Back to results
US 12,045,043 B2Granted
Machine learning based resource allocation in a manufacturing plant
AssigneeSap SE
InventorsAnuj Kumar, Sathish Karhtik Ramu
Life of this patent
Estimating the term…
Abstract
A work center in a manufacturing setup includes a machine learning model that uses a decision tree to facilitate the work of a supervisor on the production line to choose a machine to perform a particular operation on a particular part. The decision tree outputs a ranking of machines indicating the suitability of the ranked machines for performing the particular operation on the particular part.
Claims20
A method in a production line, the method comprising:
- training a decision tree using a machine learning algorithm and training data based on part attributes, operation attributes, and operation results for operations on parts by a plurality of first machines in the production line, the decision tree comprising a plurality of leaf nodes, each leaf node associated with a ranking of the plurality of first machines;
- receiving attributes of a part to be processed in the production line;
- receiving attributes of an operation to be performed on the part;
- selecting a machine from among the plurality of first machines in the production line that can perform the operation on the part, including:
- executing the decision tree using the attributes of the part and the attributes of the operation to determine a leaf node associated with a ranking of machines selected from the plurality of first machines, the ranking of machines representing machines determined by the decision tree to be suitable for the operation to be performed on the part, wherein the machines in the ranking of machines are ranked based on the attributes of the part and the attributes of the operation and indicate their suitability to perform the operation on the part;
- outputting the ranking of machines to a decision maker;
- and
- receiving input from the decision maker indicative of a machine selected based on the ranking of machines;
- and
- deploying the selected machine to perform the operation on the part.
7 more elements
A non-transitory computer-readable storage medium having stored thereon computer executable instructions, which when executed by a computer device, cause the computer device to:
- train a decision tree using a machine learning algorithm and training data based on part attributes, operation attributes, and operation results for operations on parts by a plurality of first machines in the production line, the decision tree comprising a plurality of leaf nodes, each leaf node associated with a ranking of the plurality of first machines;
- receive attributes of a part to be processed in the production line;
- receive attributes of an operation to be performed on the part;
- select a machine from among the plurality of first machines in the production line that can perform the operation on the part, including:
- execute the decision tree using the attributes of the part and the attributes of the operation to determine a leaf node associated with a ranking of machines selected from the plurality of first machines, the ranking of machines representing machines determined by the decision tree to be suitable for the operation to be performed on the part, wherein the machines in the ranking of machines are ranked based on the attributes of the part and the attributes of the operation and indicate their suitability to perform the operation on the part;
- output the ranking of machines to a decision maker;
- and
- receive input from the decision maker indicative of a machine selected based on the ranking of machines;
- and
- deploy the selected machine to perform the operation on the part.
7 more elements
An apparatus comprising:
- one or more computer processors;
- and
- a computer-readable storage medium comprising instructions for controlling the one or more computer processors to be operable to:
- train a decision tree using a machine learning algorithm and training data based on part attributes, operation attributes, and operation results for operations on parts by a plurality of first machines in the production line, the decision tree comprising a plurality of leaf nodes, each leaf node associated with a ranking of the plurality of first machines;
- receive attributes of a part to be processed in the production line;
- receive attributes of an operation to be performed on the part;
- select a machine from among the plurality of first machines in the production line that can perform the operation on the part, including:
- execute the decision tree using the attributes of the part and the attributes of the operation to determine a leaf node associated with a ranking of machines selected from the plurality of first machines, the ranking of machines representing machines determined by the decision tree to be suitable for the operation to be performed on the part, wherein the machines in the ranking of machines are ranked based on the attributes of the part and the attributes of the operation and indicate their suitability to perform the operation on the part;
- output the ranking of machines to a decision maker;
- and
- receive input from the decision maker indicative of a machine selected based on the ranking of machines;
- and
- deploy the selected machine to perform the operation on the part.
10 more elements
Dependencies are inferred from the claim text.