Abstract: A method of determining an arrival-time of a first seismic event in a seismic data set including, obtaining the seismic data set and an initial seismic velocity model, and determining an updated seismic velocity model based on the seismic data set. Furthermore, the method includes determining a simulated arrival-time of the first seismic event based on the updated seismic velocity model and defining a predicted time-window based on the simulated arrival-time of the first seismic event, and picking the arrival-time of the first seismic event in the seismic data set based on the predicted time-window.

Abstract: A system and method are provided for a analyzing a refresh rate of a device under test (DUT) such as a volatile memory device that includes a memory and an associated memory controller. The method includes acquiring refresh data based upon signals between the memory and the memory controller of the volatile memory device over a time period, determining the refresh rate of the volatile memory device for time windows of the time period based upon the acquired refresh data, and displaying the refresh rate of the volatile memory device, compared to a refresh threshold, on a graphical user interface (GUI), for each of the time windows over the time period.

Abstract: For the purpose of gas quality monitoring, a spectroscopic examination of a gas sample from a space (10) to be monitored is carried out, e.g. by Raman spectroscopy. The spectroscopic examination yields a measurement spectrum extending over a wavelength range. A deviation of the measurement spectrum from at least one comparison sample (160) is then detected. Depending on the detected deviation, a gas quality warning (QW) is produced.

Abstract: A method for partial differential equation inversion, the method including receiving measured data do; selecting an objective function having first and second measures N1 and N2, wherein the objective function depends on three independent variables V, u, and f, V being a perturbation of a wave equation operator L from a background operator L0, u being a wavefield that satisfies the wave equation operator L, and f being a source function that describes the source of the waves; optimizing with a processor the objective function by finding a minimum or a maximum using the inversion; calculating with the processor solutions V*, u*, and f* of the three independent variables V, u, and f; and generating with the processor an image of an object based on the solutions V*, u*, and f*.

Abstract: An artificial intelligence (AI) device includes a sensing unit configured to collect operation log including information on an external environment factor and an operation state of an AI device, a memory configured to store data corresponding to the operation log, and a processor configured to provide the data corresponding to the operation log to an AI model, to acquire information about whether the AI device corresponds to a normal range or a malfunction symptom range, and to perform control based on the acquired information.

Abstract: The present invention discloses a microseismic wireless monitoring, receiving and early warning system of rock, which is connected with microseismic intelligent acquisition and data wireless transmission systems of rocks through a satellite.

Abstract: A gas sensing device includes one or more chemo-resistive gas sensors; one or more heating elements for heating each of the gas sensors; a preprocessing block for filtering signal samples in order to generate filtered signal samples for each of the gas sensors; an information extraction block for generating representations for the filtered signal samples for each of the gas sensors based on dynamic characteristics of the received filtered signal samples of the respective gas sensor; and a decision making block for receiving the representations, wherein the decision making block includes a trained model based algorithm stage having an input layer and an output layer, wherein the decision making block includes trained models, wherein the decision making block creates sensing results based on output values of the output layer of the algorithm stage, and wherein the output values are created by using the trained models.

Abstract: Disclosed are a method and apparatus for estimating S-wave velocities by learning well logs, whereby the method includes a model formation step of forming an S-wave estimation model to output S-wave velocities corresponding to measured depth when the well logs are input based on train data sets including train data having values of multiple factors included in the well logs, the values being arranged corresponding to measured depth, and label data having S-wave velocities corresponding to measured depth as answers, and an S-wave velocity estimation step of inputting unseen data having values of multiple factors included in well logs acquired from a well at which S-wave velocities are to be estimated, the values being arranged corresponding to measured depth, to the S-wave estimation model to estimate S-wave velocities corresponding to measured depth.

Abstract: Strata surfaces can be identified in well logs and correlated across the well logs taking into account manual corrections. For example, a computing device can receive well logs. The computing device can determine multiple stratum-surface correlations based on the well logs. Then, the computing device can receive user input indicating a correction to a particular stratum-surface correlation. Based on the correction to the particular stratum-surface correlation, the computing device can update some or all of the other stratum-surface correlations.

Abstract: A tool for monitoring a part condition includes a computerized device having a processor and a memory. The computerized device includes at least one of a camera and an image input and a network connection configured to connect the computerized device to a data network. The memory stores instructions for causing the processor to perform the steps of providing an initial micrograph of a part to a trained model, providing a data set representative of operating conditions of the part to the trained model, and outputting an expected state of the part from the trained model based at least in part on the input data set and the initial micrograph.

Abstract: A method for analyzing constituents of a material under test is disclosed. The method includes obtaining a plurality of impedance spectroscopy measurements of the material under test over a predetermined frequency range. A data set is passed to a machine learning system, the machine learning system having been trained to return an output related to one or more constituents in the material under test based on impedance spectroscopy measurement data over the predetermined frequency range. An output of the machine learning system is received and outputted. Related systems, methods and devices are also disclosed.

