Abstract: Tools for fire monitoring are presented. One method includes an operation for accessing values of features for monitoring a fire in a region. The features include satellite images at a first resolution, vegetation information, and weather data. Further, each satellite image includes first cells associated with the geographical region and the first resolution defines a first size of each first cell. The method further includes generating a map of the geographical region comprising a plurality of second cells having a second size, which is smaller than the first size. Additionally, the method includes operations for estimating, using a machine-learning model, probability values for the second cells in the map based on the features, each probability value indicating if the second cell contains an active fire, and for updating the map based on the probability values for the second cells. The map is presented in a user interface.

Abstract: A system for fan stress tracking according to an example of the present disclosure includes, among other things, a computing device that has a memory and a processor. The computing device is operable to execute a data module and a comparison module. The data module is operable to access data corresponding to a sensed value of an engine inlet parameter, and is operable to access data corresponding to a fan stress fatigue ratio profile. The fan stress fatigue ratio profile is defined with respect to at least one fan blade. The comparison module is operable to associate the sensed value of the engine inlet parameter with a stress value according to the fan stress fatigue ratio profile. The comparison module is operable to determine whether the stress value meets at least one predetermined criterion.

Abstract: In accordance with aspects of the present invention, a method of providing a fuel gauge is provided. The method includes measuring a battery current through and a battery voltage across a battery; determining an equivalent resistance from the current and the voltage using a multiplier K; determining an open circuit voltage based, in part, on the equivalent resistance; determining a state-of-charge based on the open circuit voltage; and adjusting the multiplier K based on the current and the state-of-charge.

Abstract: The formation of dynamic, micro-climate groups consisting of passive and active weather collecting devices is provided. Such devices may collect weather information in real-time. The collected information may be distributed weather information and or forecasts to individuals in a particular geographical area or to other subscribers.

Abstract: A facility diagnosis device includes: a process data acquirer that acquires process data indicating a state of a process executed in a plant; a production data acquirer that acquires production data indicating a production state in the plant; a state information generator that generates state information for estimating an operation state of a facility operating in the process based on the acquired process data or the acquired production data, or the process data and the production data; and a determiner that determines the operation state of the facility based on the acquired process data or the generated state information and the acquired production data.

Abstract: A microelectromechanical system (MEMS) sensor testing device, system and method are provided. The testing device includes a socket having a plurality of pads configured to receive a respective plurality of pins of the MEMS sensor, a body having a plurality of operable positions associated with a respective plurality of orientations of the MEMS sensor and circuitry which performs a method for testing the MEMS sensor in the plurality of operable positions. The method includes, for each position of the plurality of operable positions, outputting an indication of the position to the plurality of operable positions, receiving one or more measurements made by the MEMS sensor at the respective position and determining whether the one or more measurements satisfy a reliability criterion. The method includes generating a report based on the plurality of measurements and indicating whether the plurality of measurements satisfy a plurality of reliability criteria, respectively.

Abstract: Methods and systems associated with aligning reference frames used for tracking an object are disclosed. One embodiment disclosed herein is a method for generating a transform between a first and second frame of reference (FOR) using a sequence of heading values of the object in the first and second FOR. The method comprises providing instructions to orient the object towards one or more external positioning devices in an orienting sequence. The method also comprises obtaining the sequence of heading values of the object in the second FOR using an onboard sensor and obtaining a sequence of position values of the object in the first FOR in accordance with the orienting sequence and using the one or more external positioning devices. The method also comprises deriving the sequence of heading values of the object in the first FOR using the sequence of position values.

Abstract: A method and system for obtaining orientation of a core sample core drilled from underlying rock. A core orientation recording device (116) records its orientation at random and/or non-predetermined time intervals from a reference time during a drilling operation. The time intervals are generated to be within a range of minimum and maximum time intervals. After a time interval elapsed from the reference time plus a wait time of at least the minimum random or non-predetermined time interval, the core sample is separated from the underlying rock and brought to the surface and its original orientation is determined from orientation data recorded closest in time to the elapsed time plus the minimum time interval. A remote communicator (160) having the elapsed time interrogates the core orientation recordal device (116) to identify the required orientation data and requires the core orientation recordal device to identify a correct orientation of the core sample.

Abstract: A processor-implemented method for vector analysis to extract a speed of a rotating part of a machine is provided. The processor-implemented method including receiving, by a processor, two channel synchronous signals derived from at least two sensors coupled to the machine and positioned 90° with respect to each other; determining, by the processor, a plurality of vector angles for a plurality of samples from the two channel synchronous signals to identify a period; determining, by the processor, a time difference based on a sample rate and a number of the plurality of samples that are within the period; determining, by the processor, the speed based on a time difference. A system for carrying out the method is also provided.

Abstract: The present invention provides a method for identifying noise data of a laser ranging device. An n number of measurement points P(i), P(i?1) and P(i+1) corresponding to an n number of projection lines that are adjacent to each other are extracted from a plurality of measurement points at which distances have been measured by a laser ranging device 1. An approximate straight line L(i) that passes through the n number of measurement points is calculated. A degree of inclination e(i) of the approximate straight line L(i) with respect to the representative line among the projection lines corresponding to the n number of measurement points is determined. If the degree of inclination is smaller than a predetermined threshold value, then the measurement data on a measurement point having a largest distance measurement value among the n number of measurement points is identified as noise data.

