Offshore wind is a rapidly maturing industry, and with new technologies continually developing and launching in the market, the complexity of offshore wind presents significant challenges to operators.
Larger, more complex offshore technologies make it increasingly important for wind farm owners and operators to establish a robust predictive maintenance strategy. Support from a service provider that understands not only the physics and engineering of onshore turbines, but large and complex offshore wind turbines makes this process easier. Owners and operators should be increasingly aware of the reliability of predictive maintenance programs and the alerts they generate and understand them in the context of the specific demands of offshore wind maintenance.
It is no surprise then that two commonly asked questions we hear from the market, in particular around offshore wind farms, are:
I. Does your predictive analytics take into account my assets’ specific physical models?
When a supplier understands the physics and engineering of a specific wind turbine make and model, it can significantly increase how accurately their solution determines the exact types and rates of failure in your machinery.
The best predictive analytics solutions have models of your specific assets already built into the software. This means that you can get up and running faster, with less time spent on implementation, because, with their own experience of working the same models elsewhere, you will not need to provide historical data to enable their algorithms to learn about your machines. This means that they give you immediate value – and you can cut out the time spent building models.
But what about when new technologies come in to the market? What if you have taken an innovative approach by adopting a new turbine design?
A good predictive maintenance supplier will be backed by years of turbine performance data, supported by engineering expertise and founded in long-term experience monitoring wind turbines, allowing it to be adaptable to new technologies and incorporate your turbine data into its software.
II. How reliable are the alerts you generate?
The bigger the turbine, the further offshore it is to be built, and fully reliable predictive maintenance system alerts, this can increase costs.
Offshore Energy Support Vessel (OESV) vessels are chartered for repair and maintenance work and often called out when turbine monitor alerts go off. This means that turbine technicians can be transferred out to the wind farm to address the alert and fix the potential issue.
OESVs and Crew Transfer Vessels (CTV) operators are currently under pressure due to accelerating demand and therefore rates are relatively high. Wind farm operators must therefore make sure repair technicians are only called out to the wind farm when work is absolutely necessary, and therefore invest in predictive maintenance technology that generates reliable alerts.
Examples of good questions to ask your predictive maintenance supplier in order to establish this are:
- What is the typical ratio of true versus false positives your solution generates on a given set of assets?
- How does your solution improve this going forward?
“False positives” are one of the most common reasons why predictive maintenance programs fail. It does not take many instances where maintenance personnel are sent out to respond to identified failures where nothing is wrong – or, even worse, tear down a machine to find out that it is actually ok – before people lose confidence in the solution.
This is even more costly on an offshore turbine, as operators will not have only spent money on the technicians’ time, but also chartered a CTV to transfer them to site. At a time where the offshore support vessel sector is under pressure due to rapid growth and continues to pushes towards increased availability, it is important to avoid unnecessary costs, adding another layer to the requirement for turbine monitoring alerts to be accurate, supported by engineering expertise and contain as few “false positives” as possible.
It is imperative that your potential supplier can demonstrate that its true/false positive ratio will not only be very good upon implementation but can and will improve over time.