Abstract: The present invention discloses a method for detecting abnormity in an unsupervised industrial system based on deep transfer learning. Labeled machine sensor sequence data from a source domain and unlabeled sensor sequence data from a target domain are used in the present invention to train an industrial system abnormal detection model with good generalization ability, and the industrial system abnormal detection model is trained and tested to finally generate a trained industrial system abnormity discrimination model. Using the model, received machine sensor sequence data can be analyzed and whether a machine is abnormal is discriminated.

Abstract: A cooling fan monitoring circuit for monitoring and immediately alerting the user of the activation of a cooling fan motor and blade assembly providing notice of the shutting down of equipment requiring cooling to prevent overheating and damage to the equipment. The circuit is capable of monitoring multiple cooling fans and shuts down equipment if any one of the cooling fans ceases function, fails a preset condition, or the equipment reaches a preset temperature.

Abstract: A method is provided for operating a gas concentration monitoring system as well as a gas-measuring device, a central unit, a gas concentration monitoring system as well as computer program product. The safety of persons or the safety of a situation is determined with respect to at least one hazardous gas. The concentration of the gas is provided to a memory and analysis device. A measured value rating number is determined for a preset period of use. A number of instances, of the measured concentration values exceeding of a preset gas concentration limit value is input. A safety code is determined from at least one of: the measured concentration values, the measured value rating numbers and from the a total number of instances in which a gas concentration limit value was exceeded.

Abstract: Systems and methods for boiler regulation are disclosed. The system can receive boiler data from a boiler and compare the boiler data to a normal operating range to detect an abnormality. Based on a plurality of rules, the system can identify an anticipated root cause and at least one corrective action. Based on the at least one corrective action, the system can generate and/or output instructions for the boiler to perform the at least one corrective action. The system can display an indication of the abnormality and/or the at least one corrective action.

Abstract: Systems and methods for measuring rotational frequency in rotating machines use variable sliding windows of measurement. The systems and methods count and store the number of internal clock cycles between the start of a measurement interval and each pulse signal from a pulse generator. Rotational frequency is determined by taking a difference between the count for a most recent pulse signal and the count for some previous pulse signal within the measurement interval. The number of pulse signals that have occurred between the most-recent pulse signal and the previous pulse signal represents a window of measurement. This window of measurement, or the size thereof, may then be used along with the count difference to determine the rotational frequency. The window of measurement may then be slid to the counts for next most recent pulse signal and the next previous pulse signal to obtain a new count difference, and so on.

Abstract: A computer-implemented method, a system, and at least one computer-readable storage device are provided. A measured value related to operation of a device is periodically received for each respective reporting period. If the measured value indicates unhealthy operation of the device, a distance of the measured value from a predetermined abnormal threshold is determined and stored in a data store. Based on the determined distance, a number of most recent reporting periods included in a window is determined. All stored distances determined from measured values received before the window of the most recent reporting periods are deleted from the data store. An occurrence of a device failure is determined based on the stored distances in the data store after the deleting. In response to determining the occurrence of the device failure, an action is performed.

Abstract: Methods and systems for a data marketplace in a conveyor environment includes a self-organizing data marketplace. The self-organizing data marketplace includes at least one data collector and at least one corresponding conveyor in an industrial environment, wherein the at least one data collector is structured to collect detection values from at least one sensor of a power roller of the at least one corresponding conveyor; a data storage structured to store a data pool comprising at least a portion of the detection values; a data marketplace structured to self-organize the data pool; and a transaction system structured to interpret a user data request, and to selectively provide a portion of the self-organized data pool to a user in response to the user data request.

Abstract: A driving action evaluating device that specifies a driving scene by using at least one of an image captured by an onboard camera and position information of an own vehicle; and derives an evaluation of driving actions by executing an evaluation logic, which corresponds to only a driving scene specified by the specifying section, among a plurality of evaluation logics that correspond to a plurality of driving scenes, respectively.

Abstract: A soft-melted parison is disposed in molds forming a shape of a measurement pipeline portion 10, the parison is expanded by means of gas inflow, and blow molding is performed. The shapes of a pipe body 11, a fluid inlet portion 12, and a fluid outlet portion 13 are formed by an inner mold of the molds. Ultrasonic wave input-output portions 14a and 14b bulging outwards in a sealed manner are formed on both sides positioned in the oblique direction of the pipe body 11 with respect to a center line of the pipe body 11. Parts of the ultrasonic wave input-output portions 14a and 14b are wall surfaces 15a and 15b for attaching ultrasonic wave transmission-reception units. The measurement pipeline portion 10 is obtained by cutting end portions of the fluid inlet portion 12 and the fluid outlet portion 13 after the parison is solidified.

Abstract: The invention relates to the estimation of a time-variable physical quantity by a distributed system comprising a centralized platform and a set of distributed measurement devices each communicating with the platform via a communication network, on the basis of the measurement (100), by each device of the set, of a local datum representative of the physical quantity, the collection (120) by the centralized platform, over a predetermined sampling period, of measurement samples originating from a subset of devices of said set via said communication network, and the estimation (130) of the physical quantity over the sampling period on the basis of the collected samples. According to the invention, each device of said set executes (110), in each sampling period, a local algorithm deciding randomly and based on a sending probability associated with each device, whether the corresponding measurement device is part of said subset.

Abstract: A method, apparatus and computer program product are provided to determine a measure of probe quality, such as a level of accuracy with which the location of a probe point is defined. In the context of a method and for a plurality of probe points, a distance is determined between a respective probe point and a line representative of a link. For the plurality of probe points, the method also includes determining a difference between a bearing of the respective probe point and a bearing of the link. The method further includes determining the measure of probe quality based upon a product of a representation of the distance between the plurality of probe points and the line representative of the link and a representation of the difference between the bearing of the plurality of probe points and the bearing of the link.