Abstract: Systems and methods for forecasting of State of Charge (SOC) of lithium ion batteries are provided. A multi-step forecasting process with experimentally obtained decreasing C-Rate datasets together with machine learning can be used. The multi-step approach can combine a univariate technique with machine learning techniques. An Auto Regressive Integrated Moving Average (ARIMA) and/or Holt Winters Exponential Smoothing (HWES) can be combined with each other and/or with machine learning techniques such as Multilayer Perceptron (MLP) and Nonlinear autoregressive neural network with external input (NARX-net).

Abstract: A tester for evaluating pullout load capacity and bond quality of anchor bolts embedded in concrete includes a Schmidt hammer for measuring a rebound number and an ultrasonic pulse velocity tester for measuring the transit time of a pulse transmitted through concrete surrounding an anchor bolt. The rebound number and the transit time are combined and matched against a database record which identifies the pullout load capacity and the bond quality. The transit time is matched to thresholds of transit times associated with porosity, internal cracking, air voids, and water pockets located around the embedded anchor bolt. The Schmidt hammer is further modified by the incorporation of a digital level for measuring the vertical and horizontal angles of inclination of the plunger with the concrete surface, a guide tube for supporting the plunger, and by using a convex plunger tip for improved registration with anchor bolt head.

Abstract: A measuring arrangement with a control unit, an energy supply unit for a plurality of two-line field devices, which apply a predetermined current upon a measuring loop in which the two-line field devices are respectively arranged, with the two-line field devices being electrically connected to the energy supply unit and communicating digitally with the control unit, with the energy supply unit comprising a voltage controller, which controls an output voltage depending on the number the means of the measuring arrangement for determining a number of two-line field devices operated in the measuring arrangement.

Abstract: A system includes sensors for monitoring pressure, flow, pump speed, temperature, and/or other signals at the output of a main hydraulic pump, and a processing system executes one or more methods for identification of hydraulic system events, from the signals, corresponding to state changes and performance of the system and/or its subcomponents. Event identification is performed with classification and/or other machine learning algorithms, with generation of novel training data sets. The sensor(s) can also be used to determine power consumption information about the system and/or its subcomponents. The system processes event-associated outputs for execution of actions for improving system performance, along with other downstream applications.

Abstract: Sensor data is received from a plurality of sensors contained in an electrical submersible pump (ESP) deployed in a well hole. An early indication of an ESP failure that is imminent is determined in real time using a pattern recognition methodology based on the sensor data and a pattern detection model that correlates historical ESP failures with historical sensor readings. A notification of the imminence of the ESP failure is provided.

Abstract: A monitoring method for monitoring equipment of electromechanical actuator type, the equipment including a three-phase electric motor, the monitoring method comprising the following steps: measuring three-phase currents powering the three-phase electric motor; projecting the three-phase currents into a Park reference frame; performing an ensemblist empirical mode decomposition processor the quadrature current coupled with a blind source separation process in order to obtain source components; from among the source components, automatically selecting a first set of source components sensitive to a first defect, and a second set of source components sensitive to a second defect; constructing a first virtual defect signal and a second virtual defect signal; and extracting a first set of signatures representative of the first defect from the first virtual defect signal, and extracting a second set of signatures representative of the second defect from the second virtual defect signal.

Abstract: A method is presented for estimating population from sample proportions that produces margins of error narrower for any specific sample size or that requires a sample size smaller for any specific margin of error than do previously existing methods applied to the same data. This method applies an unbiased estimator of the squared correlation between population and sample proportions to determine point and interval estimates of population proportions in a regression context involving simple random sampling with replacement. In virtually all reasonable applications, assuming a Dirichlet prior distribution, the margin of error produced by this method for a population proportion is shown to be 1.96 times the posterior standard deviation of the proportion.

Abstract: A computerized method of processing data for use in weather modeling is provided. The method includes receiving, from a first data source, by a first server, microwave link data including signal attenuation information. The method also includes pre-processing, in real time, by the first server, the microwave link data, thereby producing pre-processed microwave link data. The method also includes storing the pre-processed microwave link data in a first data store. The method also includes receiving, from the first data store, by a second server, the pre-processed microwave link data. The method also includes processing, on a scheduled routine, by the second server, the pre-processed microwave link data using a data transform, thereby producing first weather data.

Abstract: A system for automated process performance determination includes an interface and a processor. The interface is configured to receive log data associated with a plurality of tenants. The log data comprises one or more log data types. The processor is configured to aggregate the log data into an aggregated set of log data; and determine a set of metrics based at least in part on the aggregated set of log data. A metric of the set of metrics is associated with a tenant of the plurality of tenants and one of the one or more log data types. The processor is further configured to determine a composite metric for the tenant by combining metrics of the set of metrics associated with the tenant; determine a response based at least in part on the composite metric; and, in the event the response indicates an automated action, perform the automated action.

Abstract: A battery monitoring system includes a current sensor and a voltage sensor coupled to a battery cell. It also includes a microcontroller that opportunistically computes many estimates of the cell's ohmic resistance and filters these estimates to arrive at a stable value. Each estimate is traditionally computed from a delta change in voltage divided by delta change in current measured before and after a significant change in current magnitude. An improvement in accuracy of each resistance estimate is achieved by only computing an estimate if the rate of change of voltage and the rate of change of current exhibited by the values making up the delta voltage and delta current are tightly consistent and of the same polarity. This approach significantly minimizes errors induced in estimates not preselected in this manner by the different and also asynchronous sample rates of the cell's voltage and current.