Predictive maintenance

Everything you need to know about predictive maintenance

Get the Maintenance Manager's Guide to Digital Transformation

What is predictive maintenance?

Predictive maintenance (PdM) is a technique that uses data analysis tools and techniques to detect anomalies in your operation and possible defects in equipment and processes so you can fix them before they result in failure.

Ideally, predictive maintenance allows the maintenance frequency to be as low as possible to prevent unplanned reactive maintenance, without incurring costs associated with doing too much preventive maintenance.

How does predictive maintenance work?

Predictive maintenance uses historical and real-time data from various parts of your operation to anticipate problems before they happen. There are three main areas of your organization that factor into predictive maintenance:

  1. The real-time monitoring of asset condition and performance
  2. The analysis of work order data
  3. Benchmarking MRO inventory usage

Start benchmarking your MRO inventory with this cycle count template

There are several key elements to predictive maintenance with technology and software being one of these critical pieces. Namely, the Internet of Things (IoT), artificial intelligence, and integrated systems allow for different assets and systems to connect, work together and share, analyze, and action data.

These tools capture information using predictive maintenance sensors, industrial controls, and business systems (like EAM software and ERP software). They then make sense of it and use it to identify any areas that need attention. Some examples of using predictive maintenance and predictive maintenance sensors include vibration analysis, oil analysis, thermal imaging, and equipment observation. Visit our condition-based maintenance page to learn more about these methods.

Ready to pitch some new tech? Get your free presentation template here

Choosing the correct technique for performing condition monitoring is an important consideration that is best done in consultation with equipment manufacturers and condition monitoring experts.

When is predictive maintenance suitable?

checkmark icon

Suitable applications

Applications that are suitable for predictive maintenance (PdM) include those that:

  • Have a critical operational function
  • Have failure modes that can be cost-effectively predicted with regular monitoring
cross icon

Unsuitable applications

Unsuitable applications for predictive maintenance include those that:

  • Do not serve a critical function
  • Do not have a failure mode that can be cost-effectively predicted

See if an asset is a match for PdM with this asset criticality analysis template

Who uses predictive maintenance?

Generally speaking, a maintenance manager and maintenance team use predictive maintenance tools and asset management systems to monitor impending equipment failure and maintenance tasks.

How is predictive maintenance used?

Let's say you have a pump on your production line. If this pump breaks, it will stall production until you can fix or replace it, which could take hours. Your asset management system can monitor the pump’s temperature. If its temperature rises past a certain threshold, you know the pump is under stress and could possibly fail soon. You can then schedule some time to perform preventive maintenance before a complete failure stops production.

Predictive maintenance software can notify the maintenance team of the stress on a specific machine. It uses predictive analytics to flag issues and let the team know to set up preventative maintenance, which helps reduce costly downtime.

Advantages of predictive maintenance

Compared with preventive maintenance, predictive maintenance ensures that a piece of equipment requiring maintenance is only shut down right before imminent failure. This reduces the total time and cost spent maintaining equipment.

When predictive maintenance is working effectively as a maintenance strategy, maintenance is only performed on machines when it is required. That is, just before failure is likely to occur. This brings several cost savings:

  • Minimizing the time the equipment is being maintained
  • Minimizing the production hours lost to maintenance
  • Minimizing the cost of spare parts and supplies

Predictive maintenance programs have also been shown to lead to a tenfold increase in ROI by:

  • 25%-30% reduction in maintenance costs
  • 70%-75% decrease of breakdowns
  • 35%-45% reduction in downtime

These cost savings come at a price, however. Some condition monitoring techniques are expensive and require specialist and experienced personnel for data analysis to be effective.

Disadvantages of predictive maintenance

Compared with preventive maintenance, the cost of the condition monitoring equipment needed for predictive maintenance is often high. The skill level and experience required to accurately interpret condition monitoring data is also high. Combined, these can mean that condition monitoring has a high upfront cost. Some companies engage condition monitoring contractors to minimize the upfront costs of a condition monitoring program.

Not all assets have failures that may be more cost-effectively maintained using preventive maintenance or a run-to-failure maintenance strategy. Judgment should be exercised when deciding if predictive maintenance is best for a particular asset. Techniques such as reliability-centered maintenance provide a systematic method for determining if predictive maintenance is a good choice as an asset maintenance strategy for the particular asset of interest.

Predictive vs. preventive maintenance

Predictive maintenance

Preventive maintenance

  • Is proactive maintenance
  • Uses predictive maintenance technology to address potential problems and schedule corrective maintenance before a failure occurs
  • Focuses on asset performance, predictive analytics, and data collection for services on machinery
  • Improves overall inventory efficiency since machine parts are not run to failure and are also not replaced too soon
  • Does not often require machine downtime, and if it does, it’s generally short
  • Is planned maintenance, usually for set times and dates or after a specific data metric is reached
  • Often utilizes scheduling software to notify teams or individuals of upcoming equipment maintenance
    • For example, when a car reaches a certain amount of kilometers traveled it will notify the driver for an oil change
  • Gives you good indicators of asset performance and asset health
  • Often requires machine downtime

The bottom line: the impact of predictive maintenance

Predictive maintenance seeks to define the best time to do work on an asset so maintenance frequency is as low as possible and reliability is as high as possible without unnecessary costs.

Maintenance managers use predictive maintenance, sensor data, artificial intelligence,and machine learning to help their teams make better decisions about when maintenance should be performed.

Utilizing the Internet of Things is key for implementing a successful predictive maintenance program, as is the use of predictive maintenance sensors and techniques, such as vibration analysis, oil analysis, thermal imaging, and equipment observation.

Although there are some disadvantages to predictive maintenance (high start-up costs, the need for specialized skills, the limitations of some equipment), it allows maintenance to be performed only when required, helping facilities cut costs, save time and maximize resources. Consultation with equipment manufacturers and condition monitoring experts should be undertaken before deciding if predictive maintenance is best for particular assets.

3D Fiix logo

Empower your maintenance team

Leverage the cloud to work together, better in the new connected age of maintenance and asset management.