In today’s fast-paced world, it’s all about who can produce the most with the greatest efficiency and accuracy. That’s why predictive maintenance, also known as condition monitoring, is becoming imperative for modern operations. Consumers have become accustomed to instant gratification, so continuous production is vital for avoiding delays. The sudden loss of a critical industrial asset can cause a domino effect, disrupting the entire supply chain. Ensuing product back orders can lead consumers to turn to competing vendors, with ramifications that can ultimately be devastating to your company’s bottom line.
If you could see into the future, you would never miss a production target, endure a safety incident, or have a machine go down. While this will remain an elusive dream, you can, however, predict the future. With predictive maintenance, you can uncover unnecessary maintenance, which could save you millions of dollars in the longer term.
Some industries are a better fit for a predictive maintenance approach, particularly where the uptime of critical assets drives the bottom line. This includes large, heavy equipment in oil, gas and mining operations, as well as critical machines in continuous manufacturing operations, such as an assembly line. This type of maintenance can also be valuable in operations that experience high maintenance costs.
While predictive maintenance isn’t a new concept, the costly investments in technology typically needed to handle the massive volumes of data required, often limit deployment to only the largest organisations. Today, the high availability and low cost of digital technologies, coupled with the rise of the digital supply network (DSN), have made it possible for predictive maintenance to scale on a broad level across facilities and organisations of all sizes. More companies are therefore able to monitor and gain deeper insight into their operations in real time.
Predictive maintenance relies on a few techniques to detect problem indicators, including tactics such as vibration analysis, the use of infrared thermography equipment, and calibration. Because these tools are used to monitor machines continuously, data can be collected and analysed to create a baseline against which all further measurements can be compared. In fact, changes as subtle as an increase in vibration can indicate damage to a specific component, such as a rolling element bearing.
Most manufacturing operations rely on a combination of predictive and preventive maintenance, conducting periodic recommended tasks such as cleaning equipment, oiling parts, replacing commonly failing components, and other techniques. Methods like this have proven to extend the usable lifespan of costly assets while also allowing for continuous monitoring to identify potential issues that aren’t easily detected during routine maintenance. The combination of these activities enables companies to maintain a healthy bottom line by avoiding unplanned downtime and other disruptions that tend to have a ripple effect throughout the whole value chain.
Implementing a predictive maintenance programme is a process, and your ROI can be substantial if you take the time to do it right. To go about incorporating it into you operation, follow these three steps.
1. Identify the problem
First, determine the specific business problem you’re trying to solve, such as reducing downtime or cutting replacement costs. Then rank and analyse your existing assets, determine which (if any) assets are currently equipped with sensors and other tracking devices such as asset tags.
Identify the equipment most likely to fail and assess the costs and urgency of breakdowns. Review your assets in terms of importance:
- Are some assets more vital than others?
- How often have these assets broken down?
- What are the cost implications during downtime?
2. Find the right data to test
Identify which data you want to collect, what potential failures or other concerns you want to predict, and what issues have occurred in the past. From there, the relevant historical data is collected from sensors, industrial assets and fault logs. Predictive maintenance analytics software then examines the data to determine root causes and early warning indicators from past downtime issues. Figure out which metrics are indicative of a looming problem, and use them to alert your team before the problem occurs.
For your data to be useful, you need to collect this information for some time before using it to draw conclusions. You don’t want to base an expensive initiative on anecdotal evidence and end up doing more harm than good.
3. Update the data constantly
Once your predictive maintenance programme is off the ground, keep it running by ensuring the data stream continues to flow. Data is the fuel for your whole programme, and if it’s not up to date and comprehensive, then it’s not going to help you to detect and avoid problems successfully. By using this data, which already exists in your assets, you can reduce downtime disruptions, cut down unnecessary maintenance, and potentially reduce risks in your operations.
Of course, these are general and basic steps describing a far more complex and tailored process. But by beginning with a clearly defined business problem and then working backwards to determine the assets to monitor, metrics to measure, and ultimately how you’ll measure them, you’ll develop an effective predictive maintenance programme that will have a direct impact on your bottom line.
DOWNLOAD The economic significance of effective equipment maintenance to learn why a comprehensive asset care strategy is the key to maximising the productive capacity of your equipment.
|The TRACC framework helps organisations build standardised and integrated good practice and performance capacity across their Plan, Source, Make and Deliver functions. Simultaneously it accelerates their collaboration and alignment capacity to build world class end-to-end value chains, enabling the organisation itself to become the ultimate source of sustainable competitive advantage.|