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.

Abstract: This invention presents an innovative framework for the application of machine learning for identification of alloys or composites with desired properties of interest. For each output property of interest, we identify the corresponding driving (input) factors. These input factors may include the material composition, heat treatment, process, microstructure, temperature, strain rate, environment or testing mode. Our framework assumes selection of optimization technique suitable for the application at hand and data available, starting with simple linear, or quadratic, regression analysis. We present a physics-based model for predicting the ultimate tensile strength, a model that accounts for physical dependencies, and factors in the underlying physics as a priori information.

Abstract: A method, apparatus, system, and computer program product for estimating material properties. Training data comprising results of testing samples for a set of materials over a range of loads applied to the samples is identified by a computer system. A machine learning model is trained by the computer system to output the material properties for materials in structures using the training data.

Abstract: Real-time alerts and transmission of selected signal samples is disclosed. One example is a system including a base facility linked to a production station with an alerting system to perform anomaly analysis utilizing an anomaly model. A receiver at the base facility receives, from the production station, a selection of signal samples based on the anomaly analysis, where the received selection is optimized at the production station to be substantially relevant to an update of a statistical model while adhering to a dynamic capacity limitation of the production station. The statistical model is maintained at the base facility and incorporates features related to the production station. A management system at the base facility updates the statistical model based on the received selection, optionally derives an updated anomaly model based on the statistical model, and optionally transmits the updated anomaly model to the production station.

Abstract: Systems and methods for automated or computer assisted planning of pipe replacement projects includes searching a database of pipe segments each having assigned or calculated failure risk parameters. The searching algorithm looks for connected pipe segments falling within a customer's specified project size and identifies potential projects having a relatively high combined high failure risk.

Abstract: A sheet feed device comprises a first conveyance path and a second conveyance path which are different sheet conveyance paths, and a conveyance path merging section for merging the first conveyance path and the second conveyance path together. At least one of the first conveyance path and the second conveyance path includes an upstream side roller that feeds sheet to downstream side in a conveyance direction. The conveyance path merging section comprises a conveyance roller pair that conveys the sheet fed from the first conveyance path and the second conveyance path through a nip; a variable mechanism that makes an arrangement angle of one roller of the conveyance roller pair to the other roller thereof variable; and a transmission mechanism that transmits a driving force from the upstream side roller provided in one of the first conveyance path and the second conveyance path to the variable mechanism.

Abstract: A workstation for measuring dimensions includes an operator zone, a first fixture, a second fixture, a component delivery device, a gauge, and a collaborative robot. The second fixture is accessible to an operator in the operator zone. A component delivery device deposits a first component onto the first fixture. The envelope of the component delivery device is not accessible by the operator in the operator zone. The collaborative robot supports the gauge tool and has a range of motion capable of measuring the first component on the first fixture and a second component on the second fixture. A control module is in communication with the gauge and the collaborative robot and operates the collaborative robot to measure the first component on the first fixture and the second component on the second fixture.

Abstract: A light-emitting device includes a base that extends in one direction; a light-emitting unit in which multiple light sources that are disposed in the one direction are supported by a supporting body that extends in the one direction and that is formed from a metal block; a spacer that is interposed between the base and the light-emitting unit in a direction of an optical axis of each light source; and a fixing unit that fixes the light-emitting unit to the base in a mode in which a compressive load is applied to the spacer.

Abstract: Systems and methods for providing insights about a machine learning model are provided. The method includes, using training data to train the machine learning model to learn patterns to determine whether data associated with an event provides an indication that the event belongs to a certain class from among a plurality of classes, evaluating one or more features of the machine learning model to produce a data set pairing observed scores S and a set of predictive input variables Vi, and constructing at least one data-driven estimator based on an explanatory statistic, the estimator being represented in a computationally efficient form and packaged with the machine learning model and utilized to provide a definition of explainability for a score generated by the machine learning model.

Abstract: An angle sensor generates an angle detection value based on a first and a second detection signal. A correction apparatus performs correction processing for generating a first corrected detection signal by adding a first correction value to the first detection signal and generating a second corrected detection signal by adding a second correction value to the second detection signal. When an angle to be detected varies with a period T and if no correction processing is performed, the angle detection value contains an Nth-order angle error component varying with a period of T/N. Each of the first and second detection signals contains an (N+1)th-order signal error component. The order of the first and second correction values is N?1.

Abstract: An optical scanning device comprises an optical box that houses an optical component(s). The optical box includes a box main body and a cover member. A first engaging portion is formed on a side wall of the box main body, and a second engaging portion that engages with the first engaging portion is formed on a first fitting wall portion of the cover member. The box main body is provided with a vertical wall that is erected inside the first engaging portion. Moreover, there is formed on the cover member with a first barrier wall that is protruded downward from a top wall so as to enter a space between the first engaging portion and the vertical wall.

