Dr Xiaoqin Ma, Head of Technology and Marketing
In our recent blog post, we shared our thoughts on some of the essential questions to ask before choosing a predictive maintenance supplier. As this piece highlighted, there’s a wide range of options available to those investing in independent predictive maintenance support for the first time in order to drive reductions in CAPEX and OPEX budgets. It’s therefore important to determine what the full scope and potential of each of these offerings is when it comes to making decisions about the hardware and software you deploy across your sites and portfolios.
But, before you can even start weighing up these options, you first need to work out what type and quantity of turbine data and predictive analytics you require. This in turn will allow you to identify the predictive maintenance solution that is most fully in line with your needs, and understand just what level of investment you need for the greatest impact when it comes to lowering OPEX costs, extending the lifetime of your equipment and increasing the value of your assets.
With this in mind, here we outline how you can go about this process of self-evaluation.
Above all, you’ll want a predictive maintenance solution that is flexible enough to meet both your short-term and long-term requirements as these evolve over the lifetime of your assets, and that can be easily integrated into any pre-existing systems and a wide variety of turbine types. But alongside this primary consideration, the following three factors need to be taken into account as part of a full assessment of your predictive maintenance needs.
What is the status of my assets?
First, you’ll want to audit your existing assets and the technologies being used across sites or portfolios. If the turbines at a given site are particularly old, for instance, do they need to be retrofitted with condition monitoring hardware, or are they new enough that such technology is already in place? And, if you are considering installing condition monitoring hardware on an aging fleet, what will be the return on this investment when you factor in your turbines’ current and future failure rates. This is where the famous bathtub curve will play an important part in your financial decision-making. Equally, you’ll want to consider whether the assets are under warranty or not, and how this affects the level of service they receive.
The degree to which you have previously experienced performance issues, and the potential issues an ageing fleet may experience in the near future, will also be an important factor. Have you benchmarked your fleet against your peers to understand the performance of your assets? Do you have a clear picture of the status of your assets that allows you to draw up a priority list, which highlights the areas that you might wish to focus your predictive maintenance efforts on first, the “low-hanging fruit”? In addition, do you have a long-term view of the overall trend of your fleet health, which indicates where you will need to focus on making improvements in the near future?
How big is my maintenance budget?
Next, it is crucial to determine the scope within your existing O&M budget for implementing a predictive maintenance solution – and how much you will need to pay to secure the level of analysis you require. Again, getting the balance between a flexible offering and one that can be quickly and easily integrated with your existing assets in the short term, and expanded to accommodate the future growth of your fleet size or capabilities, is key. For instance, you may already be monitoring SCADA and/or vibration data from individual turbines or sites, but need a means of pulling data from a range of different sites together in one location and access them through a single platform. Your existing budget may allow you to take this first step, before going on to implement more sophisticated data analytics in future, such as machine learning or artificial intelligence. This will allow you to better interrogate the data to improve your operations as part of your business’ digital transformation activities.
Bear in mind that setting up a programme will involve some level of capital investment depending on the scale of your hardware and software requirements. While the cost of the ongoing monitoring, analysis and reporting will best met through operational expenditure, designed to rise or fall in line with the evolving requirements identified earlier.
It can also be a question of scale. Modern and sophisticated predictive maintenance methodologies are capable of generating vast amounts of turbine condition data, and it’s easy to become overwhelmed by the sheer volume of information they produce and that then needs to be processed. As a result, it makes sense to invest in a solution that is capable of providing you with the accurate insight you need to make the best decisions, as well as keep all the data easily accessible to your in-house team.
While the ability to accurately predict your O&M spending might seem like something of a pipedream, greater understanding of the costs for different turbine types and technologies is making this increasingly achievable at an individual site level. In turn, an appreciation of your O&M budget needs over the next three or five years will help you decide between the different maintenance strategies, from corrective to proactive and predictive.
DIY or Do-It-For-Me?
These factors naturally lead on to one final consideration in evaluating your own predictive maintenance needs: whether to carry out all assessment and monitoring in-house or outsource it to a predictive maintenance provider. The former, DIY approach may lend itself well to organisations whose personnel possess a broad and in-depth O&M experience in industries with a long track record in applying predictive analytics, and who are well placed to advise on the implementation of predictive maintenance approaches for wind assets. Equally, you may already be using some form of condition monitoring technology, and this familiarity could serve as the basis for a more fully developed predictive maintenance solution. Over time, after working with and alongside experts from your predictive maintenance supplier, you will develop levels of expertise that require less hand-holding and make some level of DIY feasible.
The DIY approach will typically see a provider install the necessary hardware and software, as well as conduct any training required, before handing over responsibility for the effective monitoring and analysis of data to your in-house team. This degree of control enables asset owners and operators to respond to issues quickly and efficiently, and carry out any necessary performance enhancements themselves.
Alternatively, it may prove more resource- and cost-effective for your predictive maintenance partner to continue to use their existing expertise to monitor, detect and pre-empt failures remotely and advise on the most suitable course of action. At least in the short-term. In the long run, and as your on-site team become more familiar with predictive maintenance technology and techniques, you could consider moving from this Do-It-For-Me approach, to a semi-DIY set-up before taking full control. Of course, for this to be an option, you’ll need to be working with a provider that can deliver this level of flexibility and a tailored approach.
Answering these three questions will allow you to better understand the degree of support you need when making the shift to a predictive maintenance strategy – whether that includes condition monitoring technology, data collection and predictive analytics, consultancy to identify the root cause of developing faults, or all of the above.
There is no one-size-fits-all solution when it comes to safeguarding turbine performance, and knowing your own capabilities and requirements can help you make the right decision for your team, technology and budget. Equally, pinpointing what it is you’re looking for in a predictive maintenance solution will allow you to adopt the elements of a solution as and when you need them, and partner with a single provider to increase efficiencies and reduce OPEX costs. Finally, focusing on your desired results and outcomes will help you to avoid any distractions or unnecessary expenditure when it comes to your predictive maintenance journey.