Intelligent Fault Diagnosis Techniques Applied to an Offshore Wind Turbine System

Abstract

Fault diagnosis of wind turbine systems is a challenging process, especially for offshore plants, and the search for solutions motivates the research discussed in this paper. In fact, these systems must have a high degree of reliability and availability to remain functional in specified operating conditions without needing expensive maintenance works. Especially for offshore plants, a clear conflict exists between ensuring a high degree of availability and reducing costly maintenance. Therefore, this paper presents viable fault detection and isolation techniques applied to a wind turbine system. The design of the so-called fault indicator relies on an estimate of the fault using data-driven methods and effective tools for managing partial knowledge of system dynamics, as well as noise and disturbance effects. In particular, the suggested data-driven strategies exploit fuzzy systems and neural networks that are used to determine nonlinear links between measurements and faults. The selected architectures are based on nonlinear autoregressive with exogenous input prototypes, which approximate dynamic relations with arbitrary accuracy. The designed fault diagnosis schemes were verified and validated using a high-fidelity simulator that describes the normal and faulty behavior of a realistic offshore wind turbine plant. Finally, by accounting for the uncertainty and disturbance in the wind turbine simulator, a hardware-in-the-loop test rig was used to assess the proposed methods for robustness and reliability. These aspects are fundamental when the developed fault diagnosis methods are applied to real offshore wind turbines.

Robust fault‐detection based on residual K–L divergence for wind turbines

“…The proposed fault-detection scheme is applied to the 5-MW offshore WT benchmark, which is provided by the FAST-Simulink model [32]. In this benchmark model, sensors are modelled in Simulink by adding signals from band limited white noise blocks, which are parameterised by noise power, to the actual variables provided by FAST.…”

Backstepping sliding mode fault-tolerant control for the wind turbine system with disturbance observer

“…To overcome these drawbacks, the AFTC algorithms are proposed, which is mainly based on FDI technology and online resetting the controller structures and parameters, so as to realize the dynamic compensation of the system faults. Subsequently, a number of studies on FDI have been investigated, such as deep learning network algorithm, 13 observer algorithm, 14 data-driven algorithm, 15 support vector machine algorithm, 16 and classifier fusion algorithm, 17 and so on. The study by Zhang and Yang 14 combines dilated linear matrix inequality (LMI) technique, observer algorithm, and FDI to propose a distributed output feedback control approach and solve the actuator faults of the multi-agent systems.…”

Robust fault estimation of a blade pitch and drivetrain system in wind turbine model

“…Observability and some restricted conditions are limitations of this design. Simani and Castaldi (2019) proposed a non-linear relationship between measurements and faults of the offshore WT model with neural networks and fuzzy inference. It has been shown that due to the increased number of data in FWTs, implementing deep learning algorithms could be effective in the analysis of the operating condition.…”