Abstract: Embodiments of determining proppant distribution for a plurality of clusters within a fracture stage of a wellbore are provided herein. The embodiments include performing computational fluid dynamics modeling on at least a portion of a wellbore without any openings and a portion of the wellbore comprising at least one opening along a single azimuth to determine proppant efficiency for the at least one opening along the single azimuth while simulating flow of fluid, proppant, or any combination thereof through the wellbore, an equilibrium proppant concentration profile for the portion of the wellbore without any openings, and an equilibrium velocity profile for the portion of the wellbore without any openings. The embodiment further comprises determining proppant efficiency for at least one other opening of the wellbore at a different azimuth, generating a model that correlates the single azimuth among other items, and using the model to determine the proppant distribution.

Abstract: A battery system includes a lithium ion battery configured to couple to an electrical system, and a battery management system configured to electrically couple to the lithium ion battery and to control one or more recharge parameters of the lithium ion battery. The battery management system is programmed with an electrochemical model, and the battery management system is configured to monitor parameters of the lithium ion battery, and to control the one or more recharge parameters of the lithium ion battery based on the electrochemical model and the one or more monitored parameters. The electrochemical model determines lithium plating reaction kinetics at an anode of the lithium ion battery, determines a quantity of plated lithium at the anode of the lithium ion battery, or both, and indicates a relationship between the one or more monitored parameters and the lithium plating reaction kinetics, the quantity of plated lithium, or both.

Abstract: Parallel processing suitable for convolution operation in a convolutional neural network is executed. Each of a plurality of selectors sequentially selects data, which is held in a two-dimensional shift register, in predetermined two-dimensional regions at least partially different from each other. Each of a plurality of two-dimensional convolution operation circuits multiplies the data selected by the corresponding selector by coefficient data stored in a coefficient memory and accumulates results of the multiplication to calculate, in parallel, two-dimensional convolution operation results in the two-dimensional regions. Each of a plurality of adder circuits adds operation results of the two-dimensional convolution operation circuits in a channel direction to output a three-dimensional convolution operation result.

Abstract: Disclosed are techniques to conserve battery of an endpoint device. Example techniques include adjusting the size of messages transmitted by an endpoint device and/or adjusting the transmission rate of an endpoint device. In some configurations, the one or more criteria are used by an endpoint device to determine what data fields to include within a message and/or adjust a transmission rate associated with the transmission of messages by the endpoint device. For instance, the one or more criteria may include the battery level of the device, the time of year, whether the data has already been transmitted by the endpoint device, whether the data has been acknowledged as received by another device, whether the endpoint device has been instructed by another device to reduce the message size and/or adjust the transmission rate, and the like.

Abstract: A device receives first well data associated with first wells where plunger lift is installed, and receives second well data associated with a candidate well where plunger lift is not installed. The device processes the first well data to determine pre-plunger lift installation data associated with the first wells, and processes the first well data and the pre-plunger lift installation data to determine a set of performing wells and a set of underperforming wells, of the first wells. The device processes the second well data and data associated with the set of performing wells to determine a first metric associated with the candidate well, and processes the second well data and data associated with the set of underperforming wells to determine a second metric associated with the candidate well. The device determines whether to install plunger lift in the candidate well based on the first metric and the second metric.

Abstract: A system and method for forecasting failures in industrial machines, including: receiving raw sensory inputs collected from at least one machine; generating a plurality of data features based on the raw sensory inputs; selecting from the plurality of data features a plurality of indicative data features, wherein the selection is based on a distribution of the plurality of indicative data features that determines an association between the plurality of indicative data features and a machine failure; selecting, based on the plurality of indicative data features, a machine learning model; applying the selected machine learning model to the plurality of indicative data features; and determining a probability for a forthcoming machine failure.

