As the research suggests, it seems that this growth is driven by the rising focus on reducing the operational costs and asset downtime.
While predictive maintenance boasts many benefits, barriers to entry such as high initial implementation costs and training requirements ensure that there is plenty of discussions that need to happen before any implementation.
If you were looking for a resource that will enable you to join that conversation, you’ve come to the right place.
1) What Is Predictive Maintenance (PdM)?
Predictive maintenance is a proactive maintenance strategy that tries to predict when a piece of equipment might fail so that maintenance work can be performed just before that happens. These predictions are based on the condition of the equipment that is evaluated based on the data gathered through the use of various condition monitoring sensors and techniques.
Like every other proactive maintenance strategy, predictive maintenance aims to:
minimize the number of unexpected breakdowns and maximizing asset uptime which improves asset reliability
reduce operational costs by optimizing the time you spend on maintenance work (in other words, doing maintenance only when you need to do it practically eliminates any chance of you wasting time doing excessive maintenance)
improve your bottom line by reducing long-term maintenance costs and maximizing production hours
You might ask: How does this make it different from preventive maintenance? Well, the short answer is that, vast operational differences aside, predictive maintenance does everything more efficiently – at a cost.
Predictive maintenance (PdM) relies on condition-monitoring equipment to assess the performance of assets in real-time. By combining condition-based diagnostics with predictive formulas and with a little help from the Internet of Things (IoT), PdM creates an accurate tool for collecting and analyzing asset data. This data allows for the identification of any areas that need or will need attention.
Let’s look at the major elements mentioned in the above paragraph to get a clear picture of how predictive maintenance works.
This step is essential because although physical inspections of equipment have traditionally been the major way through which maintenance personnel observe assets, there has been a critical shortcoming in that procedure – the most wear and tear happens “inside” the machines which means you need to take them apart to do a proper inspection.
This is far from ideal.
However, by using condition-monitoring sensors and predictive maintenance, you can have an accurate representation of what’s happening inside the asset without any kind of productivity disruptions.
These sensors measure different kinds of parameters depending on the type of machine. Most commonly, they measure vibration, noise, temperature, pressure, and oil levels, but you can go beyond that and even measure things like electrical currents and corrosion.
The Internet of Things
It is one thing to gather data, but quite another to be able to analyze and use the data for its intended purpose. By using the IoT technology, the different sensors mentioned earlier can collect and share data. PdM relies heavily on these sensors to connect the assets to a central system that stores the information coming in. These central hubs run using WLAN or LAN-based connectivity or cloud technology.
From there, the assets can communicate, work together, analyze data, and recommend remedial action or take action directly based on how the system is set up.
This exchange of information is at the core of predictive maintenance and allows maintenance techs to make sense of what’s happening in the machines and identify any assets that (will) need attention.
This is where predictive maintenance goes beyond condition-based maintenance. The data collected previously is analyzed using predictive algorithms that identify trends with the aim of detecting when an asset will require repair, servicing, or replacement.
These algorithms follow a set of predetermined rules that compare the asset’s current behavior against its expected behavior. Deviations are an indication of gradual deterioration that will lead to asset failure. Service technicians can then intervene as required to avoid breakdowns.
In fact, it’s safe to say that CMMS is at the front and center of PdM application today. Here’s why:
CMMS provides the initial data to get PdM rolling
The information gathered over time regarding asset performance helps to form the starting point and the initial dataset before PdM implementation. Though they may be other sources, like hard copy maintenance records and soft copy files, CMMS will provide the most comprehensive and easy to access source of historical information.
CMMS generates alerts and work orders
With condition-monitoring sensor integration, a modern CMMS can automatically create an alert or generate a work order whenever the system detects that an asset is operating outside predefined conditions and parameters. These alerts prompt the maintenance team to take action and they help to significantly minimize unexpected downtime, increase overall efficiency, and lower repair costs.
Here you can see how the creation of one similar task looks like in Limble (this is a task that is automatically generated when the vibration rate exceeds your predefined limit):
These automatic prompts may be for repair, servicing or routine maintenance tasks. Some common examples of alerts and work orders include:
Create a preventive maintenance work order after a machine has been running for a specific length of time or cycles.
Generate a “Fill Coolant” task when the level of coolant in the reservoir is getting too low.
Create an inspection task to check bearings in an air-conditioner’s motor.
Create an inspection task to check belt condition in a fan.
In essence, even though PdM generates highly accurate asset data, that information will be limited in ease of application if it is not combined with a CMMS or other specialized software. On the other hand, CMMS on its own cannot measure or predict machine health. By incorporating both technologies, users get a tool that is indispensable for a modern maintenance management strategy.
CMMS serves as a central organizational tool
CMMS pulls different information about assets together and presents them in a centralized platform that offers complete equipment “situation report.”
For example, PdM will give the raw data from the machines but CMMS goes further to include information from other modules like asset history, inventory, spare parts management, workforce management, repair schedules and more – thereby helping the user make better-informed decisions.
CMMS facilitates data interpretation
Although PdM tools provide valuable insights about asset condition through vibration, lubricant, heat, oil analysis etc, the data generated is enormous and would be cumbersome for humans to manage manually.
With the right CMMS, users get easy to understand “snapshot” of the data that’s coming in.
