Predictive maintenance & condition monitoring
out some of the preliminary work so that human experts can focus their energies on the toughest problems.”
Those algorithms are game changers. That is the level of capability that many are calling prescriptive maintenance.
PRESCRIPTIVE MAINTENANCE Prescriptive maintenance builds on the success of predictive maintenance. Instead of simply predicting breakdowns, prescriptive maintenance can diagnose the root causes of machine defects and can make recommendations for maintenance teams to follow.
John Bernet, mechanical application and product specialist at Fluke Reliability, says that many maintenance teams misunderstand how the data really works. “There’s a common misconception that data is nothing more than a number,” he says. “And if I start collecting data from a machine, it will give a baseline of what is good, and then once that number gets above a certain baseline, something is wrong. Then, we can go out and do some work to fix it.”
Of course, Bernet explains, it is not that simple. Data doesn’t exist in a vacuum. It is only valuable when it is contextualised. Vibration levels mean different things depending on the asset, its age, and even its location. Until recently, most analytics programs could not make those distinctions. Today, sophisticated algorithms can look beyond the raw numbers and make determinations about specific assets. This is not something that an algorithm or a CMMS can do on its own. Prescriptive maintenance requires ongoing input from human experts. In fact, the more input the algorithms receive, the more effective they get at spotting patterns or diagnosing issues. It is not essential for plants to have a deep bench of experienced technicians or data analysts. The same results can be achieved by outsourcing to experts in another location or partnering with a company that offers condition monitoring services, such as Fluke Reliability.
THE KEY TO INDUSTRY 5.0 IS SMART DATA BEFORE BIG DATA
Not long ago, the maintenance industry was advised to collect as much data as possible. Big Data was supposed to be the big focus. Unfortunately, too many businesses today are overwhelmed by the data and struggling to extract any meaningful insights. The future of work does not look like more data – it looks like smarter data.
Instead of constantly streaming every available piece of data, plants need to focus on actionable information that can be used to reduce downtime and cut costs. Sensor data can be a good example of “smart” data because it has an immediate, clear purpose. The shift to smart data also means thinking about storage. Adopters need to consider how long will each piece of data hold its value. Some information – like vibration measurements and temperature – is useful throughout a machine’s lifecycle, since it can point to a pattern. But other information loses its value over time.
It is a good idea to work with experts on building a data collection and storage plan. The bottom line is that data collection is not the end goal. The end goal is for maintenance teams to collect actionable data that makes their job easier and that makes the plant run more smoothly.
CHANGING THE FUTURE OF MAINTENANCE
Industry 5.0 will look a little different for each operation. The future of maintenance is flexible, personalised, and highly adaptable. A “one size fits all” solution is not suitable and maintenance teams should take the time to consult with experts, learn everything possible, and take the solutions that work best for that operation. With the implementation of Industry 5.0 solutions, plants can expect to see dramatic improvements to both uptime and overall productivity, as well as improvements in job satisfaction amongst maintenance teams.
Fluke Reliability
www.fluke.com
Instrumentation Monthly October 2023
41
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82
