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?

The 6 Sensors for Predictive Maintenance That Optimize Repair Timelines

Today, predictive maintenance relies on sensors in three major areas: early fault detection, failure detection, and CMMS integration.
View Article

How are sensors used in predictive maintenance?

Predictive maintenance (PdM) typically uses data from sensors that monitor various conditions on equipment. Algorithms analyze data to predict maintenance.
View Article

When should I start a predictive maintenance program?

You should start a predictive maintenance (PdM) program if you already have a preventive maintenance program in place and want to further improve uptime.
View Article

4,000+ COMPANIES RELY ON ASSET OPERATIONS MANAGEMENT

Leading the Way to a Better Future for Maintenance and Reliability

Your asset and equipment data doesn't belong in a silo. UpKeep makes it simple to see where everything stands, all in one place. That means less guesswork and more time to focus on what matters.

Capterra Shortlist 2021
IDC CMMS Leader 2021
[Review Badge] GetApp CMMS 2022 (Dark)
[Review Badge] Gartner Peer Insights (Dark)
G2 Leader