In the beginning, there was don't fix it if it ain't broke. And it was not good. Then maintenance experts put their faith in preventive maintenance. And it was better but not good enough.

Seeking still more goodness in the shop, on the truck, on the road, the words came slowly but soon became more and more apparent to those in the brotherhood of the wrench, and of the calculator. Why just try and prevent a problem? Why not predict when maintenance would be needed and beat the devil, as it were, to be sure?

Anyone who's been around trucking for a few years or more has heard the term “predictive maintenance” kicked around at a TMC meeting or two or twenty. But despite all the dollars poured into developing trucking-related business software since the 1980s, this holy grail of maintenance has remained elusive.

But now, lo and behold, Chicago-based Accenture Technology Labs says it has the key to this kingdom in hand with an “innovative, cost-cutting solution that can determine equipment failures before they happen,” dubbed Predictive Monitoring.

Accenture reports Predictive Monitoring, currently under test on municipal buses operating in a “major Midwest city,” collects historical and real-time data from sensors and “then uses sophisticated analytic models to predict the future.”

According to Jim Richmond, an Accenture consultant, the technology behind Predictive Monitoring uses real-time sensors and enterprise data to “pre-empt” equipment failures.

“Most equipment maintenance is done reactively, after a breakdown occurs, or routinely on a schedule, whether or not it's necessary,” points out Richmond. “By analyzing real-time sensor and enterprise data, we can pre-empt equipment failures before they occur. This reduces equipment maintenance costs and improves maintenance-related business processes.”

He explains that via Predictive Monitoring, an information model can be built for each particular asset that, based on mathematical modeling, can predict when components will break down.

The process starts with inputting “healthy” operating data to give “a picture of how the equipment behaves when it's humming along,” says Richmond. In effect, that represents the various modes and functions of the equipment's standard operating cycle.

“Once this model is built, we then take real time data of how the individual vehicle runs and compare it to where the model says it should be,” he continues. “If it starts deviating from the healthy model of the asset, the system can then do some prognostics and make a prediction as to the type and immediacy of a failure.”

Richmond says Predictive Monitoring models can predict failure better than manufacturers by looking more closely at equipment under different conditions, examining a number of sensors in relation to one another, and building an individualized model for each asset.

“The engine oil temperature for a properly working Cummins ISV engine, for example, is between 140 and 200 degrees, yet that doesn't necessarily take into account the differences during warm-up, idle, and full throttle, or whether it's in a very warm place like Phoenix or a very cold one like Newfoundland,” he explains. “As long as the variation is in that range, a warning light won't go on.”

Alas, even a holy grail has its limits. “Although we can predict with a great deal of certainty when a bearing is going to overheat or a compressor blade will crack, it doesn't eliminate the need for standard maintenance,” Richmond cautions.

For more information, go to and search for “predictive monitoring.”