Abstract: A method for predicting time-to-failure and remaining-life of an electrical power system asset includes analyzing characteristics of the power system asset over a specified time interval; based on the analysis, associating the power system asset with a pool of similar power system assets having similar historical performance characteristics; and based on the association, calculating time-to-failure and remaining-life probability factors for the power system asset. A computer program product is also provided for carrying out the method, and the method may further include a mechanism whereby the computer program learns ways to modify and enhance the analysis of the performance characteristics to provide for higher confidence levels in time-to-failure and remaining-life probability calculations.

Abstract: Techniques to match a signature in seismic data with a seismic attribute space. A method includes automatically selecting a first plurality of seismic attributes corresponding to seismic data as first selected seismic attributes, combining the first selected seismic attributes into a first realization of attributes, performing a first cluster analysis on the first realization of attributes to generate a first clustered volume, selecting a region of interest (ROI) in the seismic data, projecting the ROI onto the first clustered volume to generate a first signature, determining a first level of correlation between the ROI and the first signature, and determining whether the first level of correlation between the ROI and the first signature exceeds a predetermined threshold and outputting a first correlation volume corresponding to the first signature when the first level of correlation between the ROI and the first signature exceeds the predetermined threshold.

Abstract: In a device for processing imaging-analysis data, two kinds of imaging-analysis data are stored in a storage section 21: (a) first imaging-analysis data, in which measurement data of a target substance, acquired by performing a first predetermined analysis at each of a plurality of measurement points within an analysis target area of a sample S, is associated with spatial position information of the measurement point, and (b) second imaging-analysis data, in which measurement data of a reference substance, acquired by performing a second predetermined analysis at each of the measurement points, is associated with spatial position information of the measurement point. A normalization executer 28 normalizes the measurement data of the target substance at each measurement point, based on the measurement data of the reference substance acquired at the same measurement point.

Abstract: An image forming apparatus includes a scanning means provided with a light source, a polygon mirror and a driving means for driving rotation of the polygon mirror; a photosensitive member, a developing means, and a detecting means for detecting a laser light from the light source. A controller controls to execute a light emission operation so that an area including an image forming area of the photosensitive member is irradiated with the laser light. The controller controls to execute a switching operation in which a rotational speed of the polygon mirror is switched from a first speed to a second speed different from the first speed. The controller controls to execute the light emission operation in a state in which the photosensitive member and the developing means are in contact and are rotating, and to execute the switching operation based on a detecting result of the detecting means in the light emission operation.

Abstract: An exposure head includes a plurality of light emitting element array chips each having light emitting portions and a wire bonding pad. The plurality of light emitting element array chips are arranged in a staggered manner in a longitudinal direction of a printed-circuit board. One end portion of a first light emitting element array chip overlaps one end portion of a second light emitting element array chip when viewed in a width direction. Another end portion of the second light emitting element array chip overlaps one end portion of a third light emitting element array chip when viewed in the width direction. An adhesive for fixing the second light emitting element array chip to the printed-circuit board is applied in an area between the one end portion of the first light emitting element array chip and the one end portion of the third light emitting element array chip.

Abstract: A toner classification apparatus comprising a classification rotor in which the classification rotor has a vane A which extends from a rotation center direction of the classification rotor to an outer circumference direction thereof and a vane B having a length longer than that of the vane A, the vane A, and the vane B are disposed so as to satisfy a predetermined relationship, and a toner production method comprising a classification step of carrying out a classification process on particles to be classified by using the toner classification apparatus.

Abstract: The present invention is a method to determine an azimuthal orientation of a borehole seismometer sensor performed by a computing device using a control server having a database and an arithmetic function, the computing device performing a method to determine the azimuthal orientation of a borehole seismometer sensor using long-period surface waves in microseisms, including step S100 in which a data collection unit 100 collects continuous waveform data recorded by a borehole seismometer and a reference seismometer; step S200 in which a frequency band setting unit 200 sets a frequency band to be analyzed in the collected continuous waveform data; step S300 in which a filtering unit 300 performs bandpass filtering on the frequency band to be analyzed; step S400 in which a waveform dividing unit 400 divides seismic waveform into waveform segments with preset time units; step S500 in which a phase shift unit 500 shifts the phase of the divided vertical component waveforms by 90°; step S600 in which a waveform cal

Abstract: In one embodiment, a sensor device includes a sensor configured to obtain sensor data and a communication interface configured to communicate with a set of secondary sensor devices. The set of secondary sensor devices comprise a set of secondary sensors and a set of secondary processing devices. The set of secondary sensors obtain additional sensor data. The set of secondary processing devices process the additional sensor data based on a set of secondary machine learning models, and generate activation data based on the additional sensor data. The sensor device also includes a processing device. The processing device is also configured to receive the activation data from the set of secondary sensor devices and cause the sensor to obtain first sensor data based on the activation data. The processing device is further configured to generate one or more inferences based on the first sensor data and a machine learning model.

Abstract: A method of enhancing adhesion of an image to at least one surface of a substrate is provided herein. The method includes treating at least a portion of the surface by applying a composition comprising one or more polymers to the portion of the surface. The method further includes drying the composition after applying the composition to the substrate to form a treated substrate. The method further includes printing an image from an electrophotographic printer utilizing liquid toner technology on the treated substrate. The substrate is treated and dried less than about 5 minutes prior to being printed.