Luminaires which provide illumination (in some cases, in a coordinated manner with other nodes of a lighting network) in an industrial process plant include one or more environmental sensors to detect various environmental (e.g., ambient) conditions within the process plant. The luminaires transmit signals indicative of detected conditions (and optionally, respective measurements thereof) to a computing device or host which indicates, on a representation or map of a physical layout of the process plant, the respective detections at respective map locations corresponding to respective locations of the luminaires at the process plant to thereby generate an environmental condition map. The environmental condition map may be dynamically updated responsive to additional luminaire signals, utilized by a process control system to generate alarms, alerts, etc., and/or presented on user interfaces of the process control system and/or of the lighting network.

An alarm reporting apparatus determines that an alarm reporting is necessary if an abnormality occurring in a machine is to be constantly reported, determines that the alarm reporting is not necessary if the abnormality is to be reported during operation and the machine is not during operation, determines that the alarm reporting is not necessary if the abnormality is to be reported during operation, the machine is during operation, and an elapsed time from the occurrence of the abnormality has not exceeded a set monitoring time, and determines that the alarm reporting is necessary if the abnormality is to be reported during operation, the machine is during operation, and the elapsed time from the occurrence of the abnormality has exceeded the set monitoring time. When it is determined that the alarm reporting is necessary, the alarm reporting apparatus reports, to a monitoring apparatus, an alarm related to the corresponding machine.

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.

Disclosed is a system for use in a rolling mill having: (a) a roll holder housing a plurality of rollers; (b) a smart module coupled to the roll holder, the smart module comprising: (1) a power source powering the smart module; (2) a microcontroller; (3) a motor, the motor, based on instructions from the microcontroller, controlling a position of the plurality of rollers by moving the roll holder; (4) one or more position sensors, the one or more position sensors detecting the position of the roll holder; and (5) a communication module, the communication module communicating with a central controlling computer to: (i) communicate the position of the roll holder and other sensor data to the central controlling computer, and (ii) receive instructions from the central controlling computer to control the position of the roll holder.

A system for monitoring the state of health of a monitored aircraft engine comprises an anomaly detection unit which analyses engine operating parameters and raises an alarm if a result of the analysis of one of the engine operating parameters crosses a threshold, the alarm being associated with a probability of a given type of engine damage occurring. The system further comprises an engine operating conditions monitoring unit which determines a state of wear of the engine, and an alarm corroboration unit which weights the said probability of occurrence by the determined state of wear. The invention is applicable to the preventive maintenance of turbomachines.

Regarding each of a plurality of operation patterns virtually generated in regard to the operation performed by a worker with respect to an actual plant, an information processing device uses plant data related to the operation of the actual plant and uses a virtual plant which follows the actual plant, and predicts the state transition of the actual plant in the case of implementing each operation pattern. Then, the information processing device outputs each operation pattern in a corresponding manner to the state transition of the actual plant as obtained by the virtual plant.

An information processing device predicts, using a virtual plant which follows an actual plant, the occurrence of a first-type alarm in the actual plant in the case of implementation of each of a plurality of operation patterns virtually generated in relation to the operation of the actual plant by a worker. Then, the information processing device readjusts a prediction value, which serves as the basis for the prediction that the first-type alarm would be output, within a threshold value range; and performs re-prediction of the occurrence of a second-type alarm, which is different than the first-type alarm, using the virtual plant. Subsequently, based on the result of the re-prediction, the information processing device performs display control of the alarms predicted using the virtual plant.

According to one aspect of a technique the present disclosure, there is provided a processing apparatus including: an apparatus controller including a memory storing apparatus data containing monitor data containing sensor information and an alarm indicating a failure detected based on the sensor information and an alarm analysis table containing analysis items. The apparatus controller is capable of outputting the alarm containing an alarm ID for specifying a type and an occurrence time of the alarm; specifying candidates of the analysis items from the alarm ID; acquiring monitor data corresponding to the candidates; determining a rank of the cause of the alarm according to a difference between monitor data at the occurrence time and a predetermined threshold value; and displaying a relationship between the monitor data and the threshold value. The display screen displays an occurrence history of the alarm and history of acquiring the monitor data.

Apparatus and associated methods relate to a vibrational sensing system (VSS) including an accelerometer and a data processor, which determines an “operational state” of a mechanical drive unit, the processor further employing the “operational state” to gate learning of long-term vibrational data to exclude collection of non-operational data, the long-term data collected to calculate alarm thresholds. For example, vibrations from a target motor are sensed by a coupled accelerometer. Vibrational data from the accelerometer is fed into a data processor which determines the operational state of the motor. The operational state (e.g., on/off indication) may gate data collection such that data is only acquired during on-time, which may advantageously create accurate baselines from which alarm thresholds may be generated, and nuisance alarms may be avoided.

There is provided a method and system for monitoring an asset. For example, there is provided a method that includes executing, by a system configured to monitor the asset, a series of operations that can include fetching, from a database communicatively coupled to the system, a data structure including information relative to one or more sources containing event data relative to the asset. The method may include generating, from the data structure, a first table including a list of sources. The method may include generating, from the data structure, a second table including a list of unique consolidated events. The method may include generating, based on a set of predetermined rules, a mapping table configured to relate the first table and the second table. The method may include associating, based on the mapping table, an event in the second table to the one or more sources in the first table.