Answered August 03 2019
Predictive maintenance (PdM) typically uses data from sensors that monitor various conditions on equipment. As sensors collect data, algorithms analyze that data to predict when maintenance work will be needed.
For the process of collecting data, facilities can use various types of sensors. Some of these include:
Each of these types of sensors collects data readings used in PdM.
The readings collected by sensors may be logged into a CMMS or other form of software. Whenever those readings become abnormal, it’s a sign that things aren’t quite right.
Different types of readings may indicate different problems. For instance, a certain amount of vibration in one part of a turbine may indicate worn bearings, whereas other readings might mean there’s an imbalance or loose part. The point is when the readings from the sensors reach a certain threshold, it triggers a work order.
This is the basic premise of condition-based maintenance. However, PdM takes this a step further.
Predictive maintenance not only uses sensors to monitor the current state of an asset, but it also involves following trends to predict when issues might develop in the future. If a certain trend in measurements from your sensors indicates a future problem, you can schedule maintenance to prevent that problem from developing.
For instance, if a mixer tends to exhibit slightly more vibration than normal a week before the bearings need lubrication, a model of the data from the sensors will show that. From there, a work order can be created in advance to make sure the bearings are oiled at the right time.
To sum up the process:
Latest Maintenance Articles
How to Create a PLC Maintenance Checklist
Everything You Always Wanted to Know About CMRP Certification
What Are the Risks and Benefits of Using a PLC?
Comprehensive Guide to Building a Maintenance Excellence Team (Part 1: Crawl)
What You Need to Know About ISO 41001 Certification and Compliance
Why Your Maintenance Team Should Be Trained as CMMS Superusers
Oil & Gas
Establishing a regular PLC maintenance checklist can minimize or eliminate downtime by discovering potential issues before they cause problems.
While PLCs have been around for a long time, there are still some significant PLC risks that must be considered before implementation.
For industrial applications, computers commonly come in the form of what's known as a programmable logic controller (PLC).
Given that PLCs (programmable logic controllers) are integral to many industrial operations, it’s important to keep an eye on PLC maintenance.
A programmable logic controller (PLC) monitors a specified set of inputs on a piece of industrial equipment and then makes output-related decisions.
To get a better idea of what the ROI for predictive maintenance could be in your facility, let’s take a look at a few real-world examples.
We cover the ways you can use IIoT to optimize soil cultivation, crop growth, livestock raising, and their related processes.
The high upfront costs of implementing new maintenance methodologies can be difficult, but predictive maintenance can actually help ease those burdens.
A pressure sensor is a device that senses and measures pressure. Pressure in this case, is defined as the amount of force exerted over an area.
Whereas sensors monitor conditions of equipment, actuators drive events within equipment. They ensure that systems are functioning effectively.
Temperature sensors are devices on machinery that track ambient temperatures, assess readings, and measure the impact of heat conditions
IoT holds an especially significant place in manufacturing, with value estimates reaching up to $3.7 trillion in factories alone by 2025.
Today, predictive maintenance relies on sensors in three major areas: early fault detection, failure detection, and CMMS integration.
Voltage sensors are wireless tools that can be attached to any number of assets, machinery or equipment for monitoring purposes.
Industrial IoT sensors are widely used in different industries to monitor equipment, assets, systems, and overall performance.
Internet of Things technology is becoming increasingly prevalent throughout homes and businesses alike in numerous applications.
Vibration sensors can be used to give maintenance teams insight into conditions within assets that might lead to equipment failure.
Failure prediction machine learning is the application of artificial intelligence within the maintenance arena. This allows you to monitor your assets.
When working in tandem within a given system, actuators receive signals from sensors and perform some kind of task based on that input.
Any industry that uses or maintains equipment can make use of IIoT sensors. A few of them include agriculture, manufacturing, and retail.
The most exciting IIoT projects on the horizon are for maintenance and training tasks and improving energy management with AR.
We talk a lot about planning in implementing maintenance strategies, and predictive maintenance (PdM) programs are no different.
Acoustic analysis has fewer applications than PdM-tool vibration analysis, but what it lacks in breadth of application it makes up for in effectiveness.
Amongst the tools in the predictive maintenance (PdM) toolkit, vibration analysis sees tons of use because of its extremely wide variety of applications.
The best Industrial IIoT projects to start with are small ones that meet a specific business need. Once successful, you can increase the size and scope.
Industry experts say that deploying an Industrial Internet of Things (IIoT) will cost a minimum of $50,000 or roughly 10 percent of your information technology budget over three years.
Early implementers of the Industrial Internet of Things (IIoT) have reported better protection of assets, and raised levels of reliability and performance.
The top five barriers to IIoT adoption are cybersecurity issues, a lack of standardization, an installed legacy system, high upfront investment, and a lack of skilled workers
Prescriptive maintenance, is a maintenance concept that analyzes an equipment’s condition to create specialized recommendations to reduce operational risks.
Start with your most critical piece of equipment, track information related to failures, and set up alerts to generate work orders to prevent breakdowns.
Each of these challenges can be alleviated through proper application of IIoT technology, so let’s run through each one starting from helping managing cost.
If it does happen, it will probably take a long while, mainly because it would involve uprooting one well-established system in favor of installing another.
Machine learning allows for more intelligent ways of processing data to predict when an asset will require maintenance.
The term was coined in 2011 to represent the role that cyber-physical systems (CPS), cloud computing, and IIoT will have on manufacturing processes.
Almost by definition, predictive maintenance uses sensors, but the core principle of PdM doesn’t necessarily depend on them.
If your business maintains a fleet of vehicles, you’ll want to use mileage sensors to trigger regular inspections, fluid changes, and replacements.
One use case is power failure detection which can create significant downtime losses, and immediate notification can help minimize larger problems.
Choosing assets for predictive maintenance is a matter of priority, especially starting out. A few of the factors you’ll want to look at include:
Dozens of sensors are already available to monitor, track, and report on critical aspects of your operations with more under development each day.
Vibration often signals a potential problem within production facilities that can result in future breakdowns or shorter equipment lifespans.
Pressure sensors alert maintenance teams when the pressure in a certain tank or piece of equipment falls outside of a specified level,
Given the specific demands of industrial settings, IIoT needs to be more robust and flexible than most IoT devices. Characteristics that set them include:
Most equipment don’t fare too well when temperatures get too high or too low, so even using a simple thermometer can be useful for detecting issues.
The problem with PM is it’s based on the assumption that equipment failures occur on a schedule. The reality is that only 18% of assets fail based on age.
Using interconnected technology allows us to network cameras and sensors easily with existing computer systems, creating automatic maintenance events.
With predictive maintenance (PdM), it's understanding an asset's most probable failure modes and monitoring those conditions.
If you’re not focused on continuous improvement each and every day, it won’t be long before you’ll be wasting a significant amount of time and money.
Although predictive maintenance is similar to preventive maintenance, this activity requires particular preset conditions.
Without getting too technical, level of repair analysis, or LORA, is a process used to determine when and where an asset should be repaired.