Predictive Maintenance

What is predictive maintenance (PdM)?

Predictive maintenance or PdM is a proactive maintenance strategy that uses condition monitoring tools to trigger maintenance work on an asset based on signs of wear and tear or poor performance. A maintenance team that uses PdM can estimate when equipment is approaching failure and perform maintenance to prevent it. 

The goal of predictive maintenance is to make the best use of maintenance resources. By knowing when an asset may fail, maintenance managers can schedule work only when it is truly needed while still effectively preventing breakdowns.

When implemented successfully, predictive maintenance lowers operational costs, minimizes downtime, and improves overall asset health and performance.

Table of Contents

How does predictive maintenance work?
Pros and cons of predictive maintenance
Combining predictive maintenance with CMMS software
Preventive vs predictive maintenance: which one is right for you?
Application of PdM across different industries
CMMS is the ultimate preventive maintenance software

How does predictive maintenance work?

The main advantage of predictive maintenance is that maintenance work is performed when it is needed — and only when it is needed — based on an asset’s condition. However, knowing the exact condition of complex assets is anything but simple.

There are three things that organizations use to track asset condition and trigger maintenance.

• Condition-monitoring sensors installed on equipment track real-time data on performance and machine health.
• IoT technology analyzes and sends machine data to software solutions and cloud technology.
• Predictive data models use machine data and analysis to make predictions. 

1) Condition-monitoring sensors

There are a variety of condition-monitoring sensors that can be installed on assets to track their condition. They measure things like electrical currents, vibrations, temperature, pressure, oil, noise, corrosion levels, and more. The sensors you use will depend on the type of assets you are monitoring.

Condition-monitoring sensors allow you to have an accurate representation of what is happening inside the asset without any kind of productivity disruptions. In other words, you do not have to stop the asset and pull it apart in order to know it’s condition.

Based on the sensors you use and the tests you want to run, there are many condition-based predictive maintenance techniques that can be applied.

• Oil/lubrication analysis
• Vibration analysis/dynamic monitoring
• Motor circuit analysis
• Different variations of thermography
• Ultrasonic and acoustic analysis
• Radiography/radiation analysis
• Laser interferometry
• Electromagnetic measurements

For a more detailed breakdown and explanation of condition-monitoring and predictive maintenance techniques, check out this guide.

2) IoT technology

It is one thing to gather data, but quite another to analyze and use the data to help you do your job well. By using IoT (Internet of Things) technology, your sensors can collect and share data. Sharing machine data over the internet (usually WLAN or LAN-based connectivity) with other assets and software allows other systems to preform data analysis and trigger or recommend maintenance.

3) Predictive data models and algorithms

The most important part of predictive maintenance (and arguably the hardest) is building predictive algorithms. By using your data to identify patterns of machine condition, failures, and other variables,  and you can create algorithms and workflows that predict machine failures. The more variables you use, the more accurate your predictions will be. 

Algorithms and models follow a set of rules that compare an asset’s current behavior to its expected behavior. Deviations are a sign of deterioration that could lead to asset failure. Based on patterns in the type and frequency of performance deviations, predictions can be made about when a failure may occur.

Your first models may be based on asset history, personal observations and other analyses on file. You may choose to first install condition-monitoring sensors to gather baseline data before creating your first models.

Over time, sensors will generate more and more data which can be used to improve your models and make failure predictions more accurate.

The end result is an automated system that archives three main goals. 

• Monitors operating conditions via installed sensors.
• Understands and predicts patterns created by data anomalies.
• Creates alerts when there is a deviation from established thresholds.

Pros and cons of predictive maintenance

Like every other maintenance strategy, predictive maintenance comes with a clear set of pros and cons.

Predictive maintenance can require a sizeable upfront investment to buy and install condition monitoring equipment, develop predictive models, and integrate with a CMMS or other specialized software. On top of that, creating models and algorithms takes knowledge that often has to be outsourced. All of that means PdM can be complex to set up and run. This is the primary disadvantage of PdM.

However, with increasingly accessible technology, the use of predictive maintenance is expected to grow. That is because the benefits significantly outweigh the challenges. 

The bottom line is that predictive maintenance can provide a significant ROI in the long term, making this an investment work making.

Combining predictive maintenance with CMMS software

Over the years, CMMS has ushered in a shift from manual processes and reactive maintenance to more proactive strategies like preventive and predictive maintenance.

In fact, it’s safe to say that CMMS is at the front and center of PdM applications today. Here are a few reasons why.

