Data-driven maintenance – why less is more

//Data-driven maintenance – why less is more

Data-driven maintenance – why less is more

With an expensive, complex asset like a ship’s engine it would be unthinkable to consider giving it less, not more, maintenance, wouldn’t it? Yet with the right data and technologies in the right hands, it’s possible – and this means big wins on maintenance flexibility, cost efficiency and effectiveness.

Data driven maintenance, dynamic maintenance planning, predictive and condition-based maintenance – there are so many terms flying around it’s easy to get confused about what they really mean in practice. What unites them is that they are all about making educated decisions regarding often costly and time-consuming engine overhauls and maintenance based on hard facts rather than fixed schedules.

“Data driven maintenance is right up there with decarbonisation on the list of the hottest topics in the maritime industry today – no surprise given that it promises owners and operators cost savings and greater flexibility. What it really means and how it’s implemented in practice, however, are a little more mysterious to many,” says Tage Klockars, General Manager, Agreement Sales, Wärtsilä Marine Power.

Demystifying the topic is the first step towards demonstrating the huge value it has to offer – when done right. “In very simple terms data driven maintenance involves the engine control system, secure connectivity to send the data it generates and intelligent rule and AI-based analytics and expertise to make recommendations based on that data,” explains Franck Velthuis, Director, Digital Product Development, Wärtsilä Marine Power. “In the past we checked historical data against rules about once a month; now we are able to collaborate with a vessel’s chief engineer at the same time as the results from our analytics are being generated.”

A lighter, more flexible approach to maintenance

With data driven maintenance the idea is to take a condition-based approach to maintenance rather than adhering to a fixed overhaul schedule based on logged running hours and infrequent reporting. By monitoring all critical engine parameters in real time it’s possible to extend the time between overhauls – if the data shows that everything is in order – and eliminate the need for some time-consuming, costly intermediate inspections. “Not only does this reduce downtime and costs, but it also minimises the need to send external personnel onboard, which is a big benefit during the current Covid-19 pandemic,” explains Velthuis.

“Data driven maintenance means we can ‘lighten up’ the maintenance process and still get a complete picture of the engine’s actual condition based on real-time data,” says Klockars. “We can also train crews to perform less complex intermediate inspections themselves, while real-time anomaly detection, for example, means the crew and our experts are always on the same page, which is great for troubleshooting,” he points out.

“This lighter approach adds flexibility and means less downtime and, ultimately, reduced costs to the customer,” Velthuis continues. “Major overhauls – where we’re pulling out pistons and examining cylinder heads and turbochargers – are costly and time consuming, so anything we can do to safely reduce their frequency is a huge benefit to owners and operators,” Velthuis highlights. “When we know exactly what is going on with the engine we can create a tailored maintenance plan that takes into account the owner’s busines goals and the vessel’s movements.”

Adding data to the mix has allowed time between overhauls to be tripled from around 8,000 hours in the 1990s to around 24,000 hours today, with the approval of classification societies and insurers. “We even have some engines running on a mixture of gas and diesel that are going 32,000 hours between overhauls,” says Klockars.

Megabytes not megabucks

In the not-too-distant past one of the limiting factors behind the adoption of data driven maintenance was the cost of data transfer, but this is falling all the time. “Over the last decade data transfer costs have fallen dramatically,” says Velthuis. “An engine might generate 20–30 MB of data per day, and in 2009 it cost about 12 USD to send 1 MB of data, whereas today there are flat-fee plans that make data transfer far more cost effective. The entire technology ecosystem around data driven maintenance is now more available, accessible and cheaper than it was a few years ago.”

Velthuis also points out that today’s predictive maintenance service offerings are far more advanced and able to detect anomalies in engine parameters far more quickly and accurately. This early detection capability is where data driven maintenance really comes into its own – spotting the smallest of anomalies can help to avoid costly consequences.

“To give an example, by detecting a small deviation in the lubrication oil pressure at turbocharger inlet of an engine, we were able to catch a failed turbocharger compressor bearing; replacing this inexpensive part in time avoided potentially catastrophic consequences,” Velthuis highlights. Another example is early detection of small fuel leaks into lubrication oil, which would typically not be detected until the oil rose above a certain temperature, leading to bearing damage. Solving these problems early and quickly by replacing a few inexpensive seals is a far better option than dealing with the costly damages and loss of revenue this would cause.

Leave it to the experts

You can have all the engine data in the world, but without the right software and expertise to make sense of it all and draw conclusions, it’s essentially a worthless asset. The analysis of engine data is done according to a set of rules based on Wärtsilä’s vast installed base and deep OEM engineering knowledge. Wärtsilä also employs artificial intelligence to model engine behaviour and automate the detection of anomalies.

“Data and algorithms alone are useless without the right experts to interpret the results and provide recommendations,” Klockars points out. “It’s all very good that the data analysis picks up an anomaly, but what are you going to do about it? The teams at our global network of Expertise Centres are responsible for thousands of engines on vessels of all types around the world; the knowledge from our installed base, including data from thousands of engines going back twenty years, means we can not only identify what is going on with an engine but also provide clear recommendations on how and when to deal with any potential issues. An engine can fail in many ways, but what anomaly predicts each one? Our massive data set, combined with AI and human expertise, means we can optimise the performance of each asset resulting in lower fuel consumption and emissions.”

Data-driven maintenance is delivered as part of Wärtsilä’s optimised maintenance offering, with various service levels that can be tailored according to the customer’s needs. “These agreements provide the peace of mind that comes with partnering with the OEM; the ultimate goal is to ensure customers can get as much out of their engines as possible in a safe and reliable way,” Klockars explains. “Whether the customer needs a lighter touch with just monitoring or more comprehensive coverage that includes parts, maintenance work and even guaranteed performance, we can deliver it,” he continues.

To take advantage of all the benefits data driven maintenance has to offer, all you really need is a cyber-secure connection, a Wärtsilä API and a monthly data plan. No additional sensors are needed, and you can even use your own software and connectivity solution if you prefer. As the old saying goes, ‘It’s easy when you know how’.

Source: Hellenic Shipping News Worldwide

By | 2021-02-08T11:36:29+05:30 February 8th, 2021|Uncategorized|0 Comments

About the Author:

Leave A Comment

Login


Username
Create an Account!
Password
Forgot Password? (close)

Create an Account!


Username
Email
Password
Confirm Password
Want to Login? (close)

forgot password?


Username or Email
(close)