Federated learning for multi-label classification model for oil pump management

A computer implemented method for predicting failure of assets, comprising:

• partitioning features of the assets into static features, semi-static features and dynamic features;
• forming cohorts of the assets based on the static features and the semi-static features;
• generating a local model at a local site for each of the cohorts;
• sharing the local model with a central database;
• forming a pool of local models from a plurality of the local models from a respective plurality of the local sites;
• creating a global model based on an aggregation of the plurality of the local models from the plurality of the local sites;
• at each of the plurality of local sites:
• choosing one of the global model and one of the plurality of local models from the pool of local models for each of the cohorts;
• and
• operating the chosen model on local data to predict the failure of one or more of the assets belonging to one of the cohorts.

A computer implemented method for prediction failure of assets, comprising:

• partitioning features of the assets into static features, semi-static features, and dynamic features;
• forming cohorts of the assets based on the static features and the semi-static features;
• generating a local model at a local site for each of the cohorts;
• creating a global model for each of the cohorts;\
• at each of the plurality of local sites:
• choosing one of the global model and the local model for each of the cohorts;
• and
• operating the chosen model on data local to the local site to predict failure of one or more of the assets belonging to one of the cohorts.

A non-transitory computer readable storage medium tangibly embodying a computer readable program code having computer readable instructions that, when executed, causes a computer device to carry out a method of prediction failure of assets, the method comprising:

• partitioning features of the assets into static features, semi-static features, and dynamic features;
• forming cohorts of the assets based on the static features and the semi-static features;
• generating a local model at a local site for each of the cohorts;
• sharing the local model with a central database;
• forming a pool of local models from a plurality of the local models from a respective plurality of the local sites;
• creating a global model based on an aggregation of the plurality of the local models from the plurality of the local sites;
• at each of the plurality of local sites:
• choosing, one of the global model and one of the plurality of local models from the pool of local models for each of the cohorts;
• and
• operating the chosen model on the local data to predict failure of one or more of the assets belonging to one of the cohorts.

A non-transitory computer readable storage medium tangibly embodying a computer readable program code having computer readable instructions that, when executed, causes a computer device to carry out a method of prediction failure of assets, the method comprising:

• partitioning features of the assets into static features, semi-static features, and dynamic features;
• forming cohorts of the assets based on the static features and the semi-static features;
• generating a local model at a local site for each of the cohorts;
• creating a global model for each of the cohorts;
• at each of a plurality of local sites:
• choosing one of the global model and the local model for each of the cohorts;
• and
• operating the chosen model on the local data to predict failure of one or more of the assets belonging to one of the cohorts.