CMMS provides the initial data to get PdM rolling

The asset information gathered over time in a CMMS forms the starting point and the initial dataset for PdM implementation. Though there are other sources like hard copy maintenance records, a CMMS will provide the most comprehensive and easy-to-use source of historical information.

CMMS integrates with PdM technology to generate automatic tasks 

A modern CMMS can automatically create an alert or generate a work order when sensors detect an asset is operating outside predefined parameters. These alerts prompt the maintenance team to take preventive actions before the machine fails.

In essence, even though PdM generates very accurate alerts, the CMMS is what translates those alerts into actionable tasks. 

By combining both technologies, users get a powerful solution that is indispensable for a modern maintenance management team. Predictive maintenance technology does the complex analysis and sends alerts, and a CMMS helps ensure the work gets executed with the greatest efficiency.

CMMS facilitates data interpretation

Although PdM tools provide valuable insights about asset condition, the data it generates can be enormous.  With the right CMMS, maintenance teams get a user-friendly tool that helps them manage and display that data in useful and customizable formats. 

CMMS serves as a central organizational tool

A CMMS presents all the information a maintenance department needs to address PdM triggers in one centralized platform that is accessible from anywhere. While PdM provides data, analysis, and predictions, a CMMS provides helpful context such as asset history, inventory, asset-specific spare parts, workforce management, repair schedules, and more.

Preventive vs predictive maintenance: which one is right for you?

The main difference between preventive maintenance and predictive maintenance is what dictates maintenance schedules. While predictive maintenance uses condition monitoring sensor data and predictive algorithms to schedule maintenance, preventive maintenance relies on equipment usage and time intervals.

Each strategy requires different approaches to other pieces of maintenance operations including inventory management, planned downtime, and overall workforce management. 

In addition, while predictive maintenance may be the more precise strategy implementing it can be challenging and expensive. As a result, it may not be cost-effective to place all of your assets in a PdM program. 

This is where preventative maintenance still plays a role. Important assets that may not be great candidates for a predictive maintenance program can be put on a preventive maintenance plan instead. Combining preventive and predictive maintenance is a recipe for success.

Application of PdM across different industries

A report by McKinsey Global Institute projects that connecting physical assets to digital tools could generate up to $11 trillion annually in economic value by the year 2025. And PdM will continue to be adopted at a greater rate as the financial and operational cost of the technology continues to drop.

How does all this impact maintenance specifically? Here are a few industries that are at the forefront of using predictive maintenance.

PdM in the manufacturing industry

Manufacturers are taking note of the benefits of PdM. The McKinsey Global Institute report also predicts that manufacturers may save between
$240B and $630B by the year 2025 through predictive maintenance.

The everyday applications of predictive maintenance in manufacturing are numerous. 

• Using vibration sensors to identify patterns of fragile spindles in milling machines.
• Measuring the temperature differential upstream and downstream of the heat exchanger to identify the first signs of clogging.
• Monitoring robot CPU and housing temperatures, as well as positioning and overload errors, and using this data to estimate the health of a robot.

PdM in the transportation industry 

Connected transportation devices are also on the rise. PdM use by fleet managers has resulted in a measurable decrease in on-road breakdowns and mechanic diagnostic time. Less unplanned downtime, lower fuel and maintenance costs, and shorter servicing time are some of the reasons why fleets are moving towards predictive maintenance.

PdM in the aviation industry

Aircraft maintenance is where predictive maintenance actually got its start back in 1943 when British scientist C.H. Waddington noted that “inspections tend to increase breakdowns” for the Royal Air Force Coastal Command 502 Squadron. Instead, he recommended a process that was more “in-tune with the actual condition of the equipment.”

PdM is still used by aviation companies to reduce the costly effects of maintenance-related flight delays and cancellations. Predictive maintenance is also used to help airlines monitor engine health and performance during flights by measuring various temperature and vibration levels.

Future trends for industrial application of predictive maintenance

As the cost of technology decreases and makes PdM easier to achieve, there will be an exponential increase in the number of use cases across different industries. 

Early adopters of PdM are sectors that can realize the highest ROI and they usually share a few key characteristics.

• high capital and operational costs
• sensitive and very expensive equipment
• business processes that are severely affected by equipment downtime (or have a need for very high equipment uptime)
• high risks to human safety

In addition to manufacturing, transportation, and aviation, healthcare, mining, oil and gas, electric power, and construction also have a lot of potential to benefit from PdM. Because of its high risk of exposure, the energy sector is estimated to grow most quickly in adopting PdM technology.