This paper presents a test benchmark model for the evaluation of fault detection and accommodation schemes. This benchmark model deals with the wind turbine on a system level, and it includes sensor, actuator, and system faults, namely faults in the pitch system, the drive train, the generator, and the converter system. Since it is a system-level model, converter and pitch system models are simplified because these are controlled by internal controllers working at higher frequencies than the system model. The model represents a three-bladed pitch-controlled variable-speed wind turbine with a nominal power of 4.8 MW. The fault detection and isolation (FDI) problem was addressed by several teams, and five of the solutions are compared in the second part of this paper. This comparison relies on additional test data in which the faults occur in different operating conditions than in the test data used for the FDI design.

/pdf/fault-tolerant-control-of-wind-turbines-a-benchmark-model-3rp8uv86oa.pdf

Fault-Tolerant Control of Wind Turbines: A Benchmark Model

Wind energy has seen great development during the past decade. However, wind turbine availability and reliability, especially for offshore sites, still need to be improved, which strongly affect the cost of wind energy. Wind turbine operational cost is closely depending on component failure and repair rate, while fault detection and isolation will be very helpful to improve the availability and reliability factors. In this paper, an efficient machine learning method, random forests (RFs) in combination with extreme gradient boosting (XGBoost), is used to establish the data-driven wind turbine fault detection framework. In the proposed design, RF is used to rank the features by importance, which are either direct sensor signals or constructed variables from prior knowledge. Then, based on the top-ranking features, XGBoost trains the ensemble classifier for each specific fault. In order to verify the effectiveness of the proposed approach, numerical simulations using the state-of-the-art wind turbine simulator FAST are conducted for three different types of wind turbines in both the below and above rated conditions. It is shown that the proposed approach is robust to various wind turbine models including offshore ones in different working conditions. Besides, the proposed ensemble classifier is able to protect against overfitting, and it achieves better wind turbine fault detection results than the support vector machine method when dealing with multidimensional data.

A Data-Driven Design for Fault Detection of Wind Turbines Using Random Forests and XGboost

Fault Tolerant Control of Wind Turbines Â– a Benchmark Model

Wind turbines are increasingly growing larger, becoming more complex, and being located in more remote locations, especially offshore. Interest in advanced controllers for normal operation has expanded in recent years, but fault detection and fault tolerant control for wind turbines is a less well-developed area of interest. In this benchmark challenge, we have reworked a previous challenge paper to present a more sophisticated wind turbine model - a modern 5 MW turbine implemented in the FAST software - and updated fault scenarios. These updates enhance the realism of the challenge and will therefore lead to solutions that are significantly more useful to the wind industry. This paper presents the challenge model and the requirements for challenge participants. In addition, it provides additional information about the faults selected for the challenge and their basis in field data.

Songling Zhao

Papers

Fault Detection and Isolation of the Wind Turbine Benchmark: an Estimation-based Approach