Systems and methods for determining machine usage severity

A system for determining machine usage severity, comprising:

• one or more processors;
• and
• one or more memory devices having stored thereon instructions that when executed by the one or more processors cause the one or more processors to:
• collect repair data for a plurality of machines over a repair time period;
• collect telematics data from a plurality of sensors for each of the plurality of machines over an activity time period;
• calculate a plurality of predictive features from the telematics data for each of the plurality of machines;
• create a severity model based on the plurality of predictive features;
• validate the severity model with the plurality of predictive features and corresponding repair data for each of the plurality of machines, wherein validating the severity model comprises calculating a severity score for each of the plurality of machines and calculating a correlation between the severity score and each of the plurality of predictive features;
• receive telematics data from a plurality of sensors on a deployed machine corresponding to a deployed period of time;
• calculate a plurality of machine predictive features from the telematics data for the deployed machine;
• feed the plurality of machine predictive features for the deployed machine into the severity model to calculate a machine usage severity score for the deployed machine, wherein the machine usage severity score for the deployed machine indicates how severely that machine has been used relative to the plurality of machines;
• and
• display a recommendation to perform maintenance on the deployed machine when the machine usage severity score exceeds a selected threshold.

One or more non-transitory computer-readable media storing computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

• receiving telematics data from a plurality of sensors on a machine performing an activity;
• collecting repair data for a plurality of machines over a repair time period;
• collecting telematics data from a plurality of sensors for each of the plurality of machines over an activity time period;
• calculating a plurality of predictive features from the telematics data for each of the plurality of machines;
• creating a severity model based on the plurality of predictive features;
• validating the severity model with the plurality of predictive features and corresponding repair data for each of the plurality of machines, wherein validating the severity model comprises calculating a severity score for each of the plurality of machines and calculating a correlation between the severity score and each of the plurality of predictive features;
• receiving telematics data from a plurality of sensors on a deployed machine corresponding to a deployed period of time;
• calculating a plurality of machine predictive features from the telematics data for the deployed machine;
• feeding the plurality of machine predictive features for the deployed machine into the severity model to calculate a machine usage severity score for the deployed machine, wherein the machine usage severity score for the deployed machine indicates how severely that machine has been used relative to the plurality of machines;
• and
• displaying a recommendation to perform maintenance on the deployed machine when the machine usage severity score exceeds a selected threshold.