4) Establishing A Predictive Maintenance Program
Laying the groundwork for PdM is essential for creating a system that will be sustainable for many years. The key is to start small and scale up as the organization adjusts to this new way of doing things.
Here is a very brief outline of the usual steps an organization needs to take when implementing a predictive maintenance program.
Step #1 – Identify critical assets
Start by identifying that critical equipment and systems to be included in the program. Assets with high repair/replacement costs that are critical to production are often the best candidates for a PdM program.
Step #2 – Establish a database
For the PdM program to be successful, another factor to consider is the presence of sufficient information that can offer actionable insights into machine behavior. Historical data for each pilot equipment will be available from sources like CMMS, hard copy files, enterprise software from other departments, maintenance records and charts, etc.
Step #3 – Analyze and establish failures modes
At this point, the organization will need to perform an analysis on the previously identified critical assets to establish their failure modes.
Step #4 –Make failure predictions
With the most critical assets and failure modes identified, the next step is designing the right modeling approach that will form the basis for failure predictions.
The end result of this stage is to deliver a fully automated system that:
monitors operating conditions via installed sensors
understands and predicts patterns created by data anomalies
and creates alerts when there is a deviation from established thresholds
Step #5 –Deploy to pilot equipment
This is where predictive modeling is put to test and validated by deploying the technology to a selected group of pilot equipment.
If the process is executed properly, there will be significant improvements to the company’s operations, even though noticeable impacts might take a few months to kick in, depending on the size and complexity of your organization.
A report by McKinsey Global Institute estimates that the current interest in linking physical assets to the digital world may actually still be understating its full potential. They project that this connectivity could generate up to $11.1 trillion annually in economic value by the year 2025.
A striking feature of this report is that business-to-business (B2B) applications can create more value than strictly consumer uses. In fact, they project that B2B uses can generate up to 70 percent of the potential value enabled by IoT.
How does all this affect maintenance specifically? Well, predictive maintenance is changing the age-old way of doing things. It’s no longer a case of “if it isn’t broken don’t touch it” but “fix it in time before it breaks.”
Here are a few industries that are at the forefront of using predictive maintenance:
The benefits of the increased reliability that PdM offers is quite enticing and manufacturers are taking note. The same report mentioned above indicates that manufacturers’ savings from using predictive maintenance could reach between $240 and $630bn globally by 2025. That’s a considerable sum of money.
The everyday applications of predictive maintenance in manufacturing are numerous – ranging from managing equipment on the plant floor, to boosting operations and improving workers’ safety. This trend is very likely to continue, especially as the cost of sensing technology continues to drop, largely due to the switch from wire-based sensors to wireless ones.
Connected cars are on the increase as brands produce vehicles equipped with sensors that gather data and relay information about the machine’s performance. For businesses, fleet managers use this information to proactively plan for vehicle maintenance. While for consumers, alerts based on performance data are visible to the driver or goes to manufacturers and major car dealerships who then ask the car owners to take action.
Interestingly, the origin of predictive maintenance can be traced to aircraft maintenance. Back in 1943, a British scientist named C.H. Waddington commented that “inspection tends to increase breakdowns” after he observed the maintenance activities of 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.”
Since then, PdM has evolved and is still used by aviation companies to reduce the costly effects of maintenance-related flight delays and cancellations. Predictive maintenance is also used in the industry to help airlines improve aircraft health and prevent devastating accidents.
Future trends for industrial application of predictive maintenance
In the next few years, it is expected that the usage of predictive technologies will increase as there is hardly any industry that cannot benefit from it.
But, which industries would find PdM of particular interest? These will be industries with the following traits:
High capital and operational expenditure
Sensitive and very expensive equipment
High risks to human safety
On top of this list are the mining industry, oil and gas, manufacturing, construction, and aviation. Businesses operating in these sectors have a very high risk of exposure which predictive maintenance can help minimize.
6) Prescriptive Maintenance – What Comes After Predictive Maintenance
Prescriptive maintenance looks to build upon predictive maintenance as PdM improved upon CBM and preventive maintenance.
In essence, prescriptive maintenance would not only let you know when something needs to be fixed but would also suggest a few scenarios of how you can deal with the predicted problem.
As Dan Miklovic from LNS research explains in his post:
“No longer will you need an ensemble of experts to tell you how and when to maintain your assets, as the assets themselves will tell you what they need if they are unable to fix themselves.”
He goes further to explain:
“Let’s say a piece of equipment is showing increasing bearing temperature. Predictive analytics looks at the temperature profile and tells you it is likely to fail in X amount of time. On the other hand, prescriptive analytics tells you that if you slow the equipment down by Y%, the time to failure can be doubled, putting you within the already scheduled maintenance window and revealing whether you can still meet planned production requirements.”
In the same post, he suggests that the acronym for prescriptive maintenance could be RxM and while we like it, it remains to be seen if it will catch on.
Even though the applicability of prescriptive maintenance seems to be tied to advancements in AI and machine learning, how things look today, we probably won’t need to wait long until prescriptive maintenance becomes the next best thing in the maintenance industry.
And that wraps up our outlook on predictive maintenance. If you have something to add or ask, feel free to leave a comment below or get in touch with us via email.