Back to results
US 11,982,992 B2Granted
Task and cycle time detection method and system
AssigneeHitachi, Ltd.
InventorsYasutaka Serizawa, Sudhanshu Gaur
Life of this patent
Estimating the term…
Abstract
Example implementations described herein involve systems and methods that can involve extracting features from each of a plurality of time-series sensor data, the plurality of time-series sensor data associated with execution of one or more operations; clustering the extracted features into a plurality of tasks that occur from execution of the one or more operations, each of the plurality of tasks associated with a clustering identifier (ID) from the clustering; and calculating a cycle time of the cycle based on the initiation and end of the cycle recognized by referencing a cycle pattern model, wherein the cycle pattern model comprises configuration information of a cycle including a set from a plurality of the clustering IDs.
Claims13
A method, comprising:
- extracting features from each of a plurality of time-series sensor data, the plurality of time-series sensor data associated with execution of one or more operations;
- clustering the extracted features into a plurality of tasks that occur from execution of the one or more operations, each of the plurality of tasks associated with a clustering identifier (ID) from the clustering;
- calculating a cycle time of the cycle based on the initiation and end of the cycle recognized by referencing a cycle pattern model, wherein the cycle pattern model comprises configuration information of a cycle comprising a set from a plurality of the clustering IDs;
- and
- learning the cycle pattern model, the learning the cycle pattern model comprising:
- extracting features from each of a plurality of other time-series sensor data, the plurality of other time-series sensor data associated with execution of one or more operations,
- clustering the extracted features into a plurality of clusters, each of the cluster associated with a clustering identifier (ID) from the clustering,
- executing frequent pattern extraction on the clustering IDs,
- associating production operation information received in time series to the clustered features,
- determining initiation timing that meets a requirement from the production operation information, and
- determining the clustering ID from the plurality of clustering IDs which corresponds to the initiation of the cycle.
8 more elements
A non-transitory computer readable medium, storing instructions for executing a process, the instructions comprising:
- extracting features from each of a plurality of time-series sensor data, the plurality of time-series sensor data associated with execution of one or more operations;
- clustering the extracted features into a plurality of tasks that occur from execution of the one or more operations, each of the plurality of tasks associated with a clustering identifier (ID) from the clustering;
- calculating a cycle time of the cycle based on the initiation and end of the cycle recognized by referencing a cycle pattern model, wherein the cycle pattern model comprises configuration information of a cycle comprising a set from a plurality of the clustering IDs;
- and
- learning the cycle pattern model, the learning the cycle pattern model comprising:
- extracting features from each of a plurality of other time-series sensor data, the plurality of other time-series sensor data associated with execution of one or more operations,
- clustering the extracted features into a plurality of clusters, each of the cluster associated with a clustering identifier (ID) from the clustering,
- executing frequent pattern extraction on the clustering IDs,
- associating production operation information received in time series to the clustered features,
- determining initiation timing that meets a requirement from the production operation information, and
- determining the clustering ID from the plurality of clustering IDs which corresponds to the initiation of the cycle.
8 more elements
An apparatus, comprising:
- a processor, configured to:
- extract features from each of a plurality of time-series sensor data, the plurality of time-series sensor data associated with execution of one or more operations;
- cluster the extracted features into a plurality of tasks that occur from execution of the one or more operations, each of the plurality of tasks associated with a clustering identifier (ID) from the clustering;
- calculate a cycle time of the cycle based on the initiation and end of the cycle recognized by referencing a cycle pattern model, wherein the cycle pattern model comprises configuration information of a cycle comprising a set from a plurality of the clustering IDs;
- and
- learn the cycle pattern model, the learn the cycle pattern model comprising:
- extract features from each of a plurality of other time-series sensor data, the plurality of other time-series sensor data associated with execution of one or more operations,
- cluster the extracted features into a plurality of clusters, each of the cluster associated with a clustering identifier (ID) from the clustering,
- execute frequent pattern extraction on the clustering IDs,
- associate production operation information received in time series to the clustered features,
- determine initiation timing that meets a requirement from the production operation information, and
- determine the clustering ID from the plurality of clustering IDs which corresponds to the initiation of the cycle.
9 more elements
Dependencies are inferred from the claim text.