An operation mode specifying unit specifies an operation mode of a machine by comparing time-series data of an amplitude and a frequency of measurement data obtained from a sensor with definition data of the operation mode of the machine created in advance by an operation mode data creation unit. In addition, an abnormality diagnosis unit performs processing of cluster analysis for the measurement data obtained from the sensor or the like, and diagnoses abnormality of the machine according to diagnosis procedure information that is set in advance depending on the set operation mode and an abnormality mode of the machine.

Systems and methods are disclosed for asset health assessment and fleet management. An example method may include classifying a first power system asset into a first sub-system and a second sub-system. The example method may also include measuring, by a processor of a protection relay and from a first power system asset, electrical, thermal, and/or mechanical data associated with the first power system asset. The example method may also include identifying a first fault feature for the first sub-system, wherein the first fault feature is influenced by load oscillations in the first power system asset. The example method may also include comparing the first fault feature to a second fault feature of a third sub-system in a second power system asset, wherein the second fault feature is the same as the first fault feature, and wherein the second fault feature is not associated with load oscillations. The example method may also include adjusting a threshold value based on the comparison of the first fault feature to the second fault feature of the third sub-system. The example method may also include calculating, by the processor and for a first sub-system of the first power system asset, a first value based on the electrical, thermal, and/or mechanical data. The example method may also include calculating, by the processor, based on the first value, and using recent measurement data, a second value associated with the first sub-system. The example method may also include calculating, by the processor and using historical average data, a third value associated with the first sub-system. The example method may also include determining, by the processor and based on the second value and the third value, a fourth value associated with the first power system asset. The example method may also include determining, by the processor, that the fourth value is greater than a threshold value. The example method may also include generating, by the processor, a warning based on the determination that the fourth value is greater than the threshold value.

A machine learning apparatus that learns an alarm factor in a motor drive device includes a state observation unit that obtains a feature amount as a state variable from the motor drive device and an alarm factor as label data, the alarm factor corresponding to the feature amount, and a learning unit that generates a learning model for inferring a new alarm factor corresponding to a new feature amount, from a dataset created on a basis of a combination of the state variable and the label data. The feature amount includes at least one of a detected current value detected from the motor, a speed command value specifying a rotational speed of the motor, an output voltage value output to the motor, an estimated speed value of the motor, and a detected speed value of the motor.

An example method comprises receiving historical wind turbine failure data and asset data from SCADA systems, receiving first historical sensor data, determining healthy assets of the renewable energy assets by comparing signals to known healthy operating signals, training at least one machine learning model to indicate assets that may potentially fail and to a second set of assets that are operating within a healthy threshold, receiving first current sensor data of a second time period, applying a machine learning model to the current sensor data to generate a first failure prediction a failure and generate a list of assets that are operating within a healthy threshold, comparing the first failure prediction to a trigger criteria, generating and transmitting a first alert if comparing the first failure prediction to the trigger criteria indicates a failure prediction, and updating a list of assets to perform surveillance if within a healthy threshold.

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.

A hybrid data collection and analysis infrastructure combines edge-level and cloud-level computing to perform high-level monitoring and control of industrial systems and processes. Edge devices located on-premise at one or more plant facilities can collect data from multiple industrial devices on the plant floor and perform local edge-level analytics on the collected data. In addition, the edge devices maintain a communication channel to a cloud platform executing cloud-level data collection and analytic services. As necessary, the edge devices can pass selected sets of data to the cloud platform, where the cloud-level analytic services perform higher level analytics on the industrial data. The hybrid architecture operates in a bi-directional manner, allowing the cloud-level and edge-level analytics to send control instructions to industrial devices based on results of the edge-level and cloud-level analytics.

A system for managing sensors of a building includes a data repository configured to store sensor data from the sensors, a building management system (BMS) controller configured to monitor or control components of the building based on sensor data provided by the sensors, and a sensor diagnostic system. The sensor diagnostic system is configured to receive samples of the sensor data from the sensors, classify each of the samples of the sensor data as faulty or non-faulty, generate supplemental data based on a subset of the samples of the sensor data that are classified as faulty and corresponding attributes of the subset of the samples of the sensor data that are classified as faulty, and provide the supplemental data to the BMS controller to monitor or control the components of the building based on the supplemental data.

A method for facilitating analysis of a fault in a building system. The method may include determining, by a processing circuit, occurrence of a fault, and capturing, by the processing circuit at a time of occurrence of the fault, a snapshot of conditions at the time by selecting a set of data points relating to the building equipment experiencing the fault and storing, by the processing circuit, event data comprising values of the set of data points at the time of occurrence of the fault. The method may also include facilitating analysis of the fault by providing, at a later time after the time of occurrence of the fault, the snapshot via a graphical user interface. The snapshot includes the event data.

A data processing system, including a cyclic correlation establishing module, a data pattern establishing module, and a data pattern alignment module, is provided. The cyclic correlation establishing module receives a plurality of first sensor data, obtained from a first sensor operation performed on processing devices, and receives a table of processing steps and cyclic procedures. The cyclic correlation establishing module obtains a data correlation of the first sensor data according to the number of sample points in a data cycle of the first sensor data and the table to correct the first sensor data. The data pattern establishing module obtains a plurality of first data pattern features from the first sensor data. The data pattern alignment module aligns a plurality of second sensor data obtained from a second sensor operation performed on the processing devices with the first sensor data according to the first data pattern features.

Method for monitoring and controlling current distribution in load circuits of an installation control system of a technical installation, wherein a predetermined and constant output voltage is provided by a clocked power supply and distributed to the load circuits, where load circuits are protected by a switch actuated by a controller, a variation of the current in each load circuit is measured during a learning phase, a significant current profile with an associated tolerance range is derived and associated with the respective load circuit from the measured current variation which is continuously monitored by the control unit and a check is performed to determine whether a power capacity limit is reached by the clocked power supply while operate the installation, and the current consumed load circuits is reduced and/or switched off by actuating switches in load circuits in which a current variation exceeds an upper limit of the tolerance range.