Holistic analysis of turbine performance indicators

Introduction

The determination of turbine performance is often clouded by complex wind flow conditions. The presented methodology normalises the reference power curves for flow conditions using multiple methods, to allow for greater visibility on the turbine performance with respect to SCADA performance indicators. The result is an optimised maintenance plan.

Approach

Showing several methods, both with and without on-site observations, power curves are normalised for atmospheric conditions such as turbulence, shear, veer and inflow angle. The resulting power curves are considered with respect to additional SCADA parameters and benchmarked across the farm to determine turbine underperformance. The results are then ranked to determine an optimised maintenance plan.

Main body of abstract

Advanced turbine performance analysis techniques offer the opportunity to accurately predict future performance based upon past performance and also to identify and rectify any underperforming turbines ensuring that future performance is maximised. A new methodology based on machine learning algorithms is utilised to normalise the power for complex flow conditions such as turbulence, shear, veer and inflow angle for a given turbine type. Flow parameters are modelled through both the use of Ventos CFD modelling coupled with on-site observations concurrent to wind farm operation and coupled mesoscale-CFD model Ventos/M to quantify the uncertainty reduction through on-site observations.

After this initial analysis, automated tools are provided to use in a deeper investigation into the SCADA data to identify the key indicators leading to individual turbine underperformance. Strategic maintenance campaigns are derived through benchmarking of turbine performance indicators to determine an optimised maintenance strategy that will deliver the highest potential gains in performance. A case study is presented to show the results and describe the on-going maintenance campaign.


Conclusion

There is a lot of discussion on the optimum method for maintenance. This new methodology determines indicators for underperformance, allowing the operator to target specific turbines for yaw misalignment and early component faults to maximise the output of the wind farm over the lifetime.


Learning objectives
The importance of considering atmospheric variables when assessing turbine performance.
The uncertainty of performance assessment with and without on-site observations.
Power curve improvement with the consideration of atmospheric variables.
The ability to design optimised maintenance schemes to get the most out of a wind farm.