Abnormality determination device and abnormality determination system
AssigneeFanuc Corporation
InventorKeita Hada
Life of this patent
Estimating the term…
Abstract
An abnormality determination device acquires observation data observed during an operation of an industrial machine, extracts partial time-series data, including a portion representative of a feature of an operating state at a specified timing, from the observation data, calculates a statistical amount from the extracted partial time-series data, and performs processing for machine learning related to determination of operation abnormality of the industrial machine, based on the calculated statistical amount.
Claims12
An abnormality determination device configured to determine abnormality of an industrial machine, the abnormality determination device comprising:
- a processor configured to:
- acquire, as observation data, continuous data on an operation of the industrial machine observed during the operation,
- extract, from the observation data, partial time-series data including a portion representative of a feature of an operating state at a predetermined specified timing, and
- calculate at least one statistical amount from the partial time-series data, wherein the processor comprises a machine learning device configured to perform processing for machine learning related to determination of operation abnormality of the industrial machine, based on the calculated statistical amount,
- wherein the machine learning device is further configured, as the machine learning processing, to generate a learning model that has learned the calculated statistical amount.
An abnormality determination system, comprising:
- a plurality of devices connected to one another through a network, wherein
- the plurality of devices include at least one abnormality determination device configured to determine abnormality of an industrial machine, the at least one abnormality determination device comprising a first abnormality determination device,
- the first abnormality determination device comprising a processor configured to
- acquire, as observation data, continuous data on an operation of the industrial machine observed during the operation;
- and
- extract, from the observation data, partial time-series data including a portion representative of a feature of an operating state at a predetermined specified timing, and
- calculate at least one statistical amount from the partial time-series data,
- wherein the processor comprises a machine learning device configured to perform processing for machine learning related to determination of operation abnormality of the industrial machine, based on the calculated statistical amount, and
- the machine learning device is further configured, as the machine learning processing, to generate a learning model that has learned the calculated statistical amount.
Dependencies are inferred from the claim text.