahead drill bit. The system may comprise an ultra-deep transmitter operable to transmit a low frequency signal into a formation, a shallow tool operable to transmit a high frequency signal into the formation, at least one ultra-deep receiver operable to record a reflected low frequency signal, and at least one pair of collocated receivers, wherein the at least one pair of collocated receivers are operable to record a reflected high frequency signal. A method may comprise transmitting a high frequency signal from the shallow tool into the formation, transmitting a low frequency signal from the ultra-deep transmitter into the formation, evaluating the reflected high frequency signal and the reflected low frequency signal on an information handling system with a look-ahead inversion, and steering the bottom hole assembly in the formation based on the subterranean formation property.

Abstract: A seal includes an outer housing and a seal bag internal to the outer housing. The outer housing can be positioned between a pump and an electric motor of an electric submersible pump. The seal bag can include an outer layer and an inner layer. The outer layer can be made from a first material to retain a structure of the outer layer in a swellable state in a wellbore. The inner layer can be made from a second material that is swellable in the wellbore in response to contact with a polar substance to seal a tear in the outer layer.

Abstract: A system and method that includes a server computer which receives one or more vehicle inspection results including at least one of: an issue notification identifying an issue with an interior or exterior component of a vehicle or a driver certification that a vehicle is operable. If an issue notification is received, then a report of the issue is transmitted from the server computer to a maintenance information device and, in response, a maintenance certification that the vehicle is operable is received by the server computer from the maintenance information device. Responsive to receiving the driver certification or the maintenance certification, the server computer automatically selects the associated vehicle for a particular route service and the vehicle is assigned to perform the particular route service based on a request received by the server computer.

Abstract: A wheel and tire assembly for material handling machines for selective operation on or off rails include a monolithic, tubular wheel body divided into an inner tire mounting section and an outer rail engaging section. The tire mounting section is bounded by an inner rim projecting around an inner end of the wheel body and an outer rim projecting radially outward around the wheel body medially between the inner and outer ends thereof. A tire is securable around the wheel between the inner and outer rims. A rail engaging flange projects radially outward from the wheel body in outwardly spaced relation from the outer rim in a spacing adapted for reception of a rail, such as a rail formed on an upper end of a rail car sidewall therebetween.

Abstract: A linear escapement mechanism is provided for actuating a downhole tool in a controlled and predictable manner, such as in response to a certain number of pressure cycles. In an example, the actuator includes an escapement sleeve moveable with respect to an actuator housing. The escapement sleeve has a plurality of escapement teeth. A rocker secured within the actuator housing has opposing first and second pallets. An operating sleeve is reciprocable to rock the rocker back and forth to alternately move the opposing first and second pallets into engagement with the escapement sleeve as the escapement sleeve advances in an actuating direction.

Abstract: Systems and methods for operating a distributed acoustic sensing (DAS) system are disclosed that process the DAS signal by downsampling the received signal and stacking the channels, generating a plurality of sliding windows of the processed signal, analyzing the windows to either identify a microseismic event or determine that the window contains only noise, then discarding all noise windows. A convolutional neural network is used to determine an onset time and a peak channel of each microseismic event and to reduce the dimensionality of the data in time and space around the onset time. A convolutional neural network is used to identify a first arrival pick within the truncated window of all recorded phases, which are then used to determine the physical location of the source fracture.

Abstract: Provided is a patient management system for sharing patient data between and among devices. A first device of a patient management system may receive, from a second device, an indication of the presence of the second device. Based at least in part on sending a request for the patient identifier to a server for information related to the second device, the first device may receive the patient identifier. The first device may then receive, from a third device, a request for the patient identifier. Based on determining that the third device is within a threshold distance from the first device, the first device may send the patient identifier to the third device.