State determination device and method
AssigneeFanuc Corporation
InventorAtsushi Horiuchi
Life of this patent
Estimating the term…
Abstract
A state determination device acquires data on an injection molding machine and stores conditions for classifying the acquired data on the injection molding machine and a plurality of learning models. The state determination device further classifies the acquired data based on the stored classification conditions and settles a learning model to which the classified data are applied, among the plurality of stored learning models. Subsequently, the state determination device performs machine learning for the learning model settled as an application destination, based on the classified data.
Claims11
A state determination device for determining an operating state of an injection molding machine, the state determination device comprising:
- a processor configured to acquire data on the injection molding machine, wherein the data on the injection molding machine include time-series data;
- and
- a memory storing
- (i) classification conditions for classifying the data on the injection molding machine, wherein the classification conditions include a condition for dividing the time-series data by a time interval, and the time interval is at least one of a plurality of intervals in a molding process of the injection molding machine, and
- (ii) a plurality of learning models, wherein each of the plurality of learning models is associated with an interval of the plurality of intervals in the molding process;
- wherein
- the processor is configured to
- divide the time-series data by the time interval based on the classification conditions,
- classify the data based on the classification conditions,
- settle a learning model, to which the classified data are applied, among the plurality of learning models,
- perform machine learning for the learning model settled as an application destination based on the classified data, and
- manage the injection molding machine by outputting a command based on the learning model.
A state determination device for determining an operating state of an injection molding machine, the state determination device comprising:
- a processor configured to acquire data on the injection molding machine, wherein the data on the injection molding machine include time-series data;
- a memory storing
- (i) classification conditions for classifying the data on the injection molding machine, wherein the classification conditions include a condition for dividing the time-series data by a time interval, and the time interval is at least one of a plurality of intervals in a molding process of the injection molding machine, and
- (ii) a plurality of learning models, wherein each of the plurality of learning models is associated with an interval of the plurality of intervals in the molding process;
- wherein
- the processor is configured to
- divide the time-series data by the time interval based on the classification conditions,
- classify the data based on the classification conditions,
- settle a learning model to which the classified data are applied, among the plurality of learning,
- perform estimation of an abnormality related to the operating state of the injection molding machine using the learning model settled as an application destination, based on the classified data, and
- in response to estimating the operating state as being abnormal, output at least one of commands for suspension of operation of the injection molding machine, deceleration of motor torque to the injection molding machine, or restriction of the motor torque to the injection molding machine.
A state determination method of determining an operating state of an injection molding machine, the state determination method comprising:
- acquiring data on the injection molding machine, wherein the data on the injection molding machine include time-series data;
- dividing the time-series data by a time interval based on classification conditions for classifying the data on the injection molding machine, wherein the time interval is at least one of a plurality of intervals in a molding process of the injection molding machine;
- classifying the data based on the classification conditions;
- settling a learning model, to which the classified data are applied, among a plurality of learning models, wherein each of the plurality of learning models is associated with an interval of the plurality of intervals in the molding process;
- performing processing related to the learning model settled as an application destination based on the classified data, the performing the processing including
- performing machine learning for the settled learning model, or
- performing estimation using the settled learning model;
- and
- managing the injection molding machine by outputting a command based on a result of the performing the processing related to the settled learning model.
Dependencies are inferred from the claim text.