Abnormality information estimation system, operation analysis system, motor control device, abnormality information estimation method, and program

An operation analysis system, comprising:

• processing circuitry configured to:
• first analyze an operation of an industrial device, based on operation data relating to the operation of the industrial device such that the operation is based on a plurality of first analysis methods performed independent of a type of a mechanism controlled by the industrial device, and
• second analyze the operation of the industrial device based on results of the first analyze using the plurality of first analysis methods and based on a second analysis method that is dependent on the type of the mechanism controlled by the industrial device;
• and
• a display device configured to output a warning when the second analyze determines that the industrial device is in abnormal operation,
• wherein the processing circuitry is configured to first analyze and second analyze by applying machine learning model to analyze operation data by analyzing magnitudes, time-series variation, distribution, or a combination thereof, of numerical values contained in the operation data.

A motor control device, comprising:

• a controller comprising circuitry configured to control a motor;
• processing circuitry configured to
• identify, based on operation data related to an operation of the motor, a plurality of unit phenomena in an abnormal phenomenon caused by the operation, the plurality of unit phenomena including mechanical characteristics of an industrial device,
• estimate abnormality information about an abnormality occurring in a mechanism driven by the motor based on the plurality of unit phenomena, which includes the mechanical characteristics of the industrial device, and
• store, in a memory, an estimation result of the abnormality information;
• and
• a display device configured to output a warning when the abnormality is estimated by the processing circuitry identifying the abnormality occurring in the mechanism,
• wherein the processing circuitry is configured to estimate by applying machine learning model to analyze operation data by analyzing magnitudes, time-series variation, distribution, or a combination thereof, of numerical values contained in the operation data.

An abnormality information estimation method, comprising:

• identifying, by processing circuitry, a plurality of unit phenomena in an abnormal phenomenon caused by an operation of an industrial device that controls a mechanism based on operation data related to the operation, the plurality of unit phenomena including mechanical characteristics of the industrial device;
• estimating, by the processing circuitry, abnormality information about an abnormality occurring in the mechanism based on the plurality of unit phenomena, which includes the mechanical characteristics of the industrial device;
• outputting, via a display device, a warning when the abnormal phenomenon is estimated by the processing circuitry identifying the abnormality occurring in the mechanism,
• wherein the processing circuitry is configured to estimate by applying machine learning model to analyze operation data by analyzing magnitudes, time-series variation, distribution, or a combination thereof, of numerical values contained in the operation data.