Abstract: In a detection apparatus that detects an anomaly of equipment, in a case where a plurality of types of anomalies occur, it is desired to detect which type of anomaly has occurred. Provided is a detection apparatus that includes a sensor data obtaining unit configured to obtain sensor data of a sensor installed in equipment, a model storage unit configured to store detection models that are individually trained for each anomaly using the sensor data in an anomaly period in which the anomaly has occurred, for a plurality of types of respective anomalies of the equipment, and a detection unit configured to detect presence or absence of the plurality of types of respective anomalies from the sensor data that has been newly obtained, by using the detection models corresponding to the plurality of types of respective anomalies.

Abstract: Methods and systems for data collection in an industrial refining environment with haptic feedback and data storage control are disclosed. A system may include a data collector communicatively coupled to a plurality of input channels, wherein the data collector collects data based on a selected data collection routine, a data storage structured to store a plurality of collector routes and collected data, wherein the plurality of collector routes each include a different data collection routine, a data acquisition circuit structured to interpret the collected data and determine an occurrence of an anomalous condition, a data analysis circuit to evaluate a data storage constraint of the monitoring system and to adjust a volume of collected data stored in response to the evaluation, and a haptic user device for generating a haptic stimulation in response to an occurrence of a specified anomalous condition in the refining environment.

Abstract: An apparatus for automated maintenance of limited-access areas on large structures. The apparatus is a rolling or sliding tool-equipped mobile platform that is adhered to a surface by operation of one or more adherence fans and then propelled across the surface by operation of one or more propulsion fans. The adherence and propulsion fans are coupled to a base made of semi-rigid material. The adherence fans produce suction forces in one or more suction zones to adhere the mobile platform to the surface. The propulsion fans produce thrust to propel the surface-adhered mobile platform in a desired direction across the surface. The tool-equipped mobile platform is capable of adhering to and moving over a non-level surface on a large structure while keeping standoff contact elements in contact with the surface regardless of surface contour. The propulsion fans, adherence fans and maintenance tool (e.g., an NDI sensor unit) are controlled by a computer system.

Abstract: Systems and methods are provided for training a machine learned model on a large number of devices, each device acquiring a local set of training data without sharing data sets across devices. The devices train the model on the respective device's set of training data. The devices communicate a parameter vector from the trained model asynchronously with a parameter server. The parameter server updates a master parameter vector and transmits the master parameter vector to the respective device.

Abstract: A method can include receiving seismic image data; processing the received seismic image data to generate stratigraphic information using a trained convolution neural network that includes channels subjected to convolution, activation and pooling that reduce spatial resolution and subjected to deconvolution and concatenation that increase spatial resolution; and enhancing the seismic image data using the stratigraphic information to generate an enhanced seismic image.

Abstract: A method for imaging non-specular seismic events as well as correlating non-specular events with physically measurable quantites in a volume of Earth's subsurface. Includes entering as input to a computer signals detected by a plurality of seismic sensors disposed above and/or within the volume in response to actuation of at least one seismic energy source above and/or within the volume. Parameter analysis is performed to populate the initial model with point-wise, best-fit wavefront travel-time approximations. Imaging is performed to obtain undifferentiated specular and non-specular representations of the volume. Specular boundaries are mapped using the imaged volume and using the boundaries to form a model of specular components of the volume. Beamforming is used to characterize seismic attributes associated with specular and non-specular reflections as separate and differentiated data sets.

Abstract: Systems, methods, and apparatuses are provided herein that track an integrated deviation of a physical property of a material that corresponds to a variation or defect in the material. In one embodiment, molten steel begins to solidify and move past an instrumented region of a mold. Sensors in the mold can detect a deviation in temperature of the instrumented region of the mold that signifies a variation or defect in the surface of the slab material as it solidifies. The systems, methods, and apparatuses track the integrated temperature deviation to more clearly visualize defects that may otherwise not be detectable by simply observing the temperatures of the mold and slab material in real time.

Abstract: Acoustic waves are obtained from an acoustic logging tool within a borehole passing through a formation. Signal properties in a time domain, frequency domain, or both are determined based on the obtained acoustic waves. A machine learning analysis is used to determine formation slowness based on the determined signal properties and a downhole operational parameter is adjusted based on the determined formation slowness.

Abstract: Embodiments disclosed herein includes temperature monitoring in cold supply chains. In this regard, electrical conductors are affixed to containers in respective patterns that enables a set of containers to be arranged in a particular configuration in which the electrical conductors provide electrical connections between electrical conductors and, in aggregate, creates a sensing network that is operable to measure temperature of respective ones of the containers.