Abstract: A disruptor adjustment system comprising: a disruptor assembly configured to disrupt a volume of smelt flowing from a smelt spout into a dissolving tank, wherein the disruptor assembly comprises an actuator operatively engaged to a disruptor, a sensor configured to record process data from the recovery boiler; and a control system configured to receive a sensor output signal from the sensor, wherein the sensor output signal indicates the process data at a measured time, wherein the control system is further configured to compare the sensor output signal to a programmed operation range, and to send a disruptor input signal to the disruptor assembly to adjust a disruptor operating condition if the process data of the sensor output signal is outside of the programmed operation range. In certain exemplary embodiments, the sensor is an image capture device. In certain exemplary embodiments, the disruptor assembly can be adjusted remotely.

Abstract: In an embodiment, the present disclosure is directed to an assembly for preventing condensation on a surface of an object. The assembly may include a condensation mitigation device; a surface temperature sensor configured to sense a temperature; an ambient temperature sensor configured to sense an ambient temperature; and a humidity sensor configured to sense a humidity. The condensation mitigation device may be operably coupled to the surface temperature sensor, the ambient temperature sensor, and the humidity sensor.

Abstract: A plurality of known compounds with known CCS values is analyzed using a DMS device. The DMS device determines how the intensities of their transmitted ions vary with different separation voltages (SVs) and compensation voltages (CVs). A machine learning algorithm builds a data model from the known m/z value, known CCS value, and measured pairs of CV and SV values that provide optimal transmission through the DMS device for each of the known compounds. An unknown compound with an unknown CCS value is then analyzed. The DMS device determines how the intensity of its ions varies with the same different SVs and CVs. Finally, the machine learning algorithm predicts the CCS value of the unknown compound from the data model, the known m/z of the unknown compound, and the measured pairs of CV and SV values that provide optimal transmission through the DMS device for the unknown compound.

Abstract: Provided are a feature processing method and feature processing system for machine learning. The feature processing method includes: (A) acquiring a data record, wherein the data record comprises at least one piece of attribute information; (B) for each of the continuous features generated based on at least a some of the attribute information in the at least one piece of attribute information, executing a basic binning operation and at least one additional operation to generate a basic binning feature and at least one additional feature corresponding to each of the continuous features; and (C) generating a machine learning sample at least comprising the generated basic binning feature and at least one additional feature.

Abstract: A method for determining sand pumping parameters based on width distribution of fracture, including: acquire basic parameters of a target reservoir, simulate a propagation of the fracture, and obtain a propagation pattern and width distribution of the fracture; determine a maximum proppant particle size for entering the fracture at all width levels according to statistical results of the width distribution of the fracture; determine a multi-size combination of proppants according to a mapping table for particle size vs mesh of proppants, and determine an initial ratio of the proppant with each particle size; conduct a numerical simulation of proppant transportation in the fracture to determine a retention ratio of the proppants with each particle size; correct the initial ratio of the proppants with each particle size; calculate an amount of the proppants with each particle size according to the final ratio and the sand pumping intensity and fracturing interval length.

Abstract: Disclosed herein is a three-electrode-system-type electrode potential measurement device for measuring the electrode potential of a cylindrical battery cell in which a beading portion is in a divided condition, the beading portion provided between a top cap assembly and a battery case, a first electrode terminal of the cylindrical battery cell located at the top cap assembly, and a second electrode terminal of the cylindrical battery cell located at the battery case, the electrode potential measurement device including a working electrode connection unit connected to one of the first electrode terminal or the second electrode terminal; a counter electrode connection unit connected to the other of the first electrode terminal or the second electrode terminal; a reference electrode connection unit connected to a reference electrode; a measurement unit connected to the working electrode connection unit; and a short-circuit prevention member located between the top cap assembly and the battery case.

Abstract: Methods, systems, and apparatuses for monitoring health and integrity of core samples are disclosed. The apparatus includes a core container including a body portion having a plurality of chambers to accommodate a plurality of samples, and a lid portion configured to fully cover the body portion, and one or more vibration sensing devices configured to measure vibration experienced by each of the plurality of core samples. The apparatus is further configured to access a database comprising a plurality of core rock matrices and corresponding threshold vibration amplitude values, and determine, for each of the core samples, a category from a plurality of categories based on the vibration experienced by the core sample and the threshold vibration amplitude value for the corresponding core rock matrix.