Abstract: Embodiments of the present systems and methods may provide techniques to discover features such as object categories that provide improved accuracy and performance. For example, in an embodiment, a method may comprise extracting, at the computer system, features from a dataset comprising a plurality of data samples using a backbone neural network to form a features vector for each data sample, training, at the computer system, using the features vectors for at least some of the plurality of data samples, an unsupervised generative probabilistic model to perform clustering of extracted features of the at least some of the plurality of data samples by minimizing a negative Log-Likelihood function, wherein clusters of extracted features form categories, and categorizing, at the computer system, at least some different data samples of the plurality of data samples, into the formed categories.

Abstract: An agricultural harvesting machine, particularly a combine harvester or a forage harvester, has a supporting frame, a cutting mechanism, an inclined conveyor and a driver's cab. The cutting mechanism is arranged at the supporting frame by the inclined conveyor. The driver's cab is arranged at the supporting frame with the intermediary of at least one damper unit. At least one camera is arranged in an interior of the driver's cab. The camera is oriented to the cutting mechanism and/or to the inclined conveyor through a front windshield of the driver's cab. The camera is arranged in an operative area of a cleaning device of the front windshield so that a detection area of the camera can be optically acquired at least through a portion of the operative area of the cleaning device.

Abstract: The disclosed embodiments include a method, apparatus, and computer program product configured to performing automated downhole wellbore trajectory control for correcting between an actual wellbore trajectory path and a planned wellbore trajectory path. For example, in one embodiment, a PID controller is configured to obtain real-time data gathered during the drilling operation, determine whether the actual wellbore trajectory path deviates from the planned wellbore trajectory path, and automatically initiate the downhole wellbore trajectory control to change the actual wellbore trajectory path to a modified correction path that is determined using a minimum incremental wellbore energy method.

Abstract: A remaining life of a robot body is precisely estimated. A robot control apparatus 300 includes: a drive control unit 305 that controls drive of a robot body 200; a detection unit 306 that detects a feature amount quantitatively indicating a deterioration degree of the robot body 200 that is deteriorated over time as the robot body 200 is driven; a determination unit 303 that determinates presence/absence of a sign of malfunction of the robot body 200 based on the feature amount; and an estimation unit 304 that estimates a remaining life of the robot body 200 when presence of a sign of malfunction of the robot body 200 is determined.

Abstract: A fluid flow meter system for monitoring fluid flow through a lumen includes a first ultrasonic transducer configured to transmit one or more versions of a transmit (TX) signal through a fluid flowing within the lumen, and a second ultrasonic transducer configured to receive one or more respective receive (RX) signals. The fluid flow meter system includes an analog-to-digital converter (ADC) configured to sample, at a first frequency, the one or more RX ultrasonic signals and a processor configured to generate a fine resolution signal based on the one or more RX ultrasonic signals. The fine resolution signal is associated with a second sampling rate higher than the first sampling rate. The processor is also configured to compute a cross-correlation signal indicative of cross-correlation between the fine resolution signal and a waveform and determine an estimated fluid flow parameter based on the computed cross-correlation signal.

Abstract: An apparatus obtains measurements from a seismic sensor, wherein the seismic measurements include a set of seismic waves having at least a subset of seismic multiples and a machine-readable medium having program code executable by a processor to cause the apparatus to determine seismic measurements of the seismic waves, fit reflectivity model based on a set of reflectivity models using a nonlinear scheme to the seismic measurements, and identify a subset of the seismic measurements corresponding to the subset of seismic multiples. The apparatus also includes program code to cause the apparatus to generate a set of reduced-noise seismic measurements based on attenuation of the subset of the seismic measurements.

Abstract: Methods are presented for determining the location of underground features (e.g., CO2). One method includes capturing, by sensors distributed throughout a region, seismic traces associated with seismic signals generated by a seismic source. For multiple sensors, active noise is identified or passive noise is measured within each seismic trace and values for attributes associated with the active or passive noise are determined. Further, an unsupervised machine-learning model, based on the values of the attributes, is utilized to determine noise characteristics for multiple sensors. The sensors are grouped in clusters based on the noise characteristics for each sensor. For multiple clusters, a noise filter is created based on the noise characteristics of the sensors in the cluster, and the noise filter of the cluster is applied, for multiple sensors, to the seismic traces of the sensor. Additionally, the filtered seismic traces are analyzed to determine a location of CO2 underground.

Abstract: A system for inspecting or screening electrically powered device includes a signal generator inputting a preselected signal into the electrically powered device. There is also an antenna array positioned at a pre-determined distance above the electrically powered device. Apparatus collects RF energy emitted by the electrically powered device in response to input of said preselected signal. The signature of the collected RF energy is compared with an RF energy signature of a genuine part. The comparison determines one of a genuine or counterfeit condition of the electrically powered device.

Abstract: Disclosed is a novel type of computing apparatus which is integrated within a buoy that obtains the energy required to power its computing operations from winds that travel across the surface of the body of water on which the buoy floats. Additionally, these self-powered computing buoys utilize their close proximity to a body of water in order to significantly lower the cost and complexity of cooling their computing circuits. Computing tasks of an arbitrary nature are supported, as is the incorporation and/or utilization of computing circuits specialized for the execution of specific types of computing tasks. And, each buoy's receipt of a computational task, and its return of a computational result, may be accomplished through the transmission of data across satellite links, fiber optic cables, LAN cables, radio, modulated light, microwaves, and/or any other channel, link, connection, and/or network.