In one embodiment, a device in a network receives a machine learning encoder and decoder trained by a supervisory service. The service trains the encoder and decoder using vibration measurement data sent to the service by a plurality of devices. The device trains, based on the received encoder, a classifier to determine whether vibration measurement data is indicative of a behavioral anomaly. The device receives vibration measurement data captured by a particular set of one or more vibration sensors of a monitored system. The device evaluates, using the trained decoder, the received vibration measurement data to determine whether the data is indicative of a structural anomaly in the monitored system. The device evaluates, using the trained classifier, the received vibration measurement data to determine whether the data is indicative of a behavioral anomaly in the monitored system.

Methods and systems for detecting and correcting anomalies includes generating historical binary codes from historical time series segments. The historical time series segments are each made up of measurements from respective sensors. A latest binary code is generated from a latest time series segment. It is determined that the latest time series segment represents anomalous behavior, based on a comparison of the latest binary code to the historical binary codes. The sensors are ranked, based on a comparison of time series data of the sensors in the latest time series segment to respective time series data of the historical time series, to generate a sensor ranking. A corrective action is performed responsive to the detected anomaly, prioritized according to the sensor ranking.

A method of determining the location and size of a crack in a blade includes measuring a time of arrival of a tip of the blade at an angular position in a rotation, using the time of arrival to calculate a displacement of the tip of the blade, and using the displacements to calculate a first vibration condition and a second vibration condition for the blade. The method also includes comparing the first vibration condition and the second vibration condition for the blade to a predetermined baseline first vibration condition and a predetermined baseline second vibration condition for the blade to determine a change in the first vibration condition and a change in the second vibration condition, and using the magnitude of the change in the second vibration condition relative to the change in the first vibration condition to determine the likely location of the crack and using the magnitude of the change in the first vibration condition and the change in the second vibration condition to determine the size of the crack.

The progress of deterioration of a manufacturing facility is prevented while keeping KPI within an allowable range. A facility diagnosis device includes a deterioration prevention mode definition storage unit that stores information including an operation control method for preventing deterioration of a manufacturing facility or a portion thereof for each of predetermined deterioration prevention modes; a KPI calculation unit that calculates a predetermined KPI by using a deterioration degree predicted for each of the deterioration prevention modes for the manufacturing facility or the portion of the manufacturing facility, and determines whether the KPI satisfies a predetermined condition; a deterioration prevention determination unit that determines a deterioration prevention mode that should be executed from a satisfaction determination result; and a control information output unit that outputs control information on the manufacturing facility or the portion of the manufacturing facility according to the deterioration prevention mode that should be executed.

An event waveform extracting unit (3) extracts an event waveform from time-series data. A co-occurrence rate calculating unit (4) calculates co-occurrence rates of event waveforms among the time-series data. A grouping unit (5) classifies the time-series data into groups depending the co-occurrence rates of the event waveforms. An event information generating unit (6) determines the time at which the periods during which event waveforms occur overlap with each other among the time-series data included in each group, and generates event information identifying an event related to the event waveforms on the basis of the determined time.

A method of monitoring one or more manufacturing components includes clustering vibration data associated with the one or more manufacturing components to generate a plurality of clusters, determining a vibration characteristic of the one or more manufacturing components based on the plurality of clusters, comparing auxiliary data associated with the one or more manufacturing components and an auxiliary data prediction model associated with the one or more manufacturing components, and determining an auxiliary characteristic of the one or more manufacturing components based on a comparison of the auxiliary data associated and the auxiliary data prediction model. The method includes determining a state of the one or more manufacturing components based on the vibration characteristic and the auxiliary characteristic and broadcasting a notification based on the state.

A method for predicting an operating anomaly comprises steps of (i) taking an assembly comprising at least a first and a second equipment item, each equipment item comprising a first operating parameter, (ii) recording and storing measurements over time of the first parameters for the first and the second equipment items, (iii) collecting the measurements during or after the completion of at least one part of an operating cycle, (iv) processing the collected measurements to detect a possible malfunction of the first and second equipment items by establishing a coefficient of determination, (v) emitting a first notification indicating the possible malfunction and/or triggering additional steps if the first coefficient of determination is less than a first threshold, and (vi) emitting a second notification and/or adjusting the first threshold if the first coefficient of determination is greater than or equal to the first threshold.

A Dielectric Energy Storage System (DESS), a Dielectric Energy Storage System Management System (DESS-MS), and method that stores energy for a wide variety of applications.

An application processor receives first and safety state information from first and second microcontrollers, and respective first and second sets of bytes forming a first identifier of the first microcontroller and a second identifier of the second microcontroller. The processor concatenates a safety message including the first and second safety state information, the safety message including the first set of bytes and the second set of bytes. The processor transmits the safety message to a second application processor of a safety controller, which separates, the first set of bytes and the second set of bytes, compares at least one of the first set of bytes and the second set of bytes to a data structure of known microcontroller identifiers, and verifies the safety state information based on identifying a match.

A microcontroller receives, from a device, an input signal having a value. The first microcontroller generates an adjusted value by adjusting the value to an adjusted value within a range of tolerance of a state determination system, and determines a first range of the adjusted value, the first range being within one of an asserted range, an unasserted range, or a fault range. The first microcontroller compares the first range to a second range, the second range derived based on one or more of a different input signal or a different microcontroller, and determines a result of the comparison, the result being an asserted state where the first range and the second range both are within an asserted range, the result being an unasserted state where both ranges are within an unasserted range, and the result otherwise being a fault state, and outputs the result to an output controller.