How do I incorporate predictive maintenance without sensors?

Almost by definition, predictive maintenance uses sensors, but the core principle of PdM doesn’t necessarily depend on them. There are two possible ways to incorporate PdM without using the usual sensors, and they’re kind of on opposite ends of the spectrum:

  1. You correlate maintenance data, including work ordersasset failures, and PM tasks and use those to predict future failures (low-tech).
  2. You use creative methods to monitor equipment without relying on infraredvibration analysisultrasound, etc. (high tech)

The first method requires you to be tracking of data already available to you. This data would include:

  • Frequency of work orders for a given asset
  • Frequency of given faults within an asset
  • When those failures or faults occur

You’d need to pay very careful attention to the types of work done on assets and whether certain conditions seem to precipitate a failure. Timeframes may be important here—for instance, your data might suggest that the gasket on your hammer mill tends to fail every six months, or that the bearing system on a turbine tends to fail a month after it starts making that one grinding noise.

Probably the easiest way to track all this data is with the use of a CMMS. By using a CMMS to track maintenance reports, work orders, and other data related to a given asset, you can make predictions about when certain tasks should be performed to keep assets running.

Now, let’s take a look at the other method: finding ways to automatically monitor an asset’s condition without using traditional hardware.

One way to do this was recently showcased in Germany which used drivers with “virtual sensors.”

Essentially, what these drives do is measure the current, speed, and voltage on motors to infer data about the asset, such as oil temperature, vibration, or stator insulation. They found that the drive’s results weren’t far off from actual measurements, making this a possible alternative to regular sensors.

But again, it requires large volumes of data in order to work well.

In either case, in order to make PdM work without sensors, the one constant is you need to collect a great deal of information, figure out what it means, and set parameters based on your findings.

Want to keep reading?

Good choice. Here are some similar articles!

IIot Security: Know the Risks, Take Preventive Measures

The connectivity that allows IIoT to deliver amazing amounts of data also gives potential access of data and control of critical devices to hackers.

Preventative Maintenance
View Article

What is DFMEA: How To Use Design FMEA to Keep Business Safe

Design failure mode and effects analysis (DFMEA) is a process tool that helps companies locate and repair design failures.

Preventative Maintenance
View Article

What is level of repair analysis (LORA)?

Without getting too technical, level of repair analysis, or LORA, is a process used to determine when and where an asset should be repaired.

Preventative Maintenance
View Article

Sign up for a personalized tour today.

Information is 100% secure.
UpKeep logo

Sign up for newsletter!

Our newsletter full of inspiration, podcasts, trends & news.

UpKeep logo

Sign up for newsletter!

Our newsletter full of inspiration, podcasts, trends & news.

UpKeep icon
This website uses cookies to ensure you get the best experience. Privacy Policy