Systems and processes for optimizing operation of industrial equipment

A method for optimizing machine operation, comprising:

• determining, based at least in part on an optimal multivariate model, an optimal set-point for each data source of a plurality of data sources associated with a machine;
• receiving operating data from at least one of the plurality of data sources, the at least one of the plurality of data sources being selected based at least in part on a corresponding mutual information correlation value and a corresponding importance value;
• determining one or more deviations between the operating data and each optimal set-point;
• determining an overall health metric of the machine based at least in part on the one or more deviations;
• and
• controlling operation of the machine based at least in part on the overall health metric.

A method for generating a machine learning model to classify data source data sets associated with a machine, comprising:

• retrieving historical data corresponding to operation of a machine, wherein the historical data comprises readings from a plurality of data sources associated with the machine;
• generating a training dataset for training the machine learning model based at least in part on the historical data, wherein the training dataset comprises:
• a first subset of the readings associated with a plurality of optimal runtime time intervals for the machine;
• and
• a second subset of the readings associated with a plurality of pre-error time intervals for the machine;
• training the machine learning model to classify data source datasets as either optimal runtime or pre-error using the training dataset;
• outputting the machine learning model for analysis of machine operation;
• and
• controlling the machine operation based at least in part on the machine learning model.