Subsystem Health Score

A non-transitory computer-readable medium having instructions stored thereon that are executable to cause a computing system to:

• identify at least one abnormal-condition indicator associated with a given subsystem of an asset;
• based on the identified at least one abnormal-condition indicator, identify a subset of historical operating data for a plurality of assets, wherein the historical operating data comprises (i) historical abnormal-condition data associated with one or more failures that occurred at the plurality of assets in the past and (ii) historical sensor data indicating operating conditions of the plurality of assets in the past;
• based on the identified subset of the historical operating data, define a predictive model for outputting a health metric indicating whether at least one failure from a group of failures is likely to occur at the given subsystem within a given period of time in the future;
• receive sensor data indicating at least one operating condition of a given asset;
• based on the received sensor data, execute the predictive model to determine, for the given asset, a health metric indicating whether at least one failure from the group of failures is likely to occur at the given subsystem within the given period of time in the future;
• and
• transmit, to a computing device, health-metric data indicating the determined health metric for the given asset to facilitate causing the computing device to display a representation of the determined health metric for the given asset.

A computer-implemented method, the method comprising:

• identifying at least one abnormal-condition indicator associated with a given subsystem of an asset;
• based on the identified at least one abnormal-condition indicator, identifying a subset of historical operating data for a plurality of assets, wherein the historical operating data comprises (i) historical abnormal-condition data associated with one or more failures that occurred at the plurality of assets in the past and (ii) historical sensor data indicating operating conditions of the plurality of assets in the past;
• based on the identified subset of the historical operating data, defining a predictive model for outputting a health metric indicating whether at least one failure from a group of failures is likely to occur at the given subsystem within a given period of time in the future;
• receiving sensor data indicating at least one operating condition of a given asset;
• based on the received sensor data, executing the predictive model to determine, for the given asset, a health metric indicating whether at least one failure from the group of failures is likely to occur at the given subsystem within the given period of time in the future;
• and
• transmitting, to a computing device, health-metric data indicating the determined health metric for the given asset to facilitate causing the computing device to display a representation of the determined health metric for the given asset.