Glimpse The Future Of Predictive Maintenance
Maintenance Technology | June 15, 2017
Critical-asset data can help identify failures before they occur to avoid downtime and protect the 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. Unfortunately, unless we somehow gain the power of clairvoyance, this fantasy will forever be out of our reach. While we may not be able to see into the future, we can predict it.
By adopting a predictive-maintenance (PdM) strategy, you can mine your critical-asset data and identify anomalies or deviations from their standard performance. Such insights can help you discover and proactively fix issues days, weeks, or even months before they lead to failures. This can help you avoid unplanned downtime, reduce industrial maintenance overspend, and mitigate safety and environmental risks.
The case for predictive maintenance
The sudden loss of a critical industrial asset can be devastating. It can result in unplanned stoppages and maintenance that eat away at your bottom line, while production remains at a standstill. This was the situation for one company operating an oil-sands mine in Canada. The company had to shut down the operation after detecting vibrations in an ore crusher, resulting in a weeks-long production stoppage that had been averaging more than 90,000 barrels/day. According to analysts, each week of downtime reduced quarterly production by about 1.5% and cash flow by about 1%.
Beyond the impact on production and profits, unexpected failures also can cause catastrophic events, such as explosions or chemical leaks, that threaten lives and the environment.
Many companies use robust industrial-maintenance programs and costly maintenance-service agreements to help avoid these issues. However, even the most comprehensive maintenance programs likely won’t eliminate all unplanned downtime. It can only take one failure to grind your operations to a halt for an extended period of time.
A smarter approach
Predictive maintenance delivers a more data-driven approach to industrial-maintenance programs. It uses predictive analytics and machine-learning algorithms, based on historical and real-time data, to identify specific issues on the horizon. Often these issues won’t show any physical signs of degradation—even a sharp human eye or an intuitive and well-trained maintenance technician wouldn’t be able to catch them.
In addition to helping prevent downtime, a PdM approach can better identify true maintenance needs. This can assist in making sure that you are targeting personnel depolyment, maintenance activities, and maintenance dollars where they are needed most.
Predictive maintenance can be especially useful in industries where the uptime of critical assets drives the bottom line. This includes large, heavy equipment in oil and gas, and mining operations, as well as critical machines in continuous-manufacturing operations.
A perfect example is a large, multistate compressor that experienced a bearing failure resulting in more than $3 million in maintenance and lost productivity. A postmortem on the incident, which involved reviewing 16 months of data, found that the bearing cooling system had not been operating correctly for six months.
Had this data been used as part of a PdM strategy, the company likely would have been able to identify the bearing degradation and its root cause before the failure actually happened. What’s more, the company would have been able to identify detailed preventive-maintenance steps for the cooling system.
Predictive maintenance also can be valuable in operations that experience high maintenance costs.
Often, companies can invest a lot of time and resources in maintenance but lack data to know whether their strategy is effective and addressing their actual needs. Predictive maintenance can help uncover unnecessary maintenance, which could save millions of dollars every year in some industries. This was another discovery in the compressor case. The company was performing certain maintenance activities that were unnecessary and could have been eliminated.
How it works
Predictive maintenance doesn’t require an extensive overhaul of your infrastructure. Rather, it can be deployed on your existing integrated-control and information infrastructure.
The process begins with discussions to identify what data you want to collect, what potential failures or other issues you want to predict, and what issues have arisen 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. Finally, the analytics software develops and deploys “agents” that monitor data traffic either locally or in the cloud.
Analytics software uses two types of agents. The first type is failure agents, which watch for patterns that are known to predict a future failure. If such patterns are detected, the agents alert plant personnel and deliver a prescribed solution.
The second type is anomaly agents, which watch normal operating patterns and look for changes, such as operating or environmental-condition changes. These agents also alert personnel of any detected changes so they can investigate and take corrective action if necessary.
Your crystal ball
Predictive technology has been around for decades. It’s used to detect credit-card fraud, fine-tune marketing programs, and even help us search the Internet. Its role in the industrial world takes the form of a rigorous documentation of events and failures that can help us see and address machine or equipment issues in their earliest forms.
Many manufacturers already see the value of historical failure reports as a tool to help prevent failures and downtime in the future. By using this data, which already exists in your assets, you too can reduce downtime surprises, cut down unnecessary maintenance, and potentially reduce risks in your operations. MT
Information for this article was provided by Doug Weber, engineering manager, and Phil Bush, remote monitoring and analytics product manager, Rockwell Automation, Milwaukee. For more information, visit rockwellautomation.com.