FEATURE
Finally, AI can also help manufacturers in the supply chain with quality control on spare parts production. Manufacturing organisations can use machine learning to reject poorly produced spare parts that don’t meet a pre- established standard, therefore minimising the chances of asset failure, and all the costs and emissions that go alongside a repair.
Listen to the data As well as using the power of AI and machine learning to greatly improve the efficient management of assets and expenditure, reviewing historical asset data can also ensure a more sustainable and cost-effective supply chain.
If, for example, you have a remote engine running on an unmanned site, by analysing data such as the oil and water temperature and fuel consumption, and then comparing this against previous historical data you can start to see patterns, enabling the team to predict the probability and timing of an engine failure, and arrange maintenance before it breaks down.
“Manufacturing organisations can use machine learning to reject poorly produced spare parts that don’t meet a pre-established standard, therefore minimising the chances of asset failure.”
Rather than wait for a routine site inspection, often carried out when there’s nothing wrong with the asset, using this data to spot the characteristics of engine failure means its serviced only when needed and as a result should decrease the downtime of the asset as well as reducing travel and labour costs.
The facilities industry typically operates on an OEM maintenance usage model which ends up with assets being over maintained. Take, for example, two passenger lifts in a department store. The one near the front will
www.tomorrowsfm.com
likely do more trips yet a typical maintenance regime of every 12 weeks will include both lifts despite the one at the back hardly being used.
Swapping a calendar-based maintenance system with a just in time one can be hugely effective. By attaching trip meters and sensors that feed information back to control panels and to EAM systems will enable you to carry out predictive and targeted maintenance. Maintaining elements based on the number of trips, per se, rather than as part of a regular maintenance routine, means unworn components aren’t being refitted and wasted, nor are assets being taken apart which aren’t broken, which can in itself increase asset failure rates. If an asset is working why try and fix something that’s not broken? You won’t require as many people, vans on the road, nor hold as many spare parts in stock, all of which will increase profitability and make you more competitive in the market.
Finally, businesses can now combine this maintenance data with energy usage data and feed this back into product and building design, to improve the future build, performance, and environmental impact of an asset.
Not only can organisations take data such as the amount of power consumed and heat generated by assets against the cost of cooling required and carbon usage, but you can also use this data to detect if there is a design fault with an asset or an issue with the placement of an asset within a location. If an asset, for example, is failing more often when compared to the other 199 on the estate, you can start to ask questions - is this due to the assets positioning in the building? This feedback can be used for planning in future builds.
As the saying goes, knowledge is power and in the world of asset management and FM, the more data you have to predict asset maintenance requirements and identify faults the less asset downtime, the more time and money saved, and, importantly, the more efficient and sustainable your supply chain will be.
peacockengineering.com TOMORROW’S FM | 51
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
