NASHVILLE, TN -- One of the products introduced during the in.sight User Conference + Expo in Nashville was TMW Systems' TMT Predict.Fault Code, a predictive maintenance application designed to predict engine and aftertreatment component failures up to three days before they happen.

In an interview, Renaldo Adler, TMW's principal of asset maintenance, fleets and service centers, said the goal was to predict faults before "the red light goes on."

The system uses predictive models with data from 80,000 vehicles that have traveled over 1 million miles. The data was then analyzed by a team of scientists to identify patterns that occur before a part fails.

Using the PeopleNet Mobile Gateway, the application gathers 80 performance variables from the engine and aftertreatment system. Those variable are then transmitted to the cloud where they are fed into eight models, which were developed by Vusion (a sister Trimble company), and then analyzed for indicators of possible failures.

The amount of data is key, Adler explained. Typically fleets have used historical data to set maintenance intervals for various components. As a result, the more historical information gathered, the better. A fleet of 1,000 trucks and lots of miles will have better info than a fleet with 20 or 30 trucks, he says.

The Predict.Fault Code application takes advantage of the aggregated data to develop a fuller picture of vehicle health. The application is currently available for vehicles equipped with a factory-installed or aftermarket-installed PMG (PeopleNet Mobile Gateway).

The system can alert fleet managers of a possible failure and the vehicle can be called in for a full checkup. Over time, Alder said, the application will be able to provide technicians with more detailed instructions. As he pointed out, the more data that is collected, the more refined the predictions can be and, down the road, the hope is to predict even more problems.