Abstract: A sensor device includes a supply battery for supplying energy to the sensor device, a sensor unit for detecting an operating-state data of the supply battery, and a communication unit for transmitting the operating-state data can be transmitted to an evaluation system. The operating-state data of the supply battery can be detected by the sensor unit at different measurement times and are transmitted to the evaluation system which determines the energy demand of the sensor device. An action recommendation for the optimized operation of the sensor device is generated on the basis of the operating-state data and the energy demand.

Abstract: A method, a controlling unit and an electronic charging arrangement for determining a state of charge of a battery (205) during charging of the battery (205) are presented. The method comprises charging (110) the battery (205) with a charging current (410) during a first time period (T1), interrupting (120) the charging current (410) after the first time period (T1) at least for an interruption time period (T2), determining (130) a change (480) of terminal voltage (420) of the battery (205) during the interruption time period (T2), and determining (140) the state of charge based on the determined change (480) of terminal voltage (420).

Abstract: A battery management system includes a microcontroller having a first diagnostic handler application and first and second applications. The first application sets a first non-recoverable diagnostic flag to a first encoded value having each nibble thereof selected from an odd Karnaugh set of binary values. The second application sets a second non-recoverable diagnostic flag to a second encoded value having each nibble thereof selected from an even Karnaugh set of binary values. The first diagnostic handler application sets a first master non-recoverable diagnostic flag to a first encoded fault value if the first non-recoverable diagnostic flag is equal to a second encoded fault value, or the second non-recoverable diagnostic flag is equal to a third encoded fault value.

Abstract: An anomaly detecting device according to the present invention includes: a memory; and at least one processor coupled to the memory. The processor performs operations. The operations includes: when first series data are input, extracting a series feature amount being a feature amount of a signal included in the first series data; calculating a series probability distribution being a probability distribution which the series feature amount follows; storing a reference probability distribution being a probability distribution designated as a reference for the series feature amount in the first series data; calculating a state feature amount representing a fluctuation condition of the series probability distribution with respect to the reference probability distribution; and detecting an anomaly of the first series data, based on a plurality of the state feature amounts calculated from the first series data.

Abstract: A system and method for performing synchronization of a magnetic field transmitter and receiver to resolve received signal phase ambiguity based upon the phases of the magnetic fields. Three orthogonal field frequencies are selected. A Fourier transform extracts the sine and cosine of the received signal, which provides the received signal phases and results in a complex signal matrix (“Sigmat”). A search is made for a phase rotation of the frequencies to achieve convergence of the Sigmat at a point it is real-valued; the search may be limited by aligning the Sigmat such that the major element becomes real-valued and rotating the other two frequencies. The correct phase is the one in which the Sigmat has a positive determinant and minimizes any remaining imaginary portion. A transmitter and receiver may be calibrated to account for any analog phase shift. Distortion of the magnetic field may also be detected and corrected.

Abstract: A flood detection device and method that acquires meteorological data; acquires traffic volume data representing vehicle traffic volume; and determines that an area, in which a vehicle traffic volume during or after rain is less than or equal to a predetermined number of vehicles, is flooded based on the meteorological data and the traffic volume data, when a probability, that the vehicle traffic volume in a normal time is less than or equal to the predetermined number of vehicles, is less than a predetermined value, the normal time being a state in which a rainfall amount is less than a predetermined value.

Abstract: A system and method for monitoring the operating condition of a wheelset on a railcar comprising a sealed unit mounted on or near a wheelset of the railcar for collecting data from the wheelset and performing AI analyses on the collected data to determine the operational condition and predict failure modes for the wheelset. Results are communicated off-railcar wirelessly via one or more of several different methods.