Use of predictive maintenance in automotive industry

Question

I read IoT and Predictive Maintenance by Bosch.

The article states:

Predictive maintenance is one such IoT/M2M solution that helps lower operating and capital costs by facilitating proactive servicing and repair of assets, while allowing the more efficient use of repair resources – both human labor and replacement products

For vehicles equipped with such technology, does the service company use telemetry to fetch data from vehicles, mine the data to predict repairs/maintenance needs, and alerts the owner?

My car's dashboard has a number of indicators. But, generally for me and others I know, goal is to avoid these warnings and go with servicing schedule. Even then, there are times we aren't alerted by the dash, people do report mis-alerts, service personnel do not detect failures. I hope technology is moving forward, there are ways to upload data and predict which dashboard isn't equipped. E.g., car engine quickly heats up but not enough to light dash-light

I am curious to know if there are deployments of this or similar technology?

Answer 1

Calling this an IoT solution is maybe a little bit optimistic when describing current deployments. The overall goal is to move away from a set of regular service schedules (which is quite a primitive approach) and optimise the trips to the workshop to be fewer, and cover more items at once. This has probably been done with oil changes (taking temperature into account) for longer than anything else.

Taking data from multiple sources, aggregating across multiple vehicles to identify early indicators of potential failure, etc. is more of an emerging field - but companies like Tesla certainly do collect telemetry from their vehicles (and use this to tune their software, as well as sending notifications to the users). A small car is maybe not the best target to be collecting preventative maintenance data on, although there is no reason that the consumables couldn't be instrumented (and this is actually quite important for pool cars, or autonomous vehicles).

With larger machinery (or electronic components which have a limited life) there may be more scope for correlating behaviour across a wider population - and scheduling down-time maybe gives a better return for expensive equipment.

As for handling the alerts, cars are not limited to displaying a set of pre-set icons using bulbs, things have moved on. Many cars have a small dot-matrix display at least, and full colour fully flexible dash displays are not unusual. Provided the reliability issues are addressed, a flexible display may actually save money over traditional mechanical indicators.

If there is a safety issue, the car can adopt a 'limp home' mode, or a pop-up on the dash which needs to be dismissed before the car starts. How sensible it is to have cars linked to the internet, with phone apps for remote control is debatable, but this